(135d) Implementing Statistical Process Control Using Python and Iiot for Real-Time Process Monitoring and Decision-Making

Statistical Process Control (SPC) is characterized by a set of statistical tools applied to production processes, allowing the systematic reduction of interference caused by the variability of special (non-natural) causes on the main quality characteristics of the product. If such problems are eliminated without the product being affected, the cost associated with reprocessing time and analysis of out-of-spec batches is reduced [1]. In the context of Industry 4.0 and the Industrial Internet of Things (IIoT), a variety of analysis and correlation technologies have emerged to predict situations based on data collected from multiple sources. Using a data infrastructure, it is possible to develop applications that utilize this information for process evaluation, operational, economic, or strategic decision-making, as well as for developing machine learning structures and phenomenological models with numerous applications [2].

Thus, the use of a data evaluation structure becomes paramount, and Python proves to be the ideal environment for such an implementation. The objective was to determine the Statistical Process Control (SPC) control limits using the stored data on the PI System (AVEVA/OSIsoft). The purpose of this approach was to evaluate an ongoing production process and facilitate comparative analysis of relevant literature. Once such limits determined, it is possible to be used on real-time analysis, as well as the development of structures for operational, economic and/or strategic decisions. To achieve this goal, a module was developed using Python and OPC communication to connect with the PI System database, storage, and visualization applications. The module was designed to create graphics according to the prescribed parameters [1; 3] for the control charts, enabling the construction of supervision screens that can be utilized for process monitoring and decision-making.

Keywords: SPC; Variability; IIoT; Data; Python.

References

[1] MONTGOMERY, D., Introduction to Statistical Quality Control, John Wiley and Sons, 2009.

[2] ROFFEL, B. E BETLEM, B., Process Dynamics and Control - Modeling for Control and Prediction, John Wiley & Sons, 2006.

[3] WHEELER, D., Advanced Topics in Statistical Process Control: The power of Shewharts Charts, SPC Press, 2004.