基于改进PSO-LSSVM的轴类校直机校直行程预测  

Prediction of Straightening Stroke of Shaft Straightening Machine Based on Improved PSO-LSSVM

作　　者：郝建军 陈家栋 王梦帆 周娣 HAO Jianjun;CHEN Jiadong;WANG Mengfan;ZHOU Di(College of Mechanical Engineering,Chongqing University of Technology,Chongqing 400054,China)

机构地区：[1]重庆理工大学机械工程学院,重庆400054

出　　处：《重庆理工大学学报（自然科学）》2020年第4期87-94,共8页Journal of Chongqing University of Technology：Natural Science

基　　金：重庆市高校优秀成果转化资助项目(KJZH17127)。

摘　　要：传统的轴类校直通过人工操作设备和借助辅助设备的测量进行校直行程的计算。这种计算方法耗费人力,效率低下,同时也无法满足设备智能化的要求。为此,提出一种改进型的PSO-LSSVM(基于粒子群优化的最小二乘支持向量机)算法模型应用到校直行程的预测过程中。首先通过分析提取影响校直行程的相关因素,然后将这些影响因素与成功校直数据作为算法模型的输入样本进行训练,得到一个能可靠预测校直行程的PSO-LSSVM模型。通过对测试样本的数据分析,预测值与期望值的相对误差可以达到3. 14%。结果表明:此模型可以满足校直设备的校直行程计算,进而提高校直效率与校直自动化。Traditional shaft straightening stroke is calculated by manual operation and measurement of auxiliary equipment. This calculation method is labor-intensive and inefficient,and cannot meet the requirements of intelligent equipment. Therefore,an improved PSO-LSSVM( The least square support vector machine based on particle swarm optimization) algorithm model is proposed to be applied to the prediction process of straightening stroke. Firstly,by analyzing and extracting the relevant factors affecting the straightening stroke,and then training these factors and the successful alignment data as the input samples of the algorithm model,a PSO-LSSVM model that can reliably predict the alignment stroke is obtained. Through the data analysis of the test sample,the relative error between the predicted value and the expected value can reach 3. 14%. The results show that this model can satisfy the straightening stroke calculation of straightening equipment,and thus improve the straightening efficiency and automation.

关 键 词：校直行程预测 轴类校直 最小二乘支持向量机 粒子群优化 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TP273[自动化与计算机技术—控制科学与工程]