Fault Detection Effectiveness Research Articles

A Comparative Analysis of Deep Learning Convolutional Neural Network Architectures for Fault Diagnosis of Broken Rotor Bars in Induction Motors.

Induction machines (IMs) play a critical role in various industrial processes but are susceptible to degenerative failures, such as broken rotor bars. Effective diagnostic techniques are essential in addressing these issues. In this study, we propose the utilization of convolutional neural networks (CNNs) for detection of broken rotor bars. To accomplish this, we generated a dataset comprising current samples versus angular position using finite element method magnetics (FEMM) software for a squirrel-cage rotor with 28 bars, including scenarios with 0 to 6 broken bars at every possible relative position. The dataset consists of a total of 16,050 samples per motor. We evaluated the performance of six different CNN architectures, namely Inception V4, NasNETMobile, ResNET152, SeNET154, VGG16, and VGG19. Our automatic classification system demonstrated an impressive 99% accuracy in detecting broken rotor bars, with VGG19 performing exceptionally well. Specifically, VGG19 exhibited high accuracy, precision, recall, and F1-Score, with values approaching 0.994 and 0.998. Notably, VGG19 exhibited crucial activations in its feature maps, particularly after domain-specific training, highlighting its effectiveness in fault detection. Comparing CNN architectures assists in selecting the most suitable one for this application based on processing time, effectiveness, and training losses. This research suggests that deep learning can detect broken bars in induction machines with accuracy comparable to that of traditional methods by analyzing current signals using CNNs.

A fault detection method for induction motors with sliding mode observers based on stochastic resonance and the Teager energy operator

To accurately and sensitively track the stator current of an induction motor (IM) and detect faults, stochastic resonance (SR) and the Teager energy operator (TEO) are combined to detect a fault in the residual stator current of a sliding mode observer (SMO) under strong noise interference and complex weak fault conditions. First, a new reaching law is constructed to establish an SMO for better state tracking. Second, SR is used to absorb noise and amplify the detection residuals of the SMO, and the output results are estimated by the TEO in the time domain to achieve fault detection. Finally, the detection results of the IM stator and rotor winding faults and sensor intermittent faults are presented. The experimental results show that the SMO has higher state tracking accuracy and a faster rate of convergence. Moreover, the residual of the stator current is processed by SR and the TEO, and the effectiveness of fault detection is enhanced.

Route : Roads Not Taken in UI Testing

Core features (functionalities) of an app can often be accessed and invoked in several ways, i.e., through alternative sequences of user-interface (UI) interactions. Given the manual effort of writing tests, developers often only consider the typical way of invoking features when creating the tests (i.e., the “sunny day scenario”). However, the alternative ways of invoking a feature are as likely to be faulty. These faults would go undetected without proper tests. To reduce the manual effort of creating UI tests and help developers more thoroughly examine the features of apps, we present Route , an automated tool for feature-based UI test augmentation for Android apps. Route first takes a UI test and the app under test as input. It then applies novel heuristics to find additional high-quality UI tests, consisting of both inputs and assertions, that verify the same feature as the original test in alternative ways. Application of Route on several dozen tests for popular apps on Google Play shows that for 96% of the existing tests, Route was able to generate at least one alternative test. Moreover, the fault detection effectiveness of augmented test suites in our experiments showed substantial improvements of up to 39% over the original test suites.

Developing a Deep Learning-Based Defect Detection System for Ski Goggles Lenses

Ski goggles help protect the eyes and enhance eyesight. The most important part of ski goggles is their lenses. The quality of the lenses has leaped with technological advances, but there are still defects on their surface during manufacturing. This study develops a deep learning-based defect detection system for ski goggles lenses. The first step is to design the image acquisition model that combines cameras and light sources. This step aims to capture clear and high-resolution images on the entire surface of the lenses. Next, defect categories are identified, including scratches, watermarks, spotlight, stains, dust-line, and dust-spot. They are labeled to create the ski goggles lenses defect dataset. Finally, the defects are automatically detected by fine-tuning the mobile-friendly object detection model. The mentioned defect detection model is the MobileNetV3 backbone used in a feature pyramid network (FPN) along with the Faster-RCNN detector. The fine-tuning includes: replacing the default ResNet50 backbone with a combination of MobileNetV3 and FPN; adjusting the hyper-parameter of the region proposal network (RPN) to suit the tiny defects; and reducing the number of the output channel in FPN to increase computational performance. Our experiments demonstrate the effectiveness of defect detection; additionally, the inference speed is fast. The defect detection accuracy achieves a mean average precision (mAP) of 55%. The work automatically integrates all steps, from capturing images to defect detection. Furthermore, the lens defect dataset is publicly available to the research community on GitHub. The repository address can be found in the Data Availability Statement section.

An Evaluation of Ranking-to-Learn Approaches for Test Case Prioritization in Continuous Integration

Continuous Integration (CI) environments is a practice adopted by most organizations that allows frequent integration of software changes, making software evolution more rapid and cost-effective. Such environments require dynamic Test Case Prioritization (TCP) approaches that adapt better to the test budgets and frequent addition/removal of test cases. In this sense, Ranking-to-Learn approaches have been proposed and are more suitable for CI constraints. By observing past prioritizations and guided by reward functions, they learn the best prioritization for a given commit. In order to contribute for improvements and direct future research, this work evaluates how far the solutions produced by these approaches are from optimal solutions produced by a deterministic approach (ground truth). To this end, we consider two learning-based approaches i) RETECS, which is based on Reinforcement Learning; and ii) COLEMAN, an approach based on Multi-Armed Bandit. The evaluation was conducted with twelve systems, three test budgets, two reward functions, and six measures concerning fault detection effectiveness, early fault detection, test time reduction in the CI cycles, prioritization time, and accuracy. Our findings have some implications for the approaches application and reward function choice. The approaches are applicable in real scenarios and produce solutions very close to the optimal ones, respectively, in 92% and 75% of the cases. Both approaches have some limitations to learn with few historical test data (a small number of CI Cycles) and deal with a large test case set, in which many failures are distributed over many test cases.

Incremental Testing in Software Product Lines—An Event Based Approach

One way of developing fast, effective, and high-quality software products is to reuse previously developed software components and products. In the case of a product family, the software product line (SPL) approach can make reuse more effective. The goal of SPLs is faster development of low-cost and high-quality software products. This paper proposes an incremental model-based approach to test products in SPLs. The proposed approach utilizes event-based behavioral models of the SPL features. It reuses existing event-based feature models and event-based product models along with their test cases to generate test cases for each new product developed by adding a new feature to an existing product. Newly introduced featured event sequence graphs (FESGs) are used for behavioral feature and product modeling; thus, generated test cases are event sequences. The paper presents evaluations with three software product lines to validate the approach and analyze its characteristics by comparing it to the state-of-the-art ESG-based testing approach. Results show that the proposed incremental testing approach highly reuses the existing test sets as intended. Also, it is superior to the state-of-the-art approach in terms of fault detection effectiveness and test generation effort but inferior in terms of test set size and test execution effort.

Towards an Automatic Test Generation Method for Systems of Systems based on Fault Injection and Model-Based Systems Engineering

The emergence and development of systems of systems (SoSs) have expanded the complexity and adaptability of systems engineering. Due to the heterogeneity of its constituent systems, designing and analyzing an SoS faces enormous challenges. Therefore, the verification of an SoS is important in its design phase. However, related methods and techniques are still in the preliminary research state, mainly for requirements verification and system verification, and a lack of efforts in design verification for SoSs. Aiming to provide the ability to detect hazardous states at the design phase, we worked on a novel method for automatically generating test cases for model verification in SoSs. Considering the characteristics of SoSs, the method adopts fault injection and model-based system engineering as the foundations to extend the automated generation capability of test cases. This paper proposes an automatic test generation (ATG) method for an SoS based on fault injection and model-based systems engineering (MBSE). It is meant to generate test cases that can be used to check the effectiveness of fault detection or identification in SoSs and for the effective testing of their constituent systems (CSs). This paper discusses scenario generation and ATG in linear temporal logic and designs an algorithm to generate traces as test suites, taking into account the constraints of the models. By establishing a concept alignment example (CAE) as the experimental use case, three test scenarios are generated automatically, showing that the use of the proposed ATG method provides a reasonable hazardous detection capability for verification in SoS design. The main contributions of the paper are (1) the description of the proposed two-phase ATG approach with fault-centric modeling activities and generation-related activities; (2) the explanation of the designed ATG algorithm at both high and low levels; and (3) the discussion of the experiment in an emergency response CAE with three generated test scenarios.

Ground Fault Protection Methods in Microgrid Systems

Microgrids, which independently configure power supply and demand from large‐scale power grids, are attracting attention for improving resilience and increasing the rate of local production and consumption of renewable energy. The establishment of a protection system against ground fault phenomena to protect the public and equipment is a microgrid implementation challenge that has not been given sufficient attention. This study evaluated the applicability of zero‐phase potential devices (ZPDs) and earthed voltage transformers (EVTs) for real‐world ground fault detection. We evaluated the effect of the number of ZPDs and EVTs installed on the effectiveness of ground fault detection. In addition, we analyzed the dependencies of ground fault occurrence on variable ground fault resistances and ground capacitances to determine the feasibility of detecting ground faults using ZPDs and EVTs in the real world. Based on the results of this study, ground fault detection using ZPD and EVT is feasible when applied to existing distribution lines in microgrid systems. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Detection of microcracks in silicon solar cells using Otsu-Canny edge detection algorithm

The necessity for photovoltaic (PV) arrays has expanded due to the rising demand for solar electrical energy. The demand for solar cells has grown as they are a key component of the PV array. Recent years have seen a rise in solar cell production as a result of this demand. The quality of a silicon panel affects its lifespan and effectiveness in the production of solar power. The picture edge-detection method is regularly employed to identify silicon solar panel flaws. On the other hand, defect identification is impacted by the panel's grid shadow. The most modern defect detection technique uses artificial neural networks, and pre-training the model requires a large number of potential samples from picture data sets. This paper offers the innovative Otsu-Canny operator method as a fault discovery strategy to address this problem. Rapid and accurate identification of microcracks enhances the effectiveness of fault detection. The Otsu algorithm is used in this method to improve edge detection performance for microcracks by modifying the canny operator with a double threshold and eliminating the impact of grids on detection. The process was finished by performing noise removal with morphological operation, picture segmentation, and image binarization. The experimental findings demonstrate a significant improvement in purity and integrity of the image processing algorithm used in this research. The Otsu-Canny edge detection technique is more accurate than other conventional edge detection algorithms for detecting microcracks, with a 92.83 % detection rate.

Fault detection method of digital three-dimensional substation based on singular value decomposition

Abstract In the process of operation and maintenance of digital three-dimensional substation, affected by the fault feature extraction method, the anti-interference ability of the detection method is poor. Therefore, a digital three-dimensional substation fault detection method based on singular value decomposition is proposed. According to the digital twin five-dimensional concept, a three-dimensional management and control model of the substation is built, the real-time collected current signal is denoised, and then a new feature extraction method is designed by using the singular value decomposition theory, and the characteristic parameters of the fault signal are defined. Finally, the maximum wavelet singular value is calculated by combining the wavelet transformation method and the singular value decomposition principle. The fault detection is completed according to the mutation of singular value. The simulation experiment results show that the proposed fault detection method has improved the anti-interference ability by 44 and 86%. It is verified that the method proposed in this study has good fault detection effect, and provides auxiliary decision-making basis for relevant departments.

Design of Pipe-inspection Robot Based on YOLOv3

In this paper, a pipe-inspection robot system which uses STM32F103 as control core is designed. The robot system adopts YOLOv3 network model to detect and locate defects of sewage pipeline. The robot uses closed-circuit television system for detection, which is composed of hardware and defect detection. The hardware is mainly composed of robot body, winding coil and upper computer. The motor drive module, body attitude sensor of robot and camera are placed in the pipeline robot. The router, lithium battery and length measurer constitute the winding coil, which is connected with the robot through cable for data transmission and power supply. the upper computer communicates with the cable coil through WIFI, and the staff can send various instructions through the upper computer to control robot operation, and view the status of the pipeline through video. The defect detection of pipeline is mainly realized by YOLOv3 network model, which is used to automatically detect the types of defects in sewage pipeline and mark the location of defects. Finally, the feasibility and effectiveness of defect detection based on YOLOv3 network model are verified by simulation experiments.

Redefining Monitoring Rules for Intelligent Fault Detection and Classification via CNN Transfer Learning for Smart Manufacturing

Fault detection and classification has been employed to enhance yield and product quality for smart semiconductor manufacturing. For early detection of abnormal events that cause defects, the status variables identification data collected by the sensors embedded in advanced machines can be analyzed to derive the actions for advanced process control and advanced equipment control. However, the validity and effectiveness of fault detection and classification technologies may highly depend on domain knowledge and experience of the process engineers who should redefine the monitoring rules quickly when new process excursion occurred especially when ramping up new technologies and products. Motivated by realistic needs, this study aims to propose a novel strategy to empower intelligent fault detection and classification that employed convolutional neural network to analyze the feature SVID data and determine the conditions of the wafers, while shorten the cycle time for self-learning from domain knowledge and redefining new monitoring rules for fault classification in real time. This approach is validated with an empirical study in a leading semiconductor manufacturing company in Taiwan. The results have demonstrated the practical viability of the developed solution.

Fault Detection of Aero-Engine Sensor Based on Inception-CNN

The aero-engine system is complex, and the working environment is harsh. As the fundamental component of the aero-engine control system, the sensor must monitor its health status. Traditional sensor fault detection algorithms often have many parameters, complex architecture, and low detection accuracy. Aiming at this problem, a convolutional neural network (CNN) whose basic unit is an inception block composed of convolution kernels of different sizes in parallel is proposed. The network fully extracts redundant analytical information between sensors through different size convolution kernels and uses it for aero-engine sensor fault detection. On the sensor failure dataset generated by the Monte Carlo simulation method, the detection accuracy of Inception-CNN is 95.41%, which improves the prediction accuracy by 17.27% and 12.69% compared with the best-performing non-neural network algorithm and simple BP neural networks tested in the paper, respectively. In addition, the method simplifies the traditional fault detection unit composed of multiple fusion algorithms into one detection algorithm, which reduces the complexity of the algorithm. Finally, the effectiveness and feasibility of the method are verified in two aspects of the typical sensor fault detection effect and fault detection and isolation process.

Metamorphic relation prioritization for effective regression testing

SummaryMetamorphic testing (MT) is widely used for testing programs that face the oracle problem. It uses a set of metamorphic relations (MRs), which are relations among multiple inputs and their corresponding outputs to determine whether the program under test is faulty. Typically, MRs vary in their ability to detect faults in the program under test, and some MRs tend to detect the same set of faults. In this paper, we propose approaches to prioritize MRs to improve the efficiency and effectiveness of MT for regression testing. We present two MR prioritization approaches: (i) fault‐based and (ii) coverage‐based. To evaluate these MR prioritization approaches, we conduct experiments on three complex open‐source software systems. Our results show that the MR prioritization approaches developed by us significantly outperform the current practice of executing the source and follow‐up test cases of the MRs in an ad‐hoc manner in terms of fault detection effectiveness. Further, fault‐based MR prioritization leads to reducing the number of source and follow‐up test cases that needs to be executed as well as reducing the average time taken to detect a fault, which would result in saving time and cost during the testing process.

Disturbance Observer-Based Force Estimation and Fault Detection for Robotic Manipulator in Radioactive Environments

Robotic systems with force sensing have great potential for use in radioactive environments. In this study, a modified observer-based method was developed to calculate the unknown external force without adding a redundant sensor and achieve the fault detection in the presence of a force sensor. A dynamic model of a serial robotic manipulator was built and the design procedure for a modified disturbance observer (MDO) was established. The output of observer was then used to suppress the disturbance and generate the fault signature. Moreover, the stability analysis shows that the convergence of the observer error is ultimately bounded. Simulation results under the step and composite sinusoidal disturbance torque demonstrate the performance of the force estimation and disturbance rejection. The results, obtained using the Kinova Jaco2 robot manipulator, show that the estimated errors of the external force in X-Y-Z direction are bounded within ±0.5 N, ±2 N, and ±3 N, respectively. Finally, the effectiveness of fault detection is also verified by the experiment results.

Study on non-contacting diagnostic method of PEFC performance using magnetic sensors

The aim of this study is to detect defects in polymer electrolyte fuel cells (PEFCs) easily and instantly by a noninvasive method. The power generation state of the PEFC was diagnosed contactlessly, by measuring the magnetic field formed around the PEFC during power generation. In this study, we applied sparse modeling theory as an inverse problem method to estimate the current distribution in the electrode from the magnetic field, and verified the effectiveness of defect detection inside the fuel cell. First, we verified with in experiments using a fuel cell that simulated the current flow inside the fuel cell, and then in experiments using a 1-cell stack containing one layer of MEA (Membrane Electrode Assembly) with a power generation area of 50 mm x 50 mm. As a result, we succeeded in accurately detecting the defect position in the center of the electrode, which was previously impossible.

A ground fault detection method of substation DC system based on particle filter

In order to reduce the false alarm rate and false alarm rate of grounding fault detection in substation DC system and improve the efficiency of fault detection, a method of grounding fault detection in substation DC system based on particle filter is proposed. The wavelet threshold denoising method is used to remove the noise of the grounding fault signal of the substation DC system. The wavelet packet decomposition method is used to decompose the grounding fault signal of the substation DC system and extract the characteristics of the grounding fault signal of the substation DC system. Based on the particle filter algorithm, the residual smoothing value is used to detect the grounding fault of the DC system in the substation. The experimental results show that the failure detection rate and false alarm rate of the proposed method are low, which has a good fault detection effect.

Enabling Mutant Generation for Open- and Closed-Source Android Apps

Mutation testing has been widely used to assess the fault-detection effectiveness of a test suite, as well as to guide test case generation or prioritization. Empirical studies have shown that, while mutants are generally representative of real faults, an effective application of mutation testing requires “traditional” operators designed for programming languages to be augmented with operators specific to an application domain and/or technology. The case for Android apps is not an exception. Therefore, in this paper we describe the process we followed to create (i) a taxonomy of mutation operations and, (ii) two tools, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MDroid+</monospace> and <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MutAPK</monospace> for mutant generation of Android apps. To this end, we systematically devise a taxonomy of 262 types of Android faults grouped in 14 categories by manually analyzing 2,023 software artifacts from different sources ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.,</i> bug reports, commits). Then, we identified a set of 38 mutation operators, and implemented them in two tools, the first enabling mutant generation at the source code level, and the second designed to perform mutations at APK level. The rationale for having a dual-approach is based on the fact that source code is not always available when conducting mutation testing. Thus, mutation testing for APKs enables new scenarios in which researchers/practitioners only have access to APK files. The taxonomy, proposed operators, and tools have been evaluated in terms of the number of non-compilable, trivial, equivalent, and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">duplicate</i> mutants generated and their capacity to represent real faults in Android apps as compared to other well-known mutation tools.

Deep learning-based linear defects detection system for large-scale photovoltaic plants based on an edge-cloud computing infrastructure

Linear defects detection of photovoltaic (PV) modules plays a key role in the health assessment in PV plants. However, the conventional defects diagnosis is mainly carried out manually and hence is inefficient or even infeasible in practice. With the recent advances in computing and communication technologies, different forms of edge computing facilities are designed with less human intervention and a non-destructive inspection in the industry. However, the assessment of PV plants using electroluminescence images faces some fundamental challenges. This paper proposed an automatic linear defects detection system for large-scale PV plants based on an edge-cloud computing framework. A novel deep learning-based PV defects detection algorithmic solution is developed considering the trade-off between detection performance and computational complexity through allocating the computing tasks across the edge devices, edge server and cloud server. The proposed solution is evaluated through experiments using real-world data and the numerical results demonstrate its effectiveness and accuracy of PV defect detection as well as the reduction of communication overhead by decreasing the size of EL images.

A two-step vibration-sound signal fusion method for weak fault feature detection in rolling bearing systems

The vibration and sound signals get widely applications in fault diagnosis of rolling bearing systems, but the detection accuracy is unstable at different measuring positions. This paper puts forward a two-step vibration-sound signal fusion method, in which sound signal fusion and vibration-sound signal fusion are executed respectively. The sound signals are fused through weighting to the vibration signal to reduce the influence by measuring positions, and the phase difference is eliminated by a sliding window on the time axis. Then a second fusion between the vibration signal and sound signal is conducted after normalization and superposition, and the performance of two-step fusion is compared with the existing direct fusion. Results show that the two-step fusion provides a larger signal-to-noise ratio, and the amplitudes of characteristic frequencies are also higher. A cascaded bistable stochastic resonance system is applied in the post-processing of the fusion signal to make the signal features more clear, and it is proved that the fault detection effect has an obvious improvement after the whole process. This method provides a new approach for weak fault feature detection in vibration and sound signals, and is of great significance for the maintenance of rolling bearing systems.