Tips for Choosing Predictive Maintenance Software

Looking for Predictive Maintenance Software? First, read this...

Predictive maintenance (PdM) is probably the business use case most responsible for drawing manufacturers to Industry 4.0 adoption.

Preventive maintenance for production line assets (common practice until the advent of Industry 4.0) is a major cost burden for manufacturers. In fact, 40% of all preventive maintenance costs are spent on assets with a negligible effect on actually preventing failures.

It's no surprise that the ability of predictive maintenance to predict unplanned downtime events and quality deviations is proving to be a game changer.

This is due to the 8 main benefits of predictive maintenance:

  1. Reduction in lost production time - PdM allows for planned downtime which is usually much shorter than what's needed for reactive repairs, and can be scheduled for times that are convenient and less costly.
  2. Reduced maintenance costs - Repairs are done when needed, instead of routine maintenance which in many cases is redundant.
  3. Lower labor costs - Technicians are called upon for specific and focused tasks.
  4. Reduced equipment costs - Only the problematic components are dealt with, preventing unnecessary replacements and the wear and tear of adjacent parts caused by repair.
  5. Lower chances of secondary damage - PdM identifies problems early on before they escalate and cause more extensive damage to equipment.
  6. Reduced inventory expenses - With PdM, orders can be made only for the parts and materials that are needed.
  7. Longer lasting machinery - Since disassembly is carried out less frequently, equipment lasts longer, increasing remaining useful life (RUL).
  8. Reduced risk-based costs - Fewer unplanned repairs reduce safety risks and the chance of damage being done to other parts or equipment.


Preventive Vs. Predictive Maintenance
Preventive Vs. Predictive Maintenance. While preventive maintenance has been common practice for decades, predictive maintenance requires less labour and is significantly better at preventing failures.

What is predictive maintenance software?

Predictive maintenance is a method of preventing machine failure by analyzing machine data to identify patterns and predict issues before they happen.

At the intersection of human-machine interaction within the smart factory, predictive maintenance software gives manufacturers monitoring and control over PdM capabilities.

For this reason, it’s critical that PdM software offer users visual, real-time interaction that’s accurate,  reliable, and can be customized.

What to know about your company’s needs

Every manufacturing facility operates differently. Clearly understanding your operation’s needs, priorities, and economic dynamics is key in implementing the predictive maintenance software that will deliver the highest ROI for your operations.

The opinions and experience of engineers, technicians and management personnel should be included when deciding upon which software to deploy.

SEE ALSO: Pick solutions, not platforms - how to choose an industrial IoT Platform

Answer these 8 questions to get a better idea of your company’s needs:

  1. What is the monthly cost of unplanned downtime to the business?
  2. What are the common root causes of production disruptions?
  3. What are the common root causes of quality deviations?
  4. What type of problems are you looking to predict - mechanical failures (e.g. motor or bearing failures) or process-centric issues (e.g. deviations from recipes)?
  5. What is the level of in-house data analytics expertise?
  6. Who will be using the software?
  7. Is data from the production lines (OT) accessible to external systems? Is it persisted in a database (e.g. data historian)?
  8. Is data from operational systems integrated with data from business systems (IT) and process flows to enable effective and accurate data analytics?

What to look for in a predictive maintenance software solution

Here are 6 key capabilities to consider when evaluating predictive maintenance software solutions:

Industrial artificial intelligence - AI algorithms integrated into the platform that can be used to drive efficiency through use cases that are relevant to the specific manufacturing type. For example, mechanical failures and process-related issues each require specific types of machine learning.

Simple and intuitive - Predictive maintenance software should be easy-to-use for operators, technicians and management. For example, a digital twin interface can display PdM insights and supporting data in the context of the production line, allowing for quick and intuitive root cause analysis.

Human in the loop - Predictive maintenance software should be able to receive input from production line experts in parallel to data from sensors. In this way, human experience can be leveraged for more accurate predictions as the algorithm learns from expert knowledge.

Actionable and prescriptive - Insights from the software should lead to action, with information on exactly what needs to be done, and how. By pinpointing a predicted failure, technicians perform the prescribed set of corrective actions by accessing and checking off standard operating procedure tasks.

Measurable outcomes - Predictive maintenance software should be able to report on its value and the improved business outcomes using quantifiable metrics.

Compatibility - It’s common for production lines to consist of industrial assets manufactured by a variety of OEMs. PdM software should have the ability to work with different types and brands of assets, seamlessly connecting data historians and PLCs while integrating IT systems (ERP, MES, QMS, etc.)


A condition monitoring dashboard of the Seebo platform showing predictive alerts.
The Seebo platform. Predictive maintenance and quality alerts are provided in the context of the production process.

Always check what’s in the box

The predictive maintenance software market is diverse both with regards to the solutions themselves, and the support and accompanied services offered by software vendors.

Make sure you know exactly what the PdM software does - what’s included, and what’s not.
Many software solutions require significant customization to be performed by the vendor’s professional services. Make sure to factor in the extra costs of additional service providers or software applications.

Planning is everything

Once all of the above has been taken into account, there should be one underlying principle guiding you to the right choice - quick and easy deployment.

Consider solutions that can be deployed to deliver value in under 3 months, and that can be continually and easily adapted as the business requires.

Leading vendors will be able to offer you a customized deployment timeline. The timeline should include all the various deployment stages to help you configure the PdM system through prototyping, validation and finally, solution delivery.

For more in-depth information about predictive maintenance, download our free whitepaper.

Get in touch to see how PdM can significantly cut your maintenance costs and improve the performance of your production line.

Asset Performance Management in Food & Beverages Manufacturing

Asset Performance Management in Food & Beverage Manufacturing

The cost of maintenance is a common pain point amongst food and beverage manufacturers, and for manufacturers in the process industries at large.

Partial digitization has enabled manufacturers to marginally improve operations, but many factories and plants are still battling with costly maintenance and unsatisfactory OEE levels, often below 65%.

With the advent of Industry 4.0, food and beverage manufacturers now have the opportunity to make continuous improvements to maintenance activities that affect the bottom line.

The missing part of the puzzle:


The elements of an industrial IoT system - sensors, gateway devices, edge and cloud computing, connectivity protocols - are all implemented to gather and organize data.

By applying machine learning algorithms to this data, manufacturers can gain new and tangible operational efficiencies, but this requires planning and the allocation of resources.

Enter Asset Performance Management.

What is Asset Performance Management?

The term “Asset Performance Management” (APM) refers to a strategic approach that employs dedicated software applications and tools to improve the availability and performance of physical manufacturing assets.

Assets may include equipment, production machines, and factory infrastructure systems.

APM has a number of benefits:

  • Reduction in unplanned downtime
  • Increase in the availability of critical assets
  • Cuts in maintenance costs
  • Improvements in maintenance efficiency
  • Reduced environmental, health and safety (EH&S) risks

APM and Food & Beverages - A Perfect Match?

The last item in the list of benefits above is especially important in the food and beverage manufacturing sector. APM can help companies operate in compliance with ever-changing government EH&S regulations.

When machines run efficiently, waste is reduced, and safety conditions are improved as a natural byproduct.

With the predictive analytics capabilities of Industry 4.0 technologies, operators, technicians and managers are notified of imminent component, machine, or process failures well in advance.

This allows for proactive maintenance - repairs can be planned, resulting in better use of human resources and equipment. Inventory is better managed avoiding unnecessary and expensive emergency purchasing of spare parts.

Most importantly, if downtime is unavoidable, it’s scheduled so that disruptions are minimal.

APM in Food Manufacturing

Many factories and plants have avoided tackling maintenance efficiency head on. This is partly due to a somewhat conservative mindset that “accidents happen” and that preventive maintenance is good enough.

The truth is that reactive and scheduled maintenance is extremely costly, especially when it results in unplanned downtime. According to a T.A. Cook report on maintenance efficiency, 45% of maintenance activity is of no value at all.

By introducing Asset Performance Management as a consolidated strategy, food and beverage companies have the chance to leverage IIoT technologies to stay competitive and improve quality.


Predictive Maintenance Tools & Use Cases

Predictive Maintenance Tools & Use Cases - Part II

With the core elements (covered in Part I of this article series) in place, the predictive maintenance system can be deployed with the industrial IoT platform acting as a Human-Machine Interface (HMI) for continual monitoring and control over the assets...


Industrial IoT Platform (Deployment Phase)

Function: Deployment and continued interaction with the predictive maintenance solution

The IoT Platform acts as the predictive maintenance hub, notifying management and relevant personnel about any issues that require attention in real time.

Alerts are sent automatically with relevant repair information allowing for teams to collaborate and form a plan of action long before the failure is predicted to take place.

A condition monitoring dashboard of the Seebo platform showing predictive alerts.
A screenshot of the Seebo platform - a condition monitoring dashboard shows sensor information and predictive alerts.

Data Analytics

Function: Pattern detection for actionable insights that improve OEE and output quality

Through the deep analysis of historical and real-time machine data, management can be given accurate insight into the operation’s performance. Unplanned downtime nears zero since personnel is notified ahead of time of any impending issues and is given detailed instructions on the type of repair needed to prevent malfunction.

AI algorithms provide an unbiased evaluation of all aspects of the production process and can perform advanced root cause analysis to reveal dependencies that can be difficult for even very experienced professionals to detect.

The fact that the analysis is continual means that informed decisions can be made in real-time to cut the loss of defective output caused by quality issues.



Function: Optimize data flow throughout the network, allowing for problem-free scaling

Workflows are a strategic predictive maintenance tool that network managers use to help the manufacturing facility make optimal use of the system.

Workflows offer two main functions:

Device management - device registration, protocol interoperability, authentication, and access.
Event processing - the polling of data events, and the routing of data to the required destinations eg. feeding existing ERP and CRM systems.


PdM Pilots

Function: Provide a testing phase to ensure stakeholder buy-in and significant ROI.

For the successful deployment of a predictive maintenance system, it’s important to first launch well-structured and monitored pilot programs to test the waters before full adoption.

This is an opportunity to gauge the ROI of predictive maintenance for the specific operation, and to give stakeholders the chance to weigh in to the project.

While the pilot is being run, modifications can be made via the industrial IoT platform until the predictive maintenance system reaches a satisfactory level of performance.


Learn more about predictive maintenance tools and use cases by reading our complete guide to predictive maintenance or download our extensive white paper for free here.


Predictive Maintenance Tools & Use Cases

Predictive Maintenance Tools & Use Cases - Part I

Predictive maintenance is used to prevent unplanned downtime by leveraging advanced data capturing and analysis techniques.

The many benefits that arise from being able to predict failures and quality issues make predictive maintenance a leading use case of Industry 4.0.

Until now, operators and maintenance personnel have performed maintenance according to a preset schedule, also known as “preventive maintenance”. This method can consume unnecessary labor and material resources, and results in maintenance activity that only prevents about 50% of a factory’s failure events.

Join us in this 2-part article series covering predictive maintenance tools and use cases, including insight into PdM in both setup and deployment phases.


How does Predictive Maintenance work?

Part of the Industry 4.0 revolution, predictive maintenance makes use of a set of tools such as process modeling, data integration, machine learning, and insight visualization - to provide manufacturers with actionable insights about the health of their production assets and processes.

For a general idea of how this is achieved, this post will include a list of predictive maintenance tools, including the components of a typical predictive maintenance system.


Predictive Maintenance Tools - Setup

A predictive maintenance system is set up using a number of tools, each with its own defined functionality:


Function: Capture data in real time

The market for industrial sensors is constantly growing in variety and quality with a vast number of vendors offering sophisticated products at relatively low costs.

Some common parameters captured by industrial sensors include:

  • Vibration
  • Temperature
  • Pressure
  • Light
  • Water/lubricant quality
  • Chemical content
  • Liquid/solid levels

In manufacturing, data sent from these sensors can be used for predictive maintenance. Through the application of advanced analysis techniques such as machine learning and artificial neural networks, predictions are formed regarding Remaining Useful Life (RUL) and other asset health and performance-related KPIs.

The data captured by sensors can also be utilized in other manufacturing use cases such as:

Track & Trace - following raw materials, components, mobile equipment, and finished products throughout the factory/process.

Quality Assurance - testing using optical sensors and identifying equipment anomalies that will likely result in quality issues.

Inventory Management - monitoring and controlling the supply of spare parts and raw materials, preventing inventory surplus or shortages.


Data Communication and Gateway Devices

Function: Facilitate communication in the Industrial IoT network

Gateway Devices are intermediate connection points that connect controllers (PLCs, wireless devices etc.), and sensors to a computing platform - whether on-premise or on-cloud. Gateway devices also protect the IoT network and the data being transported, providing an additional layer of security.

IoT Communication Protocols form the language of the Industrial IoT network. Common protocols such as MQTT, AMQP and CoAP, make sure that devices across the network speak the same language (interoperability) while being light on resources such as power and memory consumption.


The Edge & Cloud Nodes

Function: Data aggregation and device management

Edge computing in the smart factory setting.
Edge nodes maintain the security of the industrial IoT network while reducing latency in communication.

Even a fairly simple production line can generate massive amounts of data which need to be captured, aggregated, normalized, and analyzed.

To secure the network, and to maintain a low level of data communication latency, edge nodes are deployed in close proximity to the production line. The edge nodes handle part of the analytical and processing workload. This also makes scaling the network much easier.


Industrial IoT Platform

Function: Modeling, simulation, data integration, and machine learning.

Building in-house solutions for predictive maintenance is expensive and heavy on resources, while many companies lack the relevant skills.

Industrial IoT platforms vary in the scope and quality of their features, but the more comprehensive platforms will usually offer the following capabilities:

  1. Solution Modeling - Creating a visual blueprint of the PdM solution that includes the various components within the context of your operation: physical equipment, sensors, communication protocols, data analytics, and dashboards.
  2. Simulator - A test environment to validate the functionality and cost of your PdM system before development.
  3. Data Integration - Gateways and connectors enabling streamlined IIoT development with connectivity to your OT and IT data sources.
  4. Predictive Analytics and Machine Learning - Insights from the platform are used by operational teams on the ground to uncover the root cause of manufacturing issues, maximize overall equipment effectiveness (OEE), and reduce unplanned downtime.

BONUS: Digital Twin - Leading IIoT platforms provide intuitive visualization of the condition of production lines in real time. Alerts and automated root cause analysis, powered by machine learning and AI, deliver deep insight into upcoming downtime and quality disruptions.


Read on to learn more in Part II
In Part II of this article, learn how predictive maintenance is deployed in the manufacturing setting, and how an industrial IoT platform is used as a Human-Machine Interface for maintaining control over asset and process health.


Overall Line Efficiency - An Important Metric for Industry 4.0

Why Overall Line Efficiency is a Necessary Metric for Industry 4.0

Overall Equipment Efficiency (OEE) is a widely accepted and utilized manufacturing evaluation method, but Industry 4.0 is raising the standards of production, and OEE is limited in its ability to take into account more complex systems.

To respond to this need for a better-suited metric, a technique known as Overall Line Efficiency (OLE) is being used, mostly because of its ability to describe multiple production lines and the interaction of a number of various sub-processes within a larger production process.

A complete performance evaluation approach will incorporate both OEE and OLE methods with appropriate modifications to suit the operation.


Efficiency Vs. Effectiveness

To differentiate between OEE and OLE, it helps to start by clarifying the difference between effectiveness (in OEE) and efficiency (in OLE), two terms often misused in the context of manufacturing.


Differentiate between OEE and OLE


The simple diagram above demonstrates that effectiveness focuses on performing the right tasks and aiming for the right goals while efficiency is about performing tasks in an optimal way.

Overall Equipment Effectiveness (OEE)

Overall Equipment Effectiveness is a fundamental KPI that is used to improve manufacturing processes by using benchmarking and analysis to pinpoint inefficiencies and to categorize them.

OEE seeks to describe the overall utilization of materials, equipment, and time in a production process. OEE is calculated according to the below equation, although there are a number of ways of defining the 3 contributing parameters...


OEE  = Availability X Performance X Quality

For production lines consisting of a number of unbalanced (unpaced) machines, OEE is not ideal, being better suited to evaluate individual assets.


Overall Line Efficiency (OLE)

Overall Line Efficiency is a fairly new metric in manufacturing and builds off of OEE to compare the current performance of a production line with how well it could be performing.

OLE also takes into account the personnel involved in the various processes, seeking to optimize the synchronization between the output rates of machines and the use of human resources.


OLE   =   OEE of Machine A + OEE of Machine B + OEE of Machine C

The above calculation assumes that the importance of Machine A, B, and C are the same ie. have the same “weight”. In most manufacturing scenarios this will not be the case, with different processing stages having different weights, resulting in a more complex OLE calculation.

Overall Line Efficiency can be expanded further to include a calculation for each production line (taking into account the bottleneck for each), and to formulate a calculation that incorporates a number of production lines.


New Methods for Calculating OEE and OLE

The use of artificial intelligence is steadily growing within the manufacturing sector and can be applied to both OEE and OLE calculation. AI’s advantage here is its ability to adapt to different manufacturing scenarios thanks to the algorithms’ flexibility.

In other words, an AI algorithm used to calculate OLE isn’t affected by whether the operation is in the aerospace or food processing sector and the meaningful differences between those sectors can be reflected in the algorithm by setting specific weight values for critical parameters.


Using Artificial Neural Networks for Overall Line Efficiency

Artificial Neural Networks can easily handle the complexity of OLE calculation, and lead to far more accurate results than those achievable through more traditional calculation methods.

Implementing ANNs to calculate Overall Line Efficiency is not an immediate process - the algorithm needs to be trained. This is done by feeding the ANN existing historical data categorized as input (OEE) or output (OLE) along with other relevant data from the machines and production floor. ANNs can also be fed data from observations made by operators, enhancing the training through additional information layers.


Better Manufacturing Management with Overall Line Efficiency

Using a combination of OEE and OLE calculations to monitor the performance of a manufacturing operation can be extremely useful for management. Due to the high number of variables involved, artificial intelligence in the form of Artificial Neural Networks and other techniques, is very well suited to this field and can offer actionable insights for better management decisions and greater impact.



How to Choose the Right Condition Monitoring Solution.

How to Choose the Right Condition Monitoring Solution for your Operation

Condition Monitoring plays a major part in the smart factory ecosystem, providing a foundation for Predictive Maintenance, Predictive Quality, and other Industry 4.0 applications including Digital Twin.

However, data acquisition, data communication, machine learning, visualization, security and other aspects of industrial IoT implementation can prove to be too challenging and risky for manufacturers lacking the required skill sets internally.

For this reason, companies are increasingly turning to external turnkey Condition Monitoring solutions, but as the market for this type of service grows, it’s becoming difficult to make sense of what each Condition Monitoring vendor offers, and how they compare.

Below is a breakdown of the most important factors to consider when evaluating a Condition Monitoring solution.

For a full guide with everything you need to know about choosing a Condition Monitoring solution, make sure to download our free whitepaper:
How to Choose the Right Condition Monitoring Solution.


Capabilities every Condition Monitoring solution should offer...

Solution Modeling

The goal of creating a solution model is to visualize all the use cases involving the connected assets, across all processes, and in as much detail as possible, including machines, sensors, gateway devices, PLCs, connectivity protocols, analysis, and dashboards.

A Condition Monitoring solution should offer the ability to create a visual prototype of the proposed system, including a connectivity blueprint and a list of necessary sensors and other hardware/software.


Simulating use of the proposed system with relevant Condition Monitoring use cases minimizes risk and provides a great opportunity for stakeholder buy-in.

Engineers, technicians and management can bring to the surface issues regarding the system, and provide feedback that can be implemented to make further improvements.

Data Acquisition

In any Factory 4.0 use case, data is of key importance. Acquiring data needs to be a precise, organized, and continuous operation to ensure that the system receives an accurate real-time representation of what’s happening on the factory floor.

To get the full picture of an asset’s health, or that of a system/production line, it’s important that a Condition Monitoring solution has the ability to “connect” with your existing data system: ERP and historian data sources, as well as PLCs and sensors.


Dashboards play an important role since they present the data in a way that can be interpreted to inform management decisions about maintenance tasks and other aspects of production.

Every manufacturing process is different, meaning that dashboards should be customizable, suiting the metrics and KPIs that are most important to the manufacturer, and offering the ability to set up rules for critical alerts.

Digital Twin Analytics

A Digital Twin represents the attributes of a factory, plant, or asset in real time. This data-rich interface improves anomaly detection and the identification of weak links in processes making it a very capable tool for Condition Monitoring.

Agile & Collaborative

A Condition Monitoring solution should include access to a platform that can generate a digital prototype. This prototype is crucial for keeping the development process agile and collaborative, allowing a wide scope of professionals - technicians, engineers, managers - the ability to review the proposed system. Most importantly, such a platform is likely to prevent errors in the planning of a Condition Monitoring system; errors that can be expensive to remedy further down the line.

The platform should allow for modifications to be made even after the system is in production so that improvements can easily be made, and new business demands met.

Need help with Condition Monitoring?

Seebo offers a complete Condition Monitoring solution for OEMs and plants/factories that are looking to leverage Industry 4.0 to impact their bottom line.

Book a live demo and take the first step in your digital transformation by exploring how Seebo can help you rapidly generate a Digital Twin prototype for your enterprise or asset.



Condition-Based Monitoring is Changing the Food Processing Industry

How Condition-Based Monitoring is Changing the Food Processing Industry

The food manufacturing industry is often slow to adopt new technologies because of health and hygiene regulations, but the advantages of Industry 4.0 are proving to be too significant to be ignored.

Drops in the cost of hardware (sensors, gateway devices, connectivity solutions, and cloud computing) along with improved software tools, have created a compelling case for implementing Industrial IoT (IIoT). And with proven business benefits of smart factory technology already delivered in the food and beverage industry - through Condition Monitoring and Digital Twinning - there is mounting pressure on food manufacturers to keep up with the competition.  


The Unique Challenges of Food Processing

Since the end-product is always intended for human consumption, food manufacturers face numerous unavoidable and significant costs including pest control, microbial testing, hygiene consultation and other services.

Ongoing compliance with food and beverage safety regulations demands that sanitation equipment be constantly modified. The importance of cleanliness results in production zones becoming wet environments with moisture levels high enough to damage equipment.

Food manufacturing processes are extremely elaborate and incorporate numerous stages from mincing, liquefaction and emulsification to cooking, pasteurization, and packaging. These processes demand machinery that is highly complex, making efficient maintenance a real challenge.

Condition Based Monitoring Dashboards - Food Processing Industry

Condition-Based Maintenance in Food Processing

To combat the complexity and cost of asset maintenance in food production, Condition Monitoring is used to regularly deliver a large part of the necessary data to perform Condition-Based Maintenance.

The data is captured by sensors placed on machinery that constantly capture a variety of data sets that can be used to monitor the health of an asset.

Common Condition Monitoring techniques in the food industry include vibration analysis, oil analysis, and thermal imaging.   


Predictive Maintenance in the Food Production Industry

The data collected through Condition Monitoring, combined with historic and ERP data about the various machines, can be aggregated, forming the basis for Predictive Maintenance.

Detecting deviations and performing analysis on the data using Machine Learning results in the ability to formulate predictions regarding equipment failure. In this way, preventive maintenance schedules become redundant since maintenance is only carried out when necessary, cutting significant costs in labor and minimizing unplanned downtime.


5 Major Benefits of Industrial IoT in Food Production

Food Safety

One of the most important parameters to monitor in food safety is temperature, but that’s not always a simple task considering the variety of processes and environments food is exposed to before it reaches its final point-of-sale.

The latest sensors designed for IIoT use are accurate, reliable and inexpensive, making temperature tracking extremely simple, regardless of which step of the process the product is in.

Track & Trace

IIoT enables real-time inventory tracking and detailed monitoring of the arrival and processing of raw materials, transport activities within the plant, and product distribution.

Plant conditions can be continually monitored to ensure employee safety and that of prepared food items and raw materials.

Remote Monitoring

A smart factory can be monitored remotely and grants management the ability to view an operation from a micro-to-macro viewpoint.

Beyond the evaluation of a single machine, process or facility, Remote Monitoring offers the ability to log, track and compare various processes across various facilities, and can provide valuable insights on how to optimize these processes.

Access to Data Insights

The wealth of data collected from Condition-Based Monitoring is useful because of how it can be leveraged to cut maintenance costs, but another significant advantage is that the information can be accessed by authorized personnel in a range of professions.

This makes transferring tasks much more efficient since the data on any asset is available anytime, anywhere. Also, because this detailed information is shared with employees with a variety of skill sets, it can be leveraged across the company to make changes that will directly impact the bottom line from different angles.


Performing maintenance using a data-driven approach offers a host of advantages for the food processing industry. Machinery can be closely tracked for Overall Equipment Efficiency (OEE) preventing wastage and food safety issues while unplanned downtime is dramatically reduced since maintenance tasks are only performed when necessary.


Taking Food Processing to the Next Level with IIoT

Industrial IoT is already having a significant impact on the food processing industry, with a growing number of companies implementing the solutions mentioned above.

And the future is bright - there’s still a lot more unchartered territory with regards to how this technology can be used in the food processing sector to further reduce downtime, increase throughput, and improve product quality.

Looking for a Condition Monitoring solution, but don’t know where to start?

Download our free whitepaper and learn how to find the best Condition Monitoring solution for your operation.


Why IoT Prototyping is Crucial to IoT Success

IoT introduces new complexities to product development: the introduction of data connectivity, data acquisition, data management and security, data analytics, cloud services, and dashboards.

As complexity rises, so does the cost of fixing errors, and because of the physical aspect of IoT systems - sensors, gateway devices, PLCs, routing - building a system that doesn’t meet the project’s needs can be very costly to remedy.

IoT prototyping - iot development lifecycle and costs

Correctly planning your IoT project by using the right tools and setting up a detailed work strategy upfront can end up saving you months in development, and a significant amount in costs.

General Tips for IoT Prototyping

Define your target

If you don’t know where you’re heading, how will you know when you’ve reached your destination? Clearly defining your prototype objectives and critical success factors is imperative to making sure the project will benefit from a positive ROI.

Choose your IoT platform carefully

The IIoT platform you use will play an integral part in the success of the prototype, the development process, and the resulting on-site system. There are many types of platforms available so be sure to do your due diligence when choosing an IoT platform since making the move from prototype to actual system will be much smoother without having to switch platforms.

Work with partners

Prototyping will always be a time-sensitive process which is why it’s important to have a deadline and a clearly defined roadmap. Implementing IoT into a manufacturing operation is complex. Be aware of what your strengths are, and those of your team, and know when to seek out professional IoT services. This can cut costs in the long run and save a considerable amount of time.

Don’t Cut Corners - Thorough Prototyping is Crucial for IoT Success

The IoT implementation process requires skillful orchestration. There’s no reason not to aim for the most significant ROI on your IoT project, but as with all initiatives, planning, using the right tools, and collaborating with the right partners is crucial.



Predictive Maintenance Analytics

Achieving Zero Unplanned Downtime with Predictive Maintenance Analytics

Performing preventive maintenance at regularly scheduled intervals is costly and labor-intensive. It can result in premature part replacement, machine deterioration, and unscheduled downtime.

Predictive Maintenance Analytics allows us to push the boundaries of production efficiency and reach a goal that until now has seemed unachievable - zero unplanned downtime.

To do this, an Industry 4.0 Predictive Maintenance system needs to be able to collect and store relevant production data and analyze it in order to drive actionable business outcomes. This is the true goal of Predictive Maintenance.

Preventive Vs. Predictive Maintenance

How to Improve Asset Efficiency Using Predictive Maintenance Analytics

Historical Data

The first step in predictive analytics is to consolidate all the relevant historical raw data. Before setting out to capture newly created machine data, it’s important to collect and organize as much historical information as possible.

The historical data is used to define and iteratively refine the predictive analytics models to get to the most accurate predictions.

Every machine in the production line should be considered as a data source. Historical machine data captured via Data Historians should be combined with contextual data of the manufacturing process - often captured in ERP and PLM systems - such as the product being manufactured, quality results, batch numbers, and raw materials.  

Current/New Data

Collecting a complete set of asset and contextual data on an ongoing basis is central to Predictive Maintenance systems. This data is then consolidated with the historical data and fed into the predictive maintenance analytics algorithms.

Improvements in technology have enabled the development of sensors that are reliable, non-intrusive, inexpensive, and simple to integrate into existing assets.

Some common sensor types used in industrial manufacturing include:

  • Pressure sensors
  • Temperature sensors
  • Optical sensors
  • Water quality/condition sensors (pH, conductivity, turbidity etc.)
  • Chemical sensors
  • Gas sensors
  • Smoke sensors
  • Level sensors (liquid and solid materials)
  • Accelerometers
  • Gyroscope sensors
  • Humidity sensors

Data Transport and Analysis

To securely transport the data from the sensors, IoT connectivity protocols such as MQTT are used, enabling the information to be sent via a gateway device to a designated central repository - whether on-premise or on-cloud.

Organizing and aggregating the data results in a formatted dataset that can be subjected to a variety of predictive maintenance analytical models.  

For predictive maintenance (PdM), there are two main types of data that are relevant - Static and Temporal.

Static Data refers to the technical specifications and operational attributes of a particular machine. These machine features are inherently static, but if they do have the ability to change over time, they need to have timestamps associated with them.

Temporal Data refers to live operational telemetry, the current condition of the machine, its work order log, usage history, and failure and maintenance history.

Once the data is captured and organized in a central repository, predictive analytics algorithms are applied to recognize downtime patterns and generate actionable insights in the form of dashboards and alerts.

Data Transport and Predictive Maintenance Analysis

Methods of Predictive Maintenance Analytics

There are numerous predictive maintenance analytics methods, ranging from linear regression and time series models to survival analysis and geospatial predictive modeling.

These methods can be organized into 2 main categories:

1. Regression - this set of PdM analysis techniques focuses on building a mathematical equation as a model that represents interactions between the various elements in a machine’s process. Regression models are used to calculate the RUL (Remaining Useful Life) of an asset, or in other words, how much longer an asset will remain operational before its next failure.

In the diagram below, records have been made of an asset over time. Each record (5Y, 4Y, 3Y etc.) is a time unit - nY - with n as a multiple, resulting in the RUL values taking on a continuous value.

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.

Using a Linear Regression model, the relationship between the response (dependent) variable and a group of predictor (independent) variables could be analyzed and expressed as an equation that predicts the response variable (e.g. downtime) as a linear function of all the influential elements (e.g. machine parameters and related contextual data). This model can be further optimized by minimizing the size of the residual, and testing to see that it’s distributed randomly with respect to the predictions that the model proposes.

For cases where the output (response variable) is discrete instances and not continuous, a Discrete Choice model can be used instead of multiple instances of the Linear Regression model mentioned above.

Another predictive maintenance analytical model that falls under the Regression category is Logistic Regression, which suits cases where the dependent variable is binary and we'd like to transform this data into an unbound continuous variable, estimating a common multivariate model.

To construct predictions, Likelihood-ratio and Wald tests are used to measure the statistical significance of each coefficient in the model. Finally, to assess the goodness-of-fit of the classification model being used, a "Percentage Correctly Predicted" test is used.

2. Machine Learning - Predictive maintenance analysis techniques based on Machine Learning have the ability to predict dependent variables directly, without needing to focus on the relationships between the variables. This can be very useful in scenarios where defining the dependencies between variables is extremely complex.

Machine Learning techniques for manufacturing emulate characteristics of human cognition and learn by “training” with example problems, building the ability to predict future events.

Leveraging Predictive Maintenance Analytics

The analytical processes mentioned above give birth to Predictive Quality Models that can help us determine the optimum time to perform maintenance, and the type of service needed before an asset has dropped below its performance threshold.

Because a PdM model is based upon actual machine behavior, equipment failures of any kind can be predicted, making this technology a game-changer for manufacturers. Repairs are more focused and secondary damage is prevented since technicians know the exact type of issue to prepare for, making unplanned downtime a non-issue.


Condition Monitoring in the Oil and Gas Industry

The Rise of Condition Monitoring in the Oil and Gas Industry

Oil and gas plants run some of the most complex systems in industrial production today. In addition to this complexity, should a failure occur, the financial and environmental consequences could be extremely serious. For these reasons, managing oil and gas operations with high levels of efficiency, safety, and profitability is becoming exponentially more difficult.

The emergence of Industry 4.0 introduces new opportunities to address these challenges. Since oil and gas facilities generally employ a relatively small labor force, optimizing maintenance is critical. With innovative solutions to help service and operations leaders better cope with daily maintenance, more time and resources are at hand to improve performance.

One of these solutions is Condition Monitoring (CM), a core principle of Industrial IoT that has already earned its place as a crucial element in successful modern-day oil and gas plant and remote asset management.


Condition Monitoring (CM), a core principle of Industrial IoT


What is Condition Monitoring?

Condition Monitoring refers to the act of monitoring the condition of an asset - a component, machine, system, or facility - using sensors, data processing hardware, and software applications.

Within the smart factory ecosystem, the most important element of CM is the provision of data that can be used for Predictive Maintenance (PdM) and other Industry 4.0 applications such as Digital Twin.


What do IoT and Condition Monitoring have to offer Oil & Gas?

We’re only touching the surface of Industrial IoT’s potential, but already there seems to be almost limitless potential for applying this technology to oil and gas use cases. Remote Condition Monitoring has been utilized in the petrochemical industry for a number of years, with production benefits of over 5% recorded by companies back in 2011.

Today, that figure is estimated to be much larger, especially because of the additional methods that CM is being used to cut costs. In the context of the oil and gas industry, Condition Monitoring offers:

  • Energy efficiency for upstream oil and gas facilities
  • Reduced maintenance costs
  • Materials degradation (corrosion) monitoring
  • Improved field communications
  • The ability to digitally map a plant (Digital Twin)
  • Mining automation
  • Improved safety conditions
  • Longer machinery lifespans
  • Pipeline management
  • Greenhouse gas emissions control
  • Location intelligence

This list makes it quite clear how significant this technology is in enabling companies in the oil and gas industry to streamline their processes, and enjoy better-run facilities that are safer and more profitable.


A Quick Oil & Gas Condition Monitoring Use Case

To get a sense of how powerful CM is in an industrial setting, let’s look at a simple oil/gas plant scenario.

For our example, consider a plant that currently performs maintenance according to a pre-set schedule. The rigidity of the schedule leaves open the possibility of malfunction and low-performance rates that will only be dealt with once the next scheduled check takes place. On top of this, production will have to be halted so that inspections can be performed, and this downtime includes equipment that is 100% healthy.

Condition Monitoring in the Oil and Gas Industry

It’s clear that our plant needs better monitoring of its equipment, with specifications meeting the requirements of vendors and regulatory bodies.

To answer these needs, a system is deployed that consists of the following 4 elements:

  1. Wireless sensors placed throughout the plant on motors, pumps, turbines, heat exchangers, compressors, flare stacks, coker units, and drives.
  2. A gateway device to gather, organize, and transfer the data
  3. A dedicated cloud
  4. A dashboard for controlling the system and receiving alerts

The system above allows for very specific and accurate real-time data to be collected from the plant so that it can be processed and leveraged.

  • Critical alerts trigger notifications that are immediately sent to the relevant personnel.
  • Live data is stored along with previous historical information allowing for the application of a wide variety of analytical methods.
  • The information can be accessed by both management and engineering teams.
  • The depth and quality of analysis leads to actionable decisions based upon target KPIs.


Condition Monitoring and Oil & Gas Go Hand in Hand

The many benefits of Condition Monitoring make it a powerful tool that oil and gas plants can’t afford not to take advantage of. Implementing Industrial IoT is a process, but the rewards are plentiful, significantly cutting maintenance costs and triggering innovation for further improvement. It’s no surprise, according to a recent survey by Accenture, that 62% of the executives in the global oil and gas industry are set to increase investments in digital technologies in the next 3 to 5 years.

To learn about how your oil or gas operation can take advantage of Condition Monitoring and other numerous benefits of Industrial IoT technology, sign up for a live demo of the Seebo platform today.