Research On TBM Condition Monitoring Management Systems

Machinery and equipment condition monitoring and fault diagnosis technology is an effective way to improve equipment safety and reduce accident losses, reduce maintenance costs, and improving economic efficiency. Therefore, making full use of the technology in production can reduce the occurrence of unexpected equipment failures and maintenance costs, and bring enormous economic benefits to the enterprise. Doing a good job in condition monitoring and fault diagnosis is great significance to improve the safety of equipment operation, extend equipment’s life, protect the security、stability、production、reduce maintenance costs and increase economic efficiency.With the number of railway, water conservancy projects, tunnel construction and subway construction projects increasing, TBM applications become more widely used. TBM equipment is a collection of machinery, electrical and fluid. Its work is intensity,and it has high degree of efficiency production and automation. Its construction process is a chain, so damage of a system component may result in shutdown paralysis of the entire device, thus may affect the normal construction progress, and even lead to accidents.Implementation condition monitoring in the TBM, and carrying out effective maintenance when failure is in the bud can not only make full use the equipment’s potential, but also avoid accidents.This paper first outlines the domestic and international research profiles and related techniques of TBM and other equipments’ condition monitoring management system. By studying and contrasting, the paper proposes a LabVIEW-based TBM condition monitoring scheme and a wavelet packet-BP neural network-based TBM fault diagnosis scheme. And use LabVIEW’s remote communication module to transmission the obtained data to the off-site experts to serve TBM fault diagnosis.The contents of this thesis include the following sections:(1)Analyzed the particularity of the TBM work environment and the superiority of virtual instrument for condition monitoring, and built a virtual instrument-based TBM condition monitoring systems. And selected the hardwares whose are in connection with the TBM.(2) Proposed conditioning regimen like signal filtering, because the TBM institutions is large, and it is easy for the components to affect each other in the construction process. Proposed TBM initial judgment based on the autocorrelation and FFT transform. Proposed the extraction method of certainty feature vectors, namely the energy feature vector based on wavelet packet transform, and verified the applicability of this approach.(3) Studied the advantages and disadvantages of existing several fault diagnosis, a combination of wavelet packet transform and BP neural network diagnostic methods of Fault Diagnosis was proposed. In the process of applying this method, the second study to influent the coefficient weighting method to adjust the weights of the neural network method was used, and the necessity and advantages of this study again was proved.(4) Built a TBM condition monitoring and fault diagnosis system using Lab VIEW and Matlab software.And shared the system online by using the web publishing tool. The correctness of the theory and technical feasibility were validated by the results of the operation of the system.