镁合金体育器材表面磨损量精准预测方法  

Precise Prediction Method for Surface Wear of Magnesium Alloy Sports Equipment

作　　者：王浩[1] 石晓峰[2] WANG Hao;SHI Xiao-feng(Department of Physical Education,Jinzhong University,Shanxi Jinzhong 030600,China;Shanxi University,School of Physical Education,Shanxi Taiyuan 030006,China)

机构地区：[1]晋中学院体育系,山西晋中030600 [2]山西大学体育学院,山西太原030006

出　　处：《机械设计与制造》2022年第10期165-168,173,共5页Machinery Design & Manufacture

基　　金：山西省“1331工程”重点创新团队建设计划(1331KIRT)。

摘　　要：由于当前方法没有使用最小二乘支持向量机(LS-SVM)对磨损量进行预测,导致预测结果准确性和预测速率偏低,预测费用过高。本文提出一种镁合金体育器材表面磨损量精准预测方法,分析镁合金体育器材表面的使用次数和磨损量之间的关系,设定振动信号为监测信号,通过小波包提取不同磨损状态下振动信号的频段能量,同时对其进行归一化处理。将提取的频段特征值和观测值两者相结合,组建镁合金体育器材表面磨损量精准预测模型。使用LS-SVM对模型进行自动参数寻优,获取最终的预测结果。仿真实验结果表明,所提方法能够有效降低预测费用,同时提升预测结果的准确性和预测速率。Since the current method does not use least squares support vector machine(LS-SVM)to predict the amount of wear,the accuracy of the prediction results and the prediction rate are low,and the prediction cost is too high.This paper proposes an accurate prediction method for the surface wear of magnesium alloy sports equipment,analyzes the relationship between the number of times of use and wear on the surface of magnesium alloy sports equipment,sets the vibration signal as the monitoring signal,and extracts the vibration signal under different wear conditions through wavelet packets.The energy of the frequency band is normalized at the same time.Combine the extracted characteristic values of frequency bands and observations to form an accurate prediction model for the surface wear of magnesium alloy sports equipment.Use LS-SVM to automatically optimize the parameters of the model to obtain the final prediction results.The results of simulation experiments show that the proposed method can effectively reduce the forecasting cost,and at the same time improve the accuracy of the forecasting results and the forecasting rate.

关 键 词：镁合金 体育器材 表面磨损量 精准预测 

分 类 号：TH16[机械工程—机械制造及自动化] TP391[自动化与计算机技术—计算机应用技术]