Traditional Fault Detection Methods Research Articles

Fuzzy Logic Based Hardware Faulty Node Detection And Redundancy Mechanism For Wireless Sensor Networks

In recent years, applications of wireless sensor network (WSN) is emerged as the revolutionary phase in many functional areas such as industrial, environmental, business, military and many need based self-intelligent real time systems. Some of the applications require data communication from harsh physical environment which poses great challenges to wireless sensor networks. The deployment of these sensor nodes in the hostile environment cause sensor nodes failure. This demands fast, redundant fault tolerant, energy saving approaches which meet the requirements of most recurring failures and path disruption scenarios in wireless sensor networks. Hence there is need for fuzzy knowledge based fault detection because traditional fault detection methods are endured by low detection accuracy. The proposed fuzzy knowledge based faulty node detection and redundancy approach (FNDRA) is presented to identify the faulty nodes and provide the management method for nodes reusability. The effectiveness of the proposed approach was implemented using Matlab and the results shows that the proposed approach meets the constraints and requirements of most common and predicated critical failure scenarios.

A nonlinear method for monitoring industrial process

Aiming at fault detection in industrial processes with nonlinear or high dimensions, a novel method based on locally linear embedding preserve neighborhood for fault detection is proposed in this paper. Locally linear embedding preserve neighborhood is a feature-mapping method that combines Locally linear embedding and Laplacian eigenmaps algorithms. First, two weight matrices are obtained by the Locally linear embedding and Laplacian eigenmaps, respectively. Subsequently, the two weight matrices are combined by a balance factor to obtain the objective function. Locally linear embedding preserve neighborhood method can effectively maintain the characteristics of data in high-dimensional space. The purpose of dimension reduction is to map the high-dimensional data to low-dimensional space by optimizing the objective function. Process monitoring is performed by constructing T2 and Q statistics. To demonstrate its effectiveness and superiority, the proposed locally linear embedding preserve neighborhood for fault detection method is tested under the Swiss Roll dataset and an industrial case study. Compared with traditional fault detection methods, the proposed method in this paper effectively improves the detection rate and reduces the false alarm rate.

Single-Filter Finite Fault Detection and Exclusion Methodology for Real-Time Validation of Plug-and-Play Sensors

All-source navigation has become increasingly relevant over the past decade with the development of viable alternative sensor technologies. However, as the number and type of sensors informing a system increases, so does the probability of corrupting the system with sensor modeling errors, signal interference, and undetected faults. Though the latter of these has been extensively researched, the majority of existing approaches have designed algorithms centered around the assumption of simultaneously redundant, synchronous sensors with well-understood measurement models, none of which are guaranteed for all-source systems. As part of an overall all-source assured or resilient navigation objective, this research contributes a key component-validation of sensors which have questionable sensor models, in a fault-agnostic and sensor-agnostic manner, and without compromising the ongoing navigation solution in the process. The proposed algorithm combines a residual-based test statistic with the partial update formulation of the Kalman-Schmidt filter to provide a reliable method for sensor model validation that protects the integrity of the navigation solution during the validation process, all using only a single existing filter. The performance of the proposed method is validated against traditional fault detection and exclusion methods (such as normalized solution separation and conventional residual sequence monitoring) using Monte-Carlo simulations in a 2D non-Global Positioning System navigation problem with a plug-and-play position sensor.

Fault detection and identification using Bayesian recurrent neural networks

In the processing and manufacturing industries, there has been a large push to produce higher quality products and ensure maximum efficiency of processes, which requires approaches to effectively detect and resolve disturbances to ensure optimal operations. While many types of disturbances can be compensated by a control system, it cannot handle some large process disruptions. As such, it is important to develop monitoring systems to effectively detect and identify those faults such that they can be quickly resolved by operators. This article proposes a novel probabilistic fault detection and identification method which adopts a newly developed deep learning approach using Bayesian recurrent neural networks (BRNNs) with variational dropout. The BRNN model is general and can model complex nonlinear dynamics. Moreover, compared to traditional statistic-based data-driven fault detection and identification methods, the proposed BRNN-based method yields uncertainty estimates which allow for simultaneous fault detection of chemical processes, direct fault identification, and fault propagation analysis. The performance of the method is demonstrated and contrasted to (dynamic) principal component analysis, which is widely applied in the industry, in the benchmark Tennessee Eastman process (TEP) and a real chemical manufacturing dataset.

Single-phase ground fault location technology research and application based on transient recording wave

Fault location is an important part of distribution automation. Aiming at the problem of single-phase grounding fault detection, a fault location system based on transient recording technology is proposed. Compared with the advantages and disadvantages of the traditional single-phase ground fault detection method, the single-phase ground fault location application based on transient recording is proposed. The proposed method is not only theoretically verified in the simulation of the distribution network system, but also applied to the operation of fault location network in the true test field, which verifies the effectiveness of the proposed method.

Generative adversarial network for fault detection diagnosis of chillers

Automatic fault detection and diagnosis (AFDD) for chillers has significant impacts on energy saving, indoor environment comfort and systematic building management. Recent works show that the artificial intelligence (AI) enhanced techniques outperform most of the traditional fault detection and diagnosis methods. However, one serious issue has been raised in recent studies, which shows that insufficient number of fault training samples in the training phase of AI techniques can significantly influence the final classification accuracy. The insufficient number of fault samples refers to the imbalanced-class classification problem, which is a hot topic in the field of machine learning. In this study, we re-visit the imbalanced-class problem for fault detection and diagnosis of chiller in the heating, ventilation and air-conditioning (HVAC) system. The generative adversarial network is employed and customized to re-balance the training dataset for chiller AFDD. Experimental results demonstrate the effectiveness of the proposed GAN-integrated framework compared with traditional chiller AFDD methods.

Diagnosis Model of Motor Fault of Precooled Air Conditioning Unit Based on Multivariable LSTM

The motor failure of precooled air conditioning unit (PAU) affects the operation of HVAC system directly. Traditional fault detection methods based on frequency analysis of vibration signals need high sampling frequency. However, in some actual operation and maintenance, the sampling frequency of related data is lower, it is difficult to meet the needs. In this paper, a PAU motor fault diagnosis model is constructed based on long short-term memory neural network (LSTM) combined with in-depth learning technology. The temperature of motor shell is an important symbol of motor fault. Therefore, effective features are extracted by analyzing the data characteristics. LSTM method is used to predict the motor shell temperature, and the motor fault detection and diagnosis are carried out according to the predicted residual threshold. According to the computation, the diagnostic accuracy of fault data is 100%, and the false alarm rate of fault-free data is 0.3%. The results show that the model has stronger generalization ability, higher prediction accuracy.

Image classification towards transmission line fault detection via learning deep quality-aware fine-grained categorization

Object detection and image classification are basic tasks in computer vision. In this paper, we introduce fault detection towards transmission line. Traditional fault detection methods in the transmission line are prone to be affected by the noise and transient magnitude. To overcome these limitations, we propose a novel fault zone detection method, where quality-aware fine-grained categorization model is well encoded for category cues discovery. The goal of our approach is to recognize the most discriminative image patches for classification. The key techniques of our method include quality-based discriminative feature extraction and wavelet-support vector machine. We extract the features of the line currents by leveraging Fast R-CNN based image samples decomposition, where quality module is utilized to choose the most discriminative regions. Afterwards, the extracted features are fed into a SVM to recognize the fault. We conduct comprehensive experiment on transmission line fault identification to verify the availability and superiority of our proposed method.

Fault Detection using Unsupervised Feature Learning on Big Data Based on Improved Weighted SoftMax Regression with Jaya Optimization

Intelligent fault detection is promising to deal with big data due to its ability in rapidly and efficiently processing collected signals and providing accurate detection results. In traditional fault detection methods, however, the features are manually extracted depending on prior knowledge and diagnostic expertise, such processes take advantage of human ingenuity but are time-consuming. Inspired by the idea of unsupervised feature learning artificial intelligence techniques are used to learn features from the raw data.As the dimensionality increases, the accuracy of fault identification methods implemented on big data decreases significantly. For supervised learning, large volume of data is needed which leads to high cost and time consuming. In this paper, an unsupervised learning approach is proposed on the basis of weighted softmax regression for fault detection using the power signals. In the proposed approach, the features are extracted from the unlabelled data. The developed approach is based on squirrel search algorithm and voting based weighted softmax regression with jaya optimization algorithm (IWSRJO_SSA). The proposed approach is simple and easy to carry out, though it attains high accuracy when compared to that of more advanced techniques. The features from the signals are extracted normally and some of the best features are selected using the squirrel search algorithm (SSA). Because of selecting the best features and using the improved weighted softmax regression, the proposed method achieves high accuracy in fault detection. Experiment on the power signal dataset shows the applicability of the proposed approach in fault detection on big data. The proposed system will be applicable on medical field, industrial field, electrical field and so on. The experimental results prove that the proposed method attains high accuracy and is superior to the other advanced methods.

Clearing Series AC Arc Faults and Avoiding False Alarms Using Only Voltage Waveforms

A series ac arc fault detection method based only on the voltage waveform measured at the power source is implemented. A relay de-energizes the arc fault after receiving an arc fault detected signal. Traditional arc fault detection methods use the current waveform, which may have false alarms with loads, such as electric hand drills (which intentionally generate small electric arcs) and dimmer switches because they show similar energy characteristics to an arc fault. However, in the proposed voltage-based method, a symmetric energy profile is observed, unique to the arc fault, which allows improved detection. This symmetry in the voltage waveform is exploited to derive threshold values from the sample energy that are eventually used to detect the ac arc fault. The approach avoids non-stationary signal analysis, machine learning, and advanced filtering techniques. The experimental results validate that the algorithm can successfully detect an arc fault and avoid common unwanted tripping events. Finally, devices, such as surge protectors will be able to integrate this detection algorithm without the addition of current sensors.

H_/H∞ fault detection filter design for discrete-time stochastic systems with limited communication

This paper is concerned with the fault detection (FD) problem for discrete-time stochastic systems with limited communication. A filter structure is proposed to construct the residual model for fault detection. For the limited network resources, a novel event-triggered strategy is employed to decrease the amount of data that is transmitted from the sensor to the filter. With the consideration of stochastic model and limited network resources, a novel event-based method is designed to ensure the residual system is stochastically stable and satisfies the desired fault sensitivity level and disturbance attenuation level. Compared with the traditional FD method, the proposed design strategy can not only achieve the desired fault detection performance, but also save the limited network resources. The effectiveness of design strategy is verified by two simulation examples.

Fault Detection of a Spherical Tank Using a Genetic Algorithm-Based Hybrid Feature Pool and k-Nearest Neighbor Algorithm

Fault detection in metallic structures requires a detailed and discriminative feature pool creation mechanism to develop an effective condition monitoring system. Traditional fault detection methods incorporate handcrafted features either from the time, frequency or time-frequency domains. To explore the salient information provided by the acoustic emission (AE) signals, a hybrid of feature pool creation and an optimal features subset selection mechanism is proposed for crack detection in a spherical tank. The optimal hybrid feature pool creation process is composed of two major parts: (1) extraction of statistical features from time and frequency domains, as well as extraction of traditional features associated with the AE signals; and (2) genetic algorithm (GA)-based optimal features subset selection. The optimal features subset is then provided to the k-nearest neighbor (k-NN) classifier to distinguish between normal (NC) and crack conditions (CC). Experimental results show that the proposed approach yields an average 99.8% accuracy for heath state classification. To validate the effectiveness of the proposed approach, it is compared to conventional non-linear dimensionality reduction techniques, as well as those without feature selection schemes. Experimental results show that the proposed approach outperforms conventional non-linear dimensionality reduction techniques, achieving at least 2.55% higher classification accuracy.

A tacholess order tracking method for wind turbine planetary gearbox fault detection

Wind turbine (WT) usually works under a poor condition, its operating speed varies almost all the time, therefore, the transmission mechanism of planetary gearbox tends to occur fault to a large extent, and an effective fault detection method for WT planetary gearbox is urgently needed. However, the traditional fault detection methods which are based on constant operating speed assumption will be invalid in such a complex situation, this paper provides a novel tacholess order tracking method based on generalized demodulation (GD) for WT fault detection. Firstly, the conventional GD is modified with dual path optimization ridge estimation (DPORE) strategy, and the main innovative idea of the proposed method is that the phase reference information is obtained from the generator shaft vibration signal through GD and Hilbert transform rather than the gearbox vibration signal. Then the raw gearbox vibration signal could be resampled with uniform angle. Finally, the envelope order spectrum is obtained and the fault characteristic order (FCO) related to the WT planetary gearbox fault can be identified without auxiliary sensors. The effectiveness of the proposed method is demonstrated by real-world WT vibration signals, compound-faults on planetary gearbox can be effectively uncovered and a better performance is obtained when compared with the conventional method.

Kernel regression residual signal-based improved intrinsic time-scale decomposition for mechanical fault detection

Correct identification of the faults in mechanical components is the key to monitoring health conditions of machines. However, the interference of low-frequency signals and environmental noises greatly restricts the performance of traditional fault detection methods. Considering that the signals of interest (SOI) are usually carried by high-frequency signals and the interference of low-frequency signals, a novel preprocessing technique called one-level kernel regression residual decomposition (KRRD) is presented. Combined with the improved intrinsic time-scale decomposition (IITD) and Hilbert envelope analysis technique, a novel mechanical fault detection method is proposed. The method combines KRRD to extract the high-frequency signals from the raw vibration signals to track the faulty information, IITD to further extract the SOI from the high-frequency signals by removing the noises, and Hilbert envelope analysis to demodulate the denoised signals to detect faults in the rolling element bearings and gears. In order to verify the performance of the proposed method, the simulated data and real experimental data collected from faulty bearings and gears are analyzed. Three commonly used methods, namely empirical mode decomposition (EMD), local mean decomposition (LMD) and variational mode decomposition (VMD) are introduced and comparisons with the three combinations (KRRD and EMD, KRRD and LMD, KRRD and VMD) are given. The analysis results indicate that the proposed method is superior to other methods for detecting faults in mechanical components.

Novelty detection versus traditional fault detection methods

Novelty detection is a method that defines the existence of a defect in a system without the need for prior training by data corresponding to the defect and simply by training by the data corresponding to the “normal assumed” function of the system. In the other words, in this method, the condition monitoring system is trained by purely normal (assumed) data and further, announces any deviation of the new system data from normal data. Therefore, it can be said that this method can detect and reveal the occurrence of any kind of fault and phenomenon, provided that there is a footprint or effect on the data which is extracted from the operation of the system. In the other words, this method is inherently unlimited in identifying the existence of any defect or phenomenon in a system.

On-line fault diagnosis model for locomotive traction inverter based on wavelet transform and support vector machine

A traction inverter is the power source for rail transit vehicles. An insulated-gate bipolar transistor (IGBT) is the primary component of a traction inverter. IGBT faults can cause serious problems in locomotive power supply systems. The disadvantage of traditional fault detection methods for IGBT modules is a lack of real-time processing and high efficiency. An on-line fault diagnosis method based on a wavelet transform and multi-classification support vector machine (multi-SVM) is proposed for IGBT faults. Wavelet decomposition is used to process fault current signals, and energy vectors are constructed. Multi-SVM is used to establish a fault recognition model. The validity of this method is verified by simulations with MATLAB/Simulink.

An improved incipient fault detection method based on Kullback-Leibler divergence

This paper presents an improved incipient fault detection method based on Kullback-Leibler (KL) divergence under multivariate statistical analysis frame. Different from the traditional multivariate fault detection methods, this methodology can detect slight anomalous behaviors by comparing the online probability density function (PDF) online with the reference PDF obtained from large scale off-line data set. In the principal and residual subspaces obtained via PCA, a symmetric evaluation function is defined for both single variate and multivariate cases. The uniform form of probability distribution and fault detection thresholds associated with all eigenvalues are given. In addition, the robust performance is analyzed with respect to a wide range of Signal to Noise Ratio (SNR). Case studies are conducted with three types of incipient faults on a numerical example; combining with two nonlinear projections, the proposed scheme is successfully used for incipient fault detection in non-Gaussian electrical drive system. The results can demonstrate the superiority of the proposed method than several other methods.

A decentralized sensor fault detection and self-repair method for HVAC systems

This study proposes a novel decentralized sensor fault detection and self-repair method for heating, ventilation and air-conditioning systems. From the perspective of network structure, sensor fault diagnosis in heating, ventilation and air-conditioning systems is distributed to the updated smart sensors without the monitoring host, which is necessary in the traditional centralized method. A fully distributed flat sensor network is established based on fundamental physical equations. Similar to the structure, mechanism and characteristics of biological communities, a smart sensor needs only to communicate with adjacent nodes and operate collaboratively to complete sensor fault detection and self-repair tasks. These tasks are formulated as a constrained optimization and are solved by a decentralized algorithm with a penalty function executed in all the sensor nodes in parallel. The diagnosis model introduces an exponential function method to determine the precise location and undertake self-repair of a fault node. Simulation results on a chilled water system illustrate the effectiveness of the proposed method. Practical application: The traditional sensor fault detection and diagnosis methods for heating, ventilation and air-conditioning systems are based on a centralized structure with several deficiencies, such as high maintenance and labor costs, link congestion and operational lag. This study presents a decentralized sensor network structure and exponential-function-based method that possess the advantages of plug-and-play, rapid deployment, high flexibility and convenience for engineering implementation without having to build a central monitor. The efficiency and effectiveness of the proposed method are demonstrated via a case study.

Fault Detection Using the Clustering-kNN Rule for Gas Sensor Arrays.

The k-nearest neighbour (kNN) rule, which naturally handles the possible non-linearity of data, is introduced to solve the fault detection problem of gas sensor arrays. In traditional fault detection methods based on the kNN rule, the detection process of each new test sample involves all samples in the entire training sample set. Therefore, these methods can be computation intensive in monitoring processes with a large volume of variables and training samples and may be impossible for real-time monitoring. To address this problem, a novel clustering-kNN rule is presented. The landmark-based spectral clustering (LSC) algorithm, which has low computational complexity, is employed to divide the entire training sample set into several clusters. Further, the kNN rule is only conducted in the cluster that is nearest to the test sample; thus, the efficiency of the fault detection methods can be enhanced by reducing the number of training samples involved in the detection process of each test sample. The performance of the proposed clustering-kNN rule is fully verified in numerical simulations with both linear and non-linear models and a real gas sensor array experimental system with different kinds of faults. The results of simulations and experiments demonstrate that the clustering-kNN rule can greatly enhance both the accuracy and efficiency of fault detection methods and provide an excellent solution to reliable and real-time monitoring of gas sensor arrays.

WSN-based monitoring and fault detection over a medium-voltage power line using two-end synchronized method

Traditional fault detection and location methods depend upon the values of system parameters calculated by potential and current transformers. During the faulty period, the secondary current is not the exact replica of primary current. Fault locators are being used since many years for fault location in two-end synchronized measurement system. These fault locators pose problems when faults occur at the zero crossing of sub-transmission line voltage or current. It eventually disturbs the economy too. This issue is more momentous in high-impedance lines as compared to low impedance. To remove such issue, this research presents the concept of using wireless sensors with sensor node gateways as a tool for fault location. The wireless sensors measure the magnitude of fault quality momentarily in discrete times. The concept is based on placing the wireless sensor network (WSN) at the sending and the receiving ends of sub-transmission line and analyzing the response on both sides. Peer concept of WSN for identifying and localizing the power system faults such as phase to phase and single phase to earth faults are considered in this research work.