基于BP神经网络的测功机温度补偿方法设计  

Design of Temperature Compensation Method for Dynamometer Based on BP Neural Network

作　　者：张威 张力平[1] 周浩 Zhang Wei;Zhang Liping;Zhou Hao(Key Laboratory of Road Construction Technology and Equipment,Ministry of Education,Chang′an University,Xi′an 710064,China)

机构地区：[1]长安大学道路施工技术与设备教育部重点实验室,西安710064

出　　处：《机电工程技术》2021年第1期128-130,202,共4页Mechanical & Electrical Engineering Technology

摘　　要：永磁同步电机在运行过程中,由于温度变化会直接影响电机永磁体磁链的大小以及定子绕组阻值,从而导致电机的实际输出转矩发生波动。提出一种新的前馈温度补偿策略。在分析得到磁链和绕组阻值两者与温度之间的数学表达式的基础上,建立BP神经网络仿真模型,并将其与传统的矢量控制系统相结合。利用BP神经网络温度补偿器,设计了有效的温度补偿方案并进行仿真,搭建测功机台架对整个系统进行实物实验验证。仿真和实验结果均表明此温度补偿方法能够有效抑制温度变化对电机输出转矩的影响。During the operation of PMSM, as the temperature change will directly affect the size of the permanent magnet flux and the stator winding resistance,the actual output torque of the motor will fluctuate. A new feedforward temperature compensation strategy was proposed. Based on the analysis of the mathematical expression between the flux and winding resistance and the temperature, the BP neural network simulation model was established and combined with the traditional vector control system. By using BP neural network temperature compensator, an effective temperature compensation scheme was designed and simulated, and a dynamometer bench was built to verify the whole system. Simulation and experimental results show that the temperature compensation method can effectively suppress the influence of temperature change on the motor output torque.

关 键 词：PMSM PMSM温度补偿 BP神经网络 测功机 

分 类 号：TM351[电气工程—电机]