Research on Fault Detection Method Based on Improved Euclidean Distance Control

Aiming at the problem of poor fault detection in complex industrial processes, this paper proposes a fault detection method based on improved Euclidean distance control. First, the data is standardized and the Euclidean distance is obtained; Secondly, the distance value with a larger data contribution rate is determined by the idea of exponential contribution; Thirdly, a parameter adaptive strategy is proposed to set the threshold of Euclidean distance statistics; Finally, fault detection is carried out on the statistical data, and the size of false negative rate and false alarm rate is calculated. In the fourth part of this paper, we use the fault detection method based on improved Euclidean distance control to detect the fault of the Eastman process in Tennessee. The simulation results show that the method proposed in this paper has more advantages than the traditional principal component analysis method, and can be effectively applied to complex industrial processes.