|
In this paper we try to creat a method to diagnose and recognize the fault in ahydraulic system in accordance with different technical requirements and featuresof the system.The method is implemented by means of extracting fault informationfrom pressure ripple,utilizing the autoregressive model parameters as the fault feature,and then using pattern recognition to classify what a fault pattern is existing.We have completed experimental study on the fault diagnosis of a pump system.The principle of this method... In this paper we try to creat a method to diagnose and recognize the fault in ahydraulic system in accordance with different technical requirements and featuresof the system.The method is implemented by means of extracting fault informationfrom pressure ripple,utilizing the autoregressive model parameters as the fault feature,and then using pattern recognition to classify what a fault pattern is existing.We have completed experimental study on the fault diagnosis of a pump system.The principle of this method is correct and the method is quite practical. 本文根据不同级别的故障诊断技术要求和液压系统特点,从压力脉动信号中提取故障信息,采用自回归模型参数作故障特征、用模式识别技术对系统各种状态进行分类,形成一种液压系统故障识别与诊断的方法。在泵源系统故障诊断试验研究中,采用三种分类方法,对不同传感器位置、不同模型阶次和样本容量时的确诊率、漏警率和虚警率作了比较。诊断方法原理正确,效果良好,具有很好的应用前景。 On the protection of formation from damage, the most importunt measure is to prevent it before the damage occuring, and to decide the ideas of proventing and controlling formation form damage.By making the simulation and emulation researches, we studied the identification and diagnesis of formation damages with the methods of neural network, as well as developed the computer software system IEDPTFD (Identification, Evaluation, Diagnosis, Precaution, and Treatment of Formation Damage) for formation protection.... On the protection of formation from damage, the most importunt measure is to prevent it before the damage occuring, and to decide the ideas of proventing and controlling formation form damage.By making the simulation and emulation researches, we studied the identification and diagnesis of formation damages with the methods of neural network, as well as developed the computer software system IEDPTFD (Identification, Evaluation, Diagnosis, Precaution, and Treatment of Formation Damage) for formation protection. It consists of five subsystems and their knowledge bases, a main control module, a knowledge acquisition medule, an explanation module (interpretor) and a man-machine interview module.Indentification, evaluation, diagnosis, precaution and treatment of formation damages is a systematical engineering. A set of mating protection technologies of formation from damage has been established. Application of these technologies has abtained gtal economical and social benefitial results 保护储集层应以预防和控制为主,以确立预防与控制措施为主要思路。由此进行了模拟、仿真研究,运用神经网络方法研究了储层伤害的识别与诊断。建立了保护储层的计算机软件系统,它由储层伤害的识别、评价、诊断、预防、处理5个子系统,以及各子系统的知识库、系统总控、知识获取、解释器、用户接口等模块组成。储层损害的诊断、预防、控制与处理是个系统工程,已形成配套技术,它的应用已取得十分明显的经济效益和社会效益。 In order to automatically recognize and diagnose the fault patterns of electrical machines, a pattern recogition method by using an artificial neural network is developed based on the analysis of both the classification characteristics of artificial neural networks and the traditional technology of fault diagnosis of electrical machines. For cases that the fault patterns are nonlinear separable, a radial basis function (RBF) network is adopted as by using a φ function a nonlinear separable pattern can... In order to automatically recognize and diagnose the fault patterns of electrical machines, a pattern recogition method by using an artificial neural network is developed based on the analysis of both the classification characteristics of artificial neural networks and the traditional technology of fault diagnosis of electrical machines. For cases that the fault patterns are nonlinear separable, a radial basis function (RBF) network is adopted as by using a φ function a nonlinear separable pattern can be transformed into a linear one, and achieve classification. Test results on the rotor faults of induction motor show that this fault pattern recognition method by using the RBF network can not only be effective, but also improve the average probability of correct classification by a supervised selection of centers of the RBF network. 为了实现对电机故障模式的自动识别与诊断,通过对人工神经网络分类功能及传统电机故障诊断技术的分析,提出了一种利用人工神经网络进行模式识别的方法。针对电机故障特征在实际中可能是非线性可分的情况,利用φ函数可以将非线性可分的模式转化到线性空间并实现分类,基于这种思想提出了利用径向基函数(RBF)网络实现对这种复杂故障模式的分类。以感应电机转子故障分类的实验结果表明,这种神经网络模式识别方法是有效的,并且可以通过自动调节径向基函数中心提高网络分类的正确率。
|