Accuracy Of Fault Localization Research Articles

Fault diagnosis in high-speed computing systems using big data analytics integrated evolutionary computing on the Internet of Everything platform

The significance of high-speed computing systems is paramount for diverse applications. However, their intricate structure and rigorous operational prerequisites render them susceptible to malfunctions. The conventional fault diagnosis models need help managing the copious data produced by these systems, resulting in diagnostic procedures that are both time-consuming and ineffective. The research proposed an Internet of Everything (IoE) platform and big data analytics (BDA) based Fault Diagnosis System (IBFDS) in conjunction with evolutionary computing techniques. The system integrates a hybrid intelligent algorithm that amalgamates the advantages of evolutionary computing and machine learning to enhance the precision and effectiveness of fault diagnosis. The utilization of big data analysis methodologies facilitates the processing and examination of vast quantities of system data, thereby enabling the comprehensive detection and identification of faults. Furthermore, cloud services based on the IoE allow data storage, administration, and instantaneous cooperation among various parties involved.
 Furthermore, a detection technique utilizing a Reduced Boltzmann Machine (RBoM) improves the precision of fault diagnosis. The efficacy of the proposed IBFDS was demonstrated through experimental evaluation using a high-speed computing system dataset. The results obtained were impressive, with a fault detection rate (94.11%), fault identification accuracy (93.76%), fault localization accuracy (93.71%), false positive rate (1.54%), and false negative rate (0.98%). The findings of this study make a valuable contribution to the advancement of fault diagnosis systems that are resilient and effective for high-speed computing systems. This facilitates proactive maintenance, enhances system reliability, and optimizes system performance.

Research on a Fault Diagnosis Method for the Braking Control System of an Electric Multiple Unit Based on Deep Learning Integration

A fault diagnosis method based on deep learning integration is proposed focusing on fault text data to effectively improve the efficiency of fault repair and the accuracy of fault localization in the braking control system of an electric multiple unit (EMU). First, the Borderline-SMOTE algorithm is employed to synthesize minority class samples at the boundary, addressing the data imbalance and optimizing the distribution of data within the fault text. Then, a multi-dimensional word representation is generated using the multi-layer bidirectional transformer architecture from the pre-training model, BERT. Next, BiLSTM captures bidirectional context semantics and, in combination with the attention mechanism, highlights key fault information. Finally, the LightGBM classifier is employed to reduce model complexity, enhance analysis efficiency, and increase the practicality of the method in engineering applications. An experimental analysis of fault data from the braking control system of the EMU indicates that the deep learning integration method can further improve diagnostic performance.

Improving fault localization via weighted execution graph and graph attention network

AbstractSoftware fault localization is commonly recognized as arduous and time consuming. Spectrum‐based fault localization (SBFL) has been widely used due to its lightness. However, the effectiveness of SBFL is limited since it only considers simple statistics on the coverage information, ignoring the tie problem that the spectrum matrixes of some statements are the same. Most existing deep learning‐based fault localization (DLFL) techniques convert the coverage information into a vector, which utilizes the spectrum in a simplified manner and still has limitations in practice. To solve the above problem, we propose an approach via the weighted execution graph and graph attention network (WEGAT). We use a graph structure to represent the coverage information between test cases and program elements. Then, we generate a weighted execution graph by applying the predicate execution sequence. Furthermore, we combine the weighted execution graph with the AST as an integrated graph, which is the input of the GAT for fault localization. We evaluate WEGAT in within‐project and cross‐project prediction scenarios on the Defects4J benchmark. Experimental results show that our approach outperforms traditional SBFL (Ochiai, DStar and Tarantula) and DLFL (TraPT, CNN‐FL, Grace, and AGFL) methods, effectively improving the accuracy of fault localization.

An Online Data-Efficient HV Cable Fault Localization Approach Via an AI-Enabled Recognition of Modal Wavefront in Sheath Current

Precise permanent fault localization is an important task for fast power restoration in underground HV cable systems. Among online fault localization methods, the fault localization accuracy strongly relies on the type and volume of measurement, and there is always a tradeoff between localization accuracy and measurement cost. To balance the tradeoff, a data-efficient HV cable fault localization framework is proposed in this paper. First, the fault characteristics of sheath currents are analyzed in modal mode, and compared with the conventional core conductor measurements. It is discerned that the sum of three phases sheath currents has similar characteristics, which can be measured by fewer sensors in a lower rating as the replacement of the conventional core conductor measurements. Second, the challenges of recognizing the wavefront arrival in the sheath are presented, and a Convolution Neural Network is introduced for the localization purpose. The proposed approach can realize high localization accuracy with low-cost measurement, and keep consistent performance under various scenarios through limited training datasets. A case study has been carried out using PSCAD/EMTDC platform to validate the effectiveness and feasibility of the proposed approach, followed by a discussion on the results.

Fault Identification and Localization of a Time−Frequency Domain Joint Impedance Spectrum of Cables Based on Deep Belief Networks

To improve the accuracy of shallow neural networks in processing complex signals and cable fault diagnosis, and to overcome the shortage of manual dependency and cable fault feature extraction, a deep learning method is introduced, and a time-frequency domain joint impedance spectrum is proposed for cable fault identification and localization based on a deep belief network (DBN). Firstly, based on the distribution parameter model of power cables, we model and analyze the cables under normal operation and different fault types, and we obtain the headend input impedance spectrum and the headend input time-frequency domain impedance spectrum of cables under various operating conditions. The headend input impedance amplitude and phase of normal operation and different fault cables are extracted as the original input samples of the cable fault type identification model; the real part of the headend input time-frequency domain impedance of the fault cables is extracted as the original input samples of the cable fault location model. Then, the unsupervised pre-training and supervised inverse fine-tuning methods are used for automatically learning, training, and extracting the cable fault state features from the original input samples, and the DBN-based cable fault type recognition model and location model are constructed and used to realize the type recognition and location of cable faults. Finally, the proposed method is validated by simulation, and the results show that the method has good fault feature extraction capability and high fault type recognition and localization accuracy.

Effectively Combining Risk Evaluation Metrics for Precise Fault Localization

Spectrum-based fault localization (SBFL) is an automated fault localization technique that uses risk evaluation metrics to compute the suspiciousness scores from program spectra. Thus, risk evaluation metrics determine the technique’s performance. However, the existing experimental studies still show no optimal metric for different program structures and error types. It is possible to further optimize SBFL’s performance by combining different metrics. Therefore, this paper effectively explores the combination of risk evaluation metrics for precise fault localization. Based on extensive experiments using 92 faults from SIR and 357 faults from Defects4J repositories, we highlight what and which risk evaluation metrics to combine to maximize the efficiency and accuracy of fault localization. The experimental results show that combining risk evaluation metrics with high negative correlation values can improve fault localization effectiveness. Similarly, even though the combination of positively correlated effective risk evaluation metrics can outperform most negatively correlated non-effective ones, it still cannot improve the fault localization effectiveness. Furthermore, low-correlated risk evaluation metrics should also be considered for fault localization. The study concluded that getting highly negatively correlated risk evaluation metrics is almost impossible. The combination of such risk evaluation metrics would improve fault localization accuracy.

Investigating the Impact of Test Case Density and Execution Variety on Fault Localization for Novice Programs

Programming Online Verification Exam (OE) system has been widely used in algorithm education and practice since it can automatically analyze program results (e.g., correct or incorrect) after executing the submitted programs with corresponding test cases. OE systems can provide both execution results and error information so that novice programmers can get feedback quickly. If the submitted program cannot pass all the test cases, the novice programmers will get wrong-answer feedback, and they have to find and fix the errors in the program. Automated program fault localization techniques, which can locate the errors in programs under test automatically, thus help novice programmers fix the errors quickly. However, the performance of current automated fault localization techniques is limited due to the high-density test cases in novice programs of OE system. In this paper, we analyze the impact of test case density (TCD) and execution variety on fault localization performance and propose a method to reduce TCD to improve fault localization precision for novice programs. To evaluate the performance of our method, we conduct a number of empirical studies on 1199 real fault diagnosis algorithm related novice programs, and the experimental results show that using improved test cases through our method for fault localization in OE system can enhance the precision of fault localization for novice programs. Specifically, after decreasing the test cases’ density, the improvement of fault localization accuracy ranges from 0.6% to 17.34% in terms of the Expense metric, and from the Accuracy@N metrics, the number of faulty statements that can be found increases in most cases.

Graph wavelets for fault localization in optical mesh networks

• Real-time fault detection and localization mechanism in Elastic Optical Networks (EONs). • Alarm correlation strategies fail in the face of static threshold settings. • Detects and localizes silent network failures. • Multi-resolution analysis based on graph wavelets to address fault detection and localization problems. • Exceeds alarm based engines for fault detection and localization accuracy. EONs (Elastic Optical Networks) form the backbone of web-scale cloud infrastructure. These networks should deal with network faults and restoration in real-time with high accuracy and scalability. Thus, fault management functions to detect and localize such failures, play a critical role in modern day EONs. Network impairments are complex in nature in optical networks such as fiber losses, NLI (Non Linear Impairments) and ASE (Amplified Stimulated Emission). Currently, pre-engineered thresholds are used to detect failures in optical networks. Traditional alarm correlation strategies fail in the face of these static threshold settings. In this work, we introduce a real-time fault detection and localization mechanism, which is agnostic to such pre-engineered threshold settings. We apply multi-resolution analysis based on graph wavelets to address fault detection and localization problems. Thus, we propose to use spectrograms and wavelet coefficients to identify the irregularities in an otherwise smooth graph signal. We present a real-time fault localization analysis based on a novel Wavelet Coefficients Trail (WCT) algorithm to root-cause a client signal failure due to OSNR (Optical Signal to Noise Ratio) degradation. We apply the proposed techniques and algorithms to simulated and actual network data. Our results indicate that the proposed methods can root-cause OSNR degradation to major/minor deviations in received power on optical spans. In conclusion, we present a fault localization framework based on graph wavelets in optical mesh networks.

A Fault Localization Approach Based on BiRNN and Multi-Dimensional Features

Software fault localization is notoriously tedious and time-consuming. Developed rapidly, machine learning techniques have been adopted for fault localization by researchers. Most existing approaches use the test coverage information as feature input to the learning model, ignoring the limited ability of the single-dimensional features. The effectiveness of fault localization is not greatly improved. To overcome the limitation, we propose a fault localization approach based on Bidirectional Recurrent Neural Networks (BiRNNs) and multi-dimensional features. Our approach collects suspiciousness-based, text similarity-based and fault-proneness-based features from the traditional fault localization areas and software metrics. To evaluate our approach, the experiments have been studied on the real-fault benchmark Defects4J and seeded fault program NanoXML. The experimental results show that our approach effectively improves fault localization accuracy.

Theoretical Analysis and Empirical Study on the Impact of Coincidental Correct Test Cases in Multiple Fault Localization

To improve the efficiency of the fault localization process, different automatic fault localization approaches have been proposed. Among these approaches, the spectrum-based fault localization (SBFL) approach has been widely used and studied due to its lightweight and high effectiveness. However, while the existence of coincidental correct (CC) test cases can influence the usefulness of SBFL in single-fault programs, their influence on multiple fault programs has not been thoroughly investigated. Therefore, in this article, we conduct a theoretical analysis and an empirical study to investigate the effect of CC test cases on multiple fault localization. The theoretical analysis is based on a suspiciousness calculation formula of SBFL, which divides CC test cases into three categories (specific, irrelevant, and unspecific) according to their association with a specific faulty statement. Following this analysis, we conduct an empirical study on two well-known open-source repositories (SIR and Defects4J), and the experimental results verify the correctness of our theoretical analysis. Specifically, reducing the number of specific CC test cases for a faulty statement can improve or maintain fault localization accuracy, while eliminating irrelevant CC test cases can have a negative effect. Finally, we design a CC test case identification solution based on the isolation-based multiple fault localization approach and demonstrate its effectiveness via a simulation experiment.

Unified Impedance-Based Relaying Scheme for the Protection of Hybrid AC/DC Microgrid

Even though the implementation of hybrid AC/DC microgrid is increasing, their protection schemes face multiple challenges such as inconsistent fault current supply from DGs, difficulty in discriminating internal/ external faults and missing of universal protection scheme for both AC and DC distribution networks. In this regard, a unified fault detection and localization scheme is proposed for hybrid AC/DC microgrid. By measuring the impedance at system frequency for AC circuit and at a specific pre-inserted frequency for DC network, the suggested technique achieves proper discrimination between internal faults and external events. Several fault scenarios such as internal/external faults, single/double line faults with varying fault location and fault resistance have been investigated on both AC and DC circuits by modeling hybrid AC/DC microgrid in PSCAD/EMTDC environment. The results reveal the effectiveness of the proposed algorithm in discriminating internal faults with external events and also in estimating accurate fault location even under noisy environment. Finally, a comparative evaluation of the proposed unified AC/DC protection scheme with other individual AC/DC protection schemes shows its superiority in combining both the AC and DC schemes together into a single relay, having an improved fault detection time and an increased fault localization accuracy.

Partial Discharge Localization on Power Cables Based on a Novel Signal Relay System

Time domain reflectometry (TDR) is an effective method used to detect partial discharge (PD) and localize PD sources on power cables. However, for long-length power cables, the attenuation and dispersion of PD signals are significant due to the propagated distance. The attenuation causes a serious reduction of the pulse amplitude, which makes the defects located far away from the PD detector difficult to find. The dispersion causes appreciable asymmetry in the PD pulse wave form. Thus, the localization accuracy is reduced. To solve the problem of long-length cable fault localization, a novel signal relay system is proposed in this paper. Once a weak PD pulse is captured in the signal relay system, another standard Gaussian pulse signal is initiated by a function generator. The Gaussian pulse signal is injected into the cable and travels along the cable. During this procedure, the weak PD pulse is likely to be amplified, and the fault localization accuracy is notably enhanced. To validate the effectiveness of the proposed method, an experimental platform is built in a laboratory, and PD detection of an artificial defective cable is performed. The experimental results show that the signal relay system can effectively “enlarge” the PD pulse on a long-length cable. For long-length power cables, PD detection can achieve a higher localization accuracy based on the proposed method.

ALBFL: A novel neural ranking model for software fault localization via combining static and dynamic features

Automatic software fault localization serves as a significant purpose in helping developers solve bugs efficiently. Existing approaches for software fault localization can be categorized into static methods and dynamic ones, which have improved the fault locating ability greatly by analyzing static features from the source code or tracking dynamic behaviors during the runtime respectively. However, the accuracy of fault localization is still unsatisfactory.

Numerical Analysis of Filtering Circuit for Partial Discharges

Partial Discharge (PD) is a small electrical spark that happens within the insulation of medium and high voltage electrical assets. It is important to note that the discharge will erode the insulation and eventually result in disastrous insulation failure. Thus, PD detection is a crucial issue in high voltage insulation area. However, the on-site field PD tests, the high frequency PD signals detected by sensors, are vulnerable to interferences and background noises. This has a negative effect on high voltage apparatus fault diagnosis and localization accuracy. For that reason, noise suppression has become an urgent and vital issue for field high frequency PD signal testing. Thus, this research aims to model a filtering circuit to suppress the noise along with PD in high frequency measurement. A filtering circuit was analysed by using Proteus software to filter out the noise along with PD with decent accuracy and efficiency. Then, performance investigation of active high pass and passive high pass was conducted and studies to filter out PD noise suppression in high frequency were successfully developed. The active filter was focusing on the first order stage until fourth order stage. The passive filter only concentrated on two types of order stage; first order stage and second order stage. The result demonstrated that active high pass filter presented the best performance with low decibel frequency response (-20 dB), and was suitable for this research purpose compared to passive high pass filter. Besides, 700 Vrms has been selected to check the response at high voltages and the frequency values set at 50 Hz for low frequency and 8 kHz for high frequency. This specification design values have been selected because it is suitable for situations in high-tension power line. This type of filtering circuit is suitable to be used for academic and lab experimentation.

Probabilistic probe selection algorithm for fault diagnosis in communication networks

Since faults unavoidably occur in communication networks, it is important to quickly and accurately localize the faults to ensure the stability, consistency and reliability of communication networks. Most existing works are focused on probe selection for fault diagnosis in the deterministic environment (DE). However, the information about communication networks in real applications is not deterministic due to disturbance, noise and so on, especially large scale networks. Therefore, it is urgent to solve the problem of localizing faults for communication networks in the non-deterministic environment (NDE). In this paper, we propose a probabilistic probe selection (PRPS) algorithm for network fault diagnosis in the NDE. Combining the probability language and node coverage, we use the probabilistic greedy probe selection approach to select the probes for fault detection with less probing cost to cover all network nodes in the NDE. When one or more faults are detected in the network, the probabilistic min search probe selection approach will be triggered to localize the faults. This approach uses min search method to select probes that pass through the minimum number of suspicious nodes and the maximum sum of coverage of suspicious nodes. In order to improve the ability to resist the uncertain factors, this approach updates the node state sets for multiple iterations according to the states of identified nodes. Extensive simulation experiments are conducted to compare our PRPS algorithm with the existing works and evaluate the performance on various network topologies with different parameters. The simulation results show that PRPS algorithm has satisfactory fault localization accuracy, low probing cost and strong adaptability to resist the uncertain factors in the NDE.

COMPARATIVE ANALYSIS OF NEURAL NETWORK ALGORITHM ACCURACY IN FAULT LOCALIZATION BY THE ONSET MOMENT AND TRANSITION PROCESS PARAMETERS

Fault localization in power lines and other elements of the power system is based on the analysis of transient processes parameters or, for the wave method, on fixation of the transition process onset. Both approaches require modern digital methods of signals analysis and processing. In this paper, the analysis of signals for fault localization is carried out using the simplest artificial neural network based on an elementary perceptron. Training and testing of the neural network are carried out on the example of a sample of signals (1000 to 5000 records) obtained during simulating a short circuit on a power line. Signals that correspond to the short-circuit transition process are determined by two independent random variables: the onset moment of the short circuit (voltage and current phase), and the place of fault. The simulation used a qualitative simplified approach: instead of splitting the power line into many P-sections, resistivity, inductance and power line capacity in one section were considered variable depending on the fault location. The input of the artificial neural network was supplied with voltage counts with a sample rate of 600 Hz standard for measuring organs, and the output, as a target function, was the onset moment or distance to the short circuit site. Comparative analysis of errors in training and testing the artificial neural network for different target functions at its output is carried out. The accuracy of fault localization and the possibility of using the proposed neuroalgorithm are discussed.

Improving Fault-Localization Accuracy by Referencing Debugging History to Alleviate Structure Bias in Code Suspiciousness

Spectrum-based fault localization (SBFL) techniques can automatically localize software faults. They employ the program spectrum, such as code coverage profile with test verdicts, to rank the program entities based on their code suspiciousness. In the past decades, researchers have proposed many approaches to optimize these techniques; however, the program structure, which can influence their performance, is not taken into consideration in developing and improving these techniques. In this article, we identify and analyze the effect of the program structure on the application of SBFL techniques. We observe that some specific program structures may introduce structure bias to code suspiciousness and negatively influence the output of SBFL techniques. To mitigate these effects and improve the performance of fault localization, we propose Delta4Ts, a structure-aware technique. Delta4Ts references debugging history to alleviate the impact of structure bias in the calculation of code suspiciousness. It reasons from the observable suspicious value towards the desired suspicious value and the impact of structure bias. To evaluate Delta4Ts under practical constraints, we conduct a controlled experiment using nine widely-studied SBFL formulae on 12 C programs and 6 Java programs. The experiment results show that Delta4Ts can significantly improve the accuracy of the studied SBFL formulae by an average of 34.8% on 12 C programs and 30.6% on 6 Java programs, and improve more on subject programs associated with more history versions or having larger code sizes.

SMBFL: slice-based cost reduction of mutation-based fault localization

Fault localization is one of the most important and difficult tasks in the software debugging process. Therefore, several methods have been proposed to automate and improve this process. Mutation-based fault localization is one of the states of the art techniques that try to locate faults by executing different mutants of the faulty program. In addition to favorable results, it is along with a massive increase in mutation execution cost. In this paper, we propose a new mutation-based fault localization approach called SMBFL, that aim to reduce the execution cost by reducing the number of statements to be mutated. As fewer mutants execute with SMBFL, the whole process will become faster and the cost will decrease. SMBFL only examines the statements in the dynamic slice of the program under test. The statements that present in the dynamic slice have a direct effect on the execution of the program with the specified test case. In the SMBFL method, the suspiciousness score of program statements is measured based on the entropy of their mutants. The proposed formula, MuEn, determines the suspiciousness score based on the result of executing mutants of each statement of the program. SMBFL is evaluated during a series of tests. The results show a relative increase in the accuracy of fault localization, by an average of 14.2%, and a decrease in the execution time of the fault localization process, by an average of 24.3%. Finally, the MuEn formula applies the least execution overhead to the fault localization process.

A Passed Test Case Cluster Method to Improve Fault Localization

Coverage-Based Fault Localization (CBFL) techniques are based on the conjecture that the program elements executed by more failed test cases and less passed test cases have more chance to be faulty. Coincidental Correct (CC) test case is one of the negative impacts on CBFL, for the reason that the CC test cases execute the faulty element but not propagate the faulty status to the final output. To alleviate the negative impact of CC test cases, in this paper, we propose a cluster-based technique to identify CC test cases from the passed test suite. To evaluate the effectiveness of our method, we conduct empirical studies on 102 versions from six programs. The experimental results show that, when using our method, it can accurately recognize CC test cases, where the precision and recall rate are both higher than 85%. A further study shows that, after removing identified CC test cases, the fault localization accuracy of SBFL can be improved apparently.

Improving the Accuracy of Spectrum-Based Fault Localization Using Multiple Rules

Improving the Accuracy of Spectrum-Based Fault Localization Using Multiple Rules