Randomized autoregressive dynamic slow feature analysis method for industrial process fault monitoring

Kernel-based slow feature analysis (SFA) methods have been successfully applied in the industrial process fault detection field. However, kernel-based SFA methods have high computational complexity as dealing with nonlinearity, leading to delays in detecting time-varying data features. Additionally, the uncertain kernel function and kernel parameters limit the ability of the extracted features to express process characteristics, resulting in poor fault detection performance. To alleviate the above problems, a novel randomized auto-regressive dynamic slow feature analysis (RRDSFA) method is proposed to simultaneously monitor the operating point deviations and process dynamic faults, enabling real-time monitoring of data features in industrial processes. Firstly, the proposed Random Fourier mapping-based method achieves more effective nonlinear transformation, contrasting with the current kernel-based RDSFA algorithm that may lead to significant computational complexity. Secondly, a randomized RDSFA model is developed to extract nonlinear dynamic slow features. Furthermore, a Bayesian inference-based overall fault monitoring model including all RRDSFA sub-models is developed to overcome the randomness of random Fourier mapping. Finally, the superiority and effectiveness of the proposed monitoring method are demonstrated through a numerical case and a simulation of continuous stirred tank reactor.