全断面掘进机健康管理系统的建模与仿真

System modeling and simulation for health management of tunnel boring machine

为降低隧道施工过程中的安全隐患,针对全断面掘进机庞杂系统之间的相互影响,易导致停机检查等健康管理问题,构建了基于虚拟仪器的状态监测与基于神经网络的故障诊断系统结构模型.建立了基于灰色预测和神经网络相结合的状态监测算法,以提前预知设备的健康状况.提出了基于小波包算法的能量特征向量的提取和最快速下降BP学习算法,进行故障诊断.最后,构建了基于面向服务架构(SOA)的全断面掘进机(TBM)健康管理系统,并通过历史数据仿真结果验证了方法的正确性和技术的可行性.

For reducing the safety hazards,in view of the health management problems of the large and complex system,the interaction among components easily caused to stop check for tunnel boring machine (TBM),a condition monitoring and fault diagnosis system structure model for TBM was built based on virtual instrument and neural network.A state monitoring algorithm based on grey prediction and neural network was established to predict the working state of the equipment in advance.The algorithm based on wavelet packet energy eigenvector extraction and the most rapid decline in the BP learning algorithm to act fault diagnosis.Finally,the health management system service-oriented based on SOA was constructed,and through the historical data,the validity of the method and the feasibility of the technology were verified by the simulation results.