Intelligent Fault Diagnosis Technology Research Articles

Wasserstein Generative Adversarial Network and Convolutional Neural Network (WG-CNN) for Bearing Fault Diagnosis

In recent years, intelligent fault diagnosis technology with deep learning algorithms has been widely used in industry, and they have achieved gratifying results. Most of these methods require large amount of training data. However, in actual industrial systems, it is difficult to obtain enough and balanced sample data, which pose challenges in fault identification and classification. In order to solve the problems, this paper proposes a data generation strategy based on Wasserstein generative adversarial network and convolutional neural network (WG-CNN), which uses generator and discriminator to conduct confrontation training, expands a small sample set into a high-quality dataset, and uses one-dimensional convolutional neural network (1D-CNN) to learn sample characteristics and classify different fault types. Experimental results over the standard Case Western Reserve University (CWRU) bearing fault diagnosis benchmark dataset showed that the proposed method has obvious and satisfactory fault diagnosis effect with 100% classification accuracy for few-shot learning. In different noise environments, this method also has excellent performance.

Ensemble diagnosis method based on transfer learning and incremental learning towards mechanical big data

The advancement of big data in industry has prompted the development of intelligent fault diagnosis technologies. Nevertheless, several challenges of big data are notable, such as extracting valuable features from original data, exploring general methods to accommodate data with different distributions, and handling streaming data. This paper proposed an ensemble learning method to handle these challenges. Firstly, a convolutional neural network (CNN) is trained by source domain directly. Then, a transfer learning method with pre-trained CNN is employed to extract valuable information from quite different datasets, which is useful to utilize knowledge of CNN learned in previous object and reduce modeling time. At last, an online learning method named incremental support vector machine is applied to classify various conditions. Five mechanical fault datasets acquired from three test rigs are used in the case study. Comparison study shows that the proposed method can be applied in mechanical fault diagnosis under big data era.

A novel unsupervised deep learning network for intelligent fault diagnosis of rotating machinery

Generally, the health conditions of rotating machinery are complicated and changeable. Meanwhile, its fault labeled information is mostly unknown. Therefore, it is man-sized to automatically capture the useful fault labeled information from the monitoring raw vibration signals. That is to say, the intelligent unsupervised learning approach has a significant influence on fault diagnosis of rotating machinery. In this study, a span-new unsupervised deep learning network can be constructed based on the proposed feature extractor (L12 sparse filtering (L12SF)) and the designed clustering extractor (Weighted Euclidean Affinity Propagation) for resolving the issue that the acquisition of fault sample labeled information is burdensome, yet costly. Naturally, the novel intelligent fault diagnosis method of rotating machinery based on unsupervised deep learning network is first presented in this study. Thereinto, the proposed unsupervised deep learning network consists of two layers of unsupervised feature extractor (L12SF) and one layer of unsupervised clustering (Weighted Euclidean Affinity Propagation). L12SF can improve the regularization performance of sparse filtering, and Weighted Euclidean Affinity Propagation can get rid of the traditional Euclidean distance in affinity propagation that cannot highlight the contribution of different features in fault clustering. To make a long story short, the frequency spectrum signals are first entered into the constructed unsupervised deep learning network for fault feature representation; afterward, the unsupervised feature learning and unsupervised fault classification of rotating machinery can be implemented. The superiority of the proposed algorithms and method is validated by two cases of rolling bearing fault dataset. Ultimately, the proposed unsupervised fault diagnosis method can provide a theoretical basis for the development of intelligent unsupervised fault diagnosis technology for rotating machinery.

Knowledge representation and intelligent fault diagnosis technology for power grid faults

Aiming at that the automatic fault diagnosis method is difficult to locate the fault causes under uncertain circumstances which include malfunctions of the equipment and wrong alarm messages, a knowledge model was proposed to describe the relationship, status and operation of the equipment. And based on the model, the action logic between equipment after accidents is expressed in the form of rules combined with predicate logic. The corresponding interpretation and checking results of the relative alarm messages are given by reasoning the accident chain under different fault hypothesis. And the optimal judgment result is obtained through the calculation of prior probability. The validity of the method is verified by a practical fault case.

Deep Hybrid State Network With Feature Reinforcement for Intelligent Fault Diagnosis of Delta 3-D Printers

An echo state network (ESN) is a type of recurrent neural network that is good at processing time-series data with dynamic behavior. However, the use of ESNs to enhance fault-classification accuracy continues to be challenging when the condition signals are collected by low-cost sensors. In this paper, a deep network algorithm, called a deep hybrid state network (DHSN), is proposed for fault diagnosis of three-dimensional printers using attitude data with low measurement precision. In the DHSN, the output data of a sparse auto-encoder are regarded as the abstract features of a double-structured ESN (DESN). The DESN is designed for feature reinforcement and fault recognition, wherein the first function reinforces the features and the second is used for fault classification. More specifically, feature reinforcement is developed to improve the clustering performance and replace the traditional overall feedback fine-tuning in deep models. This strategy improves learning efficiency and overcomes the vanishing-gradient problem for deep learning. The forecasting performance of the proposed approach is evaluated in experiments, and its superiority is demonstrated through comparison with other intelligent fault-diagnosis technologies.

Bearing Fault Diagnosis with a Feature Fusion Method Based on an Ensemble Convolutional Neural Network and Deep Neural Network.

Rolling bearings are the core components of rotating machinery. Their health directly affects the performance, stability and life of rotating machinery. To prevent possible damage, it is necessary to detect the condition of rolling bearings for fault diagnosis. With the rapid development of intelligent fault diagnosis technology, various deep learning methods have been applied in fault diagnosis in recent years. Convolution neural networks (CNN) have shown high performance in feature extraction. However, the pooling operation of CNN can lead to the loss of much valuable information and the relationship between the whole and the part may be ignored. In this study, we proposed CNNEPDNN, a novel bearing fault diagnosis model based on ensemble deep neural network (DNN) and CNN. We firstly trained CNNEPDNN model. Each of its local networks was trained with different training datasets. The CNN used vibration sensor signals as the input, whereas the DNN used nine time-domain statistical features from bearing vibration sensor signals as the input. Each local network of CNNEPDNN extracted different features from its own trained dataset, thus we fused features with different discrimination for fault recognition. CNNEPDNN was tested under 10 fault conditions based on the bearing data from Bearing Data Center of Case Western Reserve University (CWRU). To evaluate the proposed model, four aspects were analyzed: convergence speed of training loss function, test accuracy, F-Score and the feature clustering result by t-distributed stochastic neighbor embedding (t-SNE) visualization. The training loss function of the proposed model converged more quickly than the local models under different loads. The test accuracy of the proposed model is better than that of CNN, DNN and BPNN. The F-Score value of the model is higher than that of CNN model, and the feature clustering effect of the proposed model was better than that of CNN.

A Deep Transfer Model With Wasserstein Distance Guided Multi-Adversarial Networks for Bearing Fault Diagnosis Under Different Working Conditions

In recent years, intelligent fault diagnosis technology with the deep learning algorithm has been widely used in the manufacturing industry for substituting time-consuming human analysis method to enhance the efficiency of fault diagnosis. The rolling bearing as the connection between the rotor and support is the crucial component in rotating equipment. However, the working condition of the rolling bearing is under changing with complex operation demand, which will significantly degrade the performance of the intelligent fault diagnosis method. In this paper, a new deep transfer model based on Wasserstein distance guided multi-adversarial networks (WDMAN) is proposed to address this problem. The WDMAN model exploits complex feature space structures to enable the transfer of different data distributions based on multiple domain critic networks. The essence of our method is learning the shared feature representation by minimizing the Wasserstein distance between the source domain and target domain distribution in an adversarial training way. The experiment results demonstrate that our model outperforms the state-of-the-art methods on rolling bearing fault diagnosis under different working conditions. The t-distributed stochastic neighbor embedding (t-SNE) technology is used to visualize the learned domain invariant feature and investigate the transferability behind the great performance of our proposed model.

Research on Intelligent Fault Diagnosis and Early Warning Technology of Gateway Electrical Energy Metering Device

As the most important daily management work in power application, electrical energy metering is carried out throughout the whole process of power production, transmission and use. Ensuring the accurate and reliable operation of electric energy measurement is the key to establish a fair, just and orderly electric power marketing market. At present, there are many problems in the inspection process of electric power measurement device, which include large workload, long verification time, sampling accuracy and algorithm performance constraints. In this paper, the remote on-line diagnosis of electrical energy metering decice is studied. Based on a large amount of sampling datas of power measurement, voltage and current, it introduces the parallel computing in data mining. Based on support vector machine, data and task parallelization fault diagnosis modelsare established,the online real-time monitoring and failure warning for electric power measurement device is realized, which contains abnormal characteristics and fault state. The visualization method is used to upload the device failure pictures in time and the diversified fault early warning technology is adopted, in order that the staff can timely analyze the electrical energy metering device in the fault or abnormal condition. In this way, the remote state monitoring and operation management level of the electrical energy metering device are improved.

Complicated Manufacturing System Dynamic Measure-Control and Intelligence Diagnosis

As an important mean to ensure machining accuracy, the dynamic measurement and intelligent fault diagnosis technology can be used in aviation manufacturing machine. In recent years, several theoretical results are gotten on weak signal feature extraction, multiple sensor information fusion of early fault identification as well as the set up of embedded online monitoring units. This article is the summary of those results, the existing problems is analyzed, and the trend of the development in this field is also discussed.

A Modeling and Probabilistic Reasoning Method of Dynamic Uncertain Causality Graph for Industrial Fault Diagnosis

Online automatic fault diagnosis in industrial systems is essential for guaranteeing safe, reliable and efficient operations. However, difficulties associated with computational overload, ubiquitous uncertainties and insufficient fault samples hamper the engineering application of intelligent fault diagnosis technology. Geared towards the settlement of these problems, this paper introduces the method of dynamic uncertain causality graph, which is a new attempt to model complex behaviors of real-world systems under uncertainties. The visual representation to causality pathways and self-relied “chaining” inference mechanisms are analyzed. In particular, some solutions are investigated for the diagnostic reasoning algorithm to aim at reducing its computational complexity and improving the robustness to potential losses and imprecisions in observations. To evaluate the effectiveness and performance of this method, experiments are conducted using both synthetic calculation cases and generator faults of a nuclear power plant. The results manifest the high diagnostic accuracy and efficiency, suggesting its practical significance in large-scale industrial applications.

Research Overview on Intelligent Fault Diagnosis Technology of Turbine

The intelligent condition monitoring and diagnosis technology has become a hot spot of the research on fault diagnosis. The research, which is on the diagnostic method based on artificial intelligence and its application in fault diagnosis of Turbogenerator, has important social significance and is full of economic value. Introduce the development status of intelligent fault diagnosis technology of turbine. Focus on fault diagnosis technology based on neural network integration with experiment research, analysis and summary. Finally, point out a number of issues and trends of the further study in this area.

Design and Implementation of Universal Detection Equipment of Inertial Navigation System Based on "Platform + Adapter Structure"

According to such problems as complicated structure, too many circuit module and online difficult detection of vehicle-mounted platform inertial navigation system, the detector adopts the detection mode of platform + adapter to realize the universalization and modularization of the detection equipment. It reduced circuit scale and the difficulty of design, strengthened systems scalability, at the same time made equipment carry and use more flexible. It realized inertial navigation board level to device level detection by using intelligent fault diagnosis technology to automatic fault diagnosis of circuit. Meanwhile, with the effective optimization of lesser detection procedures, the high efficiency and accurateness of fault isolation and location had been guaranteed, detection equipments automation, integrated, accuracy greatly raised, and detection time greatly shortened.

Remote Monitoring and Intelligent Fault Diagnosis Technology Research Based on Open CNC System

In modem manufacturing,the various and complex requirement of industry makes the CNC machine tools more and more automatic and networking.While a remote monitoring and intelligent fault diagnosis system is the basic and indispensable unit for automatic and networking machine tools.This paper is focused on open CNC system,the condition monitoring, and fault diagnosis technology are researched of open CNC system. Integration achieved the CNCmachine tools' status remote monitoring and intelligent fault diagnosis, and detailed analysis of the key technologies for the components of the system. Through effectively integration of the computer technology, Fault Tree Analysis method, or other technologies to enhance the automation, networking and intelligent level of the open CNC system. Keywords: open CNC system; remote monitoring; intelligent fault diagnosis ;Fault Tree Analysis Method;

A New Method for Electronic Circuit Fault Knowledge Acquisition Using PSPICE

A new method for electronic circuit fault knowledge automatic generation Using PSpice has been put forward based on summarizing development of the intelligent fault diagnosis technology. A new algorithm of generating fault knowledge automatically has been designed by analysing the structure characteristics of the CIR file. The algorithm of search automatically has been designed by analysing the structure characteristic of the OUT file. The DC fault dictionary method has been improved and the fault order according to the minimum distance will guide the user to remove the fault. In the end, through these technologies, the fault knowledge query system has been empoldered. The feasibility of the proposed method has been proved by experiment results.

Design and Implementation of Engine Waveform Tester Based on Virtual Instrument

Engine fault diagnosis and detection is inseparable from the analysis and examination of each sensor or actuator, and the waveform display is the most intuitive and convenient way. This system is an engine waveform tester developed based on virtual instrument and the batch estimate fusion theory is used in the process of the single sensor data acquisition and processing. It is proved by practice that this instrument can conveniently and quickly realize the functions such as signal acquisition and control, waveform analysis and processing and result expressing and output, thus providing technical support for comprehensive intelligent engine fault diagnosis technology.

A Virtual Sample Generation Approach for Blast Furnace Fault Diagnosis

The blast furnace faults will cause significant economic and human losses. Therefore, the study of blast furnace intelligent fault diagnosis technology is necessary and important. But some real fault data is difficult to obtain .The training set can not be provided enough samples.So a new virtual fault samples generation method is designed to get enough tainning samples. The designed method uses group discovery technique and the Box-Muller method to generate the candidate virtual fault sample set. And then with the help of manifold contraction and the semi-supervised learning algorithm to select the virtual samples with better performance. By adding the selected virtual samples to the original training set,a new svm fault diagnosis classifier is obtained. The results show that this method can simulate the fault samples effectively,and the new classifier’s accuracy is much more acceptable.

Remote Intelligent Fault Diagnosis System Modeling Based on Multi-Agent

With the development of intelligent fault diagnosis technology, research on the application of multi-Agent theory in the remote fault diagnosis system is increasing. With avionic devices as the application background, the modeling of the remote intelligent fault diagnosis system (RIFDS) based on multi-Agent theory is researched, including the frame model, logical model and soft architecture. The key problems that need to be resolved for the realization of the system are also discussed.

Study of Intelligent Diagnosis System for Photoelectric Tracking Devices Based on Multiple Knowledge Representation

Aiming at the fatal flaws of the traditional diagnosis methods for the large-scale photoelectric tracking devices, such as poor stability and adaptive capacity, lack of inspiration and narrow domain knowledge of expert system, etc, more importantly, fundamentally improve the diagnostic efficiency and universality, in this paper, an intelligent mixed inference diagnosis expert system based on multiple knowledge representation and BP neural network is put forward. Firstly, some related key basic concepts and principles of intelligent fault diagnosis technology and several major applied diagnosis knowledge representation methods such as diagnosis fault tree, frame representation production rule and so on, were elaborated. Secondly, in view of high concurrency and relevancy of the system faults, a mixed reasoning mechanism combining BPNN and ES was researched. Finally, some interrelated essential implementation techniques, such as system architecture and VR technology, were also presented. Actual applications and experiments demonstrate that the proposed approach is robust and effective.