Impact of condition monitoring techniques on plant numbers

Errors in maintenance and safety procedures cause many problems for companies that are forced to make expensive and disruptive reactive calls once an asset has broken down.

Standard scheduled maintenance can be a wasteful practice for several reasons. The first is because a regularly maintained device does not require maintenance, making scheduled maintenance a wasted operational practice. The second is because failure catalysts are often introduced into properly functioning equipment, and devices often fail immediately after maintenance. To better control costs, process manufacturers have embarked on an aggressive campaign to minimise such operations by focusing on condition monitoring techniques to significantly improve both availability and reliability.

What are condition monitoring techniques?

The condition monitoring techniques are a type of predictive maintenance that combines software and services and involves the use of sensors to measure the condition of an asset over time while it is in operation. The data collected can be used to establish trends, predict equipment or process failures and calculate the remaining useful life of an asset. The condition monitoring techniques can create alerts and share data for use in workflows, dashboards and reports.

When using software to condition monitoring techniques, digital twin algorithms are employed that address the central problems inherent in condition-based monitoring. The algorithms look at the differences between the current behaviour of a process and the past behaviour of a process combined with historical past behaviour. This is likely to show very subtle deviations in performance.

Algorithms have to make sense of the information from the kernel monitoring. The reconstructed state is called an estimate or estimation vector. The estimate represents the good or expected behaviour of the asset given the context to the captured data. It is then compared to the behaviour of the asset as it actually occurs at a given point in time. The difference between the two signals is then analysed using sophisticated statistical algorithms to detect deviations from normality.

It's not just the algorithm itself that makes the condition monitoring techniques. It is all the supporting machinery, the additional algorithms that make sense of the output of the core machine learning algorithm and, sometimes most importantly, the expertise in analysing the output to make recommendations on next steps.

When the condition monitoring techniques are able to proactively detect problems, maintenance labour costs can be reduced by moving from unplanned to planned maintenance, decreasing the amount of time a maintenance procedure takes and extending the intervals between maintenance procedures.

In addition, there is a decrease in maintenance costs with less expense to repair or replace damaged parts. Although this type of benefit may seem insignificant, the process industry can save as much through reduced fuel and more efficient operation of their equipment as they can through savings in maintenance costs. Find out more with this Comparison between condition-based maintenance and preventive maintenance. 

How do condition monitoring techniques work?

Each team is unique and is reflected in its own historical data and you have to know what to look for and what to do with the information:

• Anomaly detection: Anomaly detection models contextualise the normal operating relationships between all relevant parameters such as load, temperatures, pressures, vibration readings and environmental conditions. Real-time analyses compare sensor readings with normal and expected values for a given machine. The software of condition monitoring techniques detects and identifies events and abnormal behaviour by the differences between the actual real-time data and the expected normal behaviour, and not by the thresholds of the actual values.
• Diagnostic analysis: Anomaly reports are compared with precursor signatures based on pattern and persistence. These provide prioritised diagnostics with a localised and apparent cause for each developing problem. For all identified problems, prompt reporting is required so that reliability and maintenance experts can track and diagnose developing faults.
• Performance time forecasting: Actuation time analytics can then be applied to the analysis process. Using multiple analytics and desired time windows, engineers can predict when equipment will actually reach an alarm limit and require immediate repair. With this information, teams can prioritise and schedule corrective actions to avoid downtime at minimal cost. Action time analysis can also be applied independently at any time to forecast future maintenance needs.

Adopting a digital solution solves some traditional limitations of equipment maintenance. Digital solutions help centralise data collection and equipment health views, and provide predictive analytics and policies, as well as analytics to modernise the way work is done and, last but not least, provide an automated and traceable process.

Benefits of condition monitoring techniques

By moving to a proactive, data-driven operations strategy, process manufacturers can expect a reduction of up to 40% in spending associated with unplanned maintenance. This leads to a decrease in production losses across all sectors: energy, oil, gas, and natural materials for metals and mining companies.

Leading companies can improve operations, optimise reliability and increase availability with today's predictive technologies. They can also improve availability and reliability because they can detect impending problems in time to act proactively before problems affect operations.

Effective predictive maintenance focuses on advanced analytics to predict, diagnose and forecast future problems. The digital twins used in the condition monitoring techniques provide automated monitoring to uncover developing problems, diagnostic guidance for analysis and causal actions, and predictive intelligence on time-to-action to ensure that repair is scheduled prior to any failure.

The software provides visualisation, analysis and case management tools, along with analytical intelligence that reliability and maintenance engineers can use to investigate alerts, perform root cause analysis, determine immediate and long-term maintenance strategies and track ultimate success.

Another positive aspect of the condition monitoring techniques is that it can extend the useful life of an asset. In addition to improving reliability, the data collected can help maintain a unified view of asset condition and operational health.

If you are thinking about adopting condition monitoring solutions for your company, don't miss out on how to make condition-based maintenance more effective to make the most of all its advantages.