Search

With data in industrial processes being larger in scale and easier to access, data-driven technologies have become more prevalent in process monitoring. Fault classification is an indispensable part of process monitoring, while machine learning is an effective tool for fault classification. In most practical cases, however, the number of fault data is far smaller than normal data, and this imbalance of dataset would lead to the significant decline in performance of common classifier learning algorithms. To this issue, we propose a data augmentation method, which is based on Generative Adversarial Networks(GAN) and aided by Gaussian Discriminant Analysis(GDA), for enhancement of fault classification accuracy. To validate the effectiveness of this method for imbalanced fault classification, on toy data and the Tennessee Eastman (TE) benchmark process, common oversampling method and the basic GAN are compared to our method, with different classification algorithms. Besides, proposed method is deployed and parallelly trained on Tensorflow platform, which is suitable for applications like data augmentation and imbalanced fault classification in industrial big data environments. • A data augmentation method for imbalanced fault classification. • Generative Adversarial Networks aided by Gaussian Discriminant Analysis. • Superiorities of the model are analyzed and discussed in detail. • Parallel implementation of the model for big data in Tensorflow. • The performance of the method is verified on both toy data and TE process. [ABSTRACT FROM AUTHOR]

Since industrial process data often presents strong correlations, high complexity, and nonlinear patterns, a proficient deep learning model is required for the fault classification task. Recent researches have shown that deep learning models like stacked autoencoder (SAE) are able to learn deep abstract features from complex process data. Nevertheless, a traditional SAE cannot extract the informative fault-relevant features and data distribution features from industrial process data, which are necessary for effective fault classification in industrial processes. Thus, this study proposes a semi-supervised Inter-Relational Mahalanobis SAE (IRM-SAE) model to learn inter-relational distribution and fault-relevant dynamic features of process data for fault classification. First, the Inter-Relational Mahalanobis loss is introduced into the original objective function of SAE to learn meaningful inter-relational distribution features within the data. Then, an active time frame technique is developed to preprocess the input data to capture the dynamic features of the data. Furthermore, to fully utilize both labeled and unlabeled data in industrial processes, the semi-supervised strategy is introduced to learn fault-related features for better fault classification. To validate the performance of the proposed model, it is applied on the Tennessee–Eastman process and a real-world industrial hydrocracking process. The experimental results show that the proposed model has higher fault classification performance compared to other deep learning models. • A novel semi-supervised Inter-Relational Mahalanobis SAE (IRM-SAE) model is proposed to learn inter-relational distribution and fault-relevant dynamic features of process data. • An active time frame technique is developed to preprocess the process data to capture the dynamic features of the data. • To fully utilize both labeled and unlabeled data in industrial processes, the semi-supervised strategy is introduced to learn fault-related features for better fault classification. • The experimental results on two industrial processes show that the proposed model has higher fault classification performance compared to other deep learning models. [ABSTRACT FROM AUTHOR]

This work deals with robust dynamic probabilistic modeling and fault classification for process data. In dynamic processes, observed variables can be numerous in amount and correlated with each other in both variable-wise and time-wise. While multivariate statistical analysis methods such as principle component analysis (PCA) are widely used to handle variable-wise correlations and also for dimension reduction purpose, the time-wise correlation among process data is typically addressed by constructing dynamical models, e.g. time-series data model, state space model, etc. In this paper, the robust probabilistic principle component analysis (RPPCA) model is introduced for feature extraction from contaminated process data, suffered from outliers, disturbances, heave noises, etc. A dynamic Bayesian network (DBN) is then constructed, with incorporation of a mixture of Gaussian components for approximation of the non-Gaussian characteristics of latent variables. Based on the developed robust dynamic Bayesian network model, a fault classification scheme is proposed. To validate the effectiveness and feasibility of the new method, two well-known benchmark case studies are carried out. Simulation results show that robust dynamic method performs better in outlier contaminated situations, where the performance has been improved by 10%–20% in most cases. [ABSTRACT FROM AUTHOR]