Subscribe to our newsletter to receive the latest news and events from TWI:

Subscribe >
Skip to content

What is Predictive Maintenance?

   

Predictive maintenance is a technique that uses condition-monitoring tools and techniques to monitor the performance of a structure or a piece of equipment during operation. The recorded information enables an engineer to predict the future failure point of the asset being monitored, allowing for the asset to be fixed or replaced just before it fails.

Predictive maintenance allows the maintenance frequency to be much lower, while still preventing unplanned reactive maintenance, and minimises the equipment down time and costs associated with preventative maintenance. Predictive maintenance allows for the lifetime of the asset being monitored to be maximised.

How Does Predictive Maintenance Work?

Predictive maintenance uses condition-monitoring equipment to evaluate asset performance. The implemented sensors record a wide range of data, such as temperature, vibrations and conductivity, etc, from the physical actions of a structure or piece of equipment. A key element of the process is the Internet of Things (IoT), which allows for different systems to work together to translate and analyse the recorded data to estimate when maintenance should be performed. Additionally, over time, new machine-learning technology can increase the accuracy of the predictive algorithms, leading to even better performance [1].

With the affordability of bandwidth and storage, very large amounts of data can be recorded and analysed to give not only a full picture of assets in a single plant, but of an entire production network. With the arrival of industry 4.0, many industries are eager to utilise IoT to gain better insights into operations [1].

What is the Difference between Predictive and Preventative Maintenance?

Preventative maintenance involves inspecting and performing maintenance on an asset at predetermined intervals, whether or not it is required. The maintenance intervals are typically based on either usage or time, which are determined from the average life cycle of an asset. Preventative maintenance does not require an asset to be condition monitored, which can reduce capital investment costs. 

Predictive maintenance allows an asset to be consistently monitored, which helps to determine a maintenance plan tailored for each individual asset. This approach contributes to maximising the life of an asset while simultaneously reducing maintenance costs.

What are the Advantages and Disadvantages of Predictive Maintenance?

Predictive maintenance offers may advantages to industry, including:

  • Minimising the time required for asset maintenance
  • Minimising lost production hours through minimised downtime
  • Minimising the cost of spare parts through maximising the life of existing assets

Significant cost savings can be achieved through the above points. For example, predictive maintenance programmes have been shown to reduce maintenance costs by 30%, reduce breakdowns by 75% and reduce downtimes by 45%.

The initial drawback for industry is that the initial investment costs for predictive maintenance are high and require specialist, experienced personnel for data analysis to be effective. However, long-term analysis shows that predictive maintenance can average about 70% of the costs of a preventative maintenance programme [2].

How Can TWI Help?

Condition monitoring is widely used in the oil and gas industry for management of pressure vessels, storage tanks, pipelines and piping. It can be applied to aircraft and ageing vehicles, and has been implemented by TWI in the rail industry using vibration analysis for train door control systems and wireless for railway condition monitoring. TWI has also used condition monitoring to evaluate the overall operational condition of a wind turbine's machinery and rotating components; generator, gearbox bearings and main shaft.

TWI has a dedicated group of highly skilled engineers who use state-of-the-art equipment – such as the Fluke Ti 30 portable thermal imaging camera, the LOT Oriel/Thermal Wave Imaging Inc system and acoustic emission testing equipment from M/s Physical Acoustics – to undertake a wide range of condition monitoring activities for Member companies.

On example of TWI's work in the area of predictive maintenance is the DiMOS Project, where we worked alongside project partners, Vibtek Ltd, CMServices Global Ltd and Brunel University, to create a condition based monitoring system for ship structures, engine machinery and other auxiliary systems. The system uses an artificial intelligence platform for early fault detection to predict the requirement for maintenance and prevent damage to systems. The project is an example of how predictive maintenance can eliminate unnecessary tasks and focus resources on improving asset lifecycles. You can find out more about this project at: www.dimosproject.com (The DiMOS Project received funding from Innovate UK with Project Reference No. 104505).

Please contact us to learn more.

References

  1. Coleman, Chris, Satish Damodaran and Ed Deuel. “Predictive Maintenance and the Smart Factory.” Deloitte. 2017. https://www2.deloitte.com/content/dam/Deloitte/us/Documents/process-and-operations/us-cons-predictive-maintenance.pdf
  2. https://www.reliableplant.com/Read/12495/preventive-predictive-maintenance

Related Frequently Asked Questions (FAQs)

For more information please email:


contactus@twi.co.uk