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.Finally,based on the data of a port simulation test platform,the optimal maintenance plan solution set was analyzed.
NETL
NSTL
万方数据
