Aiming at the problem of large positioning accuracy error of the existing photoelectric encoder of biological centrifuge based on PID,an improved BP neural network error compensation method for automatic positioning control of biological centrifuge is proposed by using artificial fish swarm algorithm to optimize the initial weight and threshold of BP neural network,and using the im-proved BP neural network to compensate the error.The simulation results show that the proposed method can effectively compensate the error of the photoelectric encoder of the biological centrifuge and improve the automatic positioning accuracy of the centrifuge.Af-ter error compensation,the maximum error is 0.039 °,the minimum error is-0.013 5 °,the average error is 4.86",and the stand-ard deviation is 0.32.Compared with before error compensation,the overall accuracy is improved by 3.34 times,which is effective.
关键词
生物离心机/自动定位/BP神经网络/人工鱼群算法/误差补偿
Key words
biological centrifuge/automatic positioning/BP neural network/artificial fish swarm algorithm/error compensation
维普
万方数据