一种改进的神经网络机械故障诊断专家系统

针对传统BP神经网络训练中收敛速度较慢的缺点,提出一种基于L-M算法的神经网络应用于机械设备故障诊断的专家系统。论述了神经网络的专家系统结构,并以7216圆锥轴承试验研究为例,建立了基于该算法的故障诊断模型。仿真结果表明:该模型显著缩短了训练时间,具有较高的准确性。运用该神经网络专家系统进行机械故障诊断是有效的。     

Development of an expert system for fault diagnosis in scooter engine platform using fuzzy-logic inference

In the present study, a fault diagnosis system using acoustic emission with an adaptive order tracking technique and fuzzy-logic interference for a scooter platform is described. Order tracking of acoustic or vibration signal is a well-known technique that can be used for fault diagnosis of rotating machinery. Unfortunately, most of the conventional order-tracking methods are primarily based on Fourier analysis with the revolution of the machinery. Thus, the frequency smearing effect often arises in some critical conditions. In the present study, the order tracking problem is treated as the tracking of frequency-varying bandpass signals and the order amplitudes can be calculated with high resolution. The order amplitude figures are then used for creating the data bank in the proposed intelligent fault diagnosis system. A fuzzy-logic inference is proposed to develop the diagnostic rules of the data base in the present fault diagnosis system. The experimental works are carried to evaluate the effect of the proposed system for fault diagnosis in a scooter platform under various operation conditions. The experimental results indicated that the proposed expert system is effective for increasing accuracy in fault diagnosis of scooters.     

A hybrid fault diagnosis approach using neural networks

A hybrid fault diagnosis method is proposed in this paper which is based on the parity equations and neural networks. Analytical redundancy is employed by using parity equations. Neural networks then are used to maximise the signal- to- noise ratio of the residual and to isolate different faults. Effectiveness of the method is demonstrated by applying it to fault detection and isolation for a hydraulic test rig. Real data simulation shows that the sensitivity of the residual to the faults is maximised, whilst that to the unknown input is minimised. The simulated faults are successfully isolated by a bank of neural nets.     

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．     

基于神经网络专家系统的钻井事故诊断

结合石油钻井工程的实际情况,依据钻井过程的监测参数,设计了利用神经网络进行知识获取、专家系统进行事故诊断的钻井工程事故智能诊断系统。通过神经网络对钻井复杂问题实例的不断学习训练,获得用于智能诊断的知识,完成对事故发生可能性的初步诊断。经过专家系统的进一步启发式反向推理验证事故是否存在,给出最后确诊,以此监控钻井参数,指导钻井参数调整的实施。应用实例结果表明,该智能诊断系统应用于钻井事故诊断是有效的,对减少钻井事故的发生与发展具有重大的实际应用价值。     

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。     

基于小波神经网络的空调系统传感器故障诊断

详细阐述了小波神经网络(WNN)的原理、结构,并对传统的BP算法进行了改进。以空调系统传感器故障检测问题为目标,提出了基于WNN的故障诊断方法。通过采集天津博物馆中的传感器数据,对训练好的WNN进行了传感器故障诊断能力的验证,对温度传感器的1℃偏差故障、0.05℃/s速率漂移故障、完全故障、与不同方差下的精度等级下降故障进行了仿真,结果表明:这种方法对传感器故障具有很好的诊断效果。     

模糊神经网络抓斗纠偏系统故障诊断

针对抓斗纠偏系统复杂性、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抓斗纠偏系统故障诊断的方法。该方法利用故障树知识提取抓斗纠偏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抓斗纠偏系统模糊神经网络故障诊断的有效性。     

Identification of shaft orbit for hydraulic generator unit using chain code and probability neural network

Shaft orbit identification plays an important role in the hydraulic generator unit fault diagnosis. In this paper, a novel shaft orbit identification method based on chain code and probability neural network (PNN) is proposed. For this approach, firstly, a modified chain code histogram and shape numbers are used to represent the feature of the shaft orbit contour. It has properties of less data, easy to calculate, and invariance to rotation, scaling and translation. Then, the feature vectors are input to PNN to identify various kinds of shaft orbit for hydraulic generator unit. In comparison with previous methods, the experimental results show the proposed method is effective and training the network is faster, and identifying the shaft orbit achieves satisfactory accuracy.     

基于神经网络观测器的卫星姿态控制系统陀螺故障诊断

针对基于解析模型的卫星姿态控制系统陀螺故障诊断方法存在设计复杂、参数求解困难的问题,提出一种基于神经网络观测器的陀螺故障诊断方法。由系统内的冗余关系导出故障诊断逻辑,实现对陀螺故障的检测和隔离;同时利用先验模型知识和神经网络的非线性建模特性对陀螺故障进行估计。仿真结果表明,该方法能够实现对陀螺故障的检测、隔离和估计。     

An expert system for engine fault diagnosis: development and application

The mass production and wider use of automobiles and the incorporation of complex electronic technologies all indicate that the control of faults should be given an integral part of engine design and usage. Today, artificial intelligence (AI) technology is widely suggested for systematic diagnosis of faults where the amount of well-defined diagnosis knowledge is vast and the sequence of steps required to identify the fault is very long. This article describes on an expert system application for automotive engines. A new prototype named EXEDS (expert engine diagnosis system) has been developed using KnowledgePro, an expert system development tool, and run on a PC. The purpose of the prototype is to assist auto mechanics in fault diagnosis of engines by providing systematic and step-by-step analysis of failure symptoms and offering maintenance or service advice. The result of this development is expected to introduce a systematic and intelligent method in engine diagnosis and mai ntenance environments.     

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.     

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。     

AKSNet: A novel convolutional neural network with adaptive kernel width and sparse regularization for machinery fault diagnosis

Convolutional kernels have significant affections on feature learning of convolutional neural network (CNN). However, it is still a challenging problem to determine appropriate kernel width. Moreover, some features learned by convolutional layers are still redundant and noisy. Thus, adaptive selection of kernel width and feature selection of feature maps are key techniques to improve feature learning performance of CNNs. In this paper, a new deep neural network (DNN) model, adaptive kernel sparse network (AKSNet) is proposed to extract multi-scale fault features from one-dimensional (1-D) vibration signals. Firstly, an adaptive kernel selection method is developed, where multiple branches with different kernels are used to extract multi-scale features from vibration signals. Channel-wise attention is developed to fuse features generated by these kernels to obtain different informative scales. Secondly, a spatial attention is used for dynamic receptive field to focus on salient region of feature maps. Thirdly, a sparse regularization layer is embedded in the deep network to further filter noise and highlight impaction of the feature maps. Finally, two cases are adopted to verify effectiveness of AKSNet-based feature learning for bearing fault diagnosis. Experimental results show that AKSNet can effectively extract features from multi-channel vibration signals and then improves fault diagnosis performance of the classifier significantly. AKSNet shows better recognition performance in comparison with that of shallow neural networks and other typical DNNs.     

改进的ART2型神经网络在故障诊断中的应用

针对传统ART2型神经网络的缺点,提出了一种增强了网络执行速度的改进的ART2型神经网络。改进后的算法避免了传统ART2因输入次序不同而导致的输出结果不同的缺陷。应用了一种新的方法计算输入模式与所有模式的相似度。为了解决传统ART2型神经网络的模式漂移问题引入了激活深度的概念。改善了ATR2型神经网络的适用性。     

An artificial neural network for fault detection in the assembly of thread-forming screws

This paper presents a method, based on a two-layer dynamic Elman neural network, for detecting faults in the assembly of thread-forming screws. Using torque measurements, the method provides a high degree of reliability in detecting assembly faults. The ability of neural networks to learn and to generalize creates an efficient detection system when there is limited or distorted information available about the assembly process.     

互感器故障诊断人工神经网络法

基于神经网络的基本结构和算法，该文建立了一个用于高压电磁式互感器故障诊断的人工神经网络。其中采用了有效的网络学习算法，旨在全面、快速和准确地实现互感器故障诊断，以提高互感器及电力系统运行的可靠性。根据互感器的故障特征，该文建立一个3层前向神经网络，采用误差逆传播学习算法进行了讨论，并由仿真计算结果加以论证。     

基于贝叶斯网络的超速离心机故障诊断专家系统研究

研究了一种超速离心机故障诊断专家系统。系统采用人机对话方式,以专家知识库为基础,对离心机运转时的实时数据采样或者通过人工对界面输入故障征兆知识;采用贝叶斯网络方法进行推理,从而诊断出故障原因和各原因可能发生的概率。使维修更具针对性,实现智能化超速离心机故障诊断,提高了设备可靠性与安全性。     

基于卷积神经网络的滚动轴承故障诊断方法

为了简单、准确地进行轴承故障诊断,结合深度学习理论,对基于卷积神经网络的滚动轴承故障诊断方法进行了研究;首先,选用了结构相对简单的LeNet5卷积神经网络;然后,对轴承振动信号原始数据进行截取和归一化处理后直接生成生成二维矩阵作为神经网络输入;接着,优选卷积核大小、批大小、学习率及迭代次数等网络模型参数;最后,应用sigmoid函数进行多标签分类;实验结果表明,该方法能有效识别正常状态及不同损伤程度下的内圈、外圈、滚动体故障状态,识别准确率达到99.50%以上水平;基于卷积神经网络的滚动轴承故障诊断方法不仅在一定程度上可以简化故障诊断的过程,而且可以充分利用卷积神经网络模型的优势实现高效准确地故障诊断。     

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。