Study of smart active fault tolerant control algorithm based onneural network for structural vibration control
LEI Yong-qin1,2,DU Yong-feng1,2
1.Northwest Center for Disaster Mitigation in Civil Engineering, Ministry of Education, Lanzhou. 730050, China2.Institute of Earthquake Protection and Disaster Mitigation, Lanzhou Univ. of Tech., Lanzhou. 730050, China
For the sensors failure of vibration control system in the huge engineering structure, the methods of dynamic characteristic identification and sensor failure detection of control system are proposed based on multi-channel RBF neural network, then the smart active fault tolerant control algorithm is presented for the huge engineering structure. The mutual interference of normal sensor and failure sensor in the process of sensor failure detection is solved by separating the sensor feedback signals as multi-channel signal to dynamic characteristic identification. When sensors are work normally, the controller calculates the control force according to the preset control algorithm. When any sensor fails, the control system will get rid of the failure sensor signal automatically and controller will switch to the control algorithm which considers this sensor failure. The effectiveness and superiority of sensor failure detection strategy and smart active fault control algorithm based on multi-channel RBF neural network presented by author are proved by the simulation of Benchmark model controlled by AMD under earthquake.
雷永勤;杜永峰;. 基于神经网络的结构振动智能主动容错控制算法研究[J]. , 2014, 33(13): 117-122.
LEI Yong-qin;DU Yong-feng;. Study of smart active fault tolerant control algorithm based onneural network for structural vibration control. , 2014, 33(13): 117-122.