Fault Detection Method For The Hybrid Machine Tool And Accuracy Of Fault-tolerant Technology

Fault tolerance and fault rectification technologies are effective approaches for enhancing reliability and safety as well as precision of electro-mechanical products(EMPs). Fault detection and isolation methodology and precision fault tolerance technology are taken as the main clue. Based on theories, methodologies and techniques such as immune neural networks and system identification technologies, Fault detection and isolation methodology and precision fault tolerance technology for hybrid machine tool are studied deeply and systemly in this paper.A fault detection approach based on radial basis function neural network(RBFNN) is presented in this paper, this approach consists of system identification, filtered residual generation and fault alarm concentration(FAC). The system identification is based on immune strategy RBFNN, and the residuals are generated by on-line comparing the system model outputs with the actual system outputs. The generalization capability of immune strategy RBFNN is enhanced by introducing generalization capability interfering factor in the affinity function of the clone selection algorithm. The proposed immune model-based fault detection approach is only sensitive to the residuals caused by faults because of the introduction of residual filtering and FAC. Simulations on a hybrid machine tool(HMT) were conducted to evaluate and validate the effectiveness and robustness of above fault detection approach, simulation results show that it can detect and locate actuator faults and sensor faults efficiently, and it is sensitive to faults while at the same time insensitive to unspecified uncertainties.To reduce the position and orientation error caused by clearance of spherical joint in HMTs, a direct error compensation interpolation algorithm is presented in this paper, this algorithm compensates the position and orientation error of the moving platform in the process of rough interpolation, it enhances the precision of HMTs effectively. The error compensation model for spherical joint clearance of HMTs is derived, problems of solving contact angle of spherical joints are also discuessed.A QNX embedded real-time operating system based fault detecter for HMTs is designed in this paper. Transplant technology of QNX real-time operating system for ARM hardware desktop is studied, software algorithm of neural network fault detecter is implementated utilizing embedded Matlab tool in QNX environment. Experiment desktop and experiment step are also planned for above fault detecterThe Fault detection and isolation methodology and precision fault tolerance technology presented in this paper will provide some effective theories, methodologies and techniques for the fault tolerance and fault rectification control of HMTs.