Multi-node knowledge graph assisted distributed fault detection for large-scale industrial processes based on graph attention network and bidirectional LSTMs.

Modern industrial processes are characterized by extensive, multiple operation units, and strong coupled correlation of subsystems. Fault detection of large-scale processes is still a challenging problem, especially for tandem plant-wide processes in multiple fields such as water treatment process. In this paper, a novel distributed graph attention network-bidirectional long short-term memory (D-GATBLSTM) fault detection model is proposed for large-scale industrial processes. Firstly, a multi-node knowledge graph (MNKG) is constructed using a joint data and knowledge driven strategy. Secondly, for large-scale industrial process, a global feature extractor of graph attention networks (GATs) is constructed, on the basis of which, sub-blocks are decomposed based on MNKG. Then, local feature extractors of bidirectional long short-term memory (Bi-LSTM) for each sub-block are constructed, in which correlations among multiple sub-blocks are considered. Finally, a multi-subblock fusion collaborative prediction model is constructed and the comprehensive fault detection results are given by the grid search method. The effectiveness of our D-GATBLSTM is exemplified in a secure water treatment process case, where it outperforms baseline models compared, with 27% improvement in precision, 15% increase in recall, and overall F-score enhancement of 0.22.

A Hybrid Method for Performance Degradation Probability Prediction of Proton Exchange Membrane Fuel Cell.

The proton exchange membrane fuel cell (PEMFC) is a promising power source, but the short lifespan and high maintenance cost restrict its development and widespread application. Performance degradation prediction is an effective technique to extend the lifespan and reduce the maintenance cost of PEMFC. This paper proposed a novel hybrid method for the performance degradation prediction of PEMFC. Firstly, considering the randomness of PEMFC degradation, a Wiener process model is established to describe the degradation of the aging factor. Secondly, the unscented Kalman filter algorithm is used to estimate the degradation state of the aging factor from monitoring voltage. Then, in order to predict the degradation state of PEMFC, the transformer structure is used to capture the data characteristics and fluctuations of the aging factor. To quantify the uncertainty of the predicted results, we also add the Monte Carlo dropout technology to the transformer to obtain the confidence interval of the predicted result. Finally, the effectiveness and superiority of the proposed method are verified on the experimental datasets.

From Nonlinear Dominant System to Linear Dominant System: Virtual Equivalent System Approach for Multiple Variable Self-Tuning Control System Analysis.

The stability and convergence analysis of a multivariable stochastic self-tuning system (STC) is very difficult because of its highly nonlinear structure. In this paper, based on the virtual equivalent system method, the structural nonlinear or nonlinear dominated multivariable self-tuning system is transformed into a structural linear or linear dominated system, thus simplifying the stability and convergence analysis of multivariable STC systems. For the control process of a multivariable stochastic STC system, parameter estimation is required, and there may be three cases of parameter estimation convergence, convergence to the actual value and divergence. For these three cases, this paper provides four theorems and two corollaries. Given the theorems and corollaries, it can be directly concluded that the convergence of parameter estimation is a sufficient condition for the stability and convergence of stochastic STC systems but not a necessary condition, and the four theorems and two corollaries proposed in this paper are independent of specific controller design strategies and specific parameter estimation algorithms. The virtual equivalent system theory proposed in this paper does not need specific control strategies, parameters and estimation algorithms but only needs the nature of the system itself, which can judge the stability and convergence of the self-tuning system and relax the dependence of the system stability convergence criterion on the system structure information. The virtual equivalent system method proposed in this paper is proved to be effective when the parameter estimation may have convergence, convergence to the actual value and divergence.

Deep residual neural-network-based robot joint fault diagnosis method.

A data driven method-based robot joint fault diagnosis method using deep residual neural network (DRNN) is proposed, where Resnet-based fault diagnosis method is introduced. The proposed method mainly deals with kinds of fault types, such as gain error, offset error and malfunction for both sensors and actuators, respectively. First, a deep residual network fault diagnosis model is derived by stacking small convolution cores and increasing the core size. meanwhile, the gaussian white noise is injected into the fault data set to verify the noise immunity for the proposed deep residual network. Furthermore, a simulation is conducted, where different fault diagnosis methods including support vector machine (SVM), artificial neural network (ANN), convolutional neural network (CNN), long-term memory network (LTMN) and deep residual neural network (DRNN) are compared, and the simulation results show the accuracy of fault diagnosis for robot system using DRNN is higher, meanwhile, DRNN needs less model training time. Visualization analysis proved the feasibility and effectiveness of the proposed method for robot joint sensor and actuator fault diagnosis using DRNN method.

Fault detection for chemical processes based on non-stationarity sensitive cointegration analysis.

Due to the time-varying operation conditions, chemical processes are characterized by non-stationary characteristics, which makes it a great challenge for conventional process monitoring methods to capture the non-stationary variations In the non-stationary processes, the abnormality would cause the stationary variables to be non-stationary. In this article, a non-stationarity sensitive cointegration analysis monitoring method is proposed to explore potential non-stationary variations. First, the essential non-stationary variables are distinguished using Augmented Dickey-Fuller test to eliminate the influence of essential non-stationary under normal conditions. Then by further analyzing the faulty data, the variables which are sensitive to the non-stationary variations are selected. On this basis, cointegration analysis models are established for both the essential non-stationary variables and non-stationarity sensitive variables to explore long-term dynamic equilibrium relationship, respectively. With the selection of non-stationarity sensitive variables, the potential faulty information is emphasized in the process monitoring model, which makes the model capable to handle the non-stationary variations. Finally, the monitoring results are combined through Bayesian inference criterion. The proposed method is applied on the Tennessee Eastman process and a vinyl acetate monomer plant model, and the feasibility and performance are demonstrated.

Sensor and Actuator Fault Diagnosis for Robot Joint Based on Deep CNN.

This paper proposes a data-driven method-based fault diagnosis method using the deep convolutional neural network (DCNN). The DCNN is used to deal with sensor and actuator faults of robot joints, such as gain error, offset error, and malfunction for both sensors and actuators, and different fault types are diagnosed using the trained neural network. In order to achieve the above goal, the fused data of sensors and actuators are used, where both types of fault are described in one formulation. Then, the deep convolutional neural network is applied to learn characteristic features from the merged data to try to find discriminative information for each kind of fault. After that, the fully connected layer does prediction work based on learned features. In order to verify the effectiveness of the proposed deep convolutional neural network model, different fault diagnosis methods including support vector machine (SVM), artificial neural network (ANN), conventional neural network (CNN) using the LeNet-5 method, and long-term memory network (LTMN) are investigated and compared with DCNN method. The results show that the DCNN fault diagnosis method can realize high fault recognition accuracy while needing less model training time.

Nonlinear quality-related fault detection using combined deep variational information bottleneck and variational autoencoder.

Deep learning has gotten much attention in industrial field, many fault detection methods based on deep learning have been developed for nonlinear industrial processes. However, most of them do not take the quality-related faults into account. In order to extract the latent variables which can represent the separated quality-related and unrelated information, this paper proposes a novel deep VIB-VAE algorithm, which combines variational autoencoder (VAE) model and deep variational information bottleneck (VIB). Deep VIB extracts quality-related latent variables by maximizing mutual information between latent variables and process quality while minimizing mutual information between latent variables and observation. VAE is used to learn the quality-unrelated part with above quality-related latent variables as auxiliary information. To monitor and distinguish quality-related and quality-unrelated faults, two monitoring statistics are designed by the two-part latent variables. The reconstruction error by VAE is introduced to improve the performance of fault detection. Finally, the effectiveness of the proposed deep VIB-VAE algorithm is demonstrated by a numerical case and a real hot strip mill process case, respectively.

A nonlinear full condition process monitoring method for hot rolling process with dynamic characteristic.

As a typical complex industrial process, hot rolling process (HRP) is different from chemical process. Strip steels are produced coil by coil, that means there is a long idle period between coils. The rolling speed is very high and the producing time of each coil is usually a few minutes. Previous researches mostly focus on fault detection in loaded condition and very few attempts have been made to exploit the monitoring of idle condition. In order to monitor the whole process, not only the loaded condition, but also the idle one, a novel nonlinear full condition process monitoring model is developed in this work. First, a dissimilarity index (DI) is defined for condition identification and a support data vector description (SVDD) model is established to monitor the idle condition. Second, t-distributed stochastic neighbor embedding (t-SNE) is used to extract nonlinear principal components (NPC) for slow feature analysis (SFA) and cointegration analysis (CA). Nonlinear cointegration analysis (NCA) can reveal the long-run dynamic relations of nonstationary parts, while nonlinear slow feature analysis (NSFA) can extract the latent temporal dynamic and static variations of stationary ones. Finally, the monitoring performance of the proposed model is verified through a real HRP.

A novel semisupervised classification framework for coupling faults in hot rolling mill process.

Compared with single fault, the occurrence and composition of coupling faults have more uncertainties and diversities, which make fault classification a challenging topic in academic research and industrial application areas. In this paper, the classification problems of coupling faults are addressed from a new perspective, which will provide diagnostic decisions for online operators to take immediate remedial measures to bring the abnormal operation back to an incontrol state. Specifically, the main innovations are: (1) a semisupervised classification scheme for coupling faults is first proposed, which combines adaptive classification with multi-task feature selection; (2) number of classifications can be learned adaptively and automatically; (3) common and specific features among single and the associated coupling faults can be captured, which are crucial for improving classification performance. A case study on hot rolling mill process is finally given to validate the effectiveness of the proposed scheme, and several competitive methods are employed to carry out the classification process. It can be observed that the obtained classification results for two different cases are more successful than the traditional methods.

A novel key performance indicator oriented hierarchical monitoring and propagation path identification framework for complex industrial processes.

As the first protective layer for modern complex industrial processes, process monitoring and fault diagnosis (PM-FD) systems play a vital role in ensuring product quality, overall equipment effectiveness and process safety, which have recently become one of the hotspots both in academic research and practical application domains. Different from previous frameworks, this paper dedicates on industrial practices and theoretical methods for hierarchical monitoring and propagation path identification of key performance indicator (KPI) oriented faults in complex industrial processes, which can not only help field engineers to timely and purposefully keep track of the state of the process, but also help them to take appropriate remedial actions to remove the abnormal behaviors from the process. For these purposes, firstly, a new data-driven gap metric approach is proposed for monitoring KPI oriented faults in the block level. Then, Bayesian fusion is implemented to form monitoring decisions from the plant-wide level. After that, a neural network architecture-based Granger causality analysis method is developed for propagation path identification of KPI oriented faults. Finally, the proposed methods are validated in Tennessee Eastman process, where detailed simulation processes are presented and better performance is shown compared with the existing approaches.

Adaptive Neural Control for Robotic Manipulators With Output Constraints and Uncertainties.

This paper investigates adaptive neural control methods for robotic manipulators, subject to uncertain plant dynamics and constraints on the joint position. The barrier Lyapunov function is employed to guarantee that the joint constraints are not violated, in which the Moore-Penrose pseudo-inverse term is used in the control design. To handle the unmodeled dynamics, the neural network (NN) is adopted to approximate the uncertain dynamics. The NN control based on full-state feedback for robots is proposed when all states of the closed loop are known. Subsequently, only the robot joint is measurable in practice; output feedback control is designed with a high-gain observer to estimate unmeasurable states. Through the Lyapunov stability analysis, system stability is achieved with the proposed control, and the system output achieves convergence without violation of the joint constraints. Simulation is conducted to approve the feasibility and superiority of the proposed NN control.

Fault detection for piecewise affine systems with application to ship propulsion systems.

In this paper, the design approach of non-synchronized diagnostic observer-based fault detection (FD) systems is investigated for piecewise affine processes via continuous piecewise Lyapunov functions. Considering that the dynamics of piecewise affine systems in different regions can be considerably different, the weighting matrices are used to weight the residual of each region, so as to optimize the fault detectability. A numerical example and a case study on a ship propulsion system are presented in the end to demonstrate the effectiveness of the proposed results.

A KPI-based process monitoring and fault detection framework for large-scale processes.

Large-scale processes, consisting of multiple interconnected subprocesses, are commonly encountered in industrial systems, whose performance needs to be determined. A common approach to this problem is to use a key performance indicator (KPI)-based approach. However, the different KPI-based approaches are not developed with a coherent and consistent framework. Thus, this paper proposes a framework for KPI-based process monitoring and fault detection (PM-FD) for large-scale industrial processes, which considers the static and dynamic relationships between process and KPI variables. For the static case, a least squares-based approach is developed that provides an explicit link with least-squares regression, which gives better performance than partial least squares. For the dynamic case, using the kernel representation of each subprocess, an instrument variable is used to reduce the dynamic case to the static case. This framework is applied to the TE benchmark process and the hot strip mill rolling process. The results show that the proposed method can detect faults better than previous methods.

Using the expected detection delay to assess the performance of different multivariate statistical process monitoring methods for multiplicative and drift faults.

Using the expected detection delay (EDD) index to measure the performance of multivariate statistical process monitoring (MSPM) methods for constant additive faults have been recently developed. This paper, based on a statistical investigation of the T2- and Q-test statistics, extends the EDD index to the multiplicative and drift fault cases. As well, it is used to assess the performance of common MSPM methods that adopt these two test statistics. Based on how to use the measurement space, these methods can be divided into two groups, those which consider the complete measurement space, for example, principal component analysis-based methods, and those which only consider some subspace that reflects changes in key performance indicators, such as partial least squares-based methods. Furthermore, a generic form for them to use T2- and Q-test statistics are given. With the extended EDD index, the performance of these methods to detect drift and multiplicative faults is assessed using both numerical simulations and the Tennessee Eastman process.