考虑维修人员约束的港口起重机轴承群体视情维修

Condition-based Maintenance of Port Crane Bearing Considering the Constraints of Maintenance Workforce

随着港口码头作业量的逐步提升,港口起重机的作业效率与成本显得至关重要。为了得到在考虑维修人员的条件下更加合适的维护方案,本文以港口起重机减速箱轴承为例,基于港口起重机轴承健康状况,利用迁移学习的理论,结合无维修人员约束、单个维修人员约束和有限W个维修人员约束的情形,进行成组维修决策。首先,对源域轴承振动信号进行时频域分析与特征融合,并基于LSTM预测进行迁移学习得到目标域轴承健康指数。其次,利用三参数威布尔分布进行函数拟合,得到健康指数函数。然后,构建了成本模型、可用度模型和群体维修模型。最后,基于某港口仿真试验平台数据,分析了最优维修计划解集。

With the increase of the ports'operations,the efficiency and cost of port cranes are very important.In order to get a more suitable maintenance plan under the condition of considering maintenance workforce,port crane gearbox bearings were took as an example.Based on the health conditions of port cranes'bearings,using transfer learning,combined with no maintenance workforce constraints,single maintenance workforce constraints and limited W maintenance workforce,group maintenance decisions were made.Firstly,time-frequency domain analysis and feature fusion were performed on the source domain bearing vibration signals,and the target domain bearing health index was obtained by migration learning based on LSTM prediction.Secondly,the three-parameter Weibull distribution was further used to perform function fitting to obtain the health index function.Then,a cost model,availability model and group maintenance model were constructed.Finaly,based on the data of a port simulation test platform,the optimal maintenance plan solution set was analyzed.