基于D-FNN的开关磁阻无位置传感器的研究

提出了一种基于扩展径向基函数(RBF)神经网络的动态模糊神经网络(D-FNN)的开关磁阻电机无位置传感器控制的新方法。动态模糊神经网络系统以在线采样的相绕组的电流和磁链为输入,以转子位置角度为输出,从而建立起电流和磁链、转子位置角度的非线性映射关系;训练完成后,用D-FNN输出结果取代位置传感器角度信号,实现电机无位置传感器运行。仿真和实验结果表明:由D-FNN获得的角度信号和由位置传感器获得的角度信号相比误差小,电机能够准确换相,且输出转矩波动小,转速曲线平滑,电机在无位置传感器下运行良好。     

一种开关磁阻电动机功率变换器故障诊断方法

针对现有开关磁阻电动机功率变换器故障诊断方法存在可靠性不高等问题,提出了一种新型的功率管故障诊断方法。该方法以不对称半桥型功率变换器主电路为研究对象,以常见的功率管开路和短路2种故障情况为诊断对象,通过比较母线电流估算值和实测值来判断故障,结合故障相绕组电流实现故障相的识别,必要时通过中断测试来确定故障点。选取电动机空载、低速度和高速度运行等较难实现故障诊断的工况进行了试验分析,结果表明,该方法均能完成故障类型的定性及故障点的准确定位。     

一类基于神经网络非线性观测器的鲁棒故障检测和诊断

利用神经网络的非线性建模能力，对一类具有建模不确定项的非线性系统提出一种基于观测器的故障检测和诊断的方法。设计的观测器不仅能实现故障检测，而旦应用神经网络设计的故障估计器能在线估计系统中的故障向量。通过分析验证了该方法对系统中的建模误差和外部扰动具有良好的鲁棒性。仿真结果表明所提出的方法是有效的。     

A Neural Network Appraoch to Fault Diagnosis in Analog Circuits

Thia paper presents a neural network based fault diagnosis approach for analog circuits,taking the tolerances of circuit elements into account.Specifically,a normalization rule of input information,a pseudo-fault domain border(PFDB)pattern selection method and a new output error function are proposed for training the backpropagation(BP) network to be a fault diagnoser.Experimental results demonstrate that the diagnoser performs as well as or better than any classical approaches in terms of accuracy,and provides at least an order-of-magnitude improvement in post-fault diagnostic speed.     

BLDC motor speed control system fault diagnosis based on LRGF neural network and adaptive lifting scheme

Brushless DC (BLDC) machines are found increasing use in applications that demand high and rugged performance. In some critical circumstance, such as aerospace, the motor must be highly reliable. In this context, a novel model-based fault diagnosis system is developed for brushless DC motor speed control system. Under the consideration of the complexity of characterizing the dynamic of BLDC motor control system with analytic expression, a LRGF neural network (LRGFNN) with pole assignment technique is carried out for modeling the system. During the diagnosis process, fault signal of the motor is isolated with LRGFNN online. Meanwhile, adaptive lifting scheme and adaptive threshold method are presented for detecting the faults from the isolated fault signal under the existence of mechanical error and electrical error. The effectiveness of the diagnosis system is demonstrated in the simulation of electrical and mechanical fault in the motor. The detection of the incipient fault is also given.     

Offline and online fault detection and diagnosis of induction motors using a hybrid soft computing model

In this paper, a hybrid soft computing model comprising the Fuzzy Min-Max (FMM) neural network and the Classification and Regression Tree (CART) for motor fault detection and diagnosis is described. Specifically, the hybrid model, known as FMM-CART, is used to detect and classify fault conditions of induction motors in both offline and online environments. A series of experiments is conducted, whereby the Motor Current Signature Analysis (MCSA) method is applied to form a database containing stator current signatures under different motor conditions. The signal harmonics from the power spectral density (PSD) are extracted, and used as the discriminative input features for fault classification with FMM-CART. Three main induction motor conditions, viz. broken rotor bars, stator winding faults, and unbalanced supply, are used to evaluate the effectiveness of FMM-CART. The results indicate that FMM-CART is able to detect motor faults in the early stage, in order to avoid further damage to the induction motor as well as the overall machine or system that uses the motor in its operations.     

基于概率超球集神经网络的发动机故障诊断

提出了一种用于发动机故障检测与诊断的概率超球集神经网络．神经网络用概率集表示发动机故障模式,概率集是由超球聚集形成的集合体,超球是由球心和半径确定．概率超球集神经网络能在两次循环中完成学习过程,并能不断融合新样本信息和精炼已存在的故障模式．YF-20发动机故障检测与诊断的仿真研究验证了概率超球集神经网络分类器的优越性能．     

Tool condition monitoring using reflectance of chip surface and neural network

A wide variety of tool condition monitoring techniques has been introduced in recent years. Among them, tool force monitoring, tool vibration monitoring and tool acoustics emission monitoring are the three most common indirect tool condition monitoring techniques. Using multiple intelligent sensors, these techniques are able to monitor tool condition with varying degrees of success. This paper presents a novel approach for the estimation of tool wear using the reflectance of cutting chip surface and a back propagation neural network. It postulates that the condition of a tool can be determined using the surface finish and color of a cutting chip. A series of experiments has been carried out. The experimental data obtained was used to train the back propagation neural network. Subsequently, the trained neural network was used to perform tool wear prediction. Results show that the prediction is in good agreement with the flank wear measured experimentally.     

On-line tool condition monitoring system with wavelet fuzzy neural network

In manufacturing systems such as flexible manufacturing systems (FMS), one of the most important issues is accurate detection of the tool conditions under given cutting conditions. An investigation is presented of a tool condition monitoring system (TCMS), which consists of a wavelet transform preprocessor for generating features from acoustic emission (AE) signals, followed by a high speed neural network with fuzzy inference for associating the preprocessor outputs with the appropriate decisions. A wavelet transform can decompose AE signals into different frequency bands in the time domain. The root mean square (RMS) values extracted from the decomposed signal for each frequency band were used as the monitoring feature. A fuzzy neural network (FNN) is proposed to describe the relationship between the tool conditions and the monitoring features; this requires less computation than a back propagation neural network (BPNN). The experimental results indicate the monitoring features have a low sensitivity to changes of the cutting conditions and FNN has a high monitoring success rate in a wide range of cutting conditions; TCMS with a wavelet fuzzy neural network is feasible.     

Tool condition monitoring in metal cutting: A neural network approach

This paper discusses the application of neural network-based pattern recognition techniques for monitoring the metal-cutting process. The specific application considered is in-process monitoring of the condition of the cutting tool. Tool condition monitoring is an important prerequisite for successful automation of the metal cutting process. In this paper, we demonstrate the application of supervised and unsupervised neural network paradigms to pattern recognition of sensor signal features. The supervised technique used is backpropagation and the unsupervised technique used is adaptive resonance theory (ART). The results support the premise that, despite excellent classification accuracy by both networks, the unsupervised system holds greater promise in a real world setting. The advantages are discussed and a framework for exploiting them in tool condition monitoring systems is presented.This work was completed as part of graduate research at University of California, Berkeley, Department of Mechanical Engineering.     

基于小波神经网络的齿轮箱故障诊断研究

论述了小波神经网络的系统结构及算法,并根据齿轮振动信号的频域变化特征,提取特征向量作为输入,利用小波神经网络建立特征向量与故障模式之间的映射关系,建立了基于该算法的齿轮故障诊断模型。仿真结果表明：与传统的BP神经网络相比,该模型显著缩短了训练时间。该小波神经网络进行机械故障诊断是有效的。     

Fault diagnosis of power electronic system based on fault gradation and neural network group

We propose a new fault diagnosis approach with fault gradation using BP (back-propagation) neural network group consisting of 3 sub BP neural networks. According to the hazard extents and the occurrence frequencies of different faults, the faults are divided into different grades. The higher the fault grade, the larger the number of the used sub neural networks is. Experimental results show that our approach makes the correctness rate of the fault diagnosis rise greatly (from less than 95.0% to 99.5%) and the performance of the whole fault diagnosis system gets much better especially for the on-line complex systems. The approach proposed in this paper also can be extended to other complex fault diagnosis systems, such as mechanical systems.     

一种改进的基于免疫网络模型(aiNet) 的故障诊断算法

根据抗体群与抗原群的匹配关系,提出一种改进的基于免疫网络模型(aiNet)的故障诊断算法.建立了自适应调整剪枝和抑制阈值的规则,并对K近邻算法的附加距离阈值加以限制,提高了基于aiNet故障诊断算法对已知故障的识别率,克服了其不能识别新故障的缺点.仿真结果表明,改进算法具有优良的故障诊断性能.     

基于改进BP网络算法的故障诊断分析

介绍BP神经网络结构和学习方法,针对误差反向传播神经网络模型学习收敛速度慢、容易陷入局部极小点等缺点,本文对BP网络模型进行了改进。对原始数据采用非线性的归一化函数,提出一种更加有效的学习率改进算法,提高了网络的收敛速度,采用了一种新的权值及阈值初始化方法,以避免训练时误差陷入局部极小解,并对改进BP算法与传统的BP算法进行比较,验证了该算法的优越性。     

基于LMD-PE与神经网络的刀具故障诊断方法

针对刀具故障诊断信号信噪比低、诊断结果不准确等问题,采用局域均值分解(LMD)结合排列熵(PE)来处理采集到的刀具加工时的振动信号,然后将提取到的特征向量输入到训练好的长短期记忆神经网络(LSTM)中得到诊断结果,为了提高LSTM的诊断效率,结合卷积神经网络(CNN)对LSTM进行了改造;试验表明,文章提出的方法诊断准确率比BP神经网络提高了将近12%,改进LSTM网络比传统LSTM的诊断时间缩短了50%。     

基于Java的发动机紧致型小波神经网络故障诊断

鉴于发动机是一种复杂的机电液一体化设备,其故障现象和原因之间存在复杂的非线性关联。本文结合小波变换的良好时频域特性和神经网络良好的非线性映射的优势,将MexicanHat小波基作为神经网络的传递函数,组建紧致型小波神经网络,用于发动机的故障诊断;本文以小波神经网络为算法基础,应用具有跨平台、可移植优点的Java语言和SQL Server2005数据库,开发出发动机智能故障诊断软件。     

基于神经网络技术的机器人并发故障自动诊断方法

为了提高柔性负载抓握机器人的故障检测能力,提出基于神经网络技术的机器人并发故障自动诊断方法.运用高分辨的智能传感器信息识别技术,结合刚度和强度等机械结构特征分析,构建柔性负载抓握机器人的故障信息采集模型,采用变刚度原理,提取柔性负载抓握机器人的振荡信息特征,通过谱特征检测和动态信息融合进行柔性负载抓握机器人的故障信息的...     

模糊神经网络变幅液压系统故障诊断

针对变幅液压系统复杂性、不确定性、模糊性的特点,提出基于故障树的模糊神经网络作为变幅液压系统故障诊断的方法。该方法利用故障树知识提取变幅液压系统故障诊断的输入变量和输出变量,引入模糊逻辑的概念,采用模糊隶属函数来描述这些故障的程度,利用Levenberg-Marquardt优化算法对神经网络进行训练,系统推理速度快,容错能力强,并通过实例分析验证了变幅液压系统模糊神经网络故障诊断的有效性。     

非线性电路的神经网络故障诊断方法

针对非线性动态电子电路,提出一种基于神经网络的故障诊断方法。通过故障字典的建立,对电路故障响应进行预处理后得到的故障特征作为神经网络的输入,然后利用神经网络对各种状态下的特征向量进行分类决策,对故障类别进行辨识,并对电路进行了可测性分析,从而实现非线性电路的故障诊断。详细的仿真过程及结果表明, 该方法有效地解决了非线性电路辨识难的问题,能较好地对故障模式进行分类,取得了满意的诊断效果。     

A bearing fault diagnosis method without fault data in new working condition combined dynamic model with deep learning

Bearing fault diagnosis plays an important role in rotating machinery equipment’s safe and stable operation. However, the fault sample collected from the equipment is seriously absent, which obstacles the establishment of the diagnostic model. In this paper, a novel false-real data synthesis method combined bearing dynamic model with a generated adversarial network is proposed to solve the problem of zero-shot in new condition. Firstly, the bearing dynamic model is constructed to simulate vibration data in different conditions. Secondly, the conversion model is trained by simulation data in different conditions, which will be employed to convert real-world data in the old condition into the conversion data in the new condition. Thirdly, the GAN model is trained by simulation data and real-world data in old condition and finetuned by simulation data and conversion data in the new condition. Finally, simulation data in the new condition are inputted to the finetuned GAN model to obtain generated data in the new condition, and the fault diagnosis model is trained by it. To validate the performance of the proposed method, various comparative experiments are carried out on one rolling bearing dataset. The results indicate that the proposed method can solve the problem of zero-shot in new condition with excellent diagnosis performance.