Mobile phone assembly process knowledge framework model construction method based on transfer learning

Abstract

The invention discloses a mobile phone assembly process knowledge framework model construction method based on transfer learning. The method comprises the following steps: A1, collecting production data of each old mobile phone assembly process produced before; a2, calculating the topological structure similarity between the assembly technological process of each old mobile phone and the assemblytechnological process of each new mobile phone, and selecting an assembly data set Xk meeting the similarity requirement; a3, taking the process requirement parameters, collected in the step A1, of the mobile phone assembling process as input, and performing feature extraction on production data through a depth sparse auto-encoder; according to the method, a large amount of labor cost can be saved, the design period of the mobile phone can be shortened, the problem of outdated data can be solved by utilizing transfer learning characteristics, the data of the previous old style mobile phone assembling process can be well utilized, and a large amount of data is provided for model training; the accuracy of a model prediction result can be improved.

Description

technical field [0001] The invention relates to the technical field of mobile phone assembly transfer learning, in particular to a method for constructing a mobile phone assembly process knowledge frame model based on transfer learning. Background technique [0002] With the improvement of living standards, the speed of mobile phone replacement is getting faster and faster, and the styles are changing frequently. Every time a new mobile phone is designed, the original mobile phone assembly line must be redesigned, and the cost and other parameters in the mobile phone assembly process must also be recalculated. Moreover, there are many assembly processes for mobile phones, some of which are completed by machines, while the other can only be completed manually. This brings difficulties to the estimation of some parameters such as cost in the mobile phone assembly process. On the one hand, it consumes a lot of manpower, and on the other hand, it is easy to cause inaccurate est...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to propose a mobile phone assembly process knowledge frame model construction method based on transfer learning, which can solve the problems existing in the prior art

Images