An improved industrial fault diagnosis model by integrating enhanced variational mode decomposition with sparse process monitoring method

With the continuous development of intelligent industrial processes, the sparse principal component analysis (SPCA), as a promising process monitoring method, has been widely used in the field of industrial fault detection. However, due to the inadequacy of data preprocessing and the insufficient detection accuracy for minor faults, the SPCA models exhibit obvious limitations in dealing with the processes with dynamic and temporal features. In this study, a Harris Hawk optimization method enhanced variational mode decomposition (HHO-VMD) coupled with the sliding window optimized adaptive SPCA (SWOASPCA) method is proposed to improve the fault detection performance of the SPCA models. In the HHO-VMD-SWOASPCA method, the process data is first preprocessed by adaptively and iteratively optimizing the number of modes and penalty terms in the VMD method via the Harris Hawk Optimization (HHO) method, and then the original SPCA model is combined with the sliding window method and the weight assignment strategy to enhance the model's adaptive capability and accuracy to detect minor faults. Moreover, an improved reconstruction-based contribution (RBC) method is presented to diagnose the detected faults for determining the fault causes. The effectiveness of the proposed method is verified by its application in the industrial sugar production process.