A novel multi-resolution network for the open-circuit faults diagnosis of automatic ramming drive system

The open-circuit fault is one of the most common faults of the automatic ramming drive system(ARDS),and it can be categorized into the open-phase faults of Permanent Magnet Synchronous Motor(PMSM)and the open-circuit faults of Voltage Source Inverter(VSI). The stator current serves as a common indicator for detecting open-circuit faults. Due to the identical changes of the stator current between the open-phase faults in the PMSM and failures of double switches within the same leg of the VSI, this paper utilizes the zero-sequence voltage component as an additional diagnostic criterion to differentiate them.Considering the variable conditions and substantial noise of the ARDS, a novel Multi-resolution Network(Mr Net) is proposed, which can extract multi-resolution perceptual information and enhance robustness to the noise. Meanwhile, a feature weighted layer is introduced to allocate higher weights to characteristics situated near the feature frequency. Both simulation and experiment results validate that the proposed fault diagnosis method can diagnose 25 types of open-circuit faults and achieve more than98.28% diagnostic accuracy. In addition, the experiment results also demonstrate that Mr Net has the capability of diagnosing the fault types accurately under the interference of noise signals(Laplace noise and Gaussian noise).

A new approach for on-line open-circuit fault diagnosis of inverters based on current trajectory

Security and reliability of inverter are an indispensable part in power electronic system. Faults of inverter are usually caused by switch elements’ operating fault. Taking the inverter with hysteresis current control as the research object, a universal open-circuit fault location method which can be applied to multiple control strategies is proposed in the paper. If the switch open-circuit fault happens in inverter, the output phase current will inevitably change, which can be used as a characteristic for diagnosis, combined with the comparison of phase-current direction before and after the fault occurrence, to diagnose and locate the open-circuit fault in a half cycle. Moreover, this method requires neither system control signals nor sensor. The validity, reliability and limitation of the fault location method in the paper are verified and analyzed through dSPACE-based experiment platform.

A Hybrid Diagnosis Method for Inverter Open-circuit Faults in PMSM Drives

In order to improve the evaluation process of inverter open-circuit faults diagnosis in permanent magnet synchronous motor(PMSM)drives,this paper presents a diagnosis method based on current residuals and machine learning models.The machine learning models are introduced to make a comprehensive evaluation for the current residuals obtained from a state observer,instead of evaluating the residuals by comparing with thresholds.Meanwhile,fault diagnosis and location are conducted simultaneously by the machine learning models,which simplifies the diagnosis process.Besides,a sampling strategy is designed to implement the proposed scheme online.Experiments are carried out on a DSP based PMSM drive,and the effectiveness of the proposed method is verified.

FEM based Electromagnetic Signature Analysis of Winding Inter-turn Short-Circuit Fault in Inverter fed Induction Motor

The intent of this paper is to analyze the electromagnetic signature of stator winding inter-turn short-circuit fault in a closed loop speed controlled Induction Motor(IM)employing Finite Element Method.Stator winding short-circuit nearly covers 21%of faults in IM.Diagnosing the inter-turn fault at an incipient stage is one of the challenging task in the area of fault detection of IM to prevent crucial damages in industrial applications.Also detecting the faults in inverter fed IM under variable speed applications under varying load is one of the major issues in industrial drives.As the signatures of electromagnetic field contains the entire data in association with the location of rotor,stator and mechanical parts of the motor,a regular monitoring of fields in the airgap can be used to diagnose the inter-turn fault in the stator winding of IM.In this direction,an IM is modeled with several inter-turn fault severities like 30 turns,15 turns,5 turns&1 turn short using ANSYS Maxwell FEA tool and coupled with ANSYS Simplorer for loading arrangements.The PWM inverter with closed loop speed controlled strategy is implemented in Matlab Simulink and co-simulated with ANSYS Simplorer to integrate all the components in one common simulation platform environment for accurate design&analysis for realistic simulation.Several electromagnetic variables like flux density,flux lines and airgap flux density distribution over the machine are analyzed.The spatial FFT spectrum of radial component of flux density in the airgap contains the information related to the diagnosis of inter-turn fault at the incipient stage.

An Efficient Fuzzy Logic Fault Detection and Identification Method of Photovoltaic Inverters

Fuzzy logic control(FLC)systems have found wide utilization in several industrial applications.This paper proposes a fuzzy logic-based fault detection and identification method for open-circuit switch fault in grid-tied photovoltaic(PV)inverters.Large installations and ambitious plans have been recently achieved for PV systems as clean and renewable power generation sources due to their improved environmental impacts and availability everywhere.Power converters represent the main parts for the grid integration of PV systems.However,PV power converters contain several power switches that construct their circuits.The power switches in PV systems are highly subjected to high stresses due to the continuously varying operating conditions.Moreover,the grid-tied systems represent nonlinear systems and the system model parameters are changing continuously.Consequently,the grid-tied PV systems have a nonlinear factor and the fault detection and identification(FDI)methods based on using mathematical models become more complex.The proposed fuzzy logic-based FDI(FL-FDI)method is based on employing the fuzzy logic concept for detecting and identifying the location of various switch faults.The proposed FL-FDI method is designed and extracted from the analysis and comparison of the various measured voltage/current components for the control purposes.Therefore,the proposed FL-FDI method does not require additional components or measurement circuits.Additionally,the proposed method can detect the faulty condition and also identify the location of the faulty switch for replacement and maintenance purposes.The proposed method can detect the faulty condition within only a single fundamental line period without the need for additional sensors and/or performing complex calculations or precise models.The proposed FL-FDI method is tested on the widely used T-type PV inverter system,wherein there are twelve different switches and the FDI process represents a challenging task.The results shows the superior and accurate performance of the proposed FL-FDI method.

Flexible Power Regulation and Limitation of Voltage Source Inverters under Unbalanced Grid Faults

This paper develops a flexible power regulation and limitation strategy of voltage source inverters(VSIs)under unbalanced grid faults.When the classical power theory is used under unbalanced grid faults,the power oscillations and current distortions are inevitable.In the proposed strategy,the extended power theory is introduced to compute the power feedbacks together with the classical power theory.Based on the combination of the classical and extended power theory,the proposed strategy can achieve the sinusoidal current provision and the flexible regulation between three common targets,i.e.,constant active power,balanced current,and constant reactive power.Meanwhile,the proposed strategy is associated with a power limiter,which is capable to keep the currents under the pre-defined threshold and to compute the maximum apparent power for better utilization of the inverter capacity.With this power limiter,the rated inverter capacity is fully used for both the active and reactive power provisions under unbalanced grid faults.Using the proposed power regulation and limitation,the VSI can avoid overcurrent tripping and flexibly regulate its power under unbalanced grid faults.All the conclusions are verified by the real-time hardware-in-loop tests.

Multilevel Feature Moving Average Ratio Method for Fault Diagnosis of the Microgrid Inverter Switch

Multilevel feature moving average ratio method is proposed to realize an open-switch fault diagnosis for any switch of the microgrid inverter. The main steps of the proposed method include multilevel signal decomposition, coefficient reconstruction, absolute average ratio process and artificial neural network U+0028 ANN U+0029 classification. Specifically, multilevel signal decomposition is realized by using the means of multi resolution analysis to obtain the different frequency band coefficients of the three-phase current signal. The related coefficient reconstruction is executed to achieve signals decomposition in different levels. Furthermore, according to the obtained data, the absolute average ratio process is used to extract absolute moving average ratio of signal decomposition in different levels for the three-phase current. Finally, to intelligently classify the inverter switch fault and realize the adaptive ability, the ANN technology is applied. Compared to conventional fault diagnosis methods, the proposed method can accurately detect and locate the open-switch fault for any location of the microgrid inverter. Additionally, it need not set related threshold of algorithm and does not require normalization process, which is relatively easy to implement. The effectiveness of the proposed fault diagnosis method is demonstrated through detailed simulation results. © 2017 Chinese Association of Automation.

Fault Detection for PMSM Motor Drive Systems by Monitoring Inverter Input Currents

This paper has proposed a fault detecting method for DC supplied permanent magnet synchronize motor(PMSM)drive systems by monitoring the drive DC input current.This method is based on the fault signal propagation from the torque disturbance on the motor shaft to the inverter input currents.The accuracy of this fault signal propagation is verified by the Matlab simulation and experiment tests with the emulated faulty conditions.The feasible of this approach is shown by the experimental test conducted by the Spectra test rig with the real gearbox fault.This detection scheme is also suitable for monitoring other drive components such as the power converter or the motor itself using only one set of current transducers mounted at the DC input side.

Open-circuit Fault-tolerant Control Strategy Based on Five-level Power Converter for SRM System

Switched reluctance motor power converters are prone to open-circuit faults because it need to withstand large voltages and currents.Due to the small number of traditional asymmetrical half bridge topology switches,it is difficult to carry out fault tolerant control when power converters has an open-circuit fault,resulting in larger output torque ripple.This paper presents a five-level power converter based on the traditional asymmetric half-bridge power converter.The five-level topology has more switching states and can work in multi-level mode.Based on the topology,different excitation and demagnetization voltages can be choose at different speeds.A fault-tolerance strategy is developed to decrease the influence of the open-circuit fault.The five-level power converter has four switches per phase,and two of them will be used in one of the operating mode.So the remaining two of the switches can be used for safe backup,enabling fault-tolerant control when an open-circuit occur.Since each phase of the five-level power converter proposed in this paper is independent of each other,a reasonable control strategy can be used to avoid the unbalance of the midpoint potential.Finally,the topology and fault-tolerant strategy proposed in this paper are verified by simulation and experiment.

Detection and Diagnosis of Urban Rail Vehicle Auxiliary Inverter Using Wavelet Packet and RBF Neural Network

This study concerns with fault diagnosis of urban rail vehicle auxiliary inverter using wavelet packet and RBF neural network. Four statistical features are selected: standard voltage signal, voltage fluctuation signal, impulsive transient signal and frequency variation signal. In this article, the original signals are decomposed into different frequency subbands by wavelet packet. Next, an automatic feature extraction algorithm is constructed. Finally, those wavelet packet energy eigenvectors are taken as fault samples to train RBF neural network. The result shows that the RBF neural network is effective in the detection and diagnosis of various urban rail vehicle auxiliary inverter faults.

Novel active fault-tolerant control scheme and its application to a double inverted pendulum system

On the basis of the gain-scheduled H∞ design strategy, a novel active fault-tolerant control scheme is proposed. Under the assumption that the effects of faults on the state-space matrices of systems can be of affine parameter dependence, a reconfigurable robust H∞ linear parameter varying controller is developed. The designed controller is a function of the fault effect factors that can be derived online by using a well-trained neural network. To demonstrate the effectiveness of the proposed method, a double inverted pendulum system, with a fault in the motor tachometer loop, is considered.

Open-Circuit Faults Diagnosis in Direct-Drive PMSG Wind Turbine Converter

The condition monitoring and fault diagnosis have been identified as the key to achieving higher availabilities of wind turbines.Numerous studies show that the open-circuit fault is a significant contributor to the failures of wind turbine converter.However,the multiple faults combinations and the influence of wind speed changes abruptly,grid voltage sags and noise interference have brought great challenges to fault diagnosis.Accordingly,concerning the open-circuit fault of converters in direct-driven PMSG wind turbine,a diagnostic method for multiple open-circuit faults is proposed in this paper,which is divided into two tasks:The first one is the fault detection and the second one is the fault localization.The detection method is based on the relative current residuals after exponential transformation and on an adaptive threshold,and the localization method is based on the average values of fault phase currents.The scheduled diagnosis method is available to both the generator-side converter and the grid-side converter,allowing to detect and locate single and double open-circuit faults.For validating this,robustness test and multiple open-circuit faults diagnosis are presented in a 2-MW direct-driven PMSG wind turbine system,the results validate the reliability and effectiveness of the proposed method.

Ride through Strategy for a Three-Level Dual Z-Source Inverter Using TRIAC

A new ride through strategy is introduced in a three-level dual Z-source inverter, for isolation under semiconductor switching failure condition. Here the output will have no significant decrease in the amplitude and quality. Instead of diodes, the triacs are added to the inverter source ends, as it can perform a bidirectional power transfer also it can operate well in both low and high voltage operating conditions. The faulted part can be isolated by simply altering the firing pulses for turning on/off the triacs using the carrier based SPWM technique and resulting in a boosting output with zero common mode voltage. Consequently, it forms a common floating point or null point with a zero common mode voltage. It is experimentally verified by using MATLAB, and digital oscilloscope.

含逆变型分布式电源和分支负荷的配电网自适应电流差动保护

电流差动保护具有良好的选择性和灵敏性。但是,逆变型分布式电源(inverter-interfaced distributed generator,IIDG)和分支负荷接入改变了配电网的故障特性,现有配电网的电流差动保护面临拒动或误动的风险。为解决以上问题,该文在计及P/Q控制的IIDG和分支负荷的故障等值建模基础上,从故障点、IIDG和分支负荷的相对位置出发,挖掘配电网线路两端正序电流差的幅值特征以及正序电流故障分量的相位特征。在此基础上,提出一种正序电流幅值与故障分量相角阈值配合的双比例制动系数自适应差动保护方案,并且利用幅相平面分析所提保护判据的可靠性和灵敏性。最后通过PSCAD/EMTDC验证了所提保护方案的有效性,仿真结果表明该方案适应不同故障类型、位置和过渡电阻,且不受IIDG以及分支负荷接入的影响。

逆变型电源场站故障稳态电流实用化计算方法

单机倍乘法常用于逆变型电源场站的故障稳态建模,可简单估算场站短路电流水平,但计算精度有待提升。文中首先分析了低电压穿越控制策略约束下,有功出力、电压跌落程度对发电单元输出的稳态电流的决定性作用,得出故障稳态电流输出特性曲线,基于此分析了场站电气距离及有功出力差异对单机倍乘法计算误差的影响。在误差分析的基础上,提出了计及发电单元分布特性的改进单机倍乘法。该方法在发电单元接入点电压计算中,利用等值阻抗来等效发电单元与并网点的电气距离;将场站分群等值为两台机组,减小发电单元间有功出力差异对短路特性的影响。不同场景下的仿真分析表明,改进方法计算精度较单机倍乘法有着较大的提升。所提方法仅需通过简单计算即可实现场站分群和短路电流聚合,有较好的工程实用性。

储能变流器信号高精度故障诊断方法

随着能源转型和碳中和的全球发展趋势,储能变流器关键组件的稳定性变得至关重要。特别是其功率器件和散热器在实际运行中的稳定性直接关系到整个系统的可靠性。关注储能变流器功率模组振动信号的故障诊断问题,传统诊断方法处理复杂信号时往往面临挑战,需要频繁地调整参数。此外,由于储能变流器的工作环境复杂,现有深度学习诊断方法的性能也不尽如人意。为此,提出一种基于大模型知识和通道注意力网络的储能变流器功率模组故障诊断方法LLMCAN。首先通过预训练的大规模语言模型,在特征提取过程中利用丰富的领域知识,增强模型对复杂功率模组振动信号的分析能力。其次引入通道注意力网络使模型能够自适应学习信号中不同通道之间的关系,提高故障诊断的准确性。在包含1000条真实工况数据的储能变流器信号数据集上进行验证,其中包括正常工况和9种故障模式。实验结果表明,该方法在多种度量指标下均显示出优越性能,其中诊断准确率高达99.8%,远超传统方法,为储能变流器功率模组的故障诊断提供一个高效、准确的解决方案。

H桥级联多电平逆变器旁路方法研究与应用

单元级联H桥逆变器因具有良好的输出电压和电流性能,在中高压变频器中逐渐得到广泛的应用,然而可靠的H桥功率单元故障旁路方法是级联H桥逆变器长期稳定运行的保证。当前逆变器应用现场要求具有高平均无故障时间(MTBF)需求,首先对级联H桥功率单元箱多电平逆变器传统旁路方法的优缺点进行分析;接着根据传统旁路方法的缺陷提出一种有着高可靠性级联H桥多电平逆变器的双重旁路方法;最后详细设计了满足双重旁路方法功能的电路并对该方法进行试验验证。试验结果表明此处所提方法能够实现级联H桥多电平逆变器的双重旁路,具有非常巨大的工程实际应用价值和意义。

基于改进GAF-SE-ResNet的光伏逆变器开路故障诊断

针对光伏逆变器一维时序信号输入卷积神经网络时无法充分捕获时间和局部特征的问题,提出一种基于格拉姆角场(GAF)与改进的深度残差网络(ResNet)结合的光伏逆变器开路故障诊断模型。采用双通道GAF编码方法将一维电流信号映射为不同像素分布的二维故障特征图像,将特征图像作为ResNet的输入,保留了数据在时间维度的相关性。ResNet在卷积神经网络中引入残差模块来解决过拟合的问题,加入压缩和激励(SE)注意力机制改进残差模块后进行图像压缩、特征重用,增强了重要特征信息,使ResNet能更深入挖掘图像信息,充分捕获局部特征,结合Swish函数和Ranger优化器优化ResNet,大幅降低模型训练难度。实验结果表明,该方法对光伏逆变器开路故障诊断准确率达99.41%,与其他模型相比,具有更好的特征提取效果和诊断速度。

基于DCM‑PCA和GA‑BP的逆变器故障诊断

针对光伏并网三相电压型逆变器开关管的开路故障,提出深度级联模型(deep cascade mode,DCM)‒主成分分析(principal component analysis,PCA)与遗传算法(genetic algorithm,GA)优化的BP神经网络结合的故障诊断方法。首先对逆变器的开路故障进行分析和仿真,确定三相电流作为故障信号,选择22类故障状态作为诊断对象,通过以稀疏表示分类(sparse representation based classififier,SRC)为基本操作单元的深度级联模型提取故障特征,DCM根据层次学习特性将故障特征分层,再由SRC部分得到不同故障的编码系数,并采用t分布—随机近邻嵌入(t⁃distributed stochastic neighbor embedding,t⁃SNE)方法验证了DCM具有较好的特征提取能力,通过PCA降低故障特征的冗余度、保留有价值的主成分提高网络映射能力,最后将故障特征向量作为GA⁃BP神经网络的输入信号实现对故障的诊断识别。通过仿真实验得到该方法的故障诊断准确率为95.64%,与DCM⁃PCA⁃BP、FFT⁃GA⁃BP和FFT⁃BP相比准确率分别提高8.71%、20.64%、51.70%,表明该方法有更好的故障特征提取能力和故障诊断效果。

面向残差评价的中点钳位型逆变器开路故障诊断方法

在基于解析模型的故障诊断系统中,为了显化残差信号所包含故障信息的能力,提出一种面向残差评价的中点钳位型三电平三相逆变器快速开路故障诊断方法。首先,构建诊断观测器获取三相电流观测值并通过观测矩阵计算电流残差;其次,通过引入基于范数的标准评价函数,计算残差性能指标与阈值,将残差转换为可用的特征信号并与阈值相比较实现高效实时的故障检测;再次,推导不同功率开关器件开路故障状态下的电流残差特性,并依据此特性实现精准的故障隔离;最后,在仿真平台及半实物实验平台上验证了该文所提算法的有效性与可行性。仿真与实验平台结果表明,相较于传统基于信号与知识的诊断方法,残差性能评价的引入使得诊断速度提高80%以上。针对NPC型三电平三相逆变器常见的四种开路故障情况,均可实现快速且精准的故障检测及定位。