Fault detection based on robust characteristic dimensionality reduction

The day-by-day increase in digital loads draws attention towards the need for an efficient and compatible distribution network. An LVDC distribution network has the capability to fulfill such digital load demands. However, the major challenge of an LVDC distribution network is its vulnerability during a fault. The need for a high-speed fault detection method is inevitable before it can be widely adopted. This paper proposes a new fault detection method which extracts the features of the current during a fault. The proposed fault detection method uses the merits of overcurrent, the first and second derivative of current, and signal processing techniques. Three different features are extracted from a time domain current signal through a sliding window. The extracted features are based upon the root squared zero, second, and fourth order moments. The features are then set with individual thresholds to discriminate low-, high-, and very high-resistance faults. Furthermore, a fault is located through the superimposed power flow. Moreover, this study proposes a new method based on the vector sum of positive and negative pole currents to identify the faulty pole. The proposed scheme is verified by using a modified IEEE 13 node distribution network, which is implemented in Matlab/Simulink. The simulation results confirm the effectiveness of the proposed fault detection and identification method. The simulation results also confirm that a fault having a resistance of 1 m Ω is detected and interrupted within 250 μ s for the test system used in this study.

Manifold regularized stacked autoencoders-based feature learning for fault detection in industrial processes

For multivariate data, tandem clustering is a well-known technique aiming to improve cluster identification through initial dimension reduction. Nevertheless, the usual approach using principal component analysis (PCA) has been criticized for focusing solely on inertia so that the first components do not necessarily retain the structure of interest for clustering. To address this limitation, a new tandem clustering approach based on invariant coordinate selection (ICS) is proposed. By jointly diagonalizing two scatter matrices, ICS is designed to find structure in the data while providing affine invariant components. Certain theoretical results have been previously derived and guarantee that under some elliptical mixture models, the group structure can be highlighted on a subset of the first and/or last components. However, ICS has garnered minimal attention within the context of clustering. Two challenges associated with ICS include choosing the pair of scatter matrices and selecting the components to retain. For effective clustering purposes, it is demonstrated that the best scatter pairs consist of one scatter matrix capturing the within-cluster structure and another capturing the global structure. For the former, local shape or pairwise scatters are of great interest, as is the minimum covariance determinant (MCD) estimator based on a carefully chosen subset size that is smaller than usual. The performance of ICS as a dimension reduction method is evaluated in terms of preserving the cluster structure in the data. In an extensive simulation study and empirical applications with benchmark data sets, various combinations of scatter matrices as well as component selection criteria are compared in situations with and without outliers. Overall, the new approach of tandem clustering with ICS shows promising results and clearly outperforms the PCA-based approach.

As the growth of Industry 4.0, online fault detection plays a crucial role in ensuring the manufacturing quality. Generally, the fault detection methods can be classified into model-based and data-driven methods. There are advantages/disadvantages between two methods. In this study, we integrated both methods in order to develop an efficient fault detection method for non-Gaussian industrial processes. The data-driven method, independent component analysis (ICA) is used to extract non-Gaussian information and dimensionality reduction. Meanwhile, the model-based method, generalized likelihood ratio (GLR) test is adopted as the charting statistic. The proposed ICA-GLR method has advantages of 1) detecting a wide range of process changes, 2) estimating the change points and 3) needless prior parameters to be specified by practitioner. The efficiency of the proposed ICA-GLR fault detection method will be verified via implementing one simulated non-Gaussian process and two real manufacturing processes: Tennessee Eastman process and semiconductor manufacturing process. Results demonstrate that the proposed ICA-GLR method has superior fault detectability when compared to traditional methods, such as principal component analysis and ICA.

This paper presents a new method for image feature extraction, namely, the fuzzy 2D discriminant locality preserving projections (F2DDLPP) based on the 2D discriminant locality preserving projections (2DDLPP) and fuzzy set theory. Firstly, we calculate the membership degree matrix by fuzzy k-nearest neighbor (FKNN), then we incorporate the membership degree matrix into the definition of the intra-class scatter matrix and inter-class scatter matrix, respectively. Secondly, we can get the fuzzy intra-class scatter matrix and fuzzy inter-class scatter matrix, respectively. The FKNN is implemented to achieve the distribution information of original samples, and this information is utilized to redefine corresponding scatter matrices. So, F2DDLPP can extract discriminative features from overlapping (outlier) samples which is different to the conventional 2DDLPP. Finally, Experiments on the Yale, ORL face databases, USPS database and PolyU palmprint database are demonstrated to verify the effectiveness of the proposed algorithm.

Long–short-term memory encoder–decoder with regularized hidden dynamics for fault detection in industrial processes

A Data-driven Fault Detection Method Based on Dissipative Trajectories

In this study, the use of instantaneous symmetrical components (ASB) for mechanical fault detection in an inverter controlled induction motor has been investigated. The proposed fault detection method is based on the calculation of the ASBs of the stator currents. The spectral density (PSD) of the positive sequence power component is estimated using the least squares method (EKY). Then, mechanical fault detection is performed using the generalized likelihood ratio test (GLRT). Modulated signals from both stator currents and closed-loop have been shown to be successful in detecting faults. The simulation results in the analytical model of an inverter controlled induction motor give the effectiveness of this proposed approach. This results in an effective fault detection method for an induction motor load torque oscillation.

Novel adaptive fault detection method based on kernel entropy component analysis integrating moving window of dissimilarity for nonlinear dynamic processes

This paper presents a simple fault detection method and fault-tolerant strategy based on the model predictive control theory. The proposed fault detection method can detect and locate a failed switch with current error signals dedicated to each switch, based on the position of space vectors. Following the fault detection, the proposed fault-tolerant control strategies are developed to produce three-phase balanced sinusoidal output voltages/currents with only normally functioning bidirectional switches. Therefore, the developed control technique for the matrix converter can preserve continuous operation even after the failure of switches and improve reliability of the drives. Simulation results are provided to validate the effectiveness of the applied detection and control strategy.

This paper proposes a new on-line fault detection method to detect open-switch faults in a Matrix Converter (MC). The proposed fault detection method is based on a two-step algorithm. The first step identifies the occurrence of the fault by monitoring the measured load currents. The second step locates the faulty switch by measuring the response of the MC to a set of predefined switching states. The proposed method allows fast detection and isolation of a faulty switch, independent of the modulation strategy, the voltage transfer ratio, or the output frequency, and without any requirement of additional voltage sensors. The paper also presents a Model Predictive Control (MPC)-based post-fault strategy that enables the MC to continue its operation during faulty conditions. Time-domain simulation studies are performed in the MATLAB/SIMULINK environment to evaluate the performance of the proposed fault detection method and the effectiveness of the MPC as a post-fault control strategy.

The self-attention mechanism has advantages in analyzing the internal characteristics of data and capturing local information. Therefore, it is applied to fault detection. Since complex industrial processes usually contain a mixture of properties, such as nonlinearity, dynamics, and non-Gaussianity, this places higher demands on fault detection methods. To further improve the performance of the self-attention mechanism for fault detection in complex industrial processes, an innovative self-attention mechanism integrating the adaptive double subspace (ISA-ADS) method is proposed for fault detection. First, the query matrix, the key matrix, and the value matrix of the self-attention mechanism are designed so that they can better focus on local information through the adaptive sample weight allocation strategy. At the same time, this design reduces the interference of nonlinear and noisy information and amplifies the impact of important fault information in the sample. Second, considering the problem of Gaussian and non-Gaussian distributions of the data and the different degrees of influence of different subspaces on the final process monitoring results, an adaptive Gaussian and non-Gaussian double subspace fault detection model based on the self-attention output matrix is established, which adaptively assigns different weights to different subspaces by determining their importance. The statistics of different subspaces are fused using the Bayesian inference and a new adaptive monitoring statistic is constructed to obtain a more accurate monitoring of the process state. Finally, the ISA-ADS is validated using the Tennessee Eastman (TE) process and the actual polyethylene production process. The results show that ISA-ADS has a low false alarm rate and a high fault detection rate, verifying the effectiveness of its fault detection performance.

A novel orthogonal self-attentive variational autoencoder method for interpretable chemical process fault detection and identification

In this paper, a reformative scatter difference discriminant criterion (SDDC) with fuzzy set theory is studied. The scatter difference between between-class and within-class as discriminant criterion is effective to overcome the singularity problem of the within-class scatter matrix due to small sample size problem occurred in classical Fisher discriminant analysis. However, the conventional SDDC assumes the same level of relevance of each sample to the corresponding class. So, a fuzzy maximum scatter difference analysis (FMSDA) algorithm is proposed, in which the fuzzy k-nearest neighbor (FKNN) is implemented to achieve the distribution information of original samples, and this information is utilized to redefine corresponding scatter matrices which are different to the conventional SDDC and effective to extract discriminative features from overlapping (outlier) samples. Experiments conducted on FERET face databases demonstrate the effectiveness of the proposed method.

Fault detection and diagnosis based on transfer learning for multimode chemical processes