Papers by Keyword: Fault Diagnosis

Abstract: It is the hotpot to study the application of stochastic resonance (SR) in the field of mechanical fault diagnosis. The fault diagnosis system based on SR was developed, using “ARM+DSP” dual-core structure as hardware and embedded system as software, implemented signal acquisition, data storage, data analysis, waveform display and so on. The SR was adopted as characteristic quantity to analyze vibration signals for fault diagnosis. The experiment results showed that the function of portable fault diagnosis instrument is stable. It has veracity and validity.

Abstract: With the development of science technology in aerospace, automobile and ship, energy and military, the product parts space type face increasingly complex and surface quality requirements more stringent. So there are higher requirements to the digital manufacturing equipment to realize high speed and high precision machining. This paper summary the related research in condition monitoring, remote control, fault diagnosis and intelligent maintenance, and based on the lack of monitoring and diagnosis technology of whole life cycle, unperfected quality control technique, the lower intelligent level in the current equipment, it establish full range monitoring and the whole life cycle of the intelligent maintenance system and present fault diagnosis, control and maintenance solutions for the whole life cycle, and point out the new development direction of the integrated monitoring and intelligent maintenance in CNC equipment.

Abstract: Fault diagnosis of train bearing is an important method to ensure the security of railway. In the paper, four time domain statistical analysis methods and resonance demodulation method as a frequency domain analysis method are introduced. A state inspection and fault diagnosis system of train axel box bearing is constructed and its efficiency is also tested by wheel set experiment.

Abstract: Rough set theory is a useful tool for attribute reduction of fault diagnosis for rotating machinery, but cannot be efficiently used to sample increased areas. Aiming at the problem of incremental attribute reduction, a novel attribute reduction algorithm was put forward based on the binary resolution matrix for the two updating situations and the algorithm had a low space complex. Finally, with the fault diagnosis experiments of the bearing, the attribute reduction method was proved to be correct.

Abstract: Based on the analysis of the advantages and limits of the traditional fault tree and Bayesian network in fault diagnosis, the method that building the fault Bayesian network based on fault tree is proposed in this paper. The paper introduces the correspondences between elements of the fault tree and the fault Bayesian network, also describes the inference process of the junction tree algorithm in the fault Bayesian network. Then with the foundation brake rigging system of CRH380AL EMU as an example, we build up the fault tree, complete its transmission to the fault Bayesian network, proving the superiority of the fault Bayesian tree in fault analysis of the complex system at last.

Abstract: Stator current signal of driving motor can be easily measured. Using it in the gearbox fault diagnosis system is inexpensive and suitable for remote monitoring. According to the application of the Motor Current Signal Analysis in machinery fault detection, we present a new gearbox fault diagnosis system. In modern signal processing technology, Stochastic Resonance theory is widely used to improve SNR (signal to noise ratio). Dynamic time warping algorithm is a simple and efficient way of the pattern identified. Combine the Stochastic Resonance theory and dynamic time warping algorithm as the basic theory of fault diagnosis. To realize the development of fault diagnosis software, we use the mixed-programming of MATLAB algorithms library and VC++.

Abstract: With the development of Internet industry, equipment data is increasing. The traditional method is not suitable for processing large data. Aiming at inefficient problem of Apriori algorithm when mining very large database, an efficient parallel association rules mining algorithm (Advanced Pruning Parallel Apriori Algorithm) based on a cluster is presented. APPAA algorithm can enhance the mining efficiency, as well as the system’s extension. Experimental results show that APPAA algorithm cuts down 85% mining time of Apriori, and it has good characteristics of parallel and expandable.so it is suitable for mining very large size database of fault diagnosis.

Abstract: For composite fault is difficult to diagnose, the characteristics of the large amount of data. This paper presents a method of The Prediction method of Composite Fault Based on data driven to establish intelligence unit Based on a collection of virtual individuals associated with the virtual failure associated collection and virtual behavior associated collection. Composite fault warning engine modeling is proposed, and give the warning value of composite fault finally. This method is fully assessing the future "dominant state" on the basis of the fully aware of current "hidden state". The impact of factors such as disturbance of hidden failures on composite fault prediction are fully considered, to some extent, the long-span composite failure prediction problem is solved, and the experiments show that the method effectively increases the accuracy of composite fault prediction.

Abstract: Complex equipment is mainly used in important areas of national defense, health care, banking, etc. Consequences of failure are relatively severe, while the hidden failures are contained in the most complex devices as the process is running. Hidden failures in the normal operation of the device is difficult to find, and only under certain conditions will be triggered, while other faults may be led. The stability of the running system will be undermined. In order to monitor the occurrence and development of hidden failure of complex equipment, a hidden failure warning model based on data mining has been put forward, and the theory of the model has been analyzed, the selection gist of the model parameters has been given. The result shows that the accuracy of hidden failure impact value forecast by the model is 93.33%, the impact degree of the hidden failure effect on the dominant failure can be effectively monitored, and the model makes a good preventative effect against the sudden failure caused by the hidden failure.

Abstract: Fault state is central to the achievement of equipment operation stability and security. On the basis of the analysis of the general process, basic characteristics and evolution of rolling bearing fault formation, according to the uncertainty of rolling bearing fault generation mechanism, highly nonlinear of fault evolution and diversity of fault modes, establishing a rolling bearing fault evolution model based on vibration time domain parameters.