Circuit Fault Detection Research Articles

AI-Augmented Fault Detection and Diagnosis in VLSI Circuits: A Step toward Intelligent Chip Design

Fault detection and diagnosis are critical challenges in Very Large Scale Integration (VLSI) circuits, where even minor defects can cause significant performance degradation or system failure. Traditional fault detection methods often struggle with scalability and real-time analysis as circuits grow increasingly complex. This paper proposes an AI-augmented framework that leverages machine learning algorithms and neural networks to enhance the fault detection process in VLSI circuits. The proposed model not only identifies and classifies faults with high accuracy but also provides root-cause diagnostics, significantly reducing testing time and maintenance costs. Simulation results demonstrate the effectiveness of the AI-based approach in comparison with conventional techniques, showcasing improved fault coverage, faster detection, and scalability for modern chip designs. This study serves as a step toward the integration of intelligent diagnostics into chip manufacturing, paving the way for more robust and self-healing electronic systems.

Machine learning based fault detection technique for hybrid multi level inverter topology

AbstractMultilevel inverters (MLIs) have a significant contribution in many industrial sectors due to their improved power quality and lesser voltage stress, over the conventional three‐level inverters. However, the implementation of MLIs with an increased device count creates the scope of development in MLIs topologies. In this regard, a hybrid MLI topology is studied in this paper whose architecture is based on conventional two‐level inverters. This topology has lesser device count characteristics when compared to conventional and most of the recently presented configurations for nine‐level output voltage generation. The major issue of capacitor voltage balancing is resolved by employing an appropriate switching strategy. However, the semiconductor switches are the most vulnerable components and causes the open circuit faults frequently that creates issues in real time operation. Hence, it is important to detect the open circuit fault in switches in the least possible time. A new approach to open circuit fault detection technique based on the analysis of load voltage waveform is proposed in this paper. The wavelet transform technique has been implemented for feature extraction of load voltage. Later, the classification of the fault has been achieved by training an artificial neural network (ANN). The proposed work has been studied in MATLAB/simulation and the obtained results are verified experimentally.

Rotor speed signature analysis‐based inter‐turn short circuit fault detection for permanent magnet synchronous machines

AbstractA rotor speed signature analysis‐ (RSSA‐)based inter‐turn short circuit (ITSC) fault diagnostic method is proposed, which is robust with regard to speed‐ and current‐loop bandwidths of permanent magnet synchronous machine (PMSM) drive systems. Conventional ITSC fault detection solutions that rely on current signals or extra devices. Thus, an initial step of investigation on the validity of RSSA is taken for residual insulation capacity monitoring of the ITSC fault at the incipient stage. The Vold–Kalman filtering order tracking method is employed for the real‐time extraction of fault features. Besides, the impact of speed‐ and current‐loop controller bandwidths on ITSC fault diagnosis is also analysed and an Adaline estimator is designed to decouple their impacts. Finally, the effectiveness of the proposed method is verified on a faulty PMSM, which exhibits satisfying results in tracking the degradation of residual insulation, even if the phase currents are significantly distorted due to low switching frequency of the inverter.

Turn‐to‐turn and phase‐to‐phase short circuit fault detection of wind turbine permanent magnet generator based on equivalent magnetic network modelling by wavelet transform approach

AbstractOne of the most common faults in electric machines is a turn‐to‐turn short circuit (TTSC), which may destroy coil insulation and demagnetise the magnet. In addition, the phase‐to‐phase short circuit (PPSC) fault, which can have even more destructive effects than the TTSC fault, is introduced and analysed. The equivalent magnetic network (EMN) method, with high modelling accuracy and a short computation time, is employed for healthy and faulty machines. The current signal under fault conditions is analysed in the dqo frame, showing the presence of the second harmonic component in its waveform. This fault detection index is processed using the signal processing technique of discrete(wavelet transform (DWT). Besides, energy analysis is used to distinguish TTSC and PPSC faults. Finally, finite element and EMN modelling results are compared with the experimental data of the prototyped permanent magnet generator. The results show that the combination of the proposed EMN method and DWT has very good accuracy and speed. Furthermore, the proposed fault detection method remains unaffected by various linear loads with different power factors.The cover image is based on the article Turn‐to‐turn and phase‐to‐phase short circuit fault detection of wind turbine permanent magnet generator based on equivalent magnetic network modelling by wavelet transform approach by Mehrage Ghods et al., https://doi.org/10.1049/elp2.12452

Fault detection in analog electronic circuits using fuzzy inference systems and particle swarm optimization

Fault detection in analog circuits is of great importance to predict the correct operation of the circuit. For this purpose, soft computing techniques such as those based on the application of fuzzy inference systems stand out. However, given the large variability that can exist in analog circuits due to component tolerance, the initial fuzzy inference system (FIS) may not be able to accurately diagnose the different hard faults. This study presents a methodology to diagnose and detect the faults that can occur in analog circuits, which is based on the development of a FIS, starting from a specific fault situation in the analog circuit, and subsequently on the optimization of the membership functions using an evolutionary algorithm so that the adjusted FIS can classify and predict different failure situations. To this end, the application of optimization techniques based on particle swarm optimization (PSO) will be analyzed to develop a FIS capable of predicting different faults. In addition, pattern search algorithm will also be analyzed. A Sallen-Key band-pass filter and a single stage of a small-signal amplifier are used as test circuits. The proposed methodology shows that it is possible to accurately predict the faults that could arise in the circuits under study.

Analysis of Fault Detection in Analog Circuits Using WSF-SKC Optimized SVM Technique

Many industrial applications and control systems depend heavily on analogue electrical circuitry. The conventional method of diagnosing such circuit faults can be time-consuming and erroneous, which might have a severe impact on the industrial output. The fault detection and analysing of analogue circuits with intelligent effective model is proposed in this work. The suggested technique primarily consists of two main stages one is extraction of features and the other is classification of faults. The analysis is performed on the response of frequency in analogue circuits. For extracting features particle swarm optimization (PSO) is utilized. The PSO is used to evaluate the fitness function of Wilks A-Statistic Filters sallen-key circuit (WSF-SKC). With fault characteristics retrieved using the particle swarm approach that are carefully selected, the fault classes may be separated more quickly. To categorise different failures in a benchmark circuit, a Support Vector Machine (SVM) classifier is built. Utilising firefly optimisation, the classifier is improved. Different fault codes were tested in experiments for defect detection and identification. The findings of the experiment indicate that this proposed technique can significantly increase the accuracy of fault diagnosis. The accuracy obtained for WS-LPF is 99.95%, WS-HPF is 99.97 and WS-BPF is 99.90% respectively.

Early Fault Detection of Stator Inter-Turn Short Circuit of Asynchronous Motor Based on Rotating High Frequency Voltage Injection

Early Fault Detection of Stator Inter-Turn Short Circuit of Asynchronous Motor Based on Rotating High Frequency Voltage Injection

Fault Detection of Interturn Short Circuit in Induction Motors Under Nonstationary Conditions and Unbalanced Supply Voltage

Fault Detection of Interturn Short Circuit in Induction Motors Under Nonstationary Conditions and Unbalanced Supply Voltage

Analysis of PMSM Short-Circuit Detection Systems Using Transfer Learning of Deep Convolutional Networks

Abstract Modern permanent magnet synchronous motor (PMSM) diagnostic systems are now combined with advanced artificial intelligence techniques, such as deep neural networks. However, the design of such systems is mainly focussed on a selected type of damage or motor type with a limited range of rated parameters. The application of the idea of transfer learning (TL) allows the fully automatic extraction of universal fault symptoms, which can be used for various diagnostic tasks. In the research, the possibility of using the TL idea in the implementation of PMSM stator windings fault-detection systems was considered. The method is based on the characteristic symptoms of stator defects determined for another type of motor or mathematical model in the target diagnostic application of PMSM. This paper presents a comparison of PMSM motor inter-turn short circuit fault detection systems using TL of a deep convolutional network. Due to the use of direct phase current signal analysis by the convolutional neural network (CNN), it was possible to ensure high accuracy of fault detection with simultaneously short reaction time to occurring fault. The technique used was based on the use of a weight coefficient matrix of a pre-trained structure, the adaptation of which was carried out for different sources of diagnostic information.

Design and implementation of a redundant control system for variable speed hydro generators

Hydro plant control system (HPCS) has gained a high level of attention in recent years because of their flexibility, reliability, and easy-to-use. This paper analyzes the performance of a 250 MW doubly-fed induction machine (DFIM) under different speed sensor faults (omission, gain, and saturation) that will clarify the need for technically feasible redundancy. The control redundancy, which consists of fault detection, speed estimation, and reconfiguration circuit, is implemented to enhance the permanence and reliability of the DFIM. The logic-based fault detection technique is implemented to detect the speed sensor fault. A second-order sliding mode controller (SOSMC) based model reference adaptive system (MRAS) estimator is implemented to estimate the rotor speed. The proposed redundancy circuit is modeled for a 250 MW hydrogenerating unit using the MATLAB/Simulink environment. It is observed that the proposed redundancy circuit is robust against uncertainty in the machine parameters. Experimental validation is performed in a scaled-down laboratory prototype. The simulation and experimental results demonstrate the efficacy of the proposed redundancy circuit. Fault detection and reconfiguration of the control redundancy circuit are performed within 20 ms.

Filter Capacitor Current Dynamics-Based Frequency-Domain Fault Detection Approach for Grid-Connected Low-Voltage DC Microgrid

This paper proposes a cost-effective short circuit fault detection method for a distribution network in the ac grid-connected low-voltage dc (LVDC) microgrid. In this method, a typical dc system is considered where a number of dc/dc, ac/dc power converters and loads are interfaced to the dc link. Further, these loads are dedicated as local loads to the converter based on the locality of the same. The discharge of a filter capacitor (FC) in power converters in the dc system is the foremost indicator of a fault. Such dynamic behavior of FC can be utilized in the identification of a fault. This method is a time-frequency domain-based wavelet transform (WT), which utilize the current dynamics of an FC for quantitative analysis of a fault current. Additionally, a detailed thresholds selection process is also explained. MATLAB/Simulink model is used to carry out simulation studies. The experimental validation of WT based fault detection method is executed on the ac grid-connected LVDC microgrid testbed interfaced to the dSPACE 1104 controller.

Circuit fault detection model using multiclass support vector machine

ABSTRACT Fault detection in a complex circuit is a tedious process, and it requires specialised manpower to detect and localise the faults. Manual detection is quite time consuming and might be wrong some times. Identification of faults automatically by analysing the circuit using transforms and machine learning algorithm is presented in this research work. A hardware model and a software model are developed to generate the test and train samples, and they are used in simulation analysis to detect the faults. A simple adiabatic adder using metal-oxide-semiconductor field-effect transistor is used in the hardware module, and multiple techniques like adaptive median filtering, Hilbert transform, geometric algebraic scale-invariant feature transform and multiclass support vector machine are used in the simulation model to detect the faults in the circuit. All the stages of simulation analysis results are presented to validate the performance of the proposed model. Normal and faulty conditions are accurately detected by the proposed model with maximum detection accuracy, which reduces the human efforts in designing and developing a circuit.

Open circuit fault diagnosis for a five-level neutral point clamped inverter in a grid-connected photovoltaic system with hybrid energy storage system

Introduction. Recently, the number of high and medium voltage applications has increased dramatically. The connection between these different applications requires series-parallel combinations of power semiconductors. Multilevel converter topologies provide major advantages to these applications. In this paper, a grid-connected photovoltaic system with a hybrid energy storage system using a five-level neutral point clamped inverter is studied. Although the multilevel inverter has many advantages over the two-level inverter, it has a high probability of experiencing an open circuit fault. In this context, the five-level inverter has 24 controllable switches, one of which may experience an open circuit fault at any time. Therefore, it plays an important part in the reliability and robustness of the whole system. The novelty of this paper presents an approach to accurately detect the open circuit fault in all insulated gate bipolar transistors of a five-level neutral point clamped inverter in a photovoltaic power generation application with a hybrid energy storage system. Purpose. Before using fault-tolerant control to ensure service continuity, fault diagnosis techniques must first be used, which are the crucial phase of reliability. Methods. A detection method based on the maximum and minimum error values is proposed. These errors are calculated using the expected and measured line-to-line pole voltages. Results. The open circuit fault detection method is implemented using MATLAB/Simulink. Simulation results showed the accuracy of detecting the open circuit fault in all insulated gate bipolar transistors in a short time. Moreover, this method is adaptable to several applications and is also robust to transient regimes imposed by solar irradiation and load variations.

Induction Motor Stator Winding Inter-Tern Short Circuit Fault Detection Based on Start-Up Current Envelope Energy.

Inter-turn short circuit (ITSC) is a common fault in induction motors. However, it is challenging to detect the early stage of ITSC fault. To address this issue, this paper proposes an ITSC fault detection method for three-phase induction motors based on start-up current envelope energy. This approach uses Akima interpolation to calculate the envelope of the measured start-up current of the induction motor. A Gaussian window weighting is applied to eliminate endpoint effects caused by the initial phase angle, and the enveloping energy is obtained using the energy formula as the fault feature. Finally, by combining this with the support vector machine (SVM) classification learner, fault detection of ITSC in induction motors is achieved. The experimental results show that the average accuracy of this method reaches 96.9%, which can quickly and accurately detect ITSC faults in asynchronous motors and determine the severity of the faults. Furthermore, the average accuracy of SVM in detecting early ITSC faults under no-load conditions is 98.8%, which is higher than other classification learners, including LR, KNN, and NN. This study provides a new idea for induction motor fault detection and can contribute to induction motor maintenance.

Inter-Turn Short Circuit Fault Detection of PMSM Based on Wavelet Packet Energy Spectrum and CEEMDAN-HT

Inter-Turn Short Circuit Fault Detection of PMSM Based on Wavelet Packet Energy Spectrum and CEEMDAN-HT

Short Circuit Fault Detection and Protection of DC Microgrid

Abstract: Due to inherent advantages of DC system over AC system such as compatibility with renewableenergy sources, storage devices and modern loads, Direct Current Microgrid (DCMG) has been one of the key research areas from last few years. In the proposed work power has been produced by using solar pv and fuel cell which is combined on the same dc bus and given to a dc load. DC microgrid protection is an important part of power system studies. The basic think which is required for protection is to get to know, where it should be provided and which component must be used. So, to address the challenges of dc microgrid protection accurate faultdetection strategies, fault current limiting method and dc circuit breaker has been used. The electricity load of the microgrid is satisfied by the power form fuel cell, pv array and battery altogether. Initially battery is charged up to 70% and at this time bidirectional converter work as a boost converter and when battery discharges till 30 %, battery starts charging and then bi- directional converter act as buck converter and battery remain in charging mode.

Fault detection and fault tole rant control of interturn short circuit of double redundancy motor

This paper presents the robust detection of interturn short circuit fault of double redundant permanent magnet synchronous motor. In the static coordinate system and double dq-axis system, the mathematical model of the fault state is established. Further, the residual signal of the dq-axis current caused by the turn-to-turn short circuit fault is predicted using the Luenberger observer. Next, the fault marker and the fault phase marker are obtained by processing the current residual signal. Finally, the processor performs the excision of the faulty phases and hardware reconfiguration, thus allowing fault-tolerant operation of the motor. The simulation results show the effectiveness of the detection and fault tolerance of double redundant permanent magnet synchronous motor.

An Open-Circuit Faults Diagnosis Method for MMC Based on Extreme Gradient Boosting

The diagnosis of open circuit faults is required for the reliability of modular multilevel converters (MMC) and the complex operating environment of MMC may cause missing data and external noise in signal detections, where some of the present open circuit fault detection methods can be disabled. This paper proposed a machine learning (ML) diagnosis strategy for open circuit faults in MMC based on extreme gradient boosting (XG-Boost). In this method, after data processing, the data segments composed of real-time capacitance voltage and current data are input into the trained XG-Boost multi-classification model for fault diagnosis without manually setting the empirical threshold, as is required in traditional change-of-rate-of-voltage-based diagnosis methods. This method has excellent robustness against external noise and missing data while better accuracy, higher speed and lower real-time calculation cost than existing ML-based methods are achieved. The effectiveness of the proposed method is verified by experiment results. It can diagnose the fault within 20ms with accuracy as high as 99.6%, even under the interference of Gaussian (GS) noise and the capacitor voltage data missing.

Open-circuit fault detection of inverter fed PMSM for electrical powertrain applications

<p>This paper aims to enhance the reliability of power electronic converters fed<br />permanent magnet synchronous machine for electrical powertrain applications.<br />Many faults like open circuit may affect the power converter and quickly lead to<br />a decline in supplied power quality and all the power train components behavior.<br />In this framework, this paper proposes an open circuit fault detection scheme for<br />inverters. First, the dynamic models of the powertrain subsystems were developed.<br />In fact, all the mathematics models of the motor, inverter, power converter,<br />battery and charger are presented. Then, a detection scheme of open-circuit fault<br />in inverter/motor. The control schemes were elaborated based on current analysis<br />method. The diagnosis strategy under discontinuous switch-ing dynamics of<br />the DC/AC inverter is proposed.</p>

A Load-Independent Controllable Z-Source Circuit Breaker With an Intrinsic Fault Detection Method

The Z-source circuit breaker using thyristor as the main switch benefits from its low cost, low conduction loss, and high ruggedness. However, the fault protection of the conventional Z-source circuit breakers only relies on the change of the load. In this paper, a load-independent controllable Z-source circuit breaker (CZCB) with an intrinsic fault detection circuit is proposed. It will not be protected by mistake during any load step change, and an accurate fault current detection can be achieved with a specific threshold. Meanwhile, the fault current is monitored by the on-state voltage of the main thyristor, so no additional sensor is needed. An auxiliary thyristor is used to turn off the main thyristor reliably when an overcurrent is detected. In addition, only one inductor is needed in the CZCB, and the <i>L-C</i> parameter is much smaller than the conventional Z-source breakers, leading to lower size and cost. The performance of the proposed CZCB is verified by simulation and experiment. The results show that the fault current can be cleared within a few microseconds, and the total fault isolation time is only about 38 <i>&#x03BC;</i>s.