Fault Diagnosis Capability Research Articles

An Adaptive Industrial Control Equipment Safety Fault Diagnosis Method in Industrial Internet of Things

With the rapid development of intelligent manufacturing and Industrial Internet of Things, many industrial control systems have high requirements for the security of the system itself. Failures of industrial control equipment will cause abnormal operation of industrial control equipment and waste of resources. It is very meaningful to detect and identify potential equipment abnormalities and failures in time and implement effective fault tolerance strategies. In the Industrial Internet of Things environment, the instructions and parameters of industrial control equipment often change due to changes in actual requirements. However, it is impractical to customize the learning method for each parameter value. Aiming at the problem, this paper proposes a fault diagnosis model based on ensemble learning and proposes a method of updating voting weights based on dynamic programming to assist decision-making. This method is based on Bagging strategy and combined with dynamic programming voting weight adjustment method to complete fault type prediction. Finally, this paper uses different loads as dynamic conditions; the diagnostic capability of the Bagging-based fault diagnosis integrated model in a dynamically changing industrial control system environment is verified by experiments. The fault diagnosis model of industrial control equipment based on ensemble learning effectively improves the adaptive ability of the model and makes the fault diagnosis framework truly intelligent. The voting weight adjustment method based on dynamic programming further improves the reliability of voting.

Research on numerical control machine fault diagnosis based on distribution adaptive one-dimensional convolutional neural network

Numerical control machine is a high-precision and high-automation equipment, if the problem occurred in operation, it can affect the processing conditions of the machinery parts first. If the fault is aggravated, it can eventually cause the numerical control machine to stop. Spindle bearings and tools are the most vulnerable parts of numerical control machine. Previously, resonance demodulation technique was used for bearing fault diagnosis. Empirical analysis or neural network was used for tool fault diagnosis. However, the numerical control machine is an entirety, the fault is usually caused by multi-dimensional factors, the above method doesn’t work when two types of faults occur at the same time. To diagnose faults of numerical control machine, a fault diagnosis model named distribution adaptive deep convolutional neural networks (DADCNN) was proposed. This model was based on One-dimensional convolution algorithm. The Batch Normalization algorithm was involved to overcome the problem of changing data distribution in the middle layer. The t-SNE algorithm was used to visualize and view the feature classification results. Experiments show that the accuracy of this model can reach 90.29%, and it has good fault diagnosis capabilities.

Bearing Fault Feature Extraction and Fault Diagnosis Method Based on Feature Fusion

Bearing is one of the most important parts of rotating machinery with high failure rate, and its working state directly affects the performance of the entire equipment. Hence, it is of great significance to diagnose bearing faults, which can contribute to guaranteeing running stability and maintenance, thus promoting production efficiency and economic benefits. Usually, the bearing fault features are difficult to extract effectively, which results in low diagnosis performance. To solve the problem, this paper proposes a bearing fault feature extraction method and it establishes a bearing fault diagnosis method that is based on feature fusion. The basic idea of the method is as follows: firstly, the time-frequency feature of the bearing signal is extracted through Wavelet Packet Transform (WPT) to form the time-frequency characteristic matrix of the signal; secondly, the Multi-Weight Singular Value Decomposition (MWSVD) is constructed by singular value contribution rate and entropy weight. The features of the time-frequency feature matrix obtained by WPT are further extracted, and the features that are sensitive to fault in the time-frequency feature matrix are retained while the insensitive features are removed; finally, the extracted feature matrix is used as the input of the Support Vector Machine (SVM) classifier for bearing fault diagnosis. The proposed method is validated by data sets from the time-varying bearing data from the University of Ottawa and Case Western Reserve University Bearing Data Center. The results show that the algorithm can effectively diagnose the bearing under the steady-state and unsteady state. This paper proposes that the algorithm has better fault diagnosis capabilities and feature extraction capabilities when compared with methods that aree based on traditional feature technology.

Research on Structure Data Link Detection Method Based on Internet of Things System

In order to improve the fault diagnosis and analysis capabilities of the cyber-physical system in the Internet of Things, it is necessary to detect and identify the vicious data chain of the cyber-physical system in the Internet of Things. Moreover, to realize the detection and identification of the vicious data link in the cyber-physical system in the Internet of Things, a fast extraction algorithm for the vicious data link of the cyber-physical system in the Internet of Things is proposed in the paper to collect vicious data from the cyber-physical system in the Internet of Things. In addition, the malignant data generated during the factor adjustment of the Internet of Things can be divided into periodic structure and non-periodic structure in structure, and the malignant data sensor network model of the cyber-physical system in the Internet of Things is constructed. Therefore, through simulation experiment analysis, the method proposed in the paper has superior performance in the detection and identification of vicious data links in the cyber-physical system of the Internet of Things.

The intermittent fault diagnosis of analog circuits based on EEMD-DBN

Aiming at the intermittent faults widely existing in analog circuits, caused by poor soldering and performance degradation of components, a method for the intermittent fault diagnosis of analog circuits based on ensemble empirical mode decomposition (EEMD) and deep belief network (DBN) is proposed. The amplitude and frequency anomaly signals in the frequency domain is regarded as triggering signals for intermittent fault detection, so the signal segments containing intermittent faults can be detected. The signal segment with intermittent fault is decomposed into multiple intrinsic mode functions (IMFs) by EEMD, and the IMF and fault features are optimized by using Pearson correlation coefficient and feature separability. The optimization feature set is established, which is used as feature vector to transmitted to DBN for fault diagnosis. The proposed method can autonomously realize the feature selection and the diagnosis of intermittent fault. The optimization features make DBN improve diagnostic accuracy, reduce diagnostic time, and can locate intermittent faults to the circuit branch with intermittent faults. The simulation experiments show that the proposed method has strong fault diagnosis capability. And the comparative experiments prove that compared with other commonly used methods, the EEMD-DBN method has higher diagnostic accuracy in intermittent fault diagnosis of analog circuits.

Structured sparsity modeling for improved multivariate statistical analysis based fault isolation

In order to improve the fault diagnosis capability of multivariate statistical methods, this article introduces a fault isolation framework based on structured sparsity modeling. The developed method relies on the reconstruction based contribution analysis and the process structure information can be incorporated into the reconstruction objective function in the form of structured sparsity regularization terms. The structured sparsity terms allow selection of fault variables over structures like blocks or networks of process variables, hence more accurate fault isolation can be achieved. Four structured sparsity terms corresponding to different kinds of process information are considered, namely, partially known sparse support, block sparsity, clustered sparsity and tree-structured sparsity. The optimization problems involving the structured sparsity terms can be solved using the Alternating Direction Method of Multipliers (ADMM) algorithm, which is fast and efficient. Through a simulation example and an application study to a coal-fired power plant, it is verified that the proposed method can better isolate faulty variables by incorporating process structure information.

Developing A Supervisory Technique for Online Fault Isolation and Coordination Tasks (Dept.E)

The control of complex automated systems requires a supervision system that includes coordination as well as fault detection and diagnosis capabilities. The objective of coordination system is to enforce the plant to legal and safe behavior, while the objective of the fault detection and isolation is to detect and isolate the failures according to the observation traces generated by the system. This paper proposes a new supervisory control technique for online fault detection, isolation and coordination based on Petri net models. This technique has two components, a supervisor, and a diagnoser. The latter evaluates the faulty states without checking the properties that restrict the performance of the conventional dignosers to certain types of Petri net models. This paper also presents two-robot surveillance system, as an application example, to test the proposed algorithm.

The Design of Marine Machinery Based on the Design Theory of Monitorability

Yang, J., 2020. The design of marine machinery based on the design theory of monitorability. In: Li, L. and Huang, X. (eds.), Sustainable Development in Coastal Regions: A Perspective of Environment, Economy, and Technology. Journal of Coastal Research, Special Issue No. 112, pp. 333-336. Coconut Creek (Florida), ISSN 0749-0208.With the rapid development of science and technology, the mechanical device of marine ship system is gradually improving to the direction of large-scale, complexity and high parameter, which will introduce more unpredictable factors. With the continuous progress of signal acquisition technology, sensor technology and signal processing technology, ship condition monitoring and fault diagnosis technology has become the main research direction. Therefore, we must test and control the mechanical design of the ship, which will avoid threatening the safety of the ship due to the failure of the mechanical system. Through the mechanical design monitoring and control, the marine ship will improve the reliability, maintainability, supportability, safety and economy of the system, which will effectively prevent, control and eliminate various faults and play the maximum effect of the machinery. Based on the design theory of monitorability, this paper describes the monitorability of marine ships in the conventional mechanical system, which will enhance the capability of condition monitoring and fault diagnosis of mechanical system engineering. Through the inspection and control of ship machinery, we can improve the safety of marine ships, which will adapt to the increasingly complex and huge marine ship system.

Improved Fault Diagnosis of Railway Switch System Using Energy-Based Thresholding Wavelets (EBTW) and Neural Networks

An improved method with feature extraction and neural network classification is proposed and applied to address the fault diagnosis problem in railway switch systems. Features are extracted by analyzing the nonstationary signal time-frequency characteristics of the electromechanical machine under different fault severities. To enhance the fault diagnosis capability, an energy-based thresholding wavelets (EBTW) approach is proposed by reconstructing a low-dimensional feature vector with selected parameters. Different from the conventional discrete wavelet transform and soft-thresholding wavelet transform, the proposed method localizes and redistributes the signal energy to achieve an efficient dimension reduction. The first step of the proposed method is to perform a wavelet transform upon the original signals, whose wavelet coefficients are then thresholded and an extraction of features is made, on the basis of the energy conservation property of wavelet transforms. Once the features are extracted and selected, several state-of-the-art neural-network-based classifiers are applied for fault diagnosis by identifying the signal features from a machine normal operation and faulty operations with multiple severities. The effectiveness of the proposed method is verified using real-world operational railway switch data and compared with conventional feature extraction methods under different classifiers.

A Fault Diagnosis Method of Rotating Machinery Based on One-Dimensional, Self-Normalizing Convolutional Neural Networks.

Aiming at the fault diagnosis issue of rotating machinery, a novel method based on the deep learning theory is presented in this paper. By combining one-dimensional convolutional neural networks (1D-CNN) with self-normalizing neural networks (SNN), the proposed method can achieve high fault identification accuracy in a simple and compact architecture configuration. By taking advantage of the self-normalizing properties of the activation function SeLU, the stability and convergence of the fault diagnosis model are maintained. By introducing -dropout mechanism twice to regularize the training process, the overfitting problem is resolved and the generalization capability of the model is further improved. The experimental results on the benchmark dataset show that the proposed method possesses high fault identification accuracy and excellent cross-load fault diagnosis capability.

Hybrid PMC (HPMC) fault model and diagnosability of interconnection networks

System level diagnosis, an area pioneered by Preparata, Metze and Chien, has been a dominant area of research in the broader area of fault-tolerant computing since the proposition of the PMC model. In this paper, we study the fault diagnosis problem for systems in hybrid fault circumstances where both node and link faults may occur. Under our diagnosis model, a test involves two adjacent processors and the link between them. We propose the definition of consistent faulty pairs and distinguishable faulty pairs. Given an assignment of testing links, we establish necessary and sufficient conditions for distinguishable faulty pairs. Finally, we introduce parameters to measure the fault diagnosis capability of multiprocessor systems under this model and as an application the fault diagnosis capability of hypercubes under this model has been evaluated.

Reliability of DQcube Based on g-Extra Conditional Fault

Abstract Diagnosability and connectivity are important metrics for the reliability and fault diagnosis capability of interconnection networks, respectively. The g-extra connectivity of a graph G, denoted by $\kappa _g(G)$, is the minimum number of vertices whose deletion will disconnect the network and every remaining component has more than $g$ vertices. The g-extra conditional diagnosability of graph G, denoted by $t_g(G)$, is the maximum number of faulty vertices that the graph G can guarantee to identify under the condition that every fault-free component contains at least g+1 vertices. In this paper, we first determine that g-extra connectivity of DQcube is $\kappa _g(G)=(g+1)(n+1)-\frac{g(g+3)}{2}$ for $0\leq g\leq n-3$ and then show that the g-extra conditional diagnosability of DQcube under the PMC model $(n\geq 4, 1\leq g\leq n-3)$ and the MM$^\ast$ model $(n\geq 7, 1\leq g\leq \frac{n-3}{4})$ is $t_g(G)=(g+1)(n+1)-\frac{g(g+3)}{2}+g$, respectively.

Hybrid fault diagnosis capability analysis of regular graphs under the PMC model

Diagnosabilty is an important metric to the capability of fault identification for multiprocessor systems. However, most researches on diagnosability focus on vertex fault. In real circumstances, not only vertex faults take place but also malfunctions may arise. In this paper, we study the diagnosability of k-regular 2-cn graph with missing edges. Let be a set of missing edges in graph G with . We prove that the diagnosability of is at most for . Furthermore, we obtain that the worst-case diagnosability (h-edge tolerable diagnosability), denoted by , is maximum number of faulty nodes that a system G can guarantee to locate when the number of faulty links does not exceed h. As applications, the diagnosabilities of many networks with missing edges are determined under the PMC model.

Failure analysis of induced draft fan used in a thermal power plant using coordinated condition monitoring approach: A case study

Early detection of the fault is not only essential to ensure the current health of the critical equipment but also to diagnose the fault before any catastrophic failure. In order to improve the capability for early fault detection and diagnosis of critical equipment, an improved form of generalized coordinated condition monitoring approach has been developed and adopted in this paper. The effectiveness of an integrated approach has been realized by concurrently using selected condition monitoring techniques viz. vibration analysis, noise measurement, wear debris analysis, ultrasonic monitoring in terms of increased fault diagnosis accuracy. A case study on failure analysis of Induced Draft (ID) fan 2A from 250 × 2 MW thermal power plant located in the western region of India is carried out. The vibration trend of acceleration parameter of hydraulic coupling input bearing found to be on the higher side and reached to 4.2 (g) level, sound level meter recorded an increased noise level of 99.8 dB, and high-frequency sound of 18 dB ultrasound was observed by the ultrasonic meter. In addition, medium alloy bearing particles of size 68 µm were found in the test oil sample, which confirmed that hydraulic coupling input bearing deterioration, has occurred.The vibration parameter provides sufficient insights into the earliest failures, and the fault location, severity, its effect on other process parameters are monitored by noise, wear, and ultrasound level. Furthermore, the secondary damages related to motor and fan were avoided. Simultaneous use of these techniques not only detects the earlier fault but can be diagnosed before any catastrophic failure. The result obtained in this study assisted the maintenance engineer of the plant for scheduling the maintenance activity well in advance.

A model-based calibration approach for structural fault diagnosis using piezoelectric impedance measurements and a finite element model

The electromechanical coupling property of piezoelectric transducers gives rise to a promising class of structural fault diagnosis methods often referred to collectively as impedance-based approaches. One active line of research in the related literature is the development of data-driven methods that can leverage the available experimental impedance measurements to accurately pinpoint the location and severity of structural faults. In this article, we offer a new perspective to the problem by casting the impedance-based fault diagnosis into a statistical calibration formulation, which has gained a wide popularity in the industrial statistics community in the past two decades. Specifically, we decide to estimate the values of the fault attributes (e.g. location and severity) that achieve the closest match between the outputs from a finite element model and those experimentally solicited from the host structure. We further propose to couple this statistical formulation with a pre-screening procedure to reduce the calibration search space and mitigate parameter identifiability issues. In addition to the merit of capably diagnosing structural faults, the proposed approach extends various useful concepts from the statistical calibration literature to the structural health monitoring applications, such as the construction of surrogate models for modeling and predicting impedance changes, the explicit use of a bias function to correct for inherent inadequacies in finite element models, as well as the ability to produce continuous probability distributions for quantifying a fault’s severity. These additional benefits substantially enhance both the fault diagnosis capability and computational efficiency. We demonstrate the effectiveness of the proposed approach using two simulated and two experimental case studies from the literature.

Rolling Bearing Fault Diagnosis Based on Wavelet Packet Transform and Convolutional Neural Network

Timely sensing the abnormal condition of the bearings plays a crucial role in ensuring the normal and safe operation of the rotating machine. Most traditional bearing fault diagnosis methods are developed from machine learning, which might rely on the manual design features and prior knowledge of the faults. In this paper, based on the advantages of CNN model, a two-step fault diagnosis method developed from wavelet packet transform (WPT) and convolutional neural network (CNN) is proposed for fault diagnosis of bearings without any manual work. In the first step, the WPT is designed to obtain the wavelet packet coefficients from raw signals, which then are converted into the gray scale images by a designed data-to-image conversion method. In the second step, a CNN model is built to automatically extract the representative features from gray images and implement the fault classification. The performance of the proposed method is evaluated by a real rolling-bearing dataset. From the experimental study, it can be seen the proposed method presents a more superior fault diagnosis capability than other machine-learning-based methods.

Online Fault Diagnosis Method for High-Performance Converters Using Inductor Voltage Polar Signatures

Recently, the high-performance converter with wide range and high gain has been widely used in these cases such as PV power generation. On the other hand, there are more highly variable stresses on switch and diode in high-performance converter than the traditional DC-DC converters due to the wide range and high gain. Therefore, it is necessary to diagnose switch and diode faults in high-performance converter. In this paper, the switch and diode fault are analyzed and compared with traditional DC-DC converters. Then, an online diagnosis technique based on the inductor voltage polarity of the DC-DC converter is proposed. This technique only uses the inductor voltage polarity and the switch gate drive signal as signatures to diagnose short-circuit or open-circuit fault of the switch and diode. The technique is cost-effective and simple because it uses simple auxiliary windings to sense the inductor voltage polar and uses some logic circuit to generate indicators. The details of the technique are discussed through an example of the quadratic Boost converter. Experiments illustrate the correctness of the proposed technique and show its capability for switch and diode fault diagnosis.

Hybrid fault diagnosis capability analysis of triangle-free graphs

Fault diagnosis capability is an important metric of the reliability of multiprocessor systems. The h-edge tolerable diagnosability is the maximum number of faulty nodes that the system can guarantee to locate when the number of faulty links does not exceed h. In fact, the 0-edge tolerable diagnosability is exactly the traditional diagnosability. In this paper, we determine the h-edge tolerable diagnosabilities of triangle-free graphs under the PMC model and the MM⁎ model, respectively, which extend the results of triangle-free regular graphs (Wei and Xu (2019) [26]). As applications, the h-edge tolerable diagnosabilities of many networks are determined under the PMC model and the MM⁎ model.

The h-edge tolerable diagnosability of balanced hypercubes

To measure the fault diagnosis capability of a multiprocessor system with faulty links, Zhu et al. (2019) [26] introduced the h-edge tolerable diagnosability. This kind of diagnosability is a generalization of the concept of traditional diagnosability. In this paper, as complement to the results in Wei and Xu (2019) [16], we completely determine the h-edge tolerable diagnosability of balanced hypercubes BHn under the PMC model and the MM⁎ model. Thus, the traditional diagnosability of BHn is also determined.

Fault diagnosis in industrial chemical processes using optimal probabilistic neural network

For fault detection and diagnosis in large‐scale industrial systems, traditional methods have a low classification accuracy, which is an issue. This paper proposes a fault diagnosis method based on the modified cuckoo search algorithm (MCS) to optimize the probabilistic neural network (PNN). The random forest treebagger (RFtb) is used to reduce the data feature and the PNN is trained for fault diagnosis and classification. However, in order to address the problem that the parameters of PNN easily fall into the local optimal value, the MCS algorithm is introduced to globally optimize the hidden layer element smoothing factor (σ) in the PNN. The MCS algorithm uses a parameters update and a better optimization mechanism to achieve excellent global convergence and to effectively improve the fault diagnosis capability of the model. During the testing process using the Tennessee Eastman (TE) process dataset, the performance of the proposed model is assessed by comparing the accuracy and the F1‐score of different methods. Graphs are presented that depict fault classification and diagnostic results for the different models. The results show that the MCS algorithm has a better optimization ability than the traditional optimization algorithm and the proposed combination method can significantly improve the accuracy of the TE process fault diagnosis.