(163b) Data Analytics Gives Manufacturing Plants Insights for Continuous Improvement

Industry 4.0 and the Industrial Internet of Things (IIOT) promise to make more data and better analytic applications available for industry. Driven by high powered analytics, including machine learning and artificial intelligence engines, both promise operational benefits including lower costs through improved Key Performance Indicators (KPI), such as First Pass Yield, Non-Standard Downtime or Overall Equipment Effectiveness. However, despite the investments in data capture and analytics, the industry faces a daunting challenge when attempting to drive continuous improvement, given the amount, types and lack of context in most manufacturing data. The result on the shop floor is often characterized by data overload and inaction. We present a proven strategy for continuous improvement in manufacturing that can provide (1) insights into process variability, (2) correlations with product quality measures, (3) real-time statistical process control (SPC), (4) hierarchically structured data for regulatory compliance, and (5) powerful machine learning algorithms to handle massive and disparate data common in process industries. Incorporation of this strategy into Continuous Improvement systems (Lean Six Sigma) has led to bottom line improvements in hundreds of work centers in a global infrastructure. An example from a Chemical Reactor is presented to illustrate the methodology and application in both an on premise and cloud based environment. Techniques are utilized employing both univariate and machine learning algorithms to illustrate how to explore and monitor complex manufacturing data sets.