Open AccessResearch on Equipment Life Cycle Cost Prediction Based on GA-LSSVM
Author(s) -
Yonghong Chen,
Yongsheng Su,
Xiang-hua Du
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1605/1/012089
Subject(s) - genetic algorithm , support vector machine , kernel (algebra) , computer science , mathematical optimization , data mining , mathematics , machine learning , combinatorics
Penalty parameter γ and kernel parameter σ 2 are two important parameters of LSSVM. In this paper, the GA-LSSVM prediction model is constructed, which the genetic algorithm was used to optimize the parameters. Comparing with LSSVM model, the GA-LSSVM model improves the disadvantage that the parameters can only obtained by experience. Also in order to check model prediction accuracy, the posterior difference method(PDM) was used. The calculation results show that the GA-LSSVM model has higher prediction accuracy than other models, and it is a feasible and reliable method for equipment life cycle cost prediction, also the model can be extended to other prediction fields.