Open circuit Fault Diagnosis using Machine Learning Classifiers

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

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.

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.

This work investigates the effect of asymmetric bridge converter switch open and short-circuit faults in a Switched Reluctance Motor (SRM) drive using Finite Element Analysis (FEA). The analysis is executed for different fault conditions such as (i) Single-switch open-circuit (ii) Single-phase (two switches) open-circuit (iii) Single-switch short-circuit (iv) Single-phase (two switches) short-circuit. Simulation is performed on a 550 W, 220 V, 4-phase, 1050 rpm, 8/6 pole SRM utilizing ANSYS Maxwell FEA tool and different electromagnetic factors namely current, speed, torque, flux line distribution inside SRM, and flux density in the airgap of SRM are analyzed under healthy and converter fault conditions. Unbalance in phase currents, reduction in speed, and asymmetry in magnetic flux distribution are noticed for single switch open-circuit fault. Whenever SRM experiences single switch short-circuit converter fault, increased oscillations in speed and phase current magnitudes and severe asymmetry are observed in radial element of flux density present in the airgap.

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.

The paper establishes an open-circuit fault diagnosis Bayesian network (OFDBN) to diagnose the faults of inverter’s IGBTs. The topological structure of the OFDBN includes two layers, an inverter faults layer and a fault symptoms layer. The faults layer includes various IGBT open-circuit faults, and the symptoms layer includes various fault features extracted from the output line voltage of the inverter. A number of fault training data and test data are obtained by the method of changing carrier frequency and modulation ratio. The study uses the maximum likelihood algorithm to train the OFDBN parameters by the training data simulated in Matlab. The trained OFDBN is used to diagnose IGBT open-circuit faults of inverters. The results show that the proposed OFDBN has a very high accuracy for both single IGBT fault and double IGBT fault, and it can accurately locate the open-circuit fault location.

This paper proposes the usage of Field Programmable Gate Arrays (FPGA) for fault distance detection and positioning of an underground cable by using GSM/GPRS. This task was produced using Very High Speed Integrated Circuit Hardware Description Languages (VHDL) and implemented on Basys-3 FPGA board by using Xilinx Vivado Design Suite 18.1. Deciding the separation of underground power line fault from the base station was done by using FPGA and Global System for Mobile Communication/General Packet Radio Service (GSM/GPRS) module. The main fault types are three phase symmetrical short circuit fault, two phase-to-earth short-circuit fault, phase-to-phase short circuit fault, phase-to-earth short circuit fault and open-circuit fault. In this study, only two types of faults were taken into consideration. The first of them is phaseto-earth short-circuit fault, while the other one is open circuit fault with broken in transmission line and both simulated by using LTspice.

To address the challenges associated with pinpointing single and double-switch open-circuit (OC) faults in conventional fault diagnosis strategies for T-type three-level (T<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$^{2}3$ </tex-math></inline-formula>L) inverters, a method for fault diagnosing based on energy feature extraction of intrinsic mode function (IMF) of voltage is proposed in this article. First, to mitigate modal aliasing and noise interference, the output voltage signal of the inverter is decomposed using the complete ensemble empirical mode decomposition (CEEMD) to extract IMF components. Subsequently, the short-term energy value of the selected IMF components is calculated by segmenting the decomposition results. By establishing a criterion for extracting fault features, the local variations in IMF short-term energy values at different fault locations are distinguished. Based on this criterion, a fault feature vector is constructed, enabling a diagnostic method for OC faults relying on the IMF components’ short-term energy values. The experimental results show that the fault diagnosis method proposed in this article can reliably achieve the diagnosis of single and double-switch OC faults in the T-type inverter. The proposed method does not require complex modeling and has strong robustness and high accuracy compared to other types of diagnostic methods.

Recently, fault detection has played a crucial role in ensuring the safety and reliability of inverter operation. Switch failures are primarily classified into Open-Circuit (OC) and short-circuit faults. While OC failures have limited negative impacts, prolonged system operation under such conditions may lead to further malfunctions. This paper demonstrates the effectiveness of employing Artificial Intelligence (AI) approaches for detecting single OC faults in a Packed E-Cell (PEC) inverter. Two promising strategies are considered: Random Forest Decision Tree (RFDT) and Feed-Forward Neural Network (FFNN). A comprehensive literature review of various fault detection approaches is first conducted. The PEC inverter’s modulation scheme and the significance of OC fault detection are highlighted. Next, the proposed methodology is introduced, followed by an evaluation based on five performance metrics, including an in-depth comparative analysis. This paper focuses on improving the robustness of fault detection strategies in PEC inverters using MATLAB/Simulink software. Simulation results show that the RFDT classifier achieved the highest accuracy of 93%, the lowest log loss value of 0.56, the highest number of correctly predicted estimations among the total samples, and nearly perfect ROC and PR curves, demonstrating exceptionally high discriminative ability across all fault categories.

This paper presents a new investigation to detect various faults within the three-phase star and delta induction motors (IMs) using a frequency response analysis (FRA). In this regard, experimental measurements using FRA are performed on three IMs of ratings 1 HP, 3 HP and 5.5 HP in normal conditions, short-circuit fault (SC) and open-circuit fault (OC) conditions. The SC and OC faults are applied artificially between the turns (Turn-to-Turn), between the coils (Coil-to-Coil) and between the phases (Phase-to-Phase). The obtained measurements show that the star and delta IMs result in dissimilar FRA signatures for the normal and faulty windings. Various statistical indicators are used to quantify the deviations between the normal and faulty FRA signatures. The calculation is performed in three frequency ranges: low, middle and high ones, as the winding parameters including resistive, inductive and capacitive components dominate the frequency characteristics at different frequency ranges. Consequently, it is proposed that the boundaries for the used indicators facilitate fault identification and quantification.

This paper presents a noninvasive approach, based on the computer-aided monitoring of the three-phase supply current Park's vector, for diagnosing converter faults in variable speed DC drives. Both simulation and laboratory tests results demonstrate the effectiveness of the proposed technique, for detecting either open-circuit or short-circuit faults in the converter power switches and also for identifying which is the faulty element.

The multilevel inverter-based drive system is greatly affected by several faults occurring on switching elements. A faulty switch in the inverter can potentially lead to more losses, extensive downtime and reduced reliability. In this paper, a novel fault identification and reconfiguration process is proposed by using discrete wavelet transform and auxiliary switching cells. Here, the discrete wavelet transform exploits a multiresolution analysis with a feature extraction methodology for fault identification and subsequently for reconfiguration. For increasing the reliability, auxiliary switching cells are integrated to replace faulty cells in a proposed reduced-switch 5-level multilevel inverter topology. The novel reconfiguration scheme compensates open circuit and short circuit faults. The complexity of the proposed system is lower relative to existing methods. This proposed technique effectively identifies and classifies faults using the multiresolution analysis. Furthermore, the measured current and voltage values during fault reconfiguration are close to those under healthy conditions. The performance is verified using the MATLAB/Simulink platform and a hardware model.

Chapter 5 - Control of PWM Inverter-Fed Induction Motors

This paper presents a novel five-phase permanent magnet synchronous motor (PMSM), which contains dual rotors and a single stator, equivalent to two five-phase motors working together. Thus, this kind of motor has the potential of good fault tolerant capability and high torque density, which makes it appropriate for use in electric vehicles. In view of the different connection types, the inside and outside stator windings can be driven in series or parallel, which results in the different performances of the magnetomotive force (MMF) and torque under open-circuit fault conditions. By decomposing the MMF, the reason that torque ripple increases after open-circuit faults is explained, and the relationship between MMF and torque is revealed. Then, the current control strategy is applied to adjust the open-circuit faults, and the electromagnetic analysis and MMF harmonics analysis are performed to interpret the phenomenon that the torque ripple is still larger than in the normal situation. The investigations are verified by finite element analysis results.

Solar Photovoltaic (PV) system consists of three main parts which are PV array, PV inverter and utility grid. From the three, PV inverter is considered the weakest link in the solar PV system. Insulated Gate Bipolar Transistor (IGBT) is the most critical component in an inverter and is often blamed for the failure of inverters. If the incipient faults of the IGBT can be detected, the breakdown possibility of the solar PV system can be improved. However, before the incipient faults can be detected, it needs to be first generated before further analysis and improvements can be made. This paper proposes a process on how to generate the incipient faults which are caused by the short-circuit fault of a single phase PWM inverter. The single phase PWM inverter consists of four IGBTs and there is a total of six parameters that need to be observed for each IGBT. The parameter that could cause short-circuit fault to the IGBTs is identified by modifying the parameters of IGBT one at a time. The response at the inverter output is observed and recorded after each modification to the parameter value is done. From the results, it shows that parameter Threshold voltage (V ge(th) ) is identified to be able to generate the short-circuit incipient faults. For the application of detection the incipient faults using neural network, a total of 100 short-circuit incipient faults and one set of normal condition waveform are collected at the output of the single phase PWM inverter. These waveforms are then used to train the feedforward backpropagation neural network. One hidden layer feedforward backpropagation neural network of 7 neurons was trained and MSE of was obtained. It was shown that the trained feedforward backpropagation neural network was able to detect which IGBT component of the single phase PWM inverter produced the short-circuit incipient faults.