Predicting the plant shutdown

Plant shutdowns have only recently evolved into a more detectable problem. These events are inevitable and when they did happen, the maintenance around them was only completed as a ‘necessary evil’, where the subsequent days of downtime and repair would affect the bottom line.

 

Within the area of asset performance management, developments and technical evolutions have always been incredibly slow, regarded as hard issues to control and deal with by the majority of the industry. However, over the past two decades these developments have become more progressive with detailed scheduling techniques although, with recent studies showing that over 85% of failures are completely random in nature, it has been proven that it is not possible to correlate failures with when and how maintenance was performed. The industry now needs something more robust to rely on, away from the calendar, that can drive these maintenance schedules.

 

To begin to alleviate these issues and further evolve in this area, to help prevent costly failures in future, there is one crucial point to address and that is of having the right working culture in place. Maintenance teams and departments should be able to work closely with the production operations, in turn this will drive robust reliability from the very foundations. This collaborative culture will need to be fuelled by a capability to predict assets easily and more accurately, this will enable the creation of optimal maintenance schedules.

 

A vast amount of companies today are relying on data scientists to build large numbers of asset models to enable the simulation of failure scenarios. Quite simply, this high quantity and level of work is unsustainable, the outputs frequently arrive too late and are usually in need of further expert consultancy to predict and interpret the model to provide a correct course of action. These consultants are also in short supply, adding another factor going against this practise. Thankfully, there have been developments in the form of low-touch machine learning, which can solve this issue. This new technology is representative of a breakthrough in automated data collection, cleaning and analysing to provide prescriptive maintenance protection for all equipment. This integration is a transition from estimated engineering with statistical models to more measured asset behaviour patterns.

 

Low-touch machine learning works by deploying accurate failure pattern recognition with high precision. This is then used to predict future equipment breakdowns, giving enough notice so that the appropriate avoidance action can be taken. If deployed alongside the appropriate automation protocols, this solution can enable far greater flexibility and agility, enabling the integration of current, historical and projected conditions from process sensors as well as mechanical and process events. As these systems increase in agility and adaptions, they incorporate the nuances of asset behaviour.

With ongoing skills shortages factored in as well, it is worth noting that a low-touch machine learning approach would eliminate the requirement for substantial resources and expertise to realise the value of the application.

 

How process data drives greater accuracy

 

A key element of the low-touch machine learning approach to asset performance management, of course, is the need to include process data to achieve more accurate and timely advanced knowledge of asset breakdown. Most asset failure today is directly related to process operations, which is why early warnings need more than condition and maintenance data.

 

Companies have gone as far as they can with condition-based monitoring (CBM), which is incapable of identifying the process-induced conditions causing the bulk of the breakdowns. Predictive maintenance requires looking upstream into process data.

 

Low-touch machine learning can deliver comprehensive monitoring of all the mechanical, upstream and downstream process conditions in a far more scalable way than data scientists or CBM. The result is hyper-accurate predictions of production degradation that ultimately leads to asset failure. Such insights are in turn exactly what is needed to get the company’s maintenance and operations teams working together to drive enhanced reliability.

 

Automating the hard work

 

Many companies today believe digitisation can result in significant operating expense savings. By tearing down silos of information and creating a more comprehensive view, companies believe they will drive better - and faster - outcomes. While this kind of approach has huge potential, any organisation that’s attempted this massive data analysis has run into issues around collection, timeliness, validation, cleansing, normalisation, synchronisation and structure.

 

With data preparation consuming 50-80 percent of the time in analysis, automation will be required for improvements in the speed of decision-making. The more an organisation can democratise the use of data by automating laborious and repetitive work, the more it can do to get value out of data.

Organisations can’t just digitise everything and hope it delivers success, of course. They need to remove barriers to return on investment by collecting the right data and automating the hard stuff, rather than just throwing tools and data at people. Any partner an organisation chooses in their digital transformation journey should have experience in managing data and information across design, operations, maintenance and the supply chain.

 

Positive Prospects

 

It has become objectively clear today, that the world of asset management is now completely unrecognisable from what it was just a few years ago. Previous maintenance practices have been reinvented and improved to recognise all the issues which affect asset degradation. The integrity of operations improves when energy companies implement the correct strategies to detect root failure causes as early as possible which provides longer lead times for the right decisions to be made in avoiding unplanned downtime. For organisations across the energy sector today, low-touch machine learning is ready to eliminate catastrophic failures of assets, to improve overall reliability and, by doing so, to positively impact the bottom line.