基于售后服务记录的卡车动力转向系统漏油分析与预测  

Analysis and prediction of oil leakage in truck’s power steering system based on after-sales service records

作　　者：蒋国璋 张翼翔 向峰 李公法[1,3] Jiang Guozhang;Zhang Yixiang;Xiang Feng;Li Gongfa(Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, China;Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan 430081, China;Institute of Precision Manufacturing, Wuhan University of Science and Technology, Wuhan 430081, China)

机构地区：[1]武汉科技大学冶金装备及其控制教育部重点实验室,湖北武汉430081 [2]武汉科技大学机械传动与制造工程湖北省重点实验室,湖北武汉430081 [3]武汉科技大学精密制造研究院,湖北武汉430081

出　　处：《武汉科技大学学报》2020年第5期362-369,共8页Journal of Wuhan University of Science and Technology

基　　金：国家自然科学基金资助项目(51975431,71271160).

摘　　要：为了分析卡车动力转向系统的漏油原因,同时避免车辆漏油问题的进一步恶化,提出一种基于售后服务记录的漏油分析预测方法。首先采用自然语言情感分析技术,通过结合注意力机制的双向长短期记忆神经网络模型(Att-BiLSTM)根据漏油描述文本进行漏油程度量化;然后采用随机森林(RF)算法并结合BP神经网络,基于卡车相关生产数据对漏油的主要原因进行分析,并建立漏油程度预测模型。通过实例验证了本文方法的有效性。对漏油相关原因的分析结果可为卡车制造企业提供工艺改进的依据,同时,根据预测模型分析漏油程度的恶化趋势,可避免严重漏油事故的发生。To pinpoint the causes of oil leakage in truck’s power steering system and avoid further deterioration of oil leakage,this paper proposed a method for analyzing and predicting oil leakage based on after-sales service records.Firstly,on the basis of sentiment analysis technique for natural languages,a bidirectional long short-term memory neural network model with attention mechanism(Att-BiLSTM)was applied to quantify oil leakage according to the description texts.Then random forest(RF)algorithm and BP neural network were used to analyze the main causes of oil leakage based on the truck related production data and establish the prediction model for oil leakage.The validity of the proposed method was verified by some examples.The analysis results of the causes of oil leak can provide the basis for enterprises to improve their production processes,and the prediction results can prevent oil leakage from deteriorating and serious accidents.

关 键 词：动力转向系统 漏油 售后服务记录 情感分析 Att-BiLSTM 随机森林算法 BP神经网络 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术] U463.442[自动化与计算机技术—计算机科学与技术]