Fault diagnosis in industrial chemical processes using optimal probabilistic neural network

Abstract

For fault detection and diagnosis in large‐scale industrial systems, traditional methods have a low classification accuracy, which is an issue. This paper proposes a fault diagnosis method based on the modified cuckoo search algorithm (MCS) to optimize the probabilistic neural network (PNN). The random forest treebagger (RFtb) is used to reduce the data feature and the PNN is trained for fault diagnosis and classification. However, in order to address the problem that the parameters of PNN easily fall into the local optimal value, the MCS algorithm is introduced to globally optimize the hidden layer element smoothing factor (σ) in the PNN. The MCS algorithm uses a parameters update and a better optimization mechanism to achieve excellent global convergence and to effectively improve the fault diagnosis capability of the model. During the testing process using the Tennessee Eastman (TE) process dataset, the performance of the proposed model is assessed by comparing the accuracy and the F1‐score of different methods. Graphs are presented that depict fault classification and diagnostic results for the different models. The results show that the MCS algorithm has a better optimization ability than the traditional optimization algorithm and the proposed combination method can significantly improve the accuracy of the TE process fault diagnosis.

Deep neural network based recursive feature learning for nonlinear dynamic process monitoring

“…The parameters of the neural network are not designed by human engineers but are learned from the data, which makes it better for nonlinear process monitoring . Recently, deep learning has gained more attention from the field of process monitoring than ever before, especially the stacked denoising auto‐encoder (SDAE) . Zhang et al proposed a process monitoring algorithm based on SDAE.…”

“…[20,21] Recently, deep learning has gained more attention from the field of process monitoring than ever before, especially the stacked denoising auto-encoder (SDAE). [22][23][24][25] Zhang et al [25] proposed a process monitoring algorithm based on SDAE. First, SDAE is utilized to model the nonlinear relationship by encoding the collected data into latent variables.…”

Chemical process fault diagnosis based on enchanted machine‐learning approach

“…In order to verify the performance of the proposed model in fault diagnosis, first we use genetic algorithm (GA), particle swarm optimization (PSO) algorithm, and MBA algorithm to optimize PNN for diagnosis. In addition, we input normal training samples and fault training samples corresponding to various fault characteristics into the MBA‐PNN model and some common diagnostic models, such as support vector machine (SVM), linear discriminant analysis (LDA), K nearest neighbour (KNN), naive Bayes (NB), and multilayer perceptron (MLP) . In terms of the parameters of the optimization model, the number of iterations is 50 and the optimal number of algorithms in the GA‐PNN, PSO‐PNN, and MBA‐PNN models is 20.…”

“…In addition, we input normal training samples and fault training samples corresponding to various fault characteristics into the MBA-PNN model and some common diagnostic models, such as support vector machine (SVM), linear discriminant analysis (LDA), K nearest neighbour (KNN), naive Bayes (NB), and multilayer perceptron (MLP). [29][30][31][32][33][34][35] In terms of the parameters of the optimization model, the number of iterations is 50 and the optimal number of algorithms in the GA-PNN, PSO-PNN, and MBA-PNN models is 20. According to the Lin et al [36] the MBA algorithm sets frequency value ω to 0.25, α to .2, and γ to 0.9.…”

Issue Highlights

“…The parameter smoothing factor (σ) in the network was optimized by the modified cuckoo search algorithm, which makes the network have a better classification effect. The experimental results compared the accuracy and F 1 ‐score of different fault diagnosis models to evaluate the diagnostic performance of the proposed model …”