A Comparative Analysis of Artificial Intelligence Techniques for Single Open-Circuit Fault Detection in a Packed E-Cell Inverter

Fast and reliable fault detection is critical in photovoltaic (PV) systems to improve reliability and energy yield and reduce maintenance costs, ensuring safe and efficient operation under varying operating conditions. Although recent data-driven PV fault detection techniques (FDTs) in literature have demonstrated high diagnostic accuracies, they often suffer from practical limitations, offline operation, lack of fault localization and/or inability to concurrently identify faults. To address these challenges, a unified framework is proposed that simultaneously integrates real-time operation, fault classification and localization, and concurrent-fault identification in a single compact diagnostic approach. This is realized by developing a parallel feedforward neural network (FFNN) architecture whose performance is enhanced by a residual model-based structure, resulting in a more interpretable, scalable, reliable and accurate scheme. In addition, Grey Wolf Optimizer–Support Vector Machine (GWO–SVM) feature selection is incorporated to select the most influential diagnostic features, thus reducing data redundancy, enhancing diagnostic accuracy, and shortening training time. The proposed approach was tested to diagnose five types of PV faults (open circuit, short circuit, partial shading, degradation, and simultaneous faults), as well as classify their intensity and location. Simulation results show that the proposed FFNNs consistently outperform conventional Support Vector Machines (SVMs) in classification accuracy, with accuracies exceeding 98% and 99% for fault classification and localization, respectively, and above 95% for noisy data. Moreover, GWO-SVM proved to offer more stable feature subsets compared to Particle Swarm Optimization–SVM (PSO–SVM) in the considered feature selection structure. Simulation results validated the effectiveness of the proposed unified multiclassification fault diagnosis approach, even under system uncertainties, making it suited for real-world PV systems.

This paper presents a stator winding faults detection in induction generator based wind turbines by using artificial neural network (ANN). Stator winding faults of induction generators are the most common fault found in wind turbines. This fault may lead to wind turbine failure. Therefore, fault detection in induction generator based wind turbines is vital to increase the reliability of wind turbines. In this project, the mathematical model of induction generator based wind turbine was developed in MATLAB Simulink. The value of impedance in the induction generators was changed to simulate the inter-turn short circuit and open circuit faults. The simulated responses of the induction generators were used as inputs in the ANN model for fault detection procedures. A set of data was taken under different conditions, i.e. normal condition, inter-turn short circuit and open circuit faults as inputs for the ANN model. The target outputs of the ANN model were set as ‘0’ or ‘1’, based on the fault conditions. Results obtained showed that the ANN model can detect different types of faults based on the output values of the ANN model. In conclusion, the stator winding faults detection procedure for induction generator based wind turbines by using ANN was successfully developed.

Review of fault detection techniques in power converters: Fault analysis and diagnostic methodologies

When the five-phase permanent magnet fault-tolerant servo motor (PMFSM) for aerospace is in the typical condition, rotating over a small position angle range, the motor phase current fluctuates up and down in a small range rather than presenting a sinusoidal waveform. Therefore, the current-based open-circuit (OC) fault diagnosis strategy would be ineffective. The OC fault diagnosis strategy based on the lower power switch voltage and line voltage can only diagnose the power switch OC fault, but not the winding OC fault. Therefore, we propose an OC fault diagnosis strategy based on phase voltage to solve the problem that the present OC fault diagnosis method cannot effectively diagnose the OC faults of power switches and windings under the typical condition of servo motors. The proposed strategy can diagnose not only the single power switch OC fault but also the single winding OC fault under the typical condition. In addition, the proposed strategy can also diagnose OC faults in multiple power switches, OC faults in multiple windings, as well as mixed OC faults in windings and power switches. The simulation results verify that the proposed strategy can quickly and accurately diagnose the OC faults of power switches and windings under the typical condition. The phase voltage diagnosis method used in this paper is the first to be used in the fault diagnosis of five-phase motors. Two thresholds are set by combining the phase voltage to diagnose the winding fault and the power switch fault respectively.

Investigating and addressing fault detection is crucial for advancing the reliability, performance, and cost‐effectiveness of grid‐connected inverter systems, thereby contributing to the stability and efficiency of modern power grids. This study introduces a novel approach for detecting and classifying open‐circuit faults (OCFs) in three‐level neutral point clamped (3‐L‐NPC) inverters connected to the grid. The proposed algorithm swiftly identifies faulty switches and clamping diodes using distorted current signals and model predictive control (MPC), eliminating the need for additional hardware or complex computations. By addressing the challenge of identifying the specific switch under grid‐connected conditions, the proposed method achieves faster detection and identification of all switches and clamping diodes in less than one fundamental period which is very good compared with recent studies and considering that no extra sensors are used. Furthermore, this work demonstrates the efficacy of MPC in tolerating OCFs in clamping diodes, showcasing its potential to enhance system resilience and performance. The proposed strategy significantly improves the reliability of 3‐L‐NPC inverters by ensuring prompt and accurate fault detection and classification. Both experimental and simulation results confirm the efficacy of the suggested fault detection and identification approach, emphasizing its practical applicability in real‐world grid‐tied inverter systems.

This study proposes a new fault detection method for modular multilevel converter (MMC) semiconductor power switches. While in common MMCs, the cells capacitor voltages are measured directly for control purposes, in this study voltage measurement point changes to the cell output terminal improving fault diagnosis ability. Based on this measurement reconfiguration, a novel fault detection algorithm is designed for MMCs semiconductor power switches. The open circuit and short circuit faults are detected based on unconformity between modules output voltage and switching signals. Simulation and experimental results confirm accurate and fast operation of the proposed method in faulty cell diagnosis. Implementation simplicity, no need to extra voltage measurements and multi faults detection ability are some other advantages of the proposed method.

Cascaded H-bridge multilevel inverters are becoming increasingly used in applications such as distribution systems, electrical traction systems, high voltage direct conversion systems, and many others. Despite the fact that multilevel inverters contain a large number of control switches, detecting a malfunction takes a significant amount of time. In the fault switch configurations diode included for freewheeling operation during open-fault condition. During short circuit fault conditions are carried out by the fuse, which can reveal the freewheeling current direction. The fault category can be identified independently and also failure of power switches harmed by the functioning and reliability of cascaded H-bridge multilevel inverters. This paper investigates the effects and performance of open and short switching faults of multilevel inverters. Output voltage characteristics of five level MLI are frequently determined from distinctive switch faults with modulation index value of 0.85 is used during simulation analysis. In the simulation study, with the modulation index value of 0.85, one second open and short circuit faults are generated for the location of the defective switch. Fault is identified automatically by means of artificial neural network technique using sinusoidal pulse width modulation based on distorted total harmonic distortion and managed by its own. The proposed topology is to be design and evaluate using MATLAB/Simulink platform.

Multiphase permanent magnet (PM) motors are popularly adopted for their high torque density, high efficiency, and good fault tolerance. Open-circuit and short-circuit faults can result in high fluctuating torque and deteriorated dynamic performance. This article proposes a novel direct torque control (DTC) approach based on disturbance observer (DOB) to minimize the torque pulsations and enhance dynamic performance of a five-phase PM motor under open-circuit and short-circuit fault conditions. The novelty of the proposed strategy is the development of fault-tolerant switching table based on closed-loop mode of third harmonic current regulation and the incorporation of DOB. Based on the switching table, the proposed method can restrain the torque fluctuations caused by open-circuit fault and suppress y-axis current. The DOB is introduced to eliminate the external disturbances, which include torque fluctuations caused by short-circuit current and unmodel dynamic. Then, the proposed strategy is applicable to the PM motor, whose back electromotive force contains third harmonic, under open-circuit or short-circuit fault condition. This fault-tolerant DTC strategy can not only smooth fluctuating torque and ensure that its dynamic performance reaches the healthy performance, but also enhance the robustness against the external disturbances under both open-circuit and short-circuit fault conditions. The simulation and experimental results are presented to validate the proposed strategy.

A strong robustness open-circuit fault diagnosis strategy for novel fault-tolerant electric drive system based on d-q-axis current signal

This paper proposes a simple and fast detection technique for power device open circuit (OC) fault in single phase H-bridge flying capacitor multilevel converters (H-FCMCs). A fault mitigation technique is also proposed adding four additional switches to the H-FCMC regardless of the number of commutation cells or levels. The fault detection concept only needs to sense the voltage and direction of current at the output terminal of the H-FCMC to detect and localize the fault. The algorithm compares the measured and expected terminal voltage considering the commanded switch state and the direction of the terminal current. A circuit with multiple windows detectors is utilized to track the output voltage level and current direction with high bandwidth. Once an OC fault is detected and localized, auxiliary switches operating at the fundamental output frequency will be activated to reconfigure the H-FCMC converter to the half H-FCMC with the same number of output voltage levels but with half the output switching frequency.

The focus of the present research work is to develop a robust induction machine emulator. The emulator can be used to test different types of open circuit and short circuit grid faults along with starting and loading transients. Power hardware in loop (PHIL) technology is used for the machine emulation. It requires a highly accurate and adaptable model for the chosen test cases and opted emulator configuration. For open circuit fault test case, the induction machine mathematical model is developed systematically to emulate the machine backemf at the open circuit terminals. The proposed model adapts to the chosen emulator configuration by incorporating the emulator parameters in it. Finally, the novel induction machine emulator proves its robustness and performance not only for open circuit faults but also for short circuit, starting and loading fault transients. Open circuit auto reclosing analysis and considerations in developing reclosing algorithms are detailed. Identification of different fault signatures, which aid fault diagnosis are also briefly presented.

This paper proposes a fault detection technique for a three-stage cascaded boost converter with open-circuit switch fault occurrence. The proposed fault detection algorithm is based on the behavior investigation of the three-stage cascaded boost converter under normal and fault operating conditions. The PI controller with one outer voltage loop and two inner current loops is employed to control the operation of the converter under both healthy and faulty modes. The slopes of two inductor currents and two controlled signals generated by the current loops of the PI controller are applied to the proposed fault detection strategy in order to identify the faulted switch. There is no additional sensor needed for fault detection. The simulation results are shown to validate the effectiveness of the proposed fault detection technique under different open-circuit switch fault operating conditions.

The Matrix converters (MCs) are widely used in a large number of applications such as Aircraft, Submarines, and AC drives. In these applications, many chances of occurrence of a critical fault that leads to a halt of the system, and due to the failure of power electric switches, the MC operations can be compromised and there is a fear of burning the components caused by the whole system shutdown. Therefore, a Fault-Tolerant Control System (FTCS) is extremely necessary for the continued operations of the Three-Phase Matrix Converter (TPMC) to improve the reliability and productivity of the system under faulty conditions. In this paper, an advanced FTCS is proposed based on detection, and dual hardware redundancy. Two types of faults are injected into the system to observe the performance of the proposed system: internal open circuit faults on switches and external short circuit faults at the load side. A Fault Detection and Isolation (FDI) unit is used to detect and isolate the faulty switches using Artificial Neural Networks (ANN), and dual hardware redundancy in the switches has been proposed for fault tolerance. In case of external fault, a load-side fault detector is implemented using ANN. The simulation results in MATLAB/Simulink environment show the accurate and stable working of TPMC under faulty conditions, and hardware-in-the-loop is implemented with STM32-Nucleo-F103RB board to verify open circuit fault results. The proposed work dual redundant FTC with FDI unit offers an excellent solution for the continued performance of TPMC which enhances the reliability of the system.

It is proposed a novel fault detection technique applied on indirect matrix converter (IMC) in order to detect open circuit faults in bidirectional switches. An IMC under input power factor control in generation systems based on Microturbine (MT) is considered in this study. The IMC under open-circuited switch failures provides continuous operation, since the performance detriment is not drastic although power quality considerably decrease. This work will focus this particular case where faults are not quite evident. The proposed detection technique is based on the continuous wavelet transform and the global wavelet spectrum function applied to the IMC input current. Simulation results are presented in order to verify the proposed diagnostic tool.

Discriminative common vector in sufficient data Case: A fault detection and classification application on photovoltaic arrays