Papers by Keyword: Fault Diagnosis

Abstract: The health of MOVA is very important for power system reliability and insulation coordination studies.MOVA is subjected to different kinds of stresses in services, which will cause degradation at early stage or in the long run.This paper present evidence theory for fault diagnosis of MOVA. Evidence theory can simultaneously analyze information from different sources,draw comprehensive conclusions,reduce single information misjudgment. In this paper, resistive leakage current and infrared imaging make up two types of evidence body for judge. Analysis of experimental data shows that this method can effectively detect early fault of the MOVA.

Abstract: A new rolling bearing fault diagnosis approach is proposed. The original vibration signal is purified using the second generation wavelet denoising. The purified signal is further decomposed by an improved ensemble empirical mode decomposition (EEMD) method. A new selection criterion, including correlation analysis and the first two intrinsic mode functions (IMFs) with the maximum energy, is put forward to eliminate the pseudo low-frequency components. Experimental investigation show that the rolling bearing fault features can be effectively extracted.

Abstract: The intelligent condition monitoring and diagnosis technology has become a hot spot of the research on fault diagnosis. The research, which is on the diagnostic method based on artificial intelligence and its application in fault diagnosis of Turbogenerator, has important social significance and is full of economic value. Introduce the development status of intelligent fault diagnosis technology of turbine. Focus on fault diagnosis technology based on neural network integration with experiment research, analysis and summary. Finally, point out a number of issues and trends of the further study in this area.

Abstract: BP neural network and evidence theory data fusion technology can be used in troubleshooting electronic equipment, from the simulation results show that the fault diagnosis method based on evidence theory and BP neural network can effectively diagnose faults in analog circuit, and it has automated intelligent characteristics.

Abstract: With the satellite development of our country, higher accuracy and stability are requires, which makes the control systems becoming more complex and requiring more telemetry parameters. Data mining techniques do not consider the physical relationship between the various components, but use of satellite telemetry parameters of the satellite states the purpose of fault identification. In this paper, we give a model based on multiple support vector machines (MM-SVM) technology satellite fault diagnosis method. The experiment shows that our method is effective in satellite equipment fault diagnosis

Abstract: The failure of hydraulic pump as a power unit in hydraulic systems affects directly the proper performance of the systems. Therefore, the monitoring of the pump performance and diagnosis of pump faults are urgent problems in want of solution. The principle of RBF algorithm is described. Study on fault diagnosis based on RBF for hydraulic pump. The test and analysis results indicate that the method is simple and efficient.

Abstract: A new power system fault diagnosis model is proposed in this paper and it will be used in the UNIX platform. It includes the Petri net system's structure, software service and hardware integration method. Though technology of Petri net is quite successful, its application to power system fault diagnosis is deficient. According to the UNIX platform, a new power system fault diagnosis model is designed and it takes an example to explain how to use its high performance computing method (or parallel computing method) and UNIX environment to design a new intelligent algorithm with information fusion and multi-data resources in power system fault diagnosis.

Abstract: The fault diagnosis of vehicle power system that the structure and characteristics of components are complex, each module and internal modules exist coupling, cross-linked mutual relations and the uncertainties, the system status and working conditions are difficult to describe by precisely mathematical model, and test cost expensive, less fault samples. Thus its fault diagnosis is the decision problem of uncertain information in a small sample. it is proposed that combining multi-signal flow graph model with Bayesian network fault diagnosis method. The fault diagnosis model of power system and the corresponding Bayesian network structure are built, which achieve the fault diagnosis of power system, Diagnosis example shows that the method of the vehicle power has a higher failure troubleshooting capabilities of the system single and multiple faults.

Abstract: The maintenance efficiency of Chinese railway turnout is closely related to the accuracy of its fault diagnosis method. A proper method will provide great help to railway staff in maintaining turnouts. The research introduced in this paper built a model based on Support Vector Machine (SVM) and Grid Search and later than tested its effect with the data from experiments. Result of that test shows that the method can achieve a diagnosis accuracy as high as 98.33%.

Abstract: The wind turbine remote monitoring and fault diagnosis is the key of improving unit efficiency, reducing maintenance costs, and ensuring safe and stable operation of the wind farms. A wide variety of wind farm monitoring systems, non-uniform communication standards, and heterogeneous communication platforms is result in a difficulty of information exchange. In this paper, on the basis of following IEC61400-25 standard, we put forward using XML technology to encapsulate data to avoid the formation of the "information island" in wind farms; By combining with VC++ Socket technology to establish a network communication system, this paper solves the data exchange problem of the wind turbine remote monitoring and fault diagnosis system through achievement of data receiving and dispatching; In the end, we use the waveform curve way to display the XML parsing of data, which is convenient for staff to observe and analyze the data.