Data-Driven Designs of Fault Detection Systems via Neural Network-Aided Learning

VAE-Based Interpretable Latent Variable Model for Process Monitoring

Latent variable-based process monitoring (PM) models have been generously developed by shallow learning approaches, such as multivariate statistical analysis and kernel techniques. Owing to their explicit projection objectives, the extracted latent variables are usually meaningful and easily interpretable in mathematical terms. Recently, deep learning (DL) has been introduced to PM and has exhibited excellent performance because of its powerful presentation capability. However, its complex nonlinearity prevents it from being interpreted as human-friendly. It is a mystery how to design a proper network structure to achieve satisfactory PM performance for DL-based latent variable models (LVMs). In this article, a variational autoencoder-based interpretable LVM (VAE-ILVM) is developed for PM. Based on Taylor expansions, two propositions are proposed to guide the design of appropriate activation functions for VAE-ILVM, allowing nondisappearing fault impact terms contained in the generated monitoring metrics (MMs). During threshold learning, the sequence of counting that test statistics exceed the threshold is considered a martingale, a representative of weakly dependent stochastic processes. A de la Peña inequality is then adopted to learn a suitable threshold. Finally, two chemical examples verify the effectiveness of the proposed method. The use of de la Peña inequality significantly reduces the minimum required sample size for modeling.

Explainable Intelligent Fault Diagnosis for Nonlinear Dynamic Systems: From Unsupervised to Supervised Learning

The increased complexity and intelligence of automation systems require the development of intelligent fault diagnosis (IFD) methodologies. By relying on the concept of a suspected space, this study develops explainable data-driven IFD approaches for nonlinear dynamic systems. More specifically, we parameterize nonlinear systems through a generalized kernel representation for system modeling and the associated fault diagnosis. An important result obtained is a unified form of kernel representations, applicable to both unsupervised and supervised learning. More importantly, through a rigorous theoretical analysis, we discover the existence of a bridge (i.e., a bijective mapping) between some supervised and unsupervised learning-based entities. Notably, the designed IFD approaches achieve the same performance with the use of this bridge. In order to have a better understanding of the results obtained, both unsupervised and supervised neural networks are chosen as the learning tools to identify the generalized kernel representations and design the IFD schemes; an invertible neural network is then employed to build the bridge between them. This article is a perspective article, whose contribution lies in proposing and formalizing the fundamental concepts for explainable intelligent learning methods, contributing to system modeling and data-driven IFD designs for nonlinear dynamic systems.

Regional Evaluation Study of VFTO Interference to Secondary Side Cables Based on Cloud Model and MARCOS

With the advent of the data era, most power secondary side equipment tends to be digitized. The power system needs more accurate numerical results to further improve its operating efficiency. Therefore, it is important to study the electromagnetic interferences of very fast transient overvoltage (VFTO) generated by gas-insulated switchgear (GIS). To protect the secondary side cable from interferences, the secondary side cable is wrapped with an outer shield and the shield is grounded. When the interference of VFTO comes, it will couple the interference current and interference voltage on the shield of the cable. By grounding, the interference is greatly discharged. However, due to the grounding resistance, there will be a potential difference between the grounding points at the two ends of the shield of the cable. This causes a corresponding interference current to flow through the shield, which will affect the transmission of signals inside the cable. In the actual substation, the resistivity of the soil, the ambient temperature and humidity of the area, and so on will have impacts on the grounding resistance. In addition, the irregularity of the cable arrangement and the time of the use of the cable will have impacts on the signal transmission of the cable. Based on the abovementioned issues, this article proposed a comprehensive assessment method based on the combination of the cloud model and measurement of alternatives and ranking according to compromise solution (MARCOS). The method brings the cloud model into MARCOS by the algorithm of the contribution of the cloud droplets. It overcomes the difficulty of cloud model quantification. By comparing the results of the proposed method with the actual conditions at the substation and the results of the common MARCOS assessment method, the validity of the method is verified, and a reference scheme is provided for substation optimization.

Reweighted Regularized Prototypical Network for Few-Shot Fault Diagnosis

In this article, we study the challenging few-shot fault diagnosis (FSFD) problem where limited faulty samples are available. Metric-based meta-learning methods have been a prevalent approach toward FSFD; however, most of them rely on learning a generalized distance metric and fall short of leveraging intraclass and interclass distribution information. To this end, we develop a novel reweighted regularized prototypical network to improve the performance of FSFD, where an intraclass reweighting strategy is proposed to reduce the influence of noise and outliers and obtain stable estimations of fault prototypes. In addition, a novel balance-enforcing regularization (BER) is proposed to hedge against the between-class imbalance and improve the discrimination capability. These two remedies help to reduce the intraclass difference and enlarge the interclass difference via episodic training. In this way, an improved metric space and a better diagnostic performance can be attained in a few-shot learning context. Case studies on the Tennessee Eastman benchmark process and a real-world railway turnout dataset demonstrate that the proposed FSFD approach compares favorably against state-of-the-art methodologies with desirable diagnostic performance.

A Reinforcement Learning-Based Pantograph Control Strategy for Improving Current Collection Quality in High-Speed Railways

In high-speed railways, the pantograph-catenary system (PCS) is a critical subsystem of the train power supply system. In particular, when the double-PCS (DPCS) is in operation, the passing of the leading pantograph (LP) causes the contact force of the trailing pantograph (TP) to fluctuate violently, affecting the power collection quality of the electric multiple units (EMUs). The actively controlled pantograph is the most promising technique for reducing the pantograph-catenary contact force (PCCF) fluctuation and improving the current collection quality. Based on the Nash equilibrium framework, this study proposes a multiagent reinforcement learning (MARL) algorithm for active pantograph control called cooperative proximity policy optimization (Coo-PPO). In the algorithm implementation, the heterogeneous agents play a unique role in a cooperative environment guided by the global value function. Then, a novel reward propagation channel is proposed to reveal implicit associations between agents. Furthermore, a curriculum learning approach is adopted to strike a balance between reward maximization and rational movement patterns. An existing MARL algorithm and a traditional control strategy are compared in the same scenario to validate the proposed control strategy's performance. The experimental results show that the Coo-PPO algorithm obtains more rewards, significantly suppresses the fluctuation in PCCF (up to 41.55%), and dramatically decreases the TP's offline rate (up to 10.77%). This study adopts MARL technology for the first time to address the coordinated control of double pantographs in DPCS.

Neural-Network-Based Adaptive Fault-Tolerant Cooperative Control of Heterogeneous Multiagent Systems With Multiple Faults and DoS Attacks

In this article, the issue of adaptive fault-tolerant cooperative control is addressed for heterogeneous multiple unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) with actuator faults and sensor faults under denial-of-service (DoS) attacks. First, a unified control model with actuator faults and sensor faults is developed based on the dynamic models of the UAVs and UGVs. To handle the difficulty introduced by the nonlinear term, a neural-network-based switching-type observer is established to obtain the unmeasured state variables when DoS attacks are active. Then, the fault-tolerant cooperative control scheme is presented by utilizing an adaptive backstepping control algorithm under DoS attacks. According to Lyapunov stability theory and improved average dwell time method by integrating the duration and frequency characteristics of DoS attacks, the stability of the closed-loop system is proved. In addition, all vehicles can track their individual references, while the synchronized tracking errors among vehicles are uniformly ultimately bounded. Finally, simulation studies are given to demonstrate the effectiveness of the proposed method.

Transfer Learning-Motivated Intelligent Fault Diagnosis Designs: A Survey, Insights, and Perspectives

Over the last decade, transfer learning has attracted a great deal of attention as a new learning paradigm, based on which fault diagnosis (FD) approaches have been intensively developed to improve the safety and reliability of modern automation systems. Because of inevitable factors such as the varying work environment, performance degradation of components, and heterogeneity among similar automation systems, the FD method having long-term applicabilities becomes attractive. Motivated by these facts, transfer learning has been an indispensable tool that endows the FD methods with self-learning and adaptive abilities. On the presentation of basic knowledge in this field, a comprehensive review of transfer learning-motivated FD methods, whose two subclasses are developed based on knowledge calibration and knowledge compromise, is carried out in this survey article. Finally, some open problems, potential research directions, and conclusions are highlighted. Different from the existing reviews of transfer learning, this survey focuses on how to utilize previous knowledge specifically for the FD tasks, based on which three principles and a new classification strategy of transfer learning-motivated FD techniques are also presented. We hope that this work will constitute a timely contribution to transfer learning-motivated techniques regarding the FD topic.

A Generalized Robot Navigation Analysis Platform (RoNAP) with Visual Results Using Multiple Navigation Algorithms

The robotic navigation task is to find a collision-free path among a mass of stationary or migratory obstacles. Various well-established algorithms have been applied to solve navigation tasks. It is necessary to test the performance of designed navigation algorithms in practice. However, it seems an extremely unwise choice to implement them in a real environment directly unless their performance is guaranteed to be acceptable. Otherwise, it takes time to test navigation algorithms because of a long training process, and imperfect performance may cause damage if the robot collides with obstacles. Hence, it is of key significance to develop a mobile robot analysis platform to simulate the real environment which has the ability to replicate the exact application scenario and be operated in a simple manner. This paper introduces a brand new analysis platform named robot navigation analysis platform (RoNAP), which is an open-source platform developed using the Python environment. A user-friendly interface supports its realization for the evaluation of various navigation algorithms. A variety of existing algorithms were able to achieve desired test results on this platform, indicating its feasibility and efficiency for navigation algorithm analysis.

A Single-Side Neural Network-Aided Canonical Correlation Analysis With Applications to Fault Diagnosis

Recently, canonical correlation analysis (CCA) has been explored to address the fault detection (FD) problem for industrial systems. However, most of the CCA-based FD methods assume both Gaussianity of measurement signals and linear relationships among variables. These assumptions may be improper in some practical scenarios so that direct applications of these CCA-based FD strategies are arguably not optimal. With the aid of neural networks, this work proposes a new nonlinear counterpart called a single-side CCA (SsCCA) to enhance FD performance. The contributions of this work are four-fold: 1) an objective function for the nonlinear CCA is first reformulated, based on which a generalized solution is presented; 2) for the practical implementation, a particular solution of SsCCA is developed; 3) an SsCCA-based FD algorithm is designed for nonlinear systems, whose optimal FD ability is illustrated via theoretical analysis; and 4) based on the difference in FD results between two test statistics, fault diagnosis can be directly achieved. The studies on a nonlinear three-tank system are carried out to verify the effectiveness of the proposed SsCCA method.

Thruster Fault Diagnostics and Fault Tolerant Control for Autonomous Underwater Vehicle with Ocean Currents

Autonomous underwater vehicle (AUV) is one of the most important exploration tools in the ocean underwater environment, whose movement is realized by the underwater thrusters, however, the thruster fault happens frequently in engineering practice. Ocean currents perturbations could produce noise for thruster fault diagnosis, in order to solve the thruster fault diagnostics, a possibilistic fuzzy C-means (PFCM) algorithm is proposed to realize the fault classification in this paper. On the basis of the results of fault diagnostics, a fuzzy control strategy is proposed to solve the fault tolerant control for AUV. Considering the uncertainty of ocean currents, it proposes a min-max robust optimization problem to optimize the fuzzy controller, which is solved by a cooperative particle swarm optimization (CPSO) algorithm. Simulation and underwater experiments are used to verify the accuracy and feasibility of the proposed method of thruster fault diagnostics and fault tolerant control.

Fault Detection for High-Speed Trains Using CCA and Just-in-Time Learning

Online monitors of the running gears systems of high-speed trains play critical roles in ensuring operational safety and reliability. Status signals collected from high-speed train running gears are very complex regarding working environments, random noises and many other real-world constraints. This paper proposed fault detection (FD) models using canonical correlation analysis (CCA) and just-in-time learning (JITL) to process scalar signals of high-speed train gears, named as CCA-JITL. After data preprocessing and normalization, CCA transforms covariance matrices of high-dimension historical data into low-dimension subspaces and maximizes correlations between the most important latent dimensions. Then, JITL components formulate local FD models which utilize subsets of testing samples with larger Euclidean distances to training data. A case study introduced a novel system design of an online FD architecture and demonstrated that CCA-JITL FD models significantly outperformed traditional CCA models. The approach is applicable to other dimension reduction FD models such as PCA and PLS.

Fault Detection of Bearing by Resnet Classifier with Model-Based Data Augmentation

It is always an important and challenging issue to achieve an effective fault diagnosis in rotating machinery in industries. In recent years, deep learning proved to be a high-accuracy and reliable method for data-based fault detection. However, the training of deep learning algorithms requires a large number of real data, which is generally expensive and time-consuming. To cope with this, we proposed a Resnet classifier with model-based data augmentation, which is applied for bearing fault detection. To this end, a dynamic model was first established to describe the bearing system by adjusting model parameters, such as speed, load, fault size, and the different fault types. Large amounts of data under various operation conditions can then be generated. The training dataset was constructed by the simulated data, which was then applied to train the Resnet classifier. In addition, in order to reduce the gap between the simulation data and the real data, the envelop signals were used instead of the original signals in the training process. Finally, the effectiveness of the proposed method was demonstrated by the real bearing experimental data. It is remarkable that the application of the proposed method can be further extended to other mechatronic systems with a deterministic dynamic model.

A Local Density-Based Abnormal Case Removal Method for Industrial Operational Optimization under the CBR Framework

Operational optimization is essential in modern industry and unsuitable operations will deteriorate the performance of industrial processes. Since measuring error and multiple working conditions are inevitable in practice, it is necessary to reduce their negative impacts on operational optimization under the case-based reasoning (CBR) framework. In this paper, a local density-based abnormal case removal method is proposed to remove the abnormal cases in a case retrieval step, so as to prevent performance deterioration in industrial operational optimization. More specifically, the reasons as to why classic CBR would retrieve abnormal cases are analyzed from the perspective of case retrieval in industry. Then, a local density-based abnormal case removal algorithm is designed based on the Local Outlier Factor (LOF), and properly integrated into the traditional case retrieval step. Finally, the effectiveness and the superiority of the local density-based abnormal case removal method was tested by a numerical simulation and an industrial case study of the cut-made process of cigarette production. The results show that the proposed method improved the operational optimization performance of an industrial cut-made process by 23.5% compared with classic CBR, and by 13.3% compared with case-based fuzzy reasoning.

An Improved Fault Diagnosis Approach Using LSSVM for Complex Industrial Systems

Fault diagnosis is a challenging topic for complex industrial systems due to the varying environments such systems find themselves in. In order to improve the performance of fault diagnosis, this study designs a novel approach by using particle swarm optimization (PSO) with wavelet mutation and least square support (LSSVM). The implementation entails the following three steps. Firstly, the original signals are decomposed through an orthogonal wavelet packet decomposition algorithm. Secondly, the decomposed signals are reconstructed to obtain the fault features. Finally, the extracted features are used as the inputs of the fault diagnosis model established in this research to improve classification accuracy. This joint optimization method not only solves the problem of PSO falling easily into the local extremum, but also improves the classification performance of fault diagnosis effectively. Through experimental verification, the wavelet mutation particle swarm optimazation and least sqaure support vector machine ( WMPSO-LSSVM) fault diagnosis model has a maximum fault recognition efficiency that is 12% higher than LSSVM and 9% higher than extreme learning machine (ELM). The error of the corresponding regression model under the WMPSO-LSSVM algorithm is 0.365 less than that of the traditional linear regression model. Therefore, the proposed fault scheme can effectively identify faults that occur in complex industrial systems.

An Adaptive Fusion Convolutional Denoising Network and Its Application to the Fault Diagnosis of Shore Bridge Lift Gearbox

Traditional fault diagnosis methods are limited in the condition detection of shore bridge lifting gearboxes due to their limited ability to extract signal features and their sensitivity to noise. In order to solve this problem, an adaptive fusion convolutional denoising network (AF-CDN) was proposed in this paper. First, a novel 1D and 2D adaptive fused convolutional neural network structure is built. The fusion of both 1D and 2D convolutional models can effectively improve the feature extraction capability of the network. Then, a gradient updating method based on the Kalman filter mechanism is designed. The effectiveness of the developed method is evaluated by using the benchmark datasets and the actual data collected for the shore bridge lift gearbox. Finally, the effectiveness of the proposed algorithm is proved through the experimental validation in the paper. The main contributions of this paper are described as follows: the proposed AF-CDN can improve the diagnosis accuracy by 1.5–9.1% when compared with the normal CNN methods. The robustness of the diagnostic network can be significantly improved.