Search

Abstract The main objective of this paper is to develop a distributed fault detection (FD) approach for large‐scale interconnected systems using sensor networks. Specifically, the one‐step prediction based on the measured data is implemented in a distributed fashion so that each node can receive corresponding estimations and innovation sequences in a real‐time manner. Then the innovation sequences are applied to improve the estimation result delivered from the one‐step prediction by filtering and smoothing. After filtering and smoothing, the residual signals are calculated to detect faults. Finally, a case study shows that the distributed approach can efficiently accomplish the FD task.

Abstract This paper studies data‐driven distributed fault diagnosis for large‐scale systems using sensor networks. To be specific, a distributed fault detection scheme based on correlation analysis is first proposed to improve the fault detection performance by minimizing the impact of noise‐induced uncertainty. The core of the method is to implement the correlation of the coupled nodes to reduce the covariance of the residual signal in a distributed manner. Then, a fault localization approach is developed to locate the fault by measuring and comparing the degree of abnormality. A case study on Tennessee Eastman process is given in the end to demonstrate the proposed approach.

This paper proposes a novel deep learning architecture for estimating the remaining useful lifetime (RUL) of industrial components, which solely relies on the recently developed transformer architectures. The RUL estimation resorts to analysing degradation patterns within multivariate time series signals. Hence, we propose a novel shared temporal attention block that allows detecting RUL patterns with the progress of time. Furthermore, we develop a split-feature attention block that enables attending to features from different sensor channels. The proposed shared temporal attention layer in the encoder fulfils the goal of attending to temporal degradation patterns in the individual sensor signals before creating a shared correlation across the feature range. We develop two transformer architectures that are specifically designed to operate with multivariate time series data based on these novel attention blocks. We apply the architectures to the well known C-MAPSS benchmark dataset and provide various hyperparameter studies to analyse their impact on the performance. In addition, we provide a thorough comparison with recently presented state-of-the-art approaches and show that the proposed transformer architectures outperform the existing methods by a considerable margin.

This paper presents an innovative and practical solution for fault-tolerant control of industrial systems based on hybrid redundant measurements. The paper proposes a fault-tolerant control scheme against single and multiple sensor faults that can occur in typical tank-based industrial applications. A robust fault detection filter based on $H_{-} /H_{\infty }$ index is designed to generate a residual signal that is robust against disturbance and sensitive to the fault, simultaneously. It also integrates camera information and image processing techniques in the control scheme to get level-measurement redundancy. The proposed scheme was tested using the well-known three-tank benchmark, with both offline and online computation. Results showed that the proposed scheme tolerated the sensor faults and preserved the correct operation of the tank levels in both single and multiple-sensor faults, without changing the original structure of the controller.

We propose a novel sequence-to-sequence prediction approach for the estimation of the remaining useful lifetime (RUL) of technical components. The approach is based on deep recurrent neural network structures, namely bidirectional Long Short Term Memory (LSTM) networks, which we augment with an attention mechanism to allow for a more fine-grained information flow between the input and output sequence. Using the base architecture as a reference, we experiment with various forms of attention mechanisms as well as different forms of additional input embeddings. Further, we analyse the impact of the sequence length on the estimation quality. We apply our approach to the well known C-MAPSS data set previously serving as a benchmark dataset for RUL prediction. We obtain state of the art results on the data set and provide a thorough hyperparameter study that underlines, that more simple but well tuned architecture can achieve comparable or better performance than highly complex architectures.

This paper is devoted to investigating the observer-based fault detection (FD) filters for nonlinear distributed processes described by hyperbolic partial differential equations (PDEs). To this end, the PDE systems are first approximated by the Takagi-Sugeno fuzzy models with spatiotemporal uncertainties. Then, the fuzzy FD filter is developed for the hyperbolic PDE systems to guarantee that the residual signal is robust against process inputs including disturbances. The dynamic threshold is designed to ensure the real-time detection of potential faults. It is worth mentioning that the distributed weighting factors are used to weigh the residual signal such that the overall fault detectability can be optimized.

Both the model-based and data-driven techniques for fault detection have their merits and drawbacks. The fault detection systems are usually laid out separately with the health monitoring systems in practice. In this paper, the well-established observer-based residual generator is formulated to construct multiple evaluation functions which are employed as the classification features of the support vector machine (SVM) for fault detection. It can be regarded as a tentative approach to combine the model-based and data-driven methods to enhance the fault detection performance. The standard SVM is modified for fault detection to achieve the quantitative tradeoff between false alarm rate and fault detection rate. In Addition, this paper also provides a unified framework for fault detection and health monitoring based on the SVM. Simulations on the ship propulsion system show the effectiveness of the proposed method.

This paper presents a novel approach for anomaly detection in industrial processes. The system solely relies on unlabeled data and employs a 1D-convolutional neural network-based deep autoencoder architecture. As a core novelty, we split the autoencoder latent space in discriminative and reconstructive latent features and introduce an auxiliary loss based on k-means clustering for the discriminatory latent variables. We employ a Top-K clustering objective for separating the latent space, selecting the most discriminative features from the latent space. We use the approach to the benchmark Tennessee Eastman data set to prove its applicability. We provide different ablation studies and analyze the method concerning various downstream tasks, including anomaly detection, binary and multi-class classification. The obtained results show the potential of the approach to improve downstream tasks compared to standard autoencoder architectures.

Data mining and analytics have played an important role in knowledge discovery and decision making/supports in the process industry over the past several decades. As a computational engine to data mining and analytics, machine learning serves as basic tools for information extraction, data pattern recognition and predictions. From the perspective of machine learning, this paper provides a review on existing data mining and analytics applications in the process industry over the past several decades. The state-of-the-art of data mining and analytics are reviewed through eight unsupervised learning and ten supervised learning algorithms, as well as the application status of semi-supervised learning algorithms. Several perspectives are highlighted and discussed for future researches on data mining and analytics in the process industry.

It is widely accepted that conventional boost algorithms are of low efficiency and accuracy in dealing with big data collected from wind turbine operations. To address this issue, this paper is devoted to the application of an adaptive LightGBM method for wind turbine fault detections. To this end, the realization of feature selection for fault detection is firstly achieved by utilizing the maximum information coefficient to analyze the correlation among features in supervisory control and data acquisition (SCADA) of wind turbines. After that, a performance evaluation criterion is proposed for the improved LightGBM model to support fault detections. In this scheme, by embedding the confusion matrix as a performance indicator, an improved LightGBM fault detection approach is then developed. Based on the adaptive LightGBM fault detection model, a fault detection strategy for wind turbine gearboxes is investigated. To demonstrate the applications of the proposed algorithms and methods, a case study with a three-year SCADA dataset obtained from a wind farm sited in Southern China is conducted. Results indicate that the proposed approaches established a fault detection framework of wind turbine systems with either lower false alarm rate or lower missing detection rate.