Detection of Intermittent Oscillation in Process Control Loops with Semi-Supervised Learning

Oscillations in the control loops indicate poor performance of loops. The occurrence oscillations process loop is quite high industry, so it needs to be reduced that can work properly. first step for oscillation reduction detection. One type difficult detect intermittent oscillation. smart factory concept encourages development detection system using machine learning by being implemented online. Therefore, this study an online program built K-nearest neighbor (KNN)-based Semi-supervised (SSL) method. SSL method applied self-training. training data was obtained a simulation Tennessee Eastman Process. segmented based on window size and extracted time series features. used build model caused stiction, tuning errors, external disturbances reactor. with sliding windows MQTT. best accuracy F1-score are 96.15% 95.15%. In detection, detects average 305 seconds.