Proposed Fault Diagnostic Method Research Articles

Applications of the TL-Based Fault Diagnostic System for the Capacitor in Hybrid Aircraft

The article concerns the problem of capacitor diagnosis in a hybrid aircraft. Capacitors are one of the most commonly damaged components of electrical vehicle drive systems. The result of these failures is an increase in voltage ripple. Most known analytical methods are based on frequency spectrum analysis, which is time-consuming and computationally complex. The use of deep neural networks (DNNs) allows for the direct use of the measurement signal, which reduces the operating time of the overall diagnostic system. However, the problem with these networks is the long training process. Therefore, this article uses transfer learning (TL), which allows for the secondary use of previously learnt DNNs. To collect data to learn the network, a test bench with the ability to simulate a capacitor failure was constructed, and a model based on it was made in the MATLAB/Simulink environment. A convolutional neural network (CNN) structure was developed and trained by the TL method to estimate the capacitance of the capacitor based on signals from the Simulink-designed model. The proposed fault diagnostic method is characterised by a nearly 100% efficiency in determining capacitance, with an operating time of about 10 ms, regardless of load and supply voltage.

Open-Circuit Fault Diagnosis of Three-Phase Permanent Magnet Machine Utilizing Normalized Flux-Producing Current

In this paper, an open-circuit fault diagnostic method is proposed for three-phase permanent magnet machines. By individually applying inverse coordination transformation to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</i> - and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">q</i> -axis currents, per-phase current can be decomposed into flux- and torque-producing currents. Their post-fault behaviors are found to be highly related with the fault types and locations. Hence, the normalized flux-producing current can be used as a single fault index to detect and identify both open-switch and open-phase faults. Since the established fault index is close to zero, the proposed fault diagnostic method is naturally robust to load/speed variations. In addition, a low decision threshold can be set to reduce fault diagnostic time. The robustness and effectiveness of the proposed method are verified by the experiments on one prototype.

Sensitivity analysis by differential importance measure for unsupervised fault diagnostics

Fault diagnostic approaches based on supervised classifiers are difficult to apply to safety-critical or new design systems, because they require the availability of labelled data collected when the systems operate abnormally, which is a rare situation. To address this challenge, we develop a novel unsupervised method for fault diagnostics based on a fault detection module and on sensitivity analysis . Specifically, the Differential Importance Measure (DIM) is originally used to quantify how much a signal is, or a set of signals are, responsible for the variation of the system health state. The proposed method is tested on simulated data from a wind turbine and on real data from a gas turbine. The advantages of the proposed fault diagnostic method are: (1) it can be developed using only normal condition data (2) it allows identifying the component responsible for the abnormality by quantifying the contribution of groups of signals to the variation of the system health state; (3) it is capable of distinguishing the abnormalities caused by changes in external conditions from those caused by components malfunctions; (4) it can be used in combination with any fault detection technique.

Acoustic Signal based Non-Contact Ball Bearing Fault Diagnosis Using Adaptive Wavelet De-Noising

This paper presents a non-contact fault diagnostic method for ball bearing using adaptive wavelet denoising, statistical-spectral acoustic features, and one-dimensional (1D) convolutional neural networks (CNN). The health conditions of the ball bearing are monitored by microphone under noisy condition. To eliminate noise, adaptive wavelet denoising method based on kurtosis-entropy (KE) index is proposed. Multiple acoustic features are extracted base on expert knowledge. The 1D ResNet is used to classify the health conditions of the bearings. Case study is presented to examine the proposed method’s capability to monitor the condition of ball bearings. The fault diagnosis results were compared with and without the adaptive wavelet denoising. The results show its effectiveness of the proposed fault diagnostic method using acoustic signals.

Fault diagnosis method for proton exchange membrane fuel cells based on EIS measurement optimization

AbstractPoor durability and reliability are key barriers to the application of proton‐exchange membrane fuel cells (PEMFCs). The timely detection and isolation of faults can improve the performance and durability of PEMFCs. This paper proposes a PEMFC fault diagnostic method based on rapid electrochemical impedance spectroscopy (EIS) measurements. To shorten the EIS measurement time, the characteristic frequency bands were separated by a fuzzy inference method to remove interference frequency bands and low‐frequency invalid frequency bands. Then, they were optimized for the corresponding characteristic frequency band points. The parameters of the improved equivalent circuit model were identified according to the electrochemical impedance spectrum, and four of the model parameters were selected as characteristic variables for fault diagnosis. Based on this, a multifault diagnosis algorithm with an improved K‐nearest neighbor classifier applied to PEMFC was proposed. The experimental results showed that the proposed fault diagnostic method accurately and quickly distinguished four health states, that is, flooding, membrane drying, air starvation, and normal state.

A fault diagnosis method for photovoltaic module current mismatch based on numerical analysis and statistics

Photovoltaic (PV) module faults will not only reduce the power generation efficiency of PV modules, but also cause a series of safety problems. As the most common fault type, current mismatched fault leads to the decrease of the output current of the PV module resulting in a step in the I-V characteristic curves and multiple peaks in the P-V curves, such that the output power of the PV modules will be greatly affected. This paper focuses on current mismatched faults caused by partial shading, hot spot and crack through the investigation of faulty PV modules in actual PV power plants. The I-V characteristics of PV modules with current mismatch type faults are tested, and their fault characteristics are extracted. Not only can the current mismatch make the I-V characteristic curve of the module a step, but also the cause of the I-V curve of each current mismatched fault is analyzed in combination with the reverse bias model of the PV cell. In order to further decouple the features of different faults in the I-V curve step, a numerical analysis and statistical method is proposed for diagnosing PV module mismatch faults, which divides the I-V curve into a high voltage area and a low voltage area. The detection line composed of key points in the low voltage area is used to detect mismatch, while the current drop and linear regression fitting of the step data are used to identify the specific fault types in the high voltage area. Combined with the actual I-V data of PV modules under different working conditions, four case studies involving various types of faults are demonstrated to show that the proposed fault diagnostic method exhibits strong discriminating power and adaptability, and high practical application value.

Use of generalized refined composite multiscale fractional dispersion entropy to diagnose the faults of rolling bearing

A typical symptom of vibration signals collected from rolling bearings with local faults is the existence of periodic transients, which makes the intrinsic structure of vibration signals become more and more regular. Generally, the vibration always contains multiple intrinsic oscillatory modes on different scales, which generally is caused by the interaction and coupling of machine components. Therefore, it is necessary to detect the behavior change of complexity of vibration signals in the view of multiple scales for fault information representation. The complexity and nonlinear failure symptom of rolling bearing can be evaluated by the recently proposed nonlinear dynamic tools, such as multiscale entropy (MSE) and its variants. Recently, the improved MSE method, multiscale dispersion entropy (MDE) and its improvement refined composite MDE (RCMDE) are developed to measure the complexity of time domain data. However, the intrinsic shortages of coarse graining approach that used in MDE and RCMDE have limited their application to fault feature representation. In this paper, an improved RCMDE approach named generalized refined composite multiscale fluctuation-based fractional dispersion entropy (GRCMFDE) is proposed to enhance MDE and RCMDE in complexity measurement of time series. GRCMFDE was compared with MPE, MDE, RCMDE by analyzing synthetic simulation signals to verify its advantages. After that, an intelligent fault diagnosis method was proposed by combining GRCMFDE with supervised multi-clustering feature selection and gray wolf optimized SVM for fault classification of rolling bearing. Lastly, the proposed fault diagnostic method was applied to two experimental data set analysis by comparing with multiscale permutation entropy, MDE- and RCMDE-based fault diagnostic methods and the comparison results indicate that the proposed method can effectively diagnose the fault locations and severities of rolling bearing and get a higher fault identifying rate than the comparative methods.

A novel fault diagnostic method for analog circuits using frequency response features

Analog circuits are an important component of complex electrical systems. Therefore, fault diagnosis of analog circuits plays a vital role in ensuring the reliability of electronic systems. A novel fault diagnostic method for analog circuits based on the support vector machine (SVM) optimized by the firefly algorithm (FA) using frequency response features is presented in this paper. Wilks Λ-statistic can effectively assess the ability of variables to resolve multiple types of samples in multivariate statistical analysis. Frequency responses of analog circuits are measured, and then, features are extracted by using the particle swarm optimization (PSO) method. Additionally, the fitness function of the PSO is set to Wilks Λ-statistic. Then, an SVM based analog circuit’s fault diagnosis model is introduced to classify the faulty components according to the extracted frequency response features. The optimal penalty parameter and kernel function parameter of SVM are obtained by using the FA. The method is fully evaluated in fault diagnosis simulations of the Sallen-Key bandpass filter and four-op-amp biquad high-pass filter. The experimental results demonstrate that the proposed fault diagnostic method can produce higher diagnosis accuracy than other typical analog circuit fault diagnosis methods.

Time-Shift Multi-scale Weighted Permutation Entropy and GWO-SVM Based Fault Diagnosis Approach for Rolling Bearing.

Multi-scale permutation entropy (MPE) is an effective nonlinear dynamic approach for complexity measurement of time series and it has been widely applied to fault feature representation of rolling bearing. However, the coarse-grained time series in MPE becomes shorter and shorter with the increase of the scale factor, which causes an imprecise estimation of permutation entropy. In addition, the different amplitudes of the same patterns are not considered by the permutation entropy used in MPE. To solve these issues, the time-shift multi-scale weighted permutation entropy (TSMWPE) approach is proposed in this paper. The inadequate process of coarse-grained time series in MPE was optimized by using a time shift time series and the process of probability calculation that cannot fully consider the symbol mode is solved by introducing a weighting operation. The parameter selections of TSMWPE were studied by analyzing two different noise signals. The stability and robustness were also studied by comparing TSMWPE with TSMPE and MPE. Based on the advantages of TSMWPE, an intelligent fault diagnosis method for rolling bearing is proposed by combining it with gray wolf optimized support vector machine for fault classification. The proposed fault diagnostic method was applied to two cases of experimental data analysis of rolling bearing and the results show that it can diagnose the fault category and severity of rolling bearing accurately and the corresponding recognition rate is higher than the rate provided by the existing comparison methods.

Newly-Designed Fault Diagnostic Method for Solar Photovoltaic Generation System Based on IV-Curve Measurement

Fault diagnosis of photovoltaic (PV) arrays is an essential task for improving the reliability and safety of a photovoltaic system (PVS). The PVS faults at the DC side are difficult to detect by traditional protective devices, which may reduce power conversion efficiency and even lead to safety matters and fire disaster. This study investigates a newly-designed fault diagnostic method for a PVS according to the following three steps. First, optimal fault features are extracted by analyzing I-V curves from different faults, including hybrid faults of the PVS under the standard test condition (STC). Moreover, the trust-region-reflective (TRR) deterministic algorithm combined with the particle-swarm-optimization (PSO) metaheuristic algorithm is proposed to standardize fault features into the ones under the STC. In addition, a multi-class adaptive boosting (AdaBoost) algorithm, which is the stage-wise additive modeling using multi-class exponential (SAMME) loss function based on the classification and regression tree (CART) as the weak classifier, is utilized to establish the fault diagnostic model. The effectiveness of the fault diagnostic model could long-term maintain by periodically updating the feature standardization equations to standardize the fault features into the ones under the STC. Various types of the PV modules are used to validate the generalization of the fault diagnostic method. Both the numerical simulations and experimental results show the accuracy and reliability of the proposed fault diagnostic method.

Open‐circuit faults diagnosis in back‐to‐back converters of DF wind turbine

The open-circuit fault in converters is one of the wind turbine faults, which degrades the power quality and can even cause potential secondary faults in other components. So, an effective fault diagnostic technique for wind turbine converters is needed. This study presents a new open-circuit fault diagnostic approach for back-to-back converters of doubly fed (DF) wind turbines. The proposed fault diagnostic method has fault detection and fault localisation. The fault detection is based on the absolute normalised Park's vector approach; this method can detect multiple open-circuit switch faults and guarantee immunity to false alarms when the DF induction generator operates around the synchronous speed. For fault localisation, this approach applies the normalised current average values, which can be used to identify single and double open-circuit switch faults. The simulation and experimental results indicate that the diagnostic method can not only diagnose multiple open-circuit faults, but that false alarms due to transients can be avoided.

Fault-Tolerant Strategy for a Photovoltaic DC--DC Converter

The photovoltaic (PV) technology has a small impact on the environment and is suitable for a wide range of applications. The main barrier for a more extensive implementation has been the reliability, mainly related to the power converters. According to this consideration, this paper presents an open-circuit fault diagnosis and fault-tolerant scheme for a three-level boost converter in a PV power system using batteries as storage devices. The fault diagnostic method takes advantage only of the control variables used for maximum power point tracking and output dc-link capacitor voltage balance. The fault-tolerant strategy requires only a few components added to the original three-level boost converter, so that, under an open-circuit power switch fault, it can be partly reconfigured into a two-level boost converter ensuring battery energy supply. Experimental results verify the proposed fault diagnostic method and reconfiguration for fault-tolerant operation.

An Open Circuit Fault Diagnostic Technique in IGBTs for AC to DC Converters Applied in Microgrid Applications

An open circuit fault diagnostic method in IGBTs for the ac to dc converters used in microgrid applications is developed in this paper. An ac to dc converter is a key technology for microgrids in order to interface both distributed generation (DG) and renewable energy resources (RES). Also, highly reliable ac to dc converters are necessary to keep converters in continuous operation as long as possible during power switch fault conditions. Therefore, the proposed fault diagnostic method is developed to reduce the fault detection time and to avoid any other fault alarms because continuous operation is desired. The proposed diagnostic method is a combination of the absolute normalized dc current technique and the false alarm suppression algorithm to overcome the long fault detection time and fault alarm problems. The simulation and experimental results show that the developed fault diagnostic method can perform fault detection within about one cycle. The results illustrate that the reliability of an ac to dc converter interfaced with a microgrid can be improved by using the proposed fault diagnostic method.