数据驱动的KDP晶体加工表面质量分类研究  

Research on Data-Driven Surface Quality Classification for KDP Crystal Processing

作　　者：张川东 汪承毅 王伟 ZHANG Chuandong;WANG Chengyi;WANG Wei(School of Mechanical and Electrical Engmeering,University of Electronic Science and Technology of China,Chengdu 611731,China)

机构地区：[1]电子科技大学机械与电气工程学院,成都611731

出　　处：《电子科技大学学报》2024年第6期844-851,共8页Journal of University of Electronic Science and Technology of China

基　　金：国家自然科学基金(52175456)。

摘　　要：为辅助监控超精密飞切机床对磷酸二氢钾(KDP)精加工过程中偶发的加工误差,结合机床加工过程中的振动数据和温度数据关键特征提取,建立晶体加工表面的预测模型。基于ResNet-18分析振动数据与KDP晶体表面是否合格之间的联系进行二分类预测,最终在测试集上模型准确率达到88.5%。同时,基于XGBoost模型分析温度数据与KDP晶体表面质量低频指标P-V的联系并进行预测,实验结果表明预测模型能较快预测加工元件表面质量,且整体误差在可接受范围内。对加工误差进行溯源分析,构建机床的整机模型,利用有限元分析计算长时间的加工状态下机床的瞬态温度场,仿真结果表明在机床运行8580 s后机床最高温度达26.9℃,并开展实验证明了仿真结果的准确性,证实了“KDP晶体加工后期质量变差”与“机床主轴系统随加工过程持续升温”有关的推论。To assist in monitoring occasional processing errors in the precision machining of Potassium Dihydrogen Phosphate(KDP)on ultra-precision fly-cutting machines,this paper combines key feature extraction of vibration data and temperature data during the machining process to establish a predictive model for crystal processing surfaces.Based on ResNet-18,the relationship between vibration data and KDP crystal surface qualification is analyzed for binary classification predictions.The established model achieves an accuracy of 88.5%on the test set.Meanwhile,based on the XGBoost model,the relationship between temperature data and the lowfrequency index P-V(Peak-to-Valley)of KDP crystal surface quality is analyzed and predicted.The experimental results show that the prediction model can predict the surface quality of the processed element quickly,and the overall error is within an acceptable range.By analyzing the processing errors,a complete machine tool model is constructed.The transient temperature field of the machine tool under long-time processing is calculated using finite element analysis.The simulation results show that the maximum temperature of the machine tool reaches 26.9℃after 8580 s of the operation.Experimental verification confirms the accuracy of the simulation results and supports the conclusion that the“decline in KDP crystal processing quality in the later stage”is related to“the continuous warming of the machine tool spindle system during the processing”.

关 键 词：有限元分析 KDP晶体 ResNet 超精密飞切机床 XGBoost 

分 类 号：TL632.1[核科学技术—核技术及应用] TQ131.13[化学工程—无机化工]