基于可靠性的切削过程状态监测异类传感器优化布置  

Optimal Deployment of Heterogeneous Sensors Based on the Reliability to the Condition Monitoring of the Cutting Process

作　　者：赵转哲 何康[2] 贾民平[3] 何慧娟 ZHAO Zhuan-zhe HE Kgng JIA Min-ping HE Hui-juan(School of Mechanical and Automotive Engineering, Anhui Polytechnic University, Wuhu 241000,China School of Mechanical and Electronic Engineering, Suzhou University, Suzhou 234000, China School of Mechanical Engineering, Southeast University, Nanjing 211189, China)

机构地区：[1]安徽工程大学机械与汽车工程学院,安徽芜湖241000 [2]宿州学院机电学院,安徽宿州234000 [3]东南大学机械工程学院,江苏南京211189

出　　处：《安徽工程大学学报》2017年第4期62-67,共6页Journal of Anhui Polytechnic University

基　　金：安徽省高校自然科学研究重点基金资助项目(KJ2016A803;KJ2017A439)

摘　　要：合理的传感器布置对于机械切削过程的状态监测与故障诊断至关重要.根据失效模式与影响分析(FMEA)的有关理论,构建传感器和故障之间的因果关系矩阵用于表征二者之间的诊断关系,得到机械切削过程状态监测的异类传感器布置的多约束优化的数学模型,采用混合蛙跳算法(SFLA)对其进行智能优化求解计算,并给出传感器的优化布置流程.实验表明,在传感器资源、系统故障检测率、故障隔离率以及故障虚警率等多约束条件下,SFLA比遗传算法(GA)具有更高的求解效率,因此,该传感器布置策略能够有效地用于切削过程的状态监测.The reasonable sensors deployment is essential to the condition monitoring and fault diagnosis of the mechanical cutting process. According to the theory on the failure mode and effect analysis （FMEA）,the causal relationship matrix between the sensors and the failure modes was built and the mathematical optimization model with the multiple constraints for the heterogeneous sensors placement in the condition monitoring of the mechanical cutting process was obtained.Then, the shuffled frog lea- ping algorithm （SFLA） was used for intelligent solution and the process of optimizing the sensor deploy- ment was given.The experimental analysis shows that with the condition of multiple constraints, such as the limited sensor resources,fault detection rate, fault isolation rate, false alarm rate and so on,SFLA has a higher efficiency than the genetic algorithm （GA） about the solution for optimization goal.Therefore, the sensors deployment strategy can be effectively applied to the condition monitoring of the mechanical cutting process.

关 键 词：传感器布置 状态监测 混合蛙跳算法 切削过程 

分 类 号：TG156[金属学及工艺—热处理]