摘要
针对离散车间传统的现场设备管理模式存在效率低、日常维护成本高等弊端,提出了基于数据驱动的设备健康监测和备品备件的库存优化方法。首先,对设备生产过程中产生的反映设备健康状况的关键信号经采集、处理与封装后,利用改进粒子群优化(IPSO)算法优化隐马尔科夫模型(HMM)评估设备当前健康等级,依据评估结果进行设备的主动维护。其次,为了优化库存降低备件更换不及时带来的损失,建立了考虑设备备件的重要度与成本最小为目标的库存控制模型。实验结果表明:健康预测模型能够实现设备健康状态的准确识别,识别精度达96%以上;库存模型可有效降低配件的总成本,结合企业实际验证了方法的可行性与有效性。
Aiming at the disadvantages of traditional on-site equipment management mode of discrete workshops such as low efficiency and high daily maintenance cost, a data-driven equipment health monitoring and spare parts inventory optimization method is proposed.Firstly, after collecting, processing and encapsulating the key signals that reflect the health of the equipment generated during the production process, the improved particle swarm optimization(IPSO) is used to optimize the hidden Markov model(HMM) to evaluate the current health level of the equipment, based on evaluation results carry out the active maintenance of the equipment.Secondly, In order to optimize inventory and reduce the loss caused by untimely replacement of spare parts, an inventory control model is established that takes into account the importance and cost of equipment spare parts as the goal.The results show that the health prediction model can accurately identify the health status of the equipment with a recognition precision of more than 96 %.The inventory model can effectively reduce the total cost of parts.Combined with the actual situation of the enterprise, the feasibility and effectiveness of the method are verified.
作者
吴浩
吉卫喜
张泽宏
张贇
党英
WU Hao;JI Weixi;ZHANG Zehong;ZHANG Yun;DANG Ying(School of Mechanical Engineering,Jiangnan University,Wuxi 214122,China;Jiangsu Provincial Key Laboratory of Food Manufacturing Equipment,Wuxi 214122,China)
出处
《传感器与微系统》
CSCD
北大核心
2022年第10期152-155,160,共5页
Transducer and Microsystem Technologies
基金
山东省重大科技创新工程项目(2019JZZY020111)。
关键词
离散车间
设备健康监测
备件库存优化
隐马尔科夫模型
discrete workshop
equipment health monitoring
spare parts inventory optimization
hidden Markov model(HMM)
