The Path to Analytics Maturity—Step 4: Implementing Inline Analysis

This is the fourth and final post in our four-part weekly series exploring analytics maturity. If you missed the beginning of the series, catch up by reading Step 1: Monitoring Critical Assets, Step 2: Applying Specific Analytics and Step 3: Leveraging Preventative Analytics.

Once a customer has made this leap—learning to monitor, apply and leverage their opportunities for analytics—and trusts their analytics, they're able to use inline analysis to drive to optimization in their process and asset health. Optimization can mean many things. Optimizing to minimize energy consumption is one kind of Captureoptimization. Optimizing for throughput is another. Typically, advanced process control and model predictive control analytics are used to adjust high-speed equipment to variances in input or process in a way that a human operator could never achieve. Done with real-time data, optimization analytics run as closed-loop systems—often at the point of control within the controls hardware.

One example that comes to mind is when a customer used advanced process control to handle variables in a drying operation where input variability to the dryer often means that operators overreact and over-dry materials in order to handle excess “lumpy” input. In their zeal to ensure proper drying for worst-case scenarios, they were spending too much time drying normal case loads. Surprisingly, this became the single largest bottleneck in their operations. By leveraging advanced process control analytics, the customer allowed the analytics to determine drying time based on variability in input load.

Using the proper drying time for each input load resulted in 10% more throughput, while also driving down energy costs. In this case, there was capacity in the system to absorb the 10% increase in throughput from the drying stage, which in turn resulted in 10% more throughput for the entire operation! Because of this, the customer saw pure profit in the range of $20 million.

As companies learn to trust analytics to help them monitor, analyze, predict and optimize their operations, they are able to see more and more benefits and profit for their efforts. The journey not only includes learning how to leverage increasingly advanced analytic techniques; the operator must also learn to trust them and change behavior based on them. At the end of the day, if the operator ignores what the analytics are saying and fails to act, the analytics are useless. Operators must learn to trust the data more than their own natural instincts. This is a journey. And GE is right there on the path with you.

Brian Courtney

A recent transplant to the MidWest, Brian thinks Big Data “rocks.” He’s recently taken the Analytics piece of GE’s business under his wing, so if you have thoughts on any of these – MidWest, Big Data or Predictive Analytics – even rocks – follow Brian on Twitter @brianscourtney.

More Posts