Fault diagnosis method of link control system for gravitational wave detection

To maintain the stability of the inter-satellite link for gravitational wave detection,an intelligent learning monitoring and fast warning method of the inter-satellite link control system failure is proposed.Different from the traditional fault diagnosis optimization algorithms,the fault intelligent learning method pro-posed in this paper is able to quickly identify the faults of inter-satellite link control system despite the existence of strong cou-pling nonlinearity.By constructing a two-layer learning network,the method enables efficient joint diagnosis of fault areas and fault parameters.The simulation results show that the average identification time of the system fault area and fault parameters is 0.27 s,and the fault diagnosis efficiency is improved by 99.8%compared with the traditional algorithm.

Uncertainty-Aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis

Recently,intelligent fault diagnosis based on deep learning has been extensively investigated,exhibiting state-of-the-art performance.However,the deep learning model is often not truly trusted by users due to the lack of interpretability of“black box”,which limits its deployment in safety-critical applications.A trusted fault diagnosis system requires that the faults can be accurately diagnosed in most cases,and the human in the deci-sion-making loop can be found to deal with the abnormal situa-tion when the models fail.In this paper,we explore a simplified method for quantifying both aleatoric and epistemic uncertainty in deterministic networks,called SAEU.In SAEU,Multivariate Gaussian distribution is employed in the deep architecture to compensate for the shortcomings of complexity and applicability of Bayesian neural networks.Based on the SAEU,we propose a unified uncertainty-aware deep learning framework(UU-DLF)to realize the grand vision of trustworthy fault diagnosis.Moreover,our UU-DLF effectively embodies the idea of“humans in the loop”,which not only allows for manual intervention in abnor-mal situations of diagnostic models,but also makes correspond-ing improvements on existing models based on traceability analy-sis.Finally,two experiments conducted on the gearbox and aero-engine bevel gears are used to demonstrate the effectiveness of UU-DLF and explore the effective reasons behind.

Fault detection and diagnosis for data incomplete industrial systems with new Bayesian network approach

For the fault detection and diagnosis problem in largescale industrial systems, there are two important issues： the missing data samples and the non-Gaussian property of the data. However, most of the existing data-driven methods cannot be able to handle both of them. Thus, a new Bayesian network classifier based fault detection and diagnosis method is proposed. At first, a non-imputation method is presented to handle the data incomplete samples, with the property of the proposed Bayesian network classifier, and the missing values can be marginalized in an elegant manner. Furthermore, the Gaussian mixture model is used to approximate the non-Gaussian data with a linear combination of finite Gaussian mixtures, so that the Bayesian network can process the non-Gaussian data in an effective way. Therefore, the entire fault detection and diagnosis method can deal with the high-dimensional incomplete process samples in an efficient and robust way. The diagnosis results are expressed in the manner of probability with the reliability scores. The proposed approach is evaluated with a benchmark problem called the Tennessee Eastman process. The simulation results show the effectiveness and robustness of the proposed method in fault detection and diagnosis for large-scale systems with missing measurements.

Deep learning technique for process fault detection and diagnosis in the presence of incomplete data

In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process operations. Various fault detection and diagnosis(FDD) methods have been proposed and implemented, the performance of which, however, could be drastically influenced by the common presence of incomplete or missing data in real industrial scenarios. This paper presents a new FDD approach based on an incomplete data imputation technique for process fault recognition. It employs the modified stacked autoencoder,a deep learning structure, in the phase of incomplete data treatment, and classifies data representations rather than the imputed complete data in the phase of fault identification. A benchmark process, the Tennessee Eastman process, is employed to illustrate the effectiveness and applicability of the proposed method.

Chiller faults detection and diagnosis with sensor network and adaptive 1D CNN

Computer-empowered detection of possible faults for Heating,Ventilation and Air-Conditioning(HVAC)subsystems,e.g.,chillers,is one of the most important applications in Artificial Intelligence(AI)integrated Internet of Things(IoT).The cyber-physical system greatly enhances the safety and security of the working facilities,reducing time,saving energy and protecting humans’health.Under the current trends of smart building design and energy management optimization,Automated Fault Detection and Diagnosis(AFDD)of chillers integrated with IoT is highly demanded.Recent studies show that standard machine learning techniques,such as Principal Component Analysis(PCA),Support Vector Machine(SVM)and tree-structure-based algorithms,are useful in capturing various chiller faults with high accuracy rates.With the fast development of deep learning technology,Convolutional Neural Networks(CNNs)have been widely and successfully applied to various fields.However,for chiller AFDD,few existing works are adopting CNN and its extensions in the feature extraction and classification processes.In this study,we propose to perform chiller FDD using a CNN-based approach.The proposed approach has two distinct advantages over existing machine learning-based chiller AFDD methods.First,the CNN-based approach does not require the feature selection/extraction process.Since CNN is reputable with its feature extraction capability,the feature extraction and classification processes are merged,leading to a more neat AFDD framework compared to traditional approaches.Second,the classification accuracy is significantly improved compared to traditional methods using the CNN-based approach.

Fault detection and diagnosis of permanent-magnetic DC motors based on current analysis and BP neural networks

In order to guarantee quality during mass serial production of motors, a convenient approach on how to detect and diagnose the faults of a permanent-magnetic DC motor based on armature current analysis and BP neural networks was presented in this paper. The fault feature vector was directly established by analyzing the armature current. Fault features were extracted from the current using various signal processing methods including Fourier analysis, wavelet analysis and statistical methods. Then an advanced BP neural network was used to finish decision-making and separate fault patterns. Finally, the accuracy of the method in this paper was verified by analyzing the mechanism of faults theoretically. The consistency between the experimental results and the theoretical analysis shows that four kinds of representative faults of low power permanent-magnetic DC motors can be diagnosed conveniently by this method. These four faults are brush fray, open circuit of components, open weld of components and short circuit between armature coils. This method needs fewer hardware instruments than the conventional method and whole procedures can be accomplished by several software packages developed in this paper.

A Reinforcement Learning System for Fault Detection and Diagnosis in Mechatronic Systems

With the increasing demand for the automation of operations and processes in mechatronic systems,fault detection and diagnosis has become a major topic to guarantee the process performance.There exist numerous studies on the topic of applying artificial intelligence methods for fault detection and diagnosis.However,much of the focus has been given on the detection of faults.In terms of the diagnosis of faults,on one hand,assumptions are required,which restricts the diagnosis range.On the other hand,different faults with similar symptoms cannot be distinguished,especially when the model is not trained by plenty of data.In this work,we proposed a reinforcement learning system for fault detection and diagnosis.No assumption is required.Feature exaction is first made.Then with the features as the states of the environment,the agent directly interacts with the environment.Optimal policy,which determines the exact category,size and location of the fault,is obtained by updating Q values.The method takes advantage of expert knowledge.When the features are unclear,action will be made to get more information from the new state for further determination.We create recurrent neural network with the long short-term memory architecture to approximate Q values.The application on a motor is discussed.The experimental results validate that the proposed method demonstrates a significant improvement compared with existing state-of-the-art methods of fault detection and diagnosis.

Novel Approach for Fault Detection and Diagnosis of Sensors in Air Handling Units Using Wavelet Energy Entropy

A novel fault diagnosis method for sensors in air handling unit（AHU） using wavelet energy entropy was presented. Instead of directly comparing the numerous data under noise conditiom, the wavelet energy entropy residual was compared in the proposed method. Three.level wavelet analysis was used to decompose the measurement data under both fault-free and faulty operation conditions. The concept of Shannon entropy was referred to define wavelet energy entropy of the wavelet coefficients. The sensor faults were diagnosed by comparing the deviation of the wavelet energy entropy of the measured signal and the estimated one with the preset threshold. Testing results showed that the wavelet energy entropy was sensitive to diagnose the biased faults. The wavelet energy entropy residuals exceed the threshold significantly when faults occur. In addition, the severer the faults were, the larger the residuals would be. The results prove that the proposed method is feasible and effective for the fault detection and diagnosis of the sensors.

An Ensemble Application of Conflict-Resolving ART-Based Neural Networks to Fault Detection and Diagnosis

Accurate fault detection and diagnosis is important for secure and profitable operation of modern power systems.In this paper,an ensemble of conflict-resolving Fuzzy ARTMAP classifiers,known as Probabilistic Multiple Fuzzy ARTMAP with Dynamic Decay Adjustment(PMFAMDDA),for accurate discrimination between normal and faulty operating conditions of a Circulating Water(CW)system in a power generation plant is proposed.The decisions of PMFAMDDA are reached through a probabilistic plurality voting strategy that is in agreement with the Bayesian theorem.The results of the proposed PMFAMDDA model are compared with those from an ensemble of Probabilistic Multiple Fuzzy ARTMAP(PMFAM)classifiers.The outcomes reveal that PMFAMDDA,in general,outperforms PMFAM in discriminating operating conditions of the CW system.

Robust fault detection and diagnosis for uncertain nonlinear systems

This paper considers robust fault detection and diagnosis for input uncertain nonlinear systems. It proposes a multi-objective fault detection criterion so that the fault residual is sensitive to the fault but insensitive to the uncertainty as much as possible. Then the paper solves the proposed criterion by maximizing the smallest singular value of the transformation from faults to fault detection residuals while minimizing the largest singular value of the transformation from input uncertainty to the fault detection residuals. This method is applied to an aircraft which has a fault in the left elevator or rudder. The simulation results show the proposed method can detect the control surface failures rapidly and efficiently.

Detection and Diagnosis of Gear Fault By the Single Gear Tooth Analysis Technique

This paper presents a procedure of sing le gear tooth analysis for early detection and diagnosis of gear faults. The objec tive of this procedure is to develop a method for more sensitive detection of th e incipient faults and locating the faults in the gear. The main idea of the sin gle gear tooth analysis is that the vibration signals collected with a high samp ling rate are divided into a number of segments with the same time interval. The number of signal segments is equal to that of the gear teeth. The analysis of i ndividual segments reveals more sensitively the changes of the vibration signals in both time and frequency domain caused by gear faults. In addition, the locat ion of a failed tooth can be indicated in terms of the position of the segment t hat deviates from the normal segments. An experimental investigation verified th e advantages of the single gear tooth analysis.

Fault Detection and Isolation in Industrial Systems Based on Spectral Analysis Diagnosis

The diagnoses in industrial systems represent an important economic objective in process industrial automation area. To guarantee the safety and the continuity in production exploitation and to record the useful events with the feedback experience for the curative maintenance. We propose in this work to examine and illustrate the application ability of the spectral analysis approach, in the area of fault detection and isolation industrial systems. In this work, we use a combined analysis diagram of time-frequency, in order to make this approach exploitable in the proposed supervision strategy with decision making module. The obtained results, show clearly how to guarantee a reliable and sure exploitation in industrial system, thus allowing better performances at the time of its exploitation on the supervision strategy.

Application of Uncertainty Reasoning Theory to Satellite Fault Detection and Diagnosis

Reasoning theories are divided into certainty reasoning theories and uncertainty reasoning theories. Now, only certainty reasoning theories are used to detect and diagnose satellite faults. However, in practice, it is difficult to detect and diagnose some faults of the satellite automatically only by use of certainty reasoning theories. The reason is that detection and diagnosis of these faults require a rational reasoning and a fault tolerant capability. Fortunately, uncertainty reasoning theories can meet these requirements. It is attracting attention of many experts in the space field all over the world that uncertainty reasoning theories are applied to detect and diagnose satellite faults. Uncertainty reasoning theories include several kinds of theories, such as inclusion degree theory, rough set theory, evidence reasoning theory, probabilistic reasoning theory, fuzzy reasoning theory, and so on. Inclusion degree theory, rough set theory and evidence reasoning theory are three advanced ones. Based on these three theories respectively, the author introduces three new methods to detect and diagnose satellite faults in this paper. It is shown that the methods, suitable for detecting and diagnosing satellite faults, especially uncertainty faults, can remedy the defects of the current methods.

APPROACH TO FAULT ON-LINE DETECTION AND DIAGNOSIS BASED ON NEURAL NETWORKS FOR ROBOT IN FMS

Based on radial basis function (RBF) neural networks, the healthy working model of each sub system of robot in FMS is established. A new approach to fault on line detection and diagnosis according to neural networks model is presented. Fault double detection based on neural network model and threshold judgement and quick fault identification based on multi layer feedforward neural networks are applied, which can meet quickness and reliability of fault detection and diagnosis for robot in FMS.

A reasoning diagram based method for fault diagnosis of railway point system

Railway Point System(RPS)is an important infrastructure in railway industry and its faults may have significant impacts on the safety and efficiency of train operations.For the fault diagnosis of RPS,most existing methods assume that sufficient samples of each failure mode are available,which may be unrealistic,especially for those modes of low occurrence frequency but with high risk.To address this issue,this work proposes a novel fault diagnosis method that only requires the power signals generated under normal RPS operations in the training stage.Specifically,the failure modes of RPS are distinguished through constructing a reasoning diagram,whose nodes are either binary logic problems or those that can be decomposed into the problems of the binary logic.Then,an unsupervised method for the signal segmentation and a fault detection method are combined to make decisions for each binary logic problem.Based on the results of decisions,the diagnostic rules are established to identify the failure modes.Finally,the data collected from multiple real-world RPSs are used for validation and the results demonstrate that the proposed method outperforms the benchmark in identifying the faults of RPSs.

Deep Learning Based Data Fusion for Sensor Fault Diagnosis and Tolerance in Autonomous Vehicles

Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors are very sensitive to light or background conditions,which will introduce a variety of global and local fault signals that bring great safety risks to autonomous driving system during long-term running.In this paper,a real-time data fusion network with fault diagnosis and fault tolerance mechanism is designed.By introducing prior features to realize the lightweight network,the features of the input data can be extracted in real time.A new sensor reliability evaluation method is proposed by calculating the global and local confidence of sensors.Through the temporal and spatial correlation between sensor data,the sensor redundancy is utilized to diagnose the local and global confidence level of sensor data in real time,eliminate the fault data,and ensure the accuracy and reliability of data fusion.Experiments show that the network achieves state-of-the-art results in speed and accuracy,and can accurately detect the location of the target when some sensors are out of focus or out of order.The fusion framework proposed in this paper is proved to be effective for intelligent vehicles in terms of real-time performance and reliability.

Fault detection and identification for dead reckoning system of mobile robot based on fuzzy logic particle filter

To deal with fault detection and diagnosis with incomplete model for dead reckoning system of mobile robot,an integrative framework of particle filter detection and fuzzy logic diagnosis was devised.Firstly,an adaptive fault space is designed for recognizing both known faults and unknown faults,in corresponding modes of modeled and model-free.Secondly,the particle filter is utilized to diagnose the modeled faults and detect model-free fault according to the low particle weight and reliability.Especially,the proposed fuzzy logic diagnosis can further analyze model-free modes and identify some soft faults in unknown fault space.The MORCS-1 experimental results show that the fuzzy diagnosis particle filter(FDPF) combinational framework improves fault detection and identification completeness.Specifically speaking,FDPF is feasible to diagnose the modeled faults in known space.Furthermore,the types of model-free soft faults can also be further identified and diagnosed in unknown fault space.

Combination Method of Principal Component Analysis and Support Vector Machine for On-line Process Monitoring and Fault Diagnosis

On-line monitoring and fault diagnosis of chemical process is extremely important for operation safety and product quality. Principal component analysis (PCA) has been widely used in multivariate statistical process monitoring for its ability to reduce processes dimensions. PCA and other statistical techniques, however, have difficulties in differentiating faults correctly in complex chemical process. Support vector machine (SVM) is a novel approach based on statistical learning theory, which has emerged for feature identification and classification. In this paper, an integrated method is applied for process monitoring and fault diagnosis, which combines PCA for fault feature extraction and multiple SVMs for identification of different fault sources. This approach is verified and illustrated on the Tennessee Eastman benchmark process as a case study. Results show that the proposed PCA-SVMs method has good diagnosis capability and overall diagnosis correctness rate.

Optimal State Estimation and Fault Diagnosis for a Class of Nonlinear Systems

This study proposes a scheme for state estimation and,consequently,fault diagnosis in nonlinear systems.Initially,an optimal nonlinear observer is designed for nonlinear systems subject to an actuator or plant fault.By utilizing Lyapunov's direct method,the observer is proved to be optimal with respect to a performance function,including the magnitude of the observer gain and the convergence time.The observer gain is obtained by using approximation of Hamilton-Jacobi-Bellman(HJB)equation.The approximation is determined via an online trained neural network(NN).Next a class of affine nonlinear systems is considered which is subject to unknown disturbances in addition to fault signals.In this case,for each fault the original system is transformed to a new form in which the proposed optimal observer can be applied for state estimation and fault detection and isolation(FDI).Simulation results of a singlelink flexible joint robot(SLFJR)electric drive system show the effectiveness of the proposed methodology.