A Three Valued Model of System Level Fault Diagnosis

We propose a three valued model of system level fault diagonsis,define a class of diagnosable systems,give a characterization of them,and study their optimal design.     

Adaptive Simulation Algorithm Based on Fuzzy Stiffness Recognition

Adaptive simulation algorithm is an effective and practical method for simulating stiff system,and the key to realize this algorithm is stiffness recognisation.This paper,based onthe previous recognizing methods,introduces fuzzy set theory in them to develop a more accurate approach which is successfully used in adaptive simulation algorithm.     

Analysis of the Modulation Phenomenon of Complex Vibration in Gearbox Fault Diagnosis

This paper presents a modulation phenomenon of complex vibration which occured when gear teeth broke or shaft seriously bent in gearbox. Based on the mechanism of gear vibration and modulation sideband,the peper analyzes this complex modulation phenomenon.     

The Three-Valued PMC Model Computer System Diagnosis Implemented by Artificial Neural Network

This paper systematically studied how to construct a neural network to realize the three-valued computer system diagnosis problems. Through a lot of simulation it seems effective to solve the computer system diagnosis problems with the help of network. Meanwhile the simulation also reveals the relations among capacity C, resistance R , gain Kand time.     

Sequential Diagnosis Algorithms in Asymmetric Models

We discuss the diagnosis algorithm for sequentially t-diagnosable systems.Wepresent two algorithms,based on the Malek and the BGM model,respectively,with a polynomialtime com pleAlty when the test graph is a bipartite groph.     

A Fault Location Algorithm for Transmission Lines in Circle Network

A fault location algorithm for transmission lines in circle network is presented.The algorithm uses local data. Its location accuracy is independent of power # flow, transient resistance and variation of remote system impedance. Simulation results are satisfactory.     

Fault Section Diagnosis Algorithm of Distribution Networks Based On Topology Identification

An algorithm of fault section diagnosis based on topology identification for distribution networks is presented. By decomposing the topologic matrix which describing the distribution network into two parts,one part only contain the complex coupling factor ,and the other ignore the complex coupling factor. Using this method, the fault zones in distribution network can be identified and isolated efficiently, and the vertexes of the zones can also be identified automatically. This approach adapts to the changefully network structures.     

A New Method of Diesel Engine Fuel System Fault Diagnosis

A method of diesel engine fuel system fault diagnosis based on wavelet transform and fuzzy C-means clustering is presented. Five characteristic parameters of reflecting fault state are distilled with wavelet transform of pressure wave of high-pressure oil pipe of diesel. The theory and generic approach of fuzzy C-means clustering algorithm (FCM) is given, and the validity of evaluating fuzzy clustering making use of partition coefficient, partition entropy and parting coefficient is pointed out. Identification of fault mode can be completed utilizing standard fault character modes established by FCM algorithm, and calculating and comparing the similarity degree between this standard mode and sample. The arithmetic is applied to all kinds of typical faults diagnose in the diesel engine fuel system. Measuring results indicate that the precision of fault diagnosis is increased with the analysis of wavelet and FCM.     

Study on the Method of Intelligence Fault Diagnosis System for Drill

It is very difficult to simulate the motion process of drill by accurate mathematics model for the complexity and invisibility of stratum. The fault of drill is usually identified and disposed by personal experience so far. This means it can not estimate the trend of the equipment running good or not and the reason conduced the fault or location and degree of fault by data measured. Farther, it can not give the expert suggestions. Based on the studying of drill fault, artificial intelligence and expert system have been used in the petroleum drilling engineering, the theory and method of fault diagnosis intelligence system for drill have been studied. It also constitutes the expert knowledge database of graphic Fuzzy Neural Network for the familiar fault of drill. The intelligence reasoning machine which consists of expert rule, Fuzzy logic and artificial Neural Network have been bring forward. And the fault diagnosis system it makes for drill can be applied in complex system which includes multi-variable, multi-parameter and multi-process.     

A Method for State Diagnosis of Grounding Grid

This paper discuses the method with which the corrosion of the grounding grid can be diagnosed .A grounding grid can handled as a circuit network. With the application of circuit network graph theory and the fault diagnosis theory of analog circuit and optimization, the fault diagnosis equations can be set up. This equations is figured out by Matlab, and the corrosion status of the grounding grid can be deduced from the result.     

Fault Diagnosis in Hydraulic Turbine Governor Based on BP Artificial Neural Network

The governing system of hydraulic turbine generator plays an important role in power system. It is significant to find out the faults of governing system and remove them quickly. This paper sets up a new fault diagnosis model of the hydraulic turbine generator governing system with the advanced ANN (artificial neural net). This 17-in-13-out model consists of three layers. It is proved that this model can find the fault accurately.     

A Multi-agent Fault Diagnosis System of Rotating Machinery Based on CBR

Recently,distributed intelligent systems based on multi-agent have been applied to many fields successfully.the multi-agent technique is introduced into the rotating machinery fault diagnosis system.With the combination of CBR technique,Basalstructure and development approach of the system are analyzed,and better cooperation among agents is realized.As a result,the system overcomes the limitation of single fault diagnosis method,and solves the contradictionbetween versatilityand adaptabilityof diagnosis software.Furthermore,a reference can be used for the research and development of multi-algorithmdiagnosis system of rotating machinery.The application in a factory's Networked Online Monitoring and Fault Diagnosis System for Turbine Fan shows that the system can diagnosefault rapidly and exactly.     

The Mathematical Model and Heuristic Algorithm of the Load Balance in the Parallel Processing System

Based on the algorithms proposed before,a model and new heuristic algorithmfor solving the load balance in a parallel processing system (cell) is put forward by authors in thispeper. The optimal goal of the propsed model benefits the minimum of the load of equipment withlargest load and the difference between and two equipments in the system. The complexity ofalogrithm is not higher than O(n2). The computational experiments show that it is a practical algorithmof engineering.     

Fault Diagnosis Expert System of Combustion Engine with Rough Set Theory

On the basis of fault diagnosis expert system, the rough set theory is introduced. Knowledge representation system table is taken as a major tool to reduce the rules of expert system in which unnecessary properties are eliminated. The redundancy of fault diagnosis information is revealed. The complexity of fault diagnosis expert system's structure is also reduced. The decision making rules are given finally.     

Orthogonal Back-Propagation Algorithm of Generalized Inverse of a Matrix

Calculating generalized inverse of a matrix is a basic algorithm for inverstigating linear equations and optimization problems. In this paper we investigate the algorithm of generalized inversion of a matrix by using Orthogonalized Back-Propagation Algorithm (OBPA). There is no problem for convergence in OBPA. It is shown how OBPA avoids some of the difficulties posed by the Back-Propagation(BP)algorithm.     

Knowledge Representation for Rotative Machine Fault Diagnosis Based on Semantic Net

Aiming at knowledge representation problem of expert system for rotary machinery fault diagnosis, semantic net knowledge representation is discussed. Semantic net to represent expert knowledge of rotary machinery fault diagnosis is explored. Its realizing method is afforded in computer language, in addition, demostrating model is also developed in Visual C++. The result shows good validity of the knowledge representation.