Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study

This work considers industrial process monitoring using a variational autoencoder (VAE). As a powerful deep generative model, the variational autoencoder and its variants have become popular for process monitoring. However, its monitoring ability, especially its fault diagnosis ability, has not been well investigated. In this paper, the process modeling and monitoring capabilities of several VAE variants are comprehensively studied. First, fault detection schemes are defined in three distinct ways, considering latent, residual, and the combined domains. Afterwards, to conduct the fault diagnosis, we first define the deep contribution plot, and then a deep reconstruction-based contribution diagram is proposed for deep domains under the fault propagation mechanism. In a case study, the performance of the process monitoring capability of four deep VAE models, namely, the static VAE model, the dynamic VAE model, and the recurrent VAE models (LSTM-VAE and GRU-VAE), has been comparatively evaluated on the industrial benchmark Tennessee Eastman process. Results show that recurrent VAEs with a deep reconstruction-based diagnosis mechanism are recommended for industrial process monitoring tasks.

Fresh new look for system-level prognostics

Model-based prognostic approaches use first-principle or regression models to estimate and predict the system’s health state in order to determine the remaining useful life (RUL). Then, in order to handle the prediction results uncertainty, the Bayesian framework is usually used, in which the prior estimates are updated by infield measurements without changing the model parameters. Nevertheless, in the case of system-level prognostic, the mere updating of the prior estimates, based on a predetermined model, is no longer sufficient. This is due to the mutual interactions between components that increase the system modeling uncertainties and may lead to an inaccurate prediction of the system RUL (SRUL). Therefore, this paper proposes a new methodology for online joint uncertainty quantification and model estimation based on particle filtering (PF) and gradient descent (GD). In detail, the inoperability input-output model (IIM) is used to characterize system degradations considering interactions between components and effects of the mission profile; and then the inoperability of system components is estimated in a probabilistic manner using PF. In the case of consecutive discrepancy between the prior and posterior estimates of the system health state, GD is used to correct and to adapt the IIM parameters. To illustrate the effectiveness of the proposed methodology and its suitability for an online implementation, the Tennessee Eastman Process is investigated as a case study.

Stacked sparse autoencoders that preserve the local and global feature structures for fault detection

Although the model based on an autoencoder (AE) exhibits strong feature extraction capability without data labeling, such model is less likely to consider the structural distribution of the original data and the extracted feature is uninterpretable. In this study, a new stacked sparse AE (SSAE) based on the preservation of local and global feature structures is proposed for fault detection. Two additional loss terms are included in the loss function of SSAE to retain the local and global structures of the original data. The preservation of the local feature considers the nearest neighbor of data in space, while that of the global feature considers the variance information of data. The final feature is not only a deep representation of data, but it also retains structural information as much as possible. The proposed model demonstrates remarkable detection performance in case studies of a numerical process and the Tennessee Eastman process.

Fault Detection and Identification for Nonlinear Process Based on Inertia-Based KEPCA and a New Combined Monitoring Index

In the present study, we introduce a new approach for the nonlinear monitoring process based on kernel entropy principal component analysis (KEPCA) and the notion of inertia. KEPCA plays double roles. First, it reduces the data in the high-dimensional space. Second, it constructs the model. Before data reduction, KEPCA transforms input data into high-dimensional feature space based on a nonlinear kernel function and automatically determines the number of principal components (PCs) based on the computation of the inertia. The retained PCs express the maximum inertia entropy of data in the feature space. Then, we use the Parzen window estimator to compute the upper control limit (UCL) for inertia-based KEPCA instead of the Gaussian assumption. Our second contribution concerns a new combined index based on the monitoring indices T2 and SPE in order to simplify the detection task of the fault and prevent any confusion. The proposed approaches have been applied to process fault detection and diagnosis for the well-known benchmark Tennessee Eastman process (TE). Results were performing.

Unsupervised Offline Changepoint Detection Ensembles

Offline changepoint detection (CPD) algorithms are used for signal segmentation in an optimal way. Generally, these algorithms are based on the assumption that signal’s changed statistical properties are known, and the appropriate models (metrics, cost functions) for changepoint detection are used. Otherwise, the process of proper model selection can become laborious and time-consuming with uncertain results. Although an ensemble approach is well known for increasing the robustness of the individual algorithms and dealing with mentioned challenges, it is weakly formalized and much less highlighted for CPD problems than for outlier detection or classification problems. This paper proposes an unsupervised CPD ensemble (CPDE) procedure with the pseudocode of the particular proposed ensemble algorithms and the link to their Python realization. The approach’s novelty is in aggregating several cost functions before the changepoint search procedure running during the offline analysis. The numerical experiment showed that the proposed CPDE outperforms non-ensemble CPD procedures. Additionally, we focused on analyzing common CPD algorithms, scaling, and aggregation functions, comparing them during the numerical experiment. The results were obtained on the two anomaly benchmarks that contain industrial faults and failures—Tennessee Eastman Process (TEP) and Skoltech Anomaly Benchmark (SKAB). One of the possible applications of our research is the estimation of the failure time for fault identification and isolation problems of the technical diagnostics.

Fault detection and classification in Industrial IoT in case of missing sensor data

This paper addresses the issue of reliability in Industrial Internet of Things (IIoT) in case of missing sensors measurements due to network or hardware problems. We propose to support the fault detection and classification modules, which are the two critical components of a monitoring system for IIoT, with a generative model. The latter is responsible of imputing missing sensor measurements so that the monitoring system performance is robust to missing data. In particular, we adopt Generative Adversarial Networks (GANs) to generate missing sensor measurements and we propose to fine-tune the training of the GAN based on the impact that the generated data have on the fault detection and classification modules. We conduct a thorough evaluation of the proposed approach using the extended Tennessee Eastman Process dataset. Results show that the GAN-imputed data mitigate the impact on the fault detection and classification even in the case of persistently missing measurements from sensors that are critical for the correct functioning of the monitoring system.