Xiangshun Li’s research while affiliated with Wuhan University of Technology and other places

In this paper, the current research status of controller performance assessment is reviewed in brief. Solving the problem of proportional–integral–derivative performance assessment usually requires step response data, and several methods are combined and extended. Using the integral of signals, implicit model information contained in process response data becomes explicit, and then the least squares approach is adopted to construct a detailed low-order process model based on process response data in more general types. A one-dimensional search algorithm is used to attain better estimation of process time delay, and integral equation approach is extended to be useful for more general process response. Based on the obtained model, a performance benchmark is established by simulating model output. Appropriate retuning methods are selected when the index of absolute integral error (IAE) indicates bad performance. Simulations and experiments verify the effectiveness of the proposed method. Issues about estimation of process time delay, data preprocessing, and parameter selection are studied and discussed.

In order to improve monitoring performance of dynamic process, a moving window independent component analysis method with adaptive threshold (MWAT-ICA) is proposed. On-line fault detection can be realized by applying moving windows technique, as well as false alarm caused by fluctuation of data can be effectively avoided by adaptive threshold. The efficiency of the proposed approach is demonstrated with a three-tank system. The results show that the MWAT-ICA can not only detect the fault quickly, but also has a high fault detection rate and no false alarm rate under the transient behaviors of the three-water tank and the normal operation process. These results demonstrate the effectiveness of the method for fault detection on the three-tank system.

Data-driven multivariate statistical analysis methods have been widely used in fault monitoring of large scale and complex industrial processes. Condition Gaussian Network (CGN) provides a way of probabilistic reasoning for continuous process variables, which has gained increasing attention. In this paper, a backward exponential filter is introduced into the discrimination rule and a CGN based on an adaptive threshold scheme is developed, which can effectively avoid process variables being misclassified due to small fluctuations caused by noise or disturbances. The purpose is to enhance the performance of the CGN method for process monitoring, while maintaining a low misclassification rate and false negative rate. The performance of the proposed method is evaluated at Tennessee Eastman Process and Intelligent Process Control-Test Facility. The results show that the proposed method performs better than the existing CGN-based methods and three conventional classification methods.

Applying fault detection and diagnosis (FDD) technology to the process industry can help to detect faults in time and minimize their impact. The purpose of this study is to propose an enhanced fault diagnosis method under a Conditional Gaussian Network(CGN) efficient and suitable for dynamic processes fault monitoring. The key paths are as follows: first, a time series model is established for the process data and decomposed into time-dependent components and time-independent components; second, time-dependent components are discarded and time-independent components void of auto-correlation are considered instead of the original data to learn the CGN model. A numerical simulation case is used to illustrate the interest of our proposal. The effectiveness of the proposed method is further verified and compared on the Tennessee Eastman Process (TEP). The obtained results show that our method has high and better accuracies regarding the diagnosis of known and unknown faults in dynamic processes.

Based on the angle and Euclidean distance similarity of the loading matrix, this paper reports on an improved principal component analysis (PCA) modeling method that is successfully applied to identify three different working conditions in the secondary loop of a nuclear power plant (NPP). First, a simulation platform of the secondary loop of the NPP is built in which three kinds of working conditions are set. Second, the multiple-PCA modeling method is used to construct the offline models. Finally, the effectiveness and superiority of the improved method is verified in the simulation platform.

In this study, a the two‐step support vector data description (TS‐SVDD) method is proposed to handle the problem of fault detection for dynamic, non‐linear, and non‐Gaussian processes. First, the dynamic structure of the data is identified and the data is divided into two components: innovation component and dynamic component. Then, the innovation component is used to make the SVDD model for fault detection. Moreover, in order to overcome the issue with two‐step principal component analysis (TS‐PCA) that the choice of parameters q and D affects the fault detection effect of the methods, a genetic algorithm (GA) is used to optimize the parameters. The proposed method combines the advantages of TS‐PCA in processing dynamic process data and SVDD in dealing with non‐linear and non‐Gaussian process data. In order to evaluate the effectiveness and superiority of the proposed method, TS‐SVDD is applied to the Tennessee Eastman (TE) process and the intelligent industrial processes control test facility (I²PC‐TF), and the fault detection performance is compared with TS‐PCA and SVDD in terms of dault detection rate (FDR) and false alarm rate (FAR). The results show that TS‐SVDD has a better monitoring performance.

In view of the randomness in the selection of kernel parameters in the traditional kernel independent component analysis (KICA) algorithm, this paper proposes a CPSO-KICA algorithm based on Chaotic Particle Swarm Optimization (CPSO) and KICA. In CPSO-KICA, the maximum entropy of the extracted independent component is first adopted as the fitness function of the PSO algorithm to determine the optimal kernel parameters, then the chaotic algorithm (CO) is used to avoid the local optimum existing in the traditional PSO algorithm. Finally, this proposed algorithm is compared with Weighted KICA (WKICA) and PSO-KICA with Tennessee Eastman Process (TEP) as the benchmark. Simulation results show that the proposed algorithm can determine the optimal kernel parameters and perform better in terms of false alarm rates (FAR), detection latency (DL) and fault detection rates (FDR).