一种不完备数据驱动的数控机床切削能耗预测建模方法

• Format: Patent
• Language: Chinese
• Published: 31.05.2022
• Subjects: CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING

本发明考虑到了数控机床切削能耗预测的数据不完备情况，根据分析数据的缺失机制和模式，进行数据过滤、缺失率估计、变量相关性分析，同时采用基于生成对抗网络的缺失数据估算法进行缺失值填补，基于此，建立基于基因表达式编程的数控机床切削能耗预测模型，并进行了交叉验证，为不完备的数据下机床切削能耗预测建模提供了一种新的解决方法。 According to the method, the data incompleteness condition of numerical control machine tool cutting energy consumption prediction is considered; according to a missing mechanism and a missing mode ofthe analysis data, data filtering, missing rate estimation and variable correlation analysis are carried out; meanwhile, a missing data estimation method based on a generative adversarial network isadopted for missing value filling. Therefore, a numerical control machine tool cutting energy consumption prediction model based on gene expression programming is established, cross validation is carried out, and a novel solution is provided for machine tool cutting energy consumption prediction modeling under incomplete data.