论文部分内容阅读
为实现弹药传输机械臂中不可测参数的辨识,建立了机械臂的虚拟样机,并将其作为样本数据的来源;考虑到样本数据的连续性和平滑特性,使用函数型数据分析和函数型主成分分析对样本数据进行了特征提取,并利用提取的特征参数和待辨识参数作为训练样本对极限学习机(ELM)进行了训练.为提高极限学习机的辨识精度和泛化能力,利用粒子群算法对极限学习机的输入层与隐含层的连接权值和隐含层节点的阈值进行了优化.最后,分别利用仿真数据与测试数据对此方法进行了验证,仿真数据的辨识结果表明,优化后的极限学习机具有更高的辨识精度和泛化能力;同时,通过对比将测试数据的辨识结果代入模型中进行仿真得到的支臂角速度与测试角速度,验证了此方法的可行性和有效性.
In order to realize the identification of the unmeasurable parameters in the ammunition transmission arm, a virtual prototype of the arm is established and used as the source of the sample data. Considering the continuity and smoothness of the sample data, The component analysis was used to extract the features of the sample data and the ELM was trained by using the extracted parameters and parameters to be identified as training samples.In order to improve the recognition accuracy and generalization ability of the extreme learning machine, The algorithm optimizes the connection weight of the input layer and the hidden layer and the threshold of the hidden layer node of the ultimate learning machine.Finally, this method is verified by the simulation data and the test data respectively, and the identification results of the simulation data show that, The optimized extreme learning machine has higher recognition accuracy and generalization ability. At the same time, by comparing the results of the test data into the model to simulate the arm angular velocity and the test angular velocity, it proves the feasibility and effectiveness of this method. Sex.