基于PCA-SVM油压状态识别的液压扳手判停方法研究  

Research on Judging and Stopping Method Based on PCA-SVM to Identify Oil Pressure State of Hydraulic Wrench

作　　者：张伟 杨其华 刘钢海 ZHANG Wei;YANG Qihua;LIU Ganghai(College of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou Zhejiang 310018,China;College of Quality and Safety Engineering,China Jiliang University,Hangzhou Zhejiang 310018,China)

机构地区：[1]中国计量大学机电工程学院,浙江杭州310018 [2]中国计量大学质量与安全工程学院,浙江杭州310018

出　　处：《机床与液压》2023年第5期111-116,共6页Machine Tool & Hydraulics

摘　　要：为了提高泵站驱动液压扳手作业的工作效率及实现扳手的自动判停,分析泵站输出油压、扳手活塞位移、螺栓扭矩随时间变化的对应关系,提出一种基于PCA-SVM油压状态识别的液压扳手判停方法,通过主成分分析(PCA)提取不同油压状态下的特征参量,作为支持向量机(SVM)的输入,完成对油压阶段的准确识别,间接实现对泵站做功状态的识别。通过缩短泵站无用功时段以提高有用功时段在加压周期所占比重,达到提高扳手工作效率的目的;并根据有用功时段油压与螺栓扭矩的对应关系实现扳手的自动判停。实验结果表明:该方法能够在提高泵站作业效率的同时实现扳手的准确判停。In order to improve the working efficiency of the hydraulic wrench driven by the pump station and realize the automatic stop of the wrench,the corresponding relationship between the output oil pressure of the pump station,the displacement of the wrench piston and the torque of the bolt with time was analyzed.A method of judging and stopping hydraulic wrench based on PCA-SVM to identify the state of oil pressure was proposed.The characteristic parameters under different oil pressure states extracted by principal component analysis(PCA)were used as the input of support vector machine(SVM)to complete the accurate recognition of oil pressure state,and to indirectly realize the recognition of work state of pump station.By shortening the period of idle work in the pump station,the proportion of active work in the pressurization cycle was increased to improve the working efficiency of the wrench,and the automatic stop of the wrench was realized according to the corresponding relationship between oil pressure and bolt torque in the active work period.The experimental results show that this method can be used to improve the working efficiency of the pump station and realize the accurate stop of the wrench.

关 键 词：油压信号 特征提取 状态识别 主成分分析 支持向量机 

分 类 号：TH137[机械工程—机械制造及自动化] TP2[自动化与计算机技术—检测技术与自动化装置]