What is predictive maintenance?
Predictive maintenance continually assesses equipment health in real time, helping you to maximise equipment performance, uptime, and lifespan while minimising total cost of ownership.
Predictive maintenance definition
Predictive maintenance is an approach to maintenance that puts the emphasis on hearing what your enterprise assets are trying to tell you. The machines in your factories, your fleet of trucks, your industrial equipment – they’ve been talking to you for years. If you can listen closely, you can understand when your machines are about to break down and what they need to run longer and more smoothly.
Predictive maintenance enables your business to anticipate equipment failures and schedule maintenance when and where it’s immediately needed. It arms you with the information needed to run your assets at peak performance without pushing them too far and risking costly breakdowns. By connecting IoT-enabled enterprise assets, applying advanced analytics to the real-time data they generate, and using the associated insights to inform cost-effective, efficient maintenance protocols, predictive maintenance prevents equipment failure and downtime, and extends the overall lifetime of vital assets.
Why is predictive maintenance so important today?
Predictive maintenance is important because it saves companies time and money by heading off costly and disruptive equipment failure. As consumer demand for product availability grows, organisations with predictive maintenance programmes can produce without disruptions. The result is ongoing customer loyalty, higher revenues, and improved competitive advantage.
Smart predictive maintenance solutions predict when asset maintenance is needed, help increase cost efficiency, and streamline complex enterprise asset management requirements. Put simply, employing predictive maintenance technology helps your business save time, money, and procedural headaches.
How does predictive maintenance work?
Predictive maintenance works by capturing and analysing equipment data in real time to predict potential issues before they lead to equipment failure.
The first step in this process involves the collection of real-time data and information from networked IoT sensors that transmit information on equipment conditions. This data must then be stored and managed in a way that it can be readily accessed, processed, and analysed. The “predictive” component comes into play when artificial intelligence (AI) and machine learning technologies are applied to the data to tell a useful and actionable story.
There are four basic stages to the architecture of predictive maintenance and an Industrial IoT (IIoT) network:
The predictive maintenance process
- Gathering data from sensors that can monitor machine characteristics such as vibration, temperature, humidity, pressure, noise, and more
- Transmitting this data in real time across the network to a central business system
- Applying intelligent technologies like AI and machine learning analytics to that data, to reveal useful and relevant insights
- Taking rapid action based on these insights, either with an automated response or through human intervention
Using predictive maintenance technologies
Condition monitoring
Predictive maintenance is made possible through cyber-physical systems that bring machines and software together into an intelligent IoT network. To build such a network, start by identifying the asset conditions that need to be monitored.
The analysis required to identify the asset conditions may be visual, auditory, thermal, or most typically, a combination of these criteria. The focus at this point is on determining the correct sensors and monitoring tools to be fitted:
Vibration analysis: Small changes in vibration patterns may indicate imbalance or misalignment, while high vibration levels may indicate impending bearing problems. Vibration analysis can give early warnings of failure and is particularly useful in detecting imbalance, misalignment, mechanical looseness, or worn or damaged parts.
Sound and ultrasonic analysis: Under normal operation, most systems create steady sound patterns. Changes in the reference sound pattern can indicate wear or other types of deterioration. Ultrasonic analyses can also give information about the overall health of the system by translating high-frequency sounds (such as those produced by steam or air leaks) into the audible range.
Infrared analysis: As with ultrasonic analysis, thermography also uncovers the hidden using infrared analysis to translate temperature changes into a visible spectrum. Even subtle changes to normal operational temperatures can warn of impending problems.
Fluid analysis: Beyond simply monitoring the fluid levels and temperature, the physical and chemical analysis of fluids can give valuable information about the condition of mechanical components. By detecting the rate of degradation in coolants and lubricants, preventive steps can be taken as soon as these insights warrant.
Others: Other predictive maintenance technologies are specialised for various unique industrial needs. These include laser alignment, electrical circuit monitoring, crack detection, fault detection, corrosion monitoring, electrical resistance changes, and other industry-specific means of measuring corrosion or deterioration.
Key predictive maintenance technologies
Once the above criteria are established, the appropriate sensors and monitors must be fitted and connected to a central business system, most commonly an enterprise resource planning (ERP) system, through a cloud-connected IoT network. Finally, AI-driven solutions must be in place to analyse the data and deliver actionable insights and recommendations from the data gathered.
IoT network: When enterprise assets are augmented with sensors, processing ability, and other technologies, they can send and receive data – usually via cloud connectivity – to and from a central business system. This comprises an IoT network and underpins the predictive maintenance strategy.
IoT gateways: Many older assets still work perfectly well, yet their analogue technology predates digital integration. These machines can be fitted with IoT gateway devices, which may include cameras, microphones, and thermometers, to gather and transmit real-time data on their operational states.
Cloud connectivity: Cloud connectivity delivers the on-demand availability of computer system resources. In an IoT network comprised of multiple industrial assets, it’s critical that multi-location data centres be integrated into a single database and system.
Modern database and ERP: Legacy disk-based databases are not well equipped to manage the voluminous and non-linear data that comprises Big Data and complex data sets. Furthermore, predictive maintenance uses AI and machine learning to perform advanced analytics on such data. This whole process is best served by a modern AI-powered ERP with an in-memory database that is fast, responsive, and almost infinitely scalable.
AI and machine learning: Machine learning is a subset of AI that uses algorithms to analyse and understand data. Predictive maintenance solutions depend on AI and machine learning to not only sort, understand, and learn from the operational data of enterprise assets but to also generate actionable recommendations and insights.
Advanced analytics: AI and machine learning power advanced analytics. Managers must determine the attributes and conditions to be assessed and the analytical outcomes desired. In this way, the algorithms that inform advanced analytics can be programmed to be as insightful and actionable as possible, and to best learn from data and new experiences over time.
Digital twins: A digital twin is a virtual recreation of an actual physical asset. By creating digital twins, managers can visit any possible operational scenario upon the twin – without any risk of actual real-life damage to a costly machine or device. This helps to augment predictive maintenance by allowing machine learning and AI tools to incorporate and learn from experiences that have never even happened.
Predictive maintenance vs. preventive maintenance
The difference between these maintenance models lays not so much in how the maintenance tasks are undertaken, but when.
Preventive maintenance: Maintenance that is informed by past performance and the knowledge and experience of engineers and operators. It includes routine, periodic, planned, or time-based maintenance. While it often prevents breakdowns, it can be inexact, which may lead to expensive maintenance before it’s needed or to unnoticed weaknesses in the maintenance process. Preventive maintenance happens at times that are pre-set, often long in advance.
Predictive maintenance: Maintenance that is made possible when IoT networks integrate all enterprise assets into a live ecosystem. The ability to transmit and analyse data in real time, means that live asset condition monitoring – rather than calendars – becomes the foundation for maintenance protocols. Predictive maintenance happens in real time, exactly when and where it’s needed.
Other asset maintenance techniques
Reactive maintenance
Maintenance performed in response to a sudden breakdown or failure of equipment. This type of maintenance is often unplanned and can result in increased downtime and costs.
Corrective maintenance
Maintenance performed to correct a defect or fault in equipment. This type of maintenance is typically undertaken after a problem has been identified and can help to prevent further issues from occurring.
Prescriptive maintenance
Maintenance that is determined by the manufacturer's recommendations or guidelines for a specific piece of equipment. This type of maintenance is based on the manufacturer's prescribed schedule for maintenance tasks.
Condition-based maintenance
Maintenance performed based on the condition of equipment, rather than a predetermined schedule. This type of maintenance uses monitoring and inspection to determine when intervention is necessary. While it can help to reduce unnecessary maintenance tasks and minimise downtime, condition-based maintenance is highly manual and time consuming.
Reliability-centred maintenance
Maintenance that prioritises tasks based on the reliability and criticality of equipment. This approach focuses on identifying the most important maintenance tasks to maximise equipment reliability and efficiency.
The evolution of asset maintenance
The following chart (adapted from Deloitte) displays the progression of technological capabilities throughout industrial revolutions and the resulting impact on maintenance strategies and equipment effectiveness.
Predictive maintenance examples in action
Oil and gas sector: Oil drilling puts enormous wear on assets and can lead to great risk and danger in the event of a failure. By monitoring oil temperature and the speed of gearboxes in drilling equipment, predictive maintenance has greatly improved safety and reduced maintenance costs by up to 38%.
Automotive industry: On assembly lines, spot-welding guns perform about 15,000 spot welds each per day. By connecting welding guns around the world and collecting their operational data, auto manufacturers can gather millions of data points, leading to unprecedented predictive accuracy on the condition and state of these assets.
Domestic appliance manufacturing: Vibration measurements of the drum rotation in the production of dryers have helped predict malfunctioning or breakdown. This predictive maintenance application has eliminated manufacturing defects by 33% and reduced consumer maintenance costs by 27%.
Railroad asset management: “Voids” occur when an empty space develops under a track leading to potential delay or even derailment. Recent innovation has led to cab-based systems that monitor a number of variables as they roll over the rails. This has led to improved void detection and an overall rise in customer safety.
Steel industry: Anomaly detection is being used to gather real-time readings of the vibration, rotational speed, and electrical current (amperes) in the cold-rolling equipment used in steel processing. This application has led to a 60% improvement in equipment lifetime and greatly reduced losses due to downtime and delays.
Benefits of predictive maintenance programmes
The implementation of predictive maintenance systems has led to impressive results across multiple industries. A 2022 report from Deloitte cites numerous quantifiable improvements. These include up to a 15% reduction in downtime, a 20% increase in labour productivity, and a 30% reduction in inventory levels with less need to stock just-in-case parts.
With technologies like AI and integrated ERP on hand, organisations are showing the benefits of predictive maintenance solutions that really work. These include:
Better visibility across your entire operation: With increased visibility into field assets and other off-site equipment, OEMs and third-party service providers can deliver more informed services and greater value.
Lower maintenance costs and improved asset performance: By minimising downtime, predictive maintenance saves you money and helps you get more use from existing assets even as you extend their lifespans.
More empowered teams: Armed with data science and real-time analytics, your asset operators, service providers, and supply chain managers can make the transition from firefighters to planners and strategists.
Overcoming common predictive maintenance challenges
This section highlights common predictive maintenance challenges and explores strategies for overcoming them.
Data quality and availability: Predictive maintenance relies heavily on high-quality and sufficient historical data. Poor data quality or insufficient data can lead to inaccurate predictions. To help ensure data quality, the best practice is to establish a data governance program backed by key stakeholders.
IoT connectivity: Setting up a connected IoT network requires smart equipment and edge devices with sensors that can connect to data lakes and transmit data in flat file formats. Put the emphasis on simplifying your connectivity scenarios so that you can connect to any IoT data source without problems.
IoT device management: Managing IoT network devices requires a focus on device security to minimise vulnerabilities to cyber-attacks. At the same time, you want to promote interoperability across devices and scale up as needed. To strike the right balance, it is best to adopt modern asset performance management solutions that support embedded advanced device management and robust connectivity capabilities.
Data integration: Integrating data from various sources such as IoT sensors, legacy systems, and maintenance records can be complex and time-consuming. Look for a powerful, enterprise-grade integration platform with a comprehensive library of pre-built connectors to support your data integration needs.
Sensor data complexity: IoT sensor data can be difficult to understand, often requiring specialised data knowledge that presents a barrier to reliability engineers. Look for asset performance management solutions that can distill data for non-technical audiences to understand and manipulate.
Algorithm selection: Choosing the right algorithms for predictive maintenance is key to success. Be sure to carefully evaluate specific use cases and the characteristics of the data in order to choose the most appropriate algorithms for your machinery and business needs.
Maintenance strategy integration: Implementing predictive maintenance requires integrating it into existing maintenance strategies and workflows. Resistance to change and organisational inertia can hinder successful implementation. Strong leadership, executive backing, clear communication, and professional change management are required for success.
How to implement a predictive maintenance program in three simple steps
- Define objectives and determine scope: Start by identifying which monitoring conditions are right for each asset. For instance, infrared thermography is best used on equipment that may leak air or steam while vibration analysis is best used on rotating equipment, but not equipment that rotates slowly (less than 5 rpm). Oil analysis and acoustic analysis are better for slow rotating equipment. Also, be sure to determine the scope of your efforts. For instance, will you monitor specific, individual assets or are you striving for more comprehensive coverage?
- Install appropriate IoT sensors: Install IoT sensors based on the types of analysis most appropriate to each monitored asset – then begin collecting data. Ensure these sensors are connected to data processing systems – like those commonly integrated into asset performance management solutions – to cut down on cost, time, and human error.
- Set up protocols: To effectively respond to anomaly detections, set up protocols to ensure assets are repaired efficiently and in alignment with uptime goals. These protocols can be automated, manual, or a mixture of both.
Transform your supply chain with predictive maintenance solutions
Many businesses have not changed their asset maintenance strategies in decades – despite having modernised other areas of their business. Changing longstanding processes is challenging and it can be difficult to get buy-in from your teams. The most successful business transformation plans begin with a good communication and change management strategy – to help engage your teams and break down silos. Speak to your software vendor to learn more about which tools and solutions will work best for your unique needs and to get you rolling with your road map and digital transformation journey.
Explore predictive maintenance solutions
Maximise your asset performance with modern predictive maintenance tools.
Driving asset, reliability, and safety with AI
Find out how railways and other asset-intensive industries can use AI-assisted visual inspection to improve reliability, optimise operations, and lower costs.