What is predictive maintenance?

Predictive maintenance for industry 4.0 is a method of preventing asset failure by analyzing production data to identify patterns and predict issues before they happen.  

Until now, factory managers and machine operators carried out scheduled maintenance and regularly repaired machine parts to prevent downtime. In addition to consuming unnecessary resources and driving productivity losses, half of all preventive maintenance activities are ineffective.

It is not a surprise therefore, that predictive maintenance has quickly emerged as a leading Industry 4.0 use case for manufacturers and asset managers. Implementing industrial IoT technologies to monitor asset health, optimize maintenance schedules, and gaining real-time alerts to operational risks, allows manufacturers to lower service costs, maximize uptime, and improve production throughput.

How does IoT predictive maintenance work?

For predictive maintenance to be carried out on an industrial asset, the following base components are required:

  1. Sensors – data-collecting sensors installed in the physical product or machine
  2. Data communication – the communication system that allows data to securely flow between the monitored asset and the central data store
  3. Central data store – the central data hub in which asset data (from OT systems), and business data (from IT systems) are stored, processed and analyzed; either on-premise or on-cloud 
  4. Predictive analytics – predictive analytics algorithms applied to the aggregated data to recognize patterns and generate insights in the form of dashboards and alerts
  5. Root cause analysis – data analysis tools used by maintenance and process engineers to investigate the insights and determine the corrective action to be performed

Production asset data is streamed from the sensors to a central repository using industrial communication protocols and gateways. Business data from ERP and MES systems, together with manufacturing process flows, are integrated into the central data repository to provide context to the production asset data. Then, predictive analytics algorithms are applied to provide insights for reducing downtime, which are investigated using root cause analysis software.
Predictive maintenance architecture diagram

Predictive maintenance architecture

To implement a predictive maintenance system effectively, manufacturers need to map the parameters of failure for machines and create a blueprint for their connected system – the manufacturing assets and sensors, business systems, communication protocols, gateways, cloud, predictive analytics, and visualization.

Using a visual IoT modeler, engineering teams can graphically capture the production processes in the shop floor, including data flows, dashboards, and the logic of the system – with rules that monitor and alert to maintenance issues. The modeler generates a system blueprint, which is critical for accurate predictive analytics.

Predictive analytics are applied to the machine data – and the system blueprint data – in order to predict conditions of upcoming failure. A dashboard for predictive analytics synthesizes operational data, allowing process and maintenance engineers to address actionable insights in the form of corrective action.

The benefits of predictive maintenance

Manufacturers and their customers get a range of business benefits from predictive maintenance. The advantages of PdM include:

  1. Reduced maintenance time– Automatic reports for strategic maintenance scheduling and proactive repairs alone reduces maintenance time by 20–50 percent and decreases overall maintenance costs by 5–10 percent. These insights save the manufacturer and their customers time and money.  
  2. Increased efficiencyanalytics-driven insights improve OEE (overall equipment effectiveness) by reducing unnecessary maintenance, extend asset life and enable root cause analysis of a system to uncover issues ahead of failure.
  3. New revenue streams- Manufacturers can monetize industrial predictive maintenance by offering analytics-driven services for their customers, including PdM dashboards, optimized maintenance schedules, or a technician dispatch service before parts need replacement. The ability to provide digital services to customers based on data presents an opportunity for recurring revenue streams and a new growth engine for companies.
  4. Improved customer satisfaction- Send customers automated alerts when parts need to be replaced and suggest timely maintenance services to boost satisfaction and provide a greater measure of predictability.
  5. Competitive advantage- Predictive maintenance strengthens company branding and value to customers, differentiating their products from the competition and allowing them to provide continuous benefit in-market.

Predictive maintenance tools

Implementing predictive maintenance requires a baseline of integrated tools.

Predictive maintenance tools include an industrial IoT platform to model, simulate, test and deploy the predictive maintenance solution.

The tools include industrial data integration and data analytics algorithms to detect patterns in machine data, and root cause analysis tools for investigating the derived insights and determining the corrective action to be taken.

What is the difference between preventive and predictive maintenance?

Manufacturers have been carrying out different forms of preventive and predictive maintenance for years. Understanding the difference between them, however, is critical with the emergence of Industry 4.0.

Preventive maintenance depends on visual inspections, followed by routine asset monitoring that provide limited, objective information about the condition of the machine or system. In this process, manufacturers regularly maintain and repair a machine to prevent failure.

On the other hand, PdM is data-driven and relies on analytics insights for maintenance and repairs ahead of disruptions in production.

How are companies using IoT predictive maintenance tools?

Organizations are implementing predictive maintenance analytics in a range of ways, from targeted solutions for a single machine part, to factory-wide deployments for increasing OEE throughout the production line.

For machine and parts manufacturers, a relatively common predictive maintenance use case is monitoring and analyzing the condition of a motor to get alerts about its productivity levels, power consumption, health status, and internal wear.

Another powerful use case of predictive maintenance is minimizing production defects and reducing waste. Often referred to as Quality 4.0, such implementations can predict when the number of defective products is likely to exceed a threshold percentage, and provide the root causes for the expected failure.

Manufacturers are also turning to predictive maintenance for Factory 4.0, or a connected factory, by installing sensors in machines, workstations, and other designated sites such as the HVAC, security cameras or worker equipment, to predict issues across the factory floor.

predictive maintenance use cases

Common approaches to IoT predictive maintenance

The two most common approaches to predictive maintenance are rule-based and machine learning-based.

Rule-based predictive maintenance

Also referred to as condition monitoring, rule-based predictive maintenance relies on sensors to continuously collect data about assets, and sends alerts according to predefined rules, including when a specified threshold has been reached.

With rule-based analytics, product teams work alongside engineering and customer service departments to establish causes or contributing factors to their machines failing.

Once common reasons for product or part failures are established, manufacturers can build a virtual model of their connected system. Here they define product use cases, with “if-this-then-that” rules which describe the behaviors and inter-dependencies between the various IoT system components.

For example, if temperature and rotation speed are above certain predefined levels, the system will send an alert to an operator dashboard, to address the issue ahead of failure.

These rules provide a level of automated, predictive maintenance, but they are still dependent on a product team’s understanding of what parts or environmental elements require measuring.

The condition monitoring dashboards can be integrated with insight from machine learning to provide a visually understandable heatmap of asset conditions in real-time.

Predictive Maintenance with AI

Industrial artificial intelligence can be applied to predictive maintenance and many other use cases in the manufacturing industry, and although we are just in the beginning of exploiting this technology, there are already many facilities benefiting from industrial AI.

AI is perfectly suited to predictive maintenance. It offers a host of techniques to analyze the huge amounts of data collected from the manufacturing process, and deliver actionable insights to reach and sustain manufacturing excellence. These techniques are referred to as Machine Learning algorithms.

Applying Machine Learning to predict asset failure

Predictive maintenance with machine learning looks at large sets of historical or test data, combined with tailored machine-learning (ML) algorithms, to run different scenarios and predict what will go wrong, and when.

Predictive Maintenance ML Algorithms

Advanced AI algorithms learn a machine’s normal data behavior and use this as a baseline to identify and alert to deviations in real-time.

The algorithms required for machine learning must analyze input (historical or a training set of data) and output data (the desired result). A machine monitoring system includes input on a range of factors from temperature to pressure and engine speed. The output is the variable in question – a warning of a future system or part failure. The system will then be able to predict when a breakdown is likely to occur.

There are two main approaches to AI and machine learning for predictive analytics – supervised and unsupervised machine learning – each is relevant for a different scenario and depends on the availability of sufficient historical training data and the frequency of asset failure.

How can OEMs offer new customer service with predictive maintenance?

Predictive maintenance offers OEMs with a business value proposition to offer data-driven customer services and get recurring revenue in return. With PdM services, companies can build a subscription-model for customers to access dashboards or reports that will improve their OEE and reduce maintenance costs. Additional opportunities for services can be found in dispatching technicians for repairs, setting up alert systems, and shipping parts that need replacement ahead of failure.

How do I get started with IoT predictive maintenance?

Predictive maintenance is often restricted to a small subset of companies whose machines have been collecting OT data for years, and can utilize advanced analytics algorithms to sort through the data with machine learning and data science experts.

But for companies implementing a connected system for the first time, with the ultimate goal of implementing machine learning and AI for predictive maintenance, a pragmatic way to get started with industry 4.0 predictive maintenance is rule-based predictive maintenance.

With rule-based PdM, manufacturers can bypass the need for a large historical data set or advanced machine learning algorithms and data science at the outset.

Predictive Maintenance Dashboard - Machine Learning

This gives companies quick business results and a stepping stone into advanced analytics. In this model, product teams start with basic assumptions or ‘rules’ based on ‘what if’ scenarios that can be easily defined, rather than a machine algorithm running possible scenarios.

Rule-based predictive maintenance is achievable, affordable, and delivers measurable business benefits. The easiest way to get started is with an industrial IoT platform centered on a rule-based model, which enables teams to quickly define, simulate and deploy a predictive maintenance solution for their products.

Advanced analytics with predictive alerts and automated root cause analysis can be applied at a later phase – once sufficient historical data has been collected to accurately identify issues before they occur.

Deploy a predictive maintenance solution in under 12 weeks

Start free