Multi-oscillations Detection for Process Variables Based on K-Nearest Neighbor

Abstract

In the process industry, a control system is important to ensure the process runs smoothly and keeps the product under predetermined specifications. Oscillations in process variables can affect the decreasing profitability of the plant. It is important to detect the oscillation before it becomes a problem for profitability. Various methods have been developed; however, the methods still need to improve when implemented online for multi-oscillation. Therefore, this research uses a machine learning-based method with the K-Nearest Neighbour (KNN) algorithm to detect multi-oscillation in the control loop, and the detection methods are made to carry out online detection from real plants. The developed method simulated the Tennessee Eastman Process (TEP), and it used Python programming to create a KNN model and extract time series data into the frequency domain. The Message Queuing Telemetry Transport (MQTT) communication protocol has been used to implement as an online system. The result of the implementation showed that two KNN models were made with different window size variations to get the best performance model. The best model for multi-oscillation detection was obtained with an F1 score of 76% for detection.