- Register


Home >Blogs>Charlotte Stonestreet >Let's work together

Let's work together

22 October 2019

Although not a particularly new soundbite, the trope that ‘data is the new oil’ seems to be more and more frequently referred to.

This isn’t really surprising as data is the driving force behind many of today’s transformative technologies; just think about AI, automation and the latest predictive maintenance. And like oil, data needs to be refined to realise its full value, and it is often at this point that organisations can become somewhat stuck - intelligent devices are providing unprecedented access to data, but what good is the data if you don’t know what to do with it?

Enter the data scientist; a new breed of analytical data expert, or dare I say, statistician, with the technical skills to solve complex problems. So, looking at the engineering sector, which is experiencing a dearth of skilled individuals, maybe the data scientist could help fill the gap? After all, the data scientist and the engineer will often have many common skills.

Well, this isn't necessarily such a great idea, according to Professor Andrew Ball, an expert in the field of diagnostic engineering. Speaking at the recent 2019 Condition Monitoring and Diagnostic Engineering Conference (COMADEM) he warned against recent claims that the future of predictive maintenance should be led by data science, and not engineers.

Professor Ball, who co-chaired the conference, told delegates that the separate techniques of detecting, diagnosing, assessing the severity and prognosis of machine faults require engineering expertise and context to achieve the accuracy and timely results demanded in the field of predictive maintenance.

“I have attended conferences recently where speakers have talked about purely data-driven approaches to predictive maintenance, with no concept of what engineering really needs,” he told his audience.

Professor Ball stressed that successful interventions could only be achieved by engineers and data scientists working together.

“Data-driven methods are truly excellent for identifying patterns and anomalies in large, complex data sets, and warn us when to undertake fault diagnosis, location and severity assessments,” he said, “but the latter steps cannot be achieved using data-driven methods alone. Predictive maintenance is an engineering discipline. One that can be significantly assisted by data science, but only if they work together.”

It is vitally important to get this balance right. Predictive maintenance has huge potential benefits, but users do need to get it right in order for these to be attained and there really is no better alternative than an experienced engineer in bringing this about.