How the Precision of Process-Based Machine Learning Solves Manufacturing Disruptions

How the Precision of Process-Based Machine Learning
Solves Manufacturing Disruptions

Predictive maintenance, predictive quality and automated root cause analysis are industry 4.0 initiatives driven by the power of AI and machine learning. However, many implementations - specifically in the process manufacturing industry - fall short in delivering the promised value of industry 4.0 due to inaccurate insights and too many false positives.

The solution? Production process context.

With process-based machine learning, the specific characteristics of the manufacturing process and its assets are taken into consideration within the algorithms.

Specific sensors in machines and mechanical equipment, production recipes, production process flows, and the facility’s environmental factors - all contribute to the algorithm’s accuracy.


Too Many Anomalies, Too Many Alerts

In process manufacturing, data from thousands of tags (sensors) are typically captured in a data historian. This data is heavily influenced by production context: which product is being manufactured, and how - product recipe, machine settings, production flow, and manual interventions.

For this reason, applying machine learning algorithms to raw data, without factoring all the relevant contextual information, will result in an abundance of alerts, most of which will be false positives.

Unfortunately, for many manufacturers, this is where the credibility of their industry 4.0 efforts begins to crumble:

Generic Vs. Process-Based Machine Learning

What about weights?

One method used as an attempt to shape data towards actionable insight is to use formulaic weights. In this method, weights are attributed to certain behaviors (measurements/groups of measurements) in an attempt to define problematic states.

While introducing weights to a process will indeed add a contextual layer to the data collected from a production line, it will also introduce new problems. This is because the logic behind weight allocation is based upon human rationale.


Process-based Machine Learning to the Rescue

The good news is that this type of problem is perfectly suited to the application of industrial AI. That’s why machine learning and artificial neural networks are considered a key part of Industry 4.0, especially when it comes to driving predictions as in the cases of predictive maintenance and predictive quality.

Including the Process

With process-based machine learning, the topology of the production floor is modeled precisely to include all the lines, manufacturing stages, machines, and the flow of the product through the system.

This model provides an accurate representation of all the assets via directional graphs and the movement of the product through each stage of the production process.

Process-based Machine Learning

Enter the Algorithms

The production context, critical for closing the gap between the representative data and the real-world manufacturing environment, is added by means of feature engineering. With this contextualized data in place, machine learning algorithms become extremely powerful predictors. While more conventional ML algorithms such as Random Forest and XGBoost may be used, applications designed for industrial process data such as the Seebo platform, use graph-based models such as Hidden Markov (HMM) and Directed Acyclic Graph (DAG).

Since the data fed into the ML algorithms includes the context of the entire operation, analytics produce accurate predictions regarding maintenance, quality, and the supply chain.

These predictions are then presented to personnel and management with enough time to be acted upon strategically, significantly improving the performance of the entire plant.


Get in touch for a 1-on-1 demo to see how process-based machine learning can significantly improve your operation’s uptime and output quality.

IoT Platform Solutions - choosing a platform per business solution

Pick solutions, not platforms!
How to choose an Industrial IoT platform

“If it ain’t broke, don’t fix it.”

That common phrase once defined manufacturing’s approach to optimization. But today, enterprises are painfully aware that smarter production lines and more efficient processes can save them millions in downtime and lost yield.

So, plant managers – people in what traditionally is one of the more conservative roles –  are actively looking to implement industry 4.0 solutions based on an Internet of Things (IoT) platform.

But are they looking in the wrong places?

Don’t make this mistake

Industrial IoT (IIoT), or Industry 4.0, touts itself as an innovative means to increase production efficiency and quality in the factory, with a compelling return on investment (ROI). The problem, though, is that every IoT platform is different, and not necessarily suited to each company’s business needs.

Companies generally start  by deploying pilots for one or two key IIoT solutions, but they don’t understand that some IoT platforms are focused on providing the underlying technical infrastructure for business solutions, while others are built to provide specific business solutions. 

So how do you know which IoT platform is best-suited to your needs?

In order to choose the right IoT platform to get started, there are a couple of things you need to know:

Different types of Industrial IoT platforms

Before choosing an IoT platform, you’ll have to define which type of platform fits your solutions.

There are over 450 IoT platforms today, and each one offers something slightly different. Broadly speaking, they fall under the categories of IoT development platforms or IoT runtime platforms. We’ve already covered the differences between the IoT platforms in this blog post.

Choosing the right type of  Industrial IoT Platform depends on your internal resources. To deploy Industry 4.0 solutions, you’ll need to capture machinery data in a central repository  to analyze that data, and visualize the resulting insights in an intuitive way.

Some companies already have sensors integrated into their assets and data connectivity solutions that capture their machinery data; they’re looking for a data analytics solution to derive and visualize actionable insights for their teams. Others need an end-to-end service, but plan on using their own data scientists to translate the data into a solution.  

It’s generally best to look for an industrial IoT platform that provides solutions for the use cases that are relevant to your business. Look for a platform that is built on standard, proven technologies for its services, such as IoT device management, data security, and data storage.

In fact, the best match between business needs and Industrial IoT platform is made by orienting your search in line with the solutions you’re looking for.

Get the manufacturer’s guide to navigating the Industrial IoT Platform landscape

Industrial IoT Platform Solutions

While industrial IoT platforms must deliver the technical infrastructure to ensure that the delivered IoT solutions are scalable, secure, and easily managed in production, the business value of the platform is derived from its solutions.

Some platforms do NOT claim to deliver solutions. Instead, they provide the tools for manufacturers to build and test the solutions themselves, requiring staff skilled in data security, data connectivity, data management, data science, and data visualization – a tall order for most manufacturers.

Other IoT platforms are focused on targeted business solutions, such as predictive maintenance, predictive quality, and condition monitoring.

Before checking out an Industrial IoT platform’s features, you should define the primary solution or solutions you want to employ.

The top 8 Industry 4.0 solutions:

  1. Predictive Maintenance

  2. Predictive Quality

  3. Digital Twin

  4. Condition Monitoring

  5. Automated Root Cause Analysis

  6. Energy optimization

  7. Transportation 

  8. Logistics 

Taking a solution-targeted approach to your IoT platform search helps you map out which capabilities to look for in the IoT platform and quickly narrow down the choices.

In fact, the solution capabilities are the prime consideration that should most inform your choice of the underlying Industrial IoT platform.

How to match the solutions you need to an Industrial IoT platform

Know thyself – and thy pain points

Examine your company’s main pain points. Identify where the drain in resources or revenue is.

You can pinpoint the right solution to launch as a test case by reviewing your overall equipment effectiveness (OEE) and choosing the aspect that can be improved on the most.

In a recent Seebo survey of process manufacturers, 62% of respondents said their main production failure root causes lay in the manufacturing processes; for another 25%, it was mechanical failures in motors and bearings of specific assets in the production line. Energy and supply chain pains took a distant third and fourth place.

Optimizing manufacturing process or preventing machine breakdown through better condition monitoring – or even preventative maintenance – require different technologies. There are platforms that are better suited for process manufacturing vs. discrete manufacturing, and vice versa. It’s clear, though, that not every Industrial IoT platform will suit every solution, so before you research platforms, verify within your company what needs to be worked on the most.

What type of services does the industrial IoT platform offer?

Going back to the different types of platforms – any solution implementation involves sensors, connectivity, data acquisition, data analytics, and visualization. You may already have some of these capabilities in-house, but any Industrial IoT solution will require all of these, from sensors embedded in million-dollar machinery to an on-cloud or on-premise data repository with advanced analytics .

Many platforms bill themselves as IoT platforms, but their solutions differ drastically – make sure you are targeting the link in the chain that is relevant for your production line.

Similarly, pay attention to which step or steps in the production lifecycle the platform focuses on.

Some solutions relate to the production line, while others focus on addressing pain points in the supply chain. Knowing this, you can look for specific capabilities in an IoT platform that address the stage where your pain points lie.

Contextualized vs. raw data

For some production lines, particularly in discrete manufacturing, it’s enough to collect data from the machines in the process. In more complex process manufacturing processes, where the materials used are ingredients that change shape and form throughout the process, there is a tremendous variety of variables that can influence results. To understand yield and product quality, production results must be contextualized via data about the production environment. For process manufacturers, it’s crucial to contextualize data in the framework of the manufacturing environment and process. Look beyond the buzzwords, and understand if the IoT Platform which offers insights based on more than data from the production assets alone.


Data security is always a serious concern. Manufacturing assets are less vulnerable to hacking than consumer devices, but captured data must be secured, and you’ll need stringent measures in place to protect who can access which data, from what location, and at what times.

Data integration

Integration is multi-directional. In process manufacturing, you will not only need to capture the OT data from PLCs and data historians, you will need to contextualize it with data from MES, ERP, and quality management systems, to name a few.

Above all, you will want to ensure that the platform considers the production processes in its data schema, to accurately reflect your production processes, in addition to the assets.

How does the IoT platform manage its integrations? Will you need additional technical support to manage it?

In a solution-centric approach, you should ask yourself which integrations your solution will need. A platform that claims to to provide a production quality solution doesn’t have to include its own quality management software, but it should provide easy integration with at least the most common quality management tools.

Solutions for whom?

Most AI solutions require a plant to have in-house data scientists. The insights produced will often be incomprehensible to the people who need the insights they provide the most: quality investigation teams, process engineers, and even operators on the factory floor. Evaluate whether your solutions are for production line staff or for data scientists, and choose an Industrial IoT platform relevant for those users.

Understand who the users of the system will be – and ensure the chosen IoT platform can serve them directly.

First, understand who the users of the system will be. Ensure that the chosen solution can serve these users directly. These teams must be able to access and understand the data that you are collecting or receiving, in order to act on them. Then, check that any platform you review is indeed accessible to these teams. If they require a data scientist, you’ll have to find a way to translate the findings to the relevant teams.  

Alternatively, look for an IoT platform which doesn’t require that you hire data scientists, or which transmit actionable insights in a way that’s visually clear to the teams that need the results the most.

With these tips in mind, you should find it easier to define the solutions you want and create a checklist of what to look for in an Industrial IoT platform.

To get more ideas for Industry 4.0 uses cases, read our blog about digital twins for production lines.

“Fishbone Diagram” created by Kaoru Ishikawa (Quality Manager at Kawasaki) in the 1960s.

Root Cause Analysis in the Age of Industry 4.0

What is Root Cause Analysis in manufacturing?

On the production floor, Root Cause Analysis (RCA) is the process of identifying factors that cause defects or quality deviations in the manufactured product.

The term “root cause” refers to the most primary reason for a production line’s drop in quality, or a decrease in the overall equipment effectiveness (OEE) of an asset.

Common examples of root cause analysis in manufacturing include methodologies such as the “Fishbone” diagram and the “5 Whys”. The simplicity of these methods is also their strength, but how effective are they in dealing with the complexity of today’s manufacturing processes?


“Fishbone Diagram” created by Kaoru Ishikawa (Quality Manager at Kawasaki) in the 1960s.
“Fishbone Diagram” created by Kaoru Ishikawa (Quality Manager at Kawasaki) in the 1960s.

Root cause analysis is undergoing a new interpretation in light of the Industry 4.0 revolution. With the power of industrial IoT and artificial intelligence at our fingertips, it’s natural that manufacturers progress to more advanced root cause analysis methods.


Why do we look for the Root Cause?

While the symptom and immediate cause might be easy and quick to solve, failing to detect and treat the root cause will very likely lead to the problem recurring.

The challenge in RCA is distinguishing between a symptom or intermediate cause, and the true root cause of a problem.


Shortcomings of Traditional Root Cause Analysis

The general approach currently used by many manufacturers when it comes to root cause analysis is to rely on on-site expert knowledge.

Experience is indeed valuable, but some production lines are so complex that being simultaneously aware of every component and sub-process is humanly impossible.

Manufacturers that do collect data from OT and IT systems still need to be able to make sense of it in order to perform RCA. This requires time and a variety of professionals to perform - in most cases, process, quality and maintenance engineers.

It’s natural that even experts can be biased towards certain ideas. And, even if the root cause of the problem is roughly identified, there may be inaccuracies in the definition of the problem, making it difficult to come up with an intelligent and lean solution.

Another disadvantage of manual root cause analysis:

Currently, most RCA information isn’t shared across manufacturing sites, leaving factories/plants of the same company to repeat each other’s mistakes, leading to unplanned downtime that could have been prevented.


The Power of Automated Root Cause Analysis

Machine Learning is a subfield of artificial intelligence that focuses on developing and researching algorithms that learn from data. The algorithms exist in the form of models which are trained with historical data in a way that allows them to make predictions and decisions based upon new data.

Thanks to significant advances in machine learning and Big Data analytics, root cause analysis can be performed using automated methods. These methods are unbiased and based purely upon historic and real-time data from the production floor.

Anomaly Detection

To perform RCA using machine learning, we need to be able to detect that something is out of the ordinary, or in other words, that an anomaly is present.

The machine learning model is trained to analyze the equipment’s data output under regular “healthy” operating conditions. An anomaly can take the form of any pattern of deviation in the amplitude, period, or synchronization phase of a signal when compared to normal behavior.

The algorithm forms a prediction based on the current behavioral pattern of the anomaly. If the predicted values exceed the threshold confirmed during the training phase, an alert is sent.

Examples of anomalies detected using automated root cause analysis include:

  • Component failure
  • Abnormal process input parameters (eg. off-spec material composition)
  • Corrupt sensor values
  • Changes made to the control logic (eg. via the PLC)
  • Changes in environmental conditions

So, is this the end of industry expertise?

Automated root cause analysis reduces the overall dependency on expert knowledge, but it doesn’t diminish the value of on-site experts who are vital in monitoring, validating and managing the RCA process.

Additionally, automated root cause analysis is powered by machine learning and probabilistic graphical models that need to be trained in order to be able to perform inference. This makes on-site experience critical in ensuring a system that takes into account all relevant parameters.

Mutual Information

Another mathematical solution suited to RCA is the probabilistic strategy known as Mutual Information. In a manufacturing setting involving a high volume of data and parameters, this approach can be used to leverage complex statistical knowledge to search for patterns.

Mutual information is an investigative tool that aims to describe the mutual dependency between two random variables. When aiming to identify causal relationships - such as in root cause analysis - mutual information helps by identifying which information can be learned about one variable through data about another.


The Role of AI in Root Cause Analysis

Artificial intelligence, specifically in the form of machine learning, catapults root cause analysis into another realm of asset management.

It’s all about timing:

The ability of AI to formulate predictions relating to machine performance and health, instead of waiting for disaster to strike, introduces a whole range of benefits that affect the bottom line.

Some examples of the direct benefits of automated root cause analysis in manufacturing are:

  • Early detection of safety issues
  • Reduced emissions due to accurate monitoring of the entire production process
  • Identification of complex process disruptions eg. inefficiency of a reactor
  • More efficient electrical consumption through anomaly detection
  • Predicting quality deviations and adjusting processes to prevent the waste of raw materials

If you had to summarize the value of machine learning in root cause analysis, it would be:

Less time spent on figuring out the problem, more time spent on fixing and preventing it.


Example of Automated Root Cause Analysis in Manufacturing

A prime example of automated root cause analysis would be to look at how machine learning can be utilized to deduce the root cause of asset failure and quality deviations in manufacturing.

We can look at a manufacturing process as consisting of:

  • an input stage - in process manufacturing, feeding the raw materials into the production line;
  • the process - a sequence of steps performed consecutively;
  • a resulting output - the finished product.

For this basic example, we will describe the framework for an automated root cause analysis system by using a Bayes Network (see Figure 1.)

Figure 1 - A Bayes Network describing causal correlations between root causes and failures.
Figure 1 - A Bayes Network describing causal correlations between root causes and failures.


The example process consists of 6 processing steps (S1 - S6), each with a number of causal nodes (the blue circles) and 4 failures or quality deviation types known as failure nodes (the orange circles).

The failures are the result of errors in one of the six processing steps, although some failures can be the result of errors in more than one processing stage. The causal correlations are represented by the dotted arrows.

Building a Bayesian Network like the one in Figure 1 requires the involvement of relevant process experts since all process stages and failure points need to be carefully defined.

Expert knowledge that includes causal correlations based upon experience, as well as historic data of known causal relationships, can be added to the algorithm which can take into account this knowledge, without being biased by it.

Once the model has been trained, new data can be fed into it to discover the root cause of new failure incidents. With data only about the failure nodes, the machine learning algorithm can infer which causal nodes were likely involved in the failure.

An example of the algorithm’s output:

Probability (Causal Node) A = 0.01
Probability (Causal Node) B = 0.81
Probability (Causal Node) C = 0.03

As you may have noticed, the results don’t add up to 1 (the standard for statistical and probabilistic calculations). This is because the algorithm takes into consideration the fact that the exact root cause might not be described as an already-defined causal node.

Another important element of this type of model is what is known as a measurement node. Measurement nodes give specific readouts of observable information pertaining to the causal nodes such as pressure or vibration measurements taken in a specific step of the process.

In this way, measurement nodes add another data layer to the model, allowing for relationships that aren’t yet defined by the model to affect the outcome.


The result:

A data-driven automated RCA system that is accurate and predictive, offering actionable insights that can be shared between cooperating facilities.

Patterns and anomalies can be detected pointing to root causes that would normally be very difficult to identify based purely upon expert knowledge.

The fact that root causes of unplanned downtime and quality deviations can be predicted makes these methods of automated root cause analysis perfectly suited to Industry 4.0 use cases.

For an in-depth example of automated root cause analysis in manufacturing, be sure to check out our free case study here.


Industrial AI is Revolutionizing Manufacturing

5 Ways Industrial AI is Revolutionizing Manufacturing

There’s no doubt that the manufacturing sector is leading the way in the application of AI technology. From significant cuts in unplanned downtime to better-designed products, manufacturers are applying AI-powered analytics to data to improve efficiency, product quality and the safety of employees.

Here’s how:

Industry 4.0 and Smart Maintenance

In manufacturing, ongoing maintenance of production line machinery and equipment represents a major expense, having a crucial impact on the bottom line of any asset-reliant production operation. Moreover, studies show that unplanned downtime costs manufacturers an estimated $50 billion annually, and that asset failure is the cause of 42% of this unplanned downtime.

For this reason, predictive maintenance has become a must-have solution for manufacturers who have much to gain from being able to predict the next failure of a part, machine, or system.

Predictive maintenance uses advanced AI algorithms in the form of machine learning and artificial neural networks to formulate predictions regarding asset malfunction.

This allows for drastic reductions in costly unplanned downtime, as well as for extending the Remaining Useful Life (RUL) of production machines and equipment.

In cases where maintenance is unavoidable, technicians are briefed ahead of time on which components need inspection and which tools and methods to use, resulting in very focused repairs that are scheduled in advance.

The Rise of Quality 4.0

Because of today’s very short time-to-market deadlines and a rise in the complexity of products, manufacturing companies are finding it increasingly harder to maintain high levels of quality and to comply with quality regulations and standards.

On the other hand, customers have come to expect faultless products, pushing manufacturers to up their quality game while understanding the damage that high defect rates and product recalls can do to a company and its brand.

Quality 4.0 involves the use of AI algorithms to notify manufacturing teams of emerging production faults that are likely to cause product quality issues. Faults can include deviations from recipes, subtle abnormalities in machine behavior, change in raw materials, and more.

By tending to these issues early on, a high level of quality can be maintained.

Additionally, Quality 4.0 enables manufacturers to collect data about the use and performance of their products in the field. This information can be powerful to product development teams in making both strategic and tactical engineering decisions.

Human-robot Collaboration

The International Federation of Robotics predicts that by the end of 2018 there will be more than 1.3 million industrial robots at work in factories all over the world. In theory, as more and more jobs are taken over by robots, workers will be trained for more advanced positions in design, maintenance, and programming.

In this interim phase, human-robot collaboration will have to be efficient and safe as more industrial robots enter the production floor alongside human workers.

Advances in AI will be central to this development, enabling robots to handle more cognitive tasks and make autonomous decisions based on real-time environmental data, further optimizing processes.


Making Better Products with Generative Design

Artificial intelligence is also changing the way we design products. One method is to enter a detailed brief defined by designers and engineers as input into an AI algorithm (in this case referred to as “generative design software”).

The brief can include data describing restrictions and various parameters such as material types, available production methods, budget limitations and time constraints. The algorithm explores every possible configuration, before honing in on a set of the best solutions.

The proposed solutions can then be tested using machine learning, offering additional insight as to which designs work best. The process can be repeated until an optimal design solution is reached.

One of the major advantages of this approach is that an AI algorithm is completely objective - it doesn’t default to what a human designer would regard as a “logical” starting point. No assumptions are taken at face value and everything is tested according to actual performance against a wide range of manufacturing scenarios and conditions.

Adapting to an Ever-Changing Market

Artificial intelligence is a core element of the Industry 4.0 revolution and is not limited to use cases from the production floor. AI algorithms can also be used to optimize manufacturing supply chains, helping companies anticipate market changes. This gives management a huge advantage, moving from a reactionary/response mindset, to a strategic one.

AI algorithms formulate estimations of market demands by looking for patterns linking location, socioeconomic and macroeconomic factors, weather patterns, political status, consumer behavior and more.

This information is invaluable to manufacturers as it allows them to optimize staffing, inventory control, energy consumption, and the supply of raw materials.

Industrial AI will Continue to Transform the Manufacturing Sector

The manufacturing sector is a perfect fit for the application of artificial intelligence. Even though the Industry 4.0 revolution is still in its early stages, we’re already witnessing significant benefits from AI. From the design process and production floor, to the supply chain and administration, AI is destined to change the way we manufacture products and process materials forever.


This article was featured in CIO magazine.


AI in Manufacturing

Artificial Intelligence - The Driving Force of Industry 4.0

A lot of the hype surrounding artificial intelligence in manufacturing is focused on industrial automation, but this is just one aspect of the smart factory revolution; a natural next-step in the pursuit of efficiency. What artificial intelligence also brings to the manufacturing table is its capability to open up completely new avenues for business.

Below is an outline that covers both these aspects of artificial intelligence within the Industry 4.0 paradigm, and how this powerful technology is already being used by manufacturers to drive efficiency, improve quality and better manage supply chains.


Industrial AI’s Impact on Manufacturing

Artificial intelligence’s impact on manufacturing can be organized into 5 main areas:

  • Maintenance / OEE

Predictive maintenance has become a very sought-after use case for manufacturers looking to advance to Industry 4.0. Instead of performing maintenance according to a predetermined schedule, predictive maintenance uses algorithms to predict the next failure of a component/machine/system and then alerts personnel to perform focused maintenance procedures to prevent the failure, but not too early so as to waste downtime unnecessarily.

One of the most common applications of AI for manufacturing is machine learning, and most predictive maintenance systems rely on this technique to formulate predictions. The advantages are numerous and can significantly reduce costs while eliminating the need for planned downtime in many cases.

By preempting a failure with a machine learning algorithm, systems can continue to function without unnecessary interruptions. When maintenance is needed, it’s very focused – technicians are informed of the components that need inspection, repair and replacement; which tools to use, and which methods to follow.

Predictive maintenance also leads to a longer Remaining Useful Life (RUL) of machinery and equipment since secondary damage is prevented while smaller labour forces are needed to perform maintenance procedures.

Regression labeling for Predictive Maintenance.
Regression labeling for Predictive Maintenance. Each recorded instant (5Y, 4Y, 3Y etc.) describes the Remaining Useful Life of an asset before it is predicted to fail.


  • Quality 4.0

Manufacturers are finding it harder than ever to maintain consistently high levels of quality. This is due in part to a rising complexity in products (that integrate software, for example) and very short time-to-market goals.

Despite these challenges, managers are highlighting quality as a top priority, realising the importance of the customer’s experience of a product and the power of customers to push a brand forward as well as being aware of the pain point of high defect percentages and product recalls.

Using Industry 4.0 techniques, this new quest for quality has been appropriately named Quality 4.0 and artificial intelligence is at its forefront. Quality issues cost companies a lot of money, but with the use of AI algorithms developed through machine learning, manufacturers can be alerted of initially minor issues causing quality drops, similar to the way alerts are created for predictive maintenance.

Quality 4.0 allows manufacturers to continually improve the quality of their output while collecting usage and performance data from products and machinery in the field. This data becomes a vital source of information that forms the basis for product development and crucial business decisions.


  • Human-robot collaboration

According to the International Federation of Robotics, by the end of 2018, there will be 1.3 million industrial robots working in factories around the world. The general approach is that as jobs get taken over by robots, workers will be offered training for higher-level positions in programming, design, and maintenance. In the meantime, the efficiency of human-robot collaborative work is being improved as manufacturing robots are approved for work alongside humans.

As the adoption of robotics in manufacturing increases, AI will play a major part in ensuring the safety of human personnel as well as giving robots more responsibility to make decisions that can further optimize processes based on real-time data collected from the production floor.


  • Generative design

Manufacturers can also make use of artificial intelligence in the design phase. With a clearly defined design brief as input, designers and engineers can make use of an AI algorithm, generally referred to as generative design software, to explore all the possible configurations of a solution. The brief can include restrictions and definitions for material types, production methods, time constraints and budget limitations.

The set of solutions generated by the algorithm can then be tested using machine learning. The testing phase provides additional information about which ideas/design decisions worked, and which did not. In this way, additional improvements can be made until an optimal solution is found.


  • Market adaptation / Supply chain

Artificial intelligence permeates the entire Industry 4.0 ecosystem and is not only limited to the production floor. One example of this is the use of AI algorithms to optimize the supply chain of manufacturing operations and to help them better respond to, and anticipate, changes in the market.

To construct estimations of market demand, an algorithm can take into account demand patterns categorized by date, location, socioeconomic attributes, macroeconomic behavior, political status, weather patterns and more.

This is groundbreaking for manufacturers who can use this information to optimize inventory control, staffing, energy consumption, raw materials, and make better financial decisions regarding the company’s strategy.


Industry 4.0 Demands Collaboration

The complexity of using artificial intelligence in industrial automation requires that manufacturers collaborate with specialists to reach customized solutions. Attempting to build the required technology is costly and most manufacturers don’t have the necessary skills and knowledge in-house.

An Industry 4.0 system consists of a number of elements/phases that need to be configured to suit the manufacturer’s needs:

  • Historical data collection
  • Live data capturing via sensors
  • Data aggregation
  • Connectivity via communication protocols, routing and gateway devices
  • Integration with PLCs
  • Dashboards for monitoring and analysis
  • AI applications: machine learning and other techniques

To truly leverage AI, manufacturers will do well to partner with experts who understand their goals and who can help create a clearly defined roadmap with an agile development process that links the AI implementation to relevant KPIs.


quality 4.0 adoption zones

Quality 4.0 - Better Processes & Better Performance for Better Products

One would think that the acceleration of technological growth would automatically result in improvements in manufacturing quality, but it seems that the opposite is true in many cases. There are a number of factors making it more challenging than ever for manufacturers to maintain a high level of output quality.

Today’s products are complex, often incorporating or integrating with software, and the highly competitive nature of the manufacturing sector means that time-to-market goals are shorter than ever.

Managers are aware of this phenomenon, and quality is moving up to take its place as a top priority for many companies. With Industry 4.0 making such a huge impact on manufacturing, it’s only natural that these methodologies be leveraged to meet the new quality demands. And so, the birth of Quality 4.0 – a term used to describe a new focal point in industry – is finally upon us.


What is Quality 4.0?

Like Industry 4.0Quality 4.0 isn’t a closed-ended term that defines just one technology or activity. Instead, Quality 4.0 describes a new approach to manufacturing, where production is not just gauged based upon output rate and cost, but on the quality of the product, the quality of the process, and the quality of the services provided surrounding the product.

The “4.0” is a reference to Industry 4.0 and its associated technologies such as Industrial IoT, Digital Twin, AI in the form of machine learning algorithms and artificial neural networks, and others.

These are all technologies that can be leveraged to improve quality. For example, Predictive Quality Analytics is a use case that utilizes the aforementioned technologies to predict changes in production quality. This information is crucial to manufacturers who realize the importance of quality to customers, and who are interested in developing a much leaner operation while making better products.


Quality 4.0 – The Time is Now

In our current reality, Quality 4.0 is still in its early stages of adoption. In fact, most manufacturing facilities still rely on traditional quality evaluation methods; methods that in many cases are no longer relevant for current products. Companies that fail to take an innovative stance on quality, for current and new production processes, will find it hard to survive, let alone lead, in future markets.

The bottom line is that quality issues cost companies a lot of money, and in doing so, affect the potential longevity of a manufacturing operation especially in a market that is ever-changing and more competitive than ever.


The Opportunity Presented by Quality 4.0

Advancing to Quality 4.0 requires financial and organizational resources, but the process presents a huge opportunity for manufacturers. Searching for new innovative ways to optimize quality is an opportunity to nurture a culture of development which can lead to better products that cost less to produce.

Introducing Quality 4.0 can also help to strengthen and differentiate a brand within its market, and improve awareness among existing and potential new customers.

As with Factory 4.0, Quality 4.0 levels the manufacturing playing field since mid and even small-scale enterprises can leverage new technology to make significant advances in production efficiency and better meet the demands of customers.


Challenges in the Current Quality Arena

Today’s manufacturers face a number of quality-related challenges:

  • Maintaining a high level of quality amidst high expectations and changes in customer demands.
  • Allocating resources for innovation and for research into new methods of quality improvement.
  • Compliance with changes in regulation laws.
  • Agility: increases in product variety demand work on multiple products simultaneously (development and production stages).
  • Global standardization: companies producing from a number of locations have to offer consistent output quality regardless of differences in the standard of local raw materials and production conditions.

Industry 4.0, along with its suite of powerful use cases such as predictive quality & maintenance, remote monitoring, and digital twin, enables manufacturers to meet the above challenges head-on. For example, changes in regulations can be directly communicated to production lines or code can be modified remotely so that new and existing products comply with the new laws.


The Four Zones of Quality 4.0 Adoption

The Four Zones of Quality 4.0 Adoption


  1. Concept & Design

In the past, “quality” has usually been associated with production processes – raw materials used, assembly, finishing and packaging – but quality should be an integral part of the conceptualization/design and industrialization phases as well.

By including the quality perspective in the early stages of the product lifecycle all the way through production and delivery, manufacturers will be able to achieve higher levels of customer satisfaction. After all, the quality of a product’s concept is an attribute that affects how a customer experiences the use and value of that product.

  1. Production

This particular zone represents where most of the quality activity has taken place in manufacturing prior to the Industry 4.0 revolution. Traditional data analytics and process harmonization methods are being replaced by techniques that involve artificial intelligence such as Machine Learning, and advanced levels of monitoring and connectivity such as Digital Twin.

  1. Service & Performance in the Field

A unique characteristic of Quality 4.0 is that a product’s performance is monitored (and modified, if necessary, and possible) even after delivery.

By collecting and making sense of user data from the field, future failures can be prevented with minimum loss of materials in rejected batches. The time it takes from failure identification to elimination can be extremely short, reducing wastage and maintaining customer satisfaction despite temporary disappointments.

In software-integrated products, updates can be made remotely, eliminating bugs and adding features requested by users.

  1. Company Culture

Quality 4.0 is a broad field of activity, and companies should aim to instill the quality approach as part of the overall company culture.

Since every employee, and every interaction with the manufacturing process, can be considered within the quality paradigm, Quality 4.0 is not limited to a particular segment of manufacturing.


Industry 4.0 – Taking Quality into the Future

Technologies associated with smart factory – IIoT, Big Data, AI, Machine Learning etc. – can all be utilized to improve quality. However, methods for quality improvement are lagging behind the development of other production-enhancing technologies. This is especially true for methods involving B2C communication and feedback loops. In other words, the power of Quality 4.0 has yet to be fully unleashed.

The good news is that industrial IoT techniques – connectivity protocols, sensors, gateway devices, dashboards, analytics – provide the perfect toolbox for Quality 4.0 implementation.

One way of demonstrating this is through examining remote monitoring as a Quality 4.0 use case…


Remote Monitoring for Quality 4.0

Using sensors to collect data for root cause analysis, diagnosis techniques can be performed remotely. By gathering feedback from a number of devices, “swarm intelligence” can also be used as a method of further analysis into machine behavior or product performance.

By using predictive analytics on the collected data, we can identify correlative patterns and enable predictive maintenance. Beyond efficient maintenance and the prevention of malfunction, this analysis provides insight into parameters affecting output or performance quality.

A common argument is that only software or data-related issues can be handled remotely, but in the field it’s become evident that extremely often, service technicians are summoned for just that reason. In the automotive industry, for example, software issues represent a significant portion of all the reasons behind service requests. And in cases where an on-site visit is needed, technicians arrive informed of the details of the issue, and equipped with the necessary components, tools and methods for the specific repair.

Remote monitoring and maintenance allows manufacturers to continually improve quality over time while the usage and performance data collected from products or production machines provides an invaluable source of information for business and product development insights.

factory 4.0

How Factory 4.0 is Changing the Way we Make Products and Process Materials

What is Factory 4.0?

Around the world, and in practically every sector, manufacturing facilities are undergoing a major transformation. Digitization is changing the way we process materials and make products, and data is becoming the golden key that can open a door to technological possibilities with the power to completely reshape manufacturing.

The traditional manufacturing model is evolving into what is referred to as a “smart factory” or Factory 4.0 – a connected system that links machinery, personnel, maintenance activity, and analytics for a completely integrated approach to factory management.

Factory 4.0 leverages technologies and industry 4.0 components such as non-intrusive sensors, wireless connectivity, cloud computing, artificial intelligence, machine learning and others, to affect all phases of manufacturing business from raw materials processing, safety, and production, to quality assurance, packaging, and distribution.

The Building Blocks of Factory 4.0

There are numerous approaches for digitally transforming a manufacturing facility, but any typical Factory 4.0 solution will include the following core elements:


Sensor technology has developed greatly in recent years and today’s market of sensor providers offers a wide variety of low-cost sensors that can measure parameters that include temperature, pressure, light, vibration, water/lubricant quality, chemical content, liquid/solid levels and many more.

Depending on what they’re monitoring, sensors can be placed on or inside machines, at designated workstations, on devices carried by personnel, or in part of the factory’s existing systems such as the HVAC or security network.

Some use cases for industrial IoT sensors include:

  • Tracking the movement and position of raw materials, components, finished products, and valuable equipment throughout the factory
  • Quality assurance (optical testing and analytics)
  • Inventory: monitoring the supply of raw materials and spare parts
  • Identifying equipment behavior anomalies that could result in quality issues
  • Safety: sensors on machinery to restrict activity near personnel; sensors carried by personnel that measure potential environmental threats, lack of movement etc.

Connectivity Protocols

IoT connectivity protocols form the language of an IoT system. These communication standards allow data to be transferred and understood by the various components of the system – from the sensors to the cloud via PLCs and gateway devices; and finally to a software program for analysis.

Deciding on the correct protocol early on is critical for building a successful smart factory.

Cloud Computing

The cloud represents Factory 4.0’s main data center. Here, information collected from the sensors is stored, processed and analyzed. The cloud is also utilized for edge computing to further optimize data processing by minimizing the reliance on centralized processing nodes.

Analytics & Machine Learning

The large amounts of data captured continuously from the shop floor, and collected from historian systems, including information about every aspect of production. Data can be analyzed using statistical algorithms as well as by implementing machine learning techniques which automatically derive actionable insights from root-cause analysis and historical data.

This continual analytical activity triggers insights that lead to improved machinery performance, more efficient processes (eg. on-site transport, production line configuration, maintenance etc.), and reduced downtime.

Use Cases Drawing Manufacturers to Factory 4.0

Factory 4.0 is Changing the Way we Make Products and Process Materials

Implementing changes to a manufacturing system is a complex and costly process, but the use cases driving companies to adopt Factory 4.0 are highly compelling, with the potential to begin positively affecting ROI within a single quarter.

Improving OEE (Overall Equipment Effectiveness)

Analytics-driven insights enable the identification of the root cause of system issues. This understanding, based directly upon machine output data, allows management to hone in on areas that require changes while taking into consideration real-time availability of equipment, performance levels, and the quality of output.

From Corrective to Predictive Maintenance

Using predictive analytics to leverage the data collected from machines, it’s possible to monitor asset health to the point where equipment failure can be predicted, improving reliability and greatly reducing maintenance costs.

With Factory 4.0, manufacturers receive automatic alerts when anomalies occur and can optimize maintenance schedules to completely side-step machine failure.

This method of preempting system errors does away with the need for corrective or preventive maintenance, cutting labor costs and building a strong sense of reliability amongst customers.

Remote Asset Monitoring

A powerful use case for management, Remote Asset Monitoring offers improved visibility of the factory floor as well as mobile assets regardless of their location. Alerts about the condition of individual machines, equipment, and the factory environment are sent to stakeholders who can make data-driven decisions to increase efficiency and maintain compliance with regulations.

Enter the Digital Twin

A Digital Twin is a digital representation of an asset, process or facility; a visual model that offers real-time data about its physical correspondent. Digital Twins are the culmination of a number of technological capabilities that fall under the Factory 4.0 umbrella.

Digital Twin software offers full visualization of its “real-life” twin, allowing management to experiment with parameters and explore ideas for further optimization, without the risk of harming performance or damaging equipment.

The Many Benefits of Factory 4.0

Every production facility is different, and the nature of process manufacturing differs greatly from discrete manufacturing. That being said, there are a number of benefits to Factory 4.0 that are relevant across the board.

The Constant Pursuit of Quality

Using artificial intelligence along with input from management, Factory 4.0 continually learns how to optimize itself, reacting to changes in conditions in real-time, and running entire manufacturing processes autonomously.

Besides detecting risks, predicting failures, and preventing unplanned downtime, Factory 4.0 and predictive quality can help detect decreasing quality trends (increases in defects) and can suggest areas for improvement by identifying human, machine, or environmental factors that are affecting the number of defects.

Cutting Costs & Impacting the Bottom Line

The improved optimization brought on by Factory 4.0 technology cuts costs in a number of ways, leading to a leaner operation overall. Inventory can be managed in a much more precise manner since maintenance is far more predictable.

Repairs are proactive and timely, keeping machine health optimal. Since technicians know ahead of time the exact type of malfunction they’ll be working on, secondary damage is prevented and repairs are much quicker.

Having data on all aspects of the process also enables better-informed decisions regarding staff. This allows for more accurate employee allocations per task, preventing unnecessary spending on labor.

The “Why” behind Factory 4.0 is Crystal Clear

Replacing corrective maintenance with predictive maintenance is just the tip of the iceberg.

Factory 4.0 represents a new paradigm in how we produce materials and products. The use of Big Data and the high level of connectivity and control offered by smart factories allows manufacturers to focus on taking their operations, products, and services to the next level.

Interested in Factory 4.0 technology for your operation? Book a free demo to learn about Seebo’s smart factory solution for manufacturers.


Top IoT Development Platforms

Seebo Gets High Score from the Leading SaaS Review Platform

FinancesOnline, a popular software directory that thousands of businesses rely on to choose the top 10 IoT development software solutions that match their unique requirements, just ranked Seebo with a high 8.7 rating.

According to SaaS review experts from FinancesOnline, “with Seebo, manufacturers have access to an innovative and highly visual platform for smart connected product developments.” Impressed with Seebo’s IoT development platform, they also ranked Seebo #27 out of the top 100 IoT Management Software.

Top IoT Development Softwares
FinancesOnline praised Seebo’s “unparalleled visual modeling and simulation” that allows for agile product ideation, early stakeholder feedback, and customer buy-in. They also lauded
Seebo for accelerated product delivery with the platform’s automatically generated specs and simulations, enabling manufacturers to simply communicate their vision which the platform then turns into a reality.

Other benefits of Seebo, according to FinancesOnline’s team of B2B experts, include integrations to IoT Clouds, efficient team collaboration, analytical and behavior market insights for data-driven development, easy validation of financial feasibility, and much more.

FinancesOnline also utilized its unique Customer Satisfaction Algorithm to determine the general perception of Seebo users. The algorithm gathers all comments, feedback, opinions, and user reviews about Seebo which generated an extremely positive, 95 percent user satisfaction rating. The site also ranked Seebo in their IoT development software alternatives, proving that the Seebo IoT development platform can truly help manufacturers bring new products to the market quickly and cost-efficiently.

IoT Platforms

How to Choose an IoT Platform

Updated: September 2th, 2018

A majority of companies today are evaluating or adopting IoT initiatives to take advantage of new business opportunities and stay ahead of the competition. To do so quickly, cost-effectively, and with minimal risk, companies turn to IoT platforms for capabilities ranging from the design and delivery of connected products to collecting and analyzing system data once in-market.

There are now close to 450 IoT platforms available to companies. Understanding how to navigate the Industrial IoT platform market, and choose the right one for your business needs, is therefore more important now than ever before.

Two categories of platforms

There are an endless number of ways to categorize IoT platforms. Here we have chosen to broadly define two — IoT Development Platforms and IoT Runtime Platforms. IoT platforms in the first category focus on the design and delivery of an IoT system; those in the second, on the management of the system and its data once deployed. Companies will likely employ both IoT Development and IoT Runtime Platforms, as there is no one platform that covers all needs.

How to Choose an IoT Platform

IoT Development Platforms

The first set of IoT platforms provide the tools to design, validate, deliver, and analyze a connected system. Here companies ideate product concepts and design the complete IoT system that gets engineered and moved into production. At every stage of the product lifecycle, IoT Development Platforms are essential for companies to continuously receive closed-loop feedback from product usage, driving improvements in subsequent releases.

To choose the right IoT development platform, the following set of capabilities are key: 

  • IoT Modeling - with integration to CAD
  • IoT Simulation
  • IoT Prototyping
  • IoT Execution
  • IoT Product Analytics

IoT Runtime Platforms

Once a connected system is in operation, the second set of IoT platforms come into play for the management of the system and its data. Here companies monitor, analyze, and maintain the devices and data cloud in production operation.    

To choose the right IoT runtime platform, the following set of capabilities are key: 

  • Device Management
  • Data Management
  • Security
  • Operational Analytics

Completing the IoT Lifecycle

Both IoT Development and IoT Runtime Platforms are needed to ensure the successful design, delivery, management, and analysis of a connected system.

IoT platform lifecycle

The combination of platforms provides a closed-loop cycle for companies to continuously innovate and improve their products.

Here, data-driven feedback on the performance, customer usage and issues detected in the IoT system gets sent from the runtime platform back to the development platform.

For the complete guide to navigating IoT platforms and understanding which capabilities are most important, download a copy of our whitepaper: 

Get the free whitepaper - Navigating the IoT Platform Landscape

IoT platform comparison whitepaper

This whitepaper provides an in-depth comparison between platforms and tips for choosing the right one.


Top 4 Business Benefits of IIoT

The Industrial IoT Revolution is happening now.

Smart products and systems are delivering transformative value for manufacturers – from smart mining equipment, to precision agriculture, connected food processing machinery, and every sector in between.

The rapid growth of Industrial IoT (IIoT) translates into a significant market opportunity. By 2025, McKinsey estimates that IoT will have a yearly economic impact of $4 trillion to $11 trillion. IIoT use cases will account for close to 70% of the projected value - versus 30% of consumer IoT use cases.

Manufacturers are taking advantage of the IIoT opportunity to meet their business goals, while delivering new value to their customers.

Based on hundreds of use cases, we have synthesized the top four business benefits for manufacturers that embrace IIoT.

1. Create new business models

IIoT provides manufacturers a range of new business models, the most important of which is the ability to turn products into services.

Digital services drive new revenue for a product in-market, like a subscription model where customers can unlock premium control and monitoring features for machinery.

Data services are another key service manufacturers offer to improve user experience and increase adoption. Insights from machine sensor data can be provided to customers to help drive compliance adherence, minimize machinery downtime, enhance worker productivity and safety.

industrial iot in the automotive industry
German automotive company, MAN, tracks a truck’s raw data in real-time and translates it into a report offered as a paid service to customers.

2. Enhance innovation process and brand identity

Forward-thinking companies are constantly innovating and looking for ways to lead their industry. The culture of creativity inside organizations is key to improve products, come up with new product concepts and turn ideas into market disruption, quickly and profitably.

IoT allows companies to reimagine how their products should look, act and react as well as the data they can collect. In-market analytics provide insights into how users are engaging with the product for making informed decisions about improvements and understanding the wants and needs of customers.

Innovative products and systems have the added benefit of strengthening the brand of a company and providing a competitive advantage.

iot in manufacturing
Stanley Black & Decker introduces 1,000 new tool and storage products each year. As part of their investment in a company culture of innovation, product teams prototyped and pitched smart power tools for disrupting the industry with the first IoT tools.

3. Achieve customer-centricity

To compete in a rapidly changing global economy, manufacturers are constantly looking for ways to build stronger relationships with their customers.

Manufacturers are leveraging IoT to focus on customer needs and the best solutions for meeting them. Smart systems can provide a range of valuable outcomes for customers, like the ability to track health and safety compliance, improve worker oversight, utilize assets more efficiently and increase facility production and operations.

For instance, machinery and equipment firm Caterpillar uses IoT to enable their customers to monitor and optimize fleets of ships. By tracking fuel data and providing necessary insights into optimal operating parameters, customers are able to utilize their ships more efficiency.

4. Provide proactive repair and service

According to Deloitte, poor maintenance scheduling can decrease the productivity of a plant by 5-20%. IoT changes this equation with predictive maintenance - the ability to understand when machine parts will require repairs and how to best schedule maintenance based on monitoring analytics.  

Predictive maintenance can provide manufacturers and customers with automatic reports for strategic maintenance scheduling and proactive repairs. This ability reduces maintenance time by 20–50% and decreases overall maintenance costs by 5–10%. Saving both the manufacturer and customer time and money.

reduce machine downtime with iot
ThyssenKrup is reducing elevator downtime by monitoring everything from motor temperature to shaft alignment, enabling technicians to use real-time IIoT data to spot issues before a breakdown occurs and reduce repair time.

Interested in learning more on developing IIoT and taking advantage of its business benefits? Visit Seebo’s IoT resources liberary.