| 人工鱼群神经网络速度辨识器及应用 |
| |
| 引用本文： | 曹承志,毛春雷.人工鱼群神经网络速度辨识器及应用[J].计算机仿真,2008,25(10). |
| |
| 作者姓名： | 曹承志 毛春雷 |
| |
| 作者单位： | 沈阳工业大学信息科学与工程学院,辽宁,沈阳,110023 |
| |
| 基金项目： | 辽宁省自然科学基金，教育部春晖计划合作科研项目，辽宁省教育厅高校科研项项目 |
| |
| 摘 要： | 为实现无速度传感器直接转矩控制,有时采用神经网络转速辨识器,但前馈神经网络结构难以确定,运用BP算法时又极易陷入局部解.将人工鱼群算法和BP算法结合,采用人工鱼群算法优化神经网络的结构及网络初始权值,再利用BP算法对网络权值进行精确调节;将人工鱼群算法与BP算法相结合的AFSA BP算法,实现了人工鱼群算法的全局搜索能力与BP算法的局部寻优性能的互补结合.将所设计的神经网络转速辨识器运用到直接转矩控制系统当中.利用MAT-LAB/SIMULINk实现无速度传感器控制系统的仿真实验结果表明,该算法具有良好辨识效果.
|
| 关 键 词： | 神经网络 人工鱼群算法 直接转矩控制系统 |
Artificial Fish BP Neural Network Speed Identifier and Its Application |
| |
| CAO Cheng-zhi,MAO Chun-lei.Artificial Fish BP Neural Network Speed Identifier and Its Application[J].Computer Simulation,2008,25(10). |
| |
| Authors: | CAO Cheng-zhi MAO Chun-lei |
| |
| Affiliation: | CAO Cheng-zhi,MAO Chun-lei(Shenyang University of Technology,Shenyang Liaoning 110023,China) |
| |
| Abstract: | To achieve speed-sensorless direct torque control (DTC) system, Neural Network (NN) was applied to design speed identifier. But, feed forward network is difficult to confirm the structure and BP algorithm is easy to plunge into local solution. Artificial Fish School Algorithm(AFSA) of mixed coding was used to optimize the structure and initial values, and then BP algorithm adjusted weight accurately. This algorithm combined AFSA with BP, which is called AFSA+BP algorithm and it realized the combination of A... |
| |
| Keywords: | Artificial fish school algorithm Neural network (NN) Direct torque control( DTC) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
