基于改进的反向传播神经网络的地下铲运机自动换挡控制策略研究

Research on control Strategy of automatic shift of Scraper based on improved Back Propagation Neuron Network

针对地下铲运机工作时,载荷频繁变化、传动系统工作效率低、换挡频繁以及操作者劳动强度大的问题,结合地下铲运机的工作特点,提出了基于改进的反向传播神经网络的地下铲运机节能换挡控制策略,并在此基础上建立了神经网络模型和传动系统的仿真模型,进行了网络训练和计算机仿真。仿真结果表明,基于改进的反向传播神经网络的自动换挡控制系统,能够根据工况实时改变变速箱的挡位,以保证液力变矩器工作在高效区域。

When scraper worked,load frequent variation,efficiency of transmission system is low,shift gear is frequent,and the labour intensity of worker is high.Aiming at the working condition of scraper,a 4-paremeter shift strategy based on improved-back-propagation neuron network for saving energy is presented.The model of neuron network and transmission system is set up in the basis;the network training and simulation are carried out.The simulation results show that the controller can change the gear in real time according to the present working condition,so that the hydraulic torque converter works in an efficient range.