基于多源信息融合和集成学习的薄壁件铣削加工变形误差预测

doi:10.3969/j.issn.1004-132X.2025.06.013

中国机械工程 ›› 2025, Vol. 36 ›› Issue (06): 1261-1268.DOI: 10.3969/j.issn.1004-132X.2025.06.013

基于多源信息融合和集成学习的薄壁件铣削加工变形误差预测

尹佳¹;郑健²;刘尧³*;贾保国¹;段晓蕊¹

1.中航西安飞机工业集团股份有限公司,西安,710089
2.西安电子科技大学机电工程学院,西安,710071
3.西安邮电大学通信与信息工程学院,西安,710121

出版日期:2025-06-25 发布日期:2025-08-04
作者简介:尹佳，男，1981年生，研究员级高级工程师。研究方向为航空制造技术。
基金资助:
陕西省科技重大专项（2019zdzx01-01-02）

Thin-walled Workpiece Milling Deformation Error Prediction Based on Multi-source Information Fusion and Ensemble Learning

YIN Jia¹;ZHENG Jian²;LIU Yao³*;JIA Baoguo¹;DUAN Xiaorui¹

1.AVIC Xian Aircraft Industry Group Company Ltd.,Xian,710089
2.School of Mechano-Electronic Engineering,Xidian University,Xian,710071
3.School of Communications and Information Engineering,Xian University of Posts and
Telecommunications,Xian,710121

Online:2025-06-25 Published:2025-08-04

摘要/Abstract

摘要： 在实际加工过程中，薄壁件加工精度易受到切削力、强迫振动、颤振、工件几何特征、材料等因素影响，导致薄壁件变形难以预测和控制。提出了一种多源信息融合的薄壁件铣削加工变形误差预测方法，融合加工过程信息和振动信号等数据，基于Stacking集成学习思想构建薄壁件铣削加工变形误差预测模型，并进行了实验验证。对比实验表明，相比于常规数据驱动方法，所构建模型的鲁棒性和准确度更高，实用性更好。

关键词: 薄壁件, 铣削加工, 变形误差, 多源信息融合, 集成学习

Abstract: In practical machining processes, the dimensional accuracy of thin-walled workpiece was significantly affected by multiple factors including cutting forces, forced vibrations, chatter phenomena, geometric characteristics of workpiece and material properties, rendering deformation prediction and control particularly challenging. A multi-source information fusion method for deformation error prediction in thin-walled workpiece milling processes was developed. Machining parameters, vibration signals, and other relevant data were integrated to establish a deformation error prediction model through Stacking ensemble learning methodology, with comprehensive experimental validation performed. Comparative analyses reveal that the constructed model demonstrates superior robustness, higher accuracy, and enhanced practicality when compared with conventional data-driven prediction methods.

Key words: thin-walled workpiece, milling process, deformation error, multi-source information fusion, ensemble learning

中图分类号:

TH17

尹佳1, 郑健2, 刘尧3, 贾保国1, 段晓蕊1. 基于多源信息融合和集成学习的薄壁件铣削加工变形误差预测[J]. 中国机械工程, 2025, 36(06): 1261-1268.

YIN Jia1, ZHENG Jian2, LIU Yao3, JIA Baoguo1, DUAN Xiaorui1. Thin-walled Workpiece Milling Deformation Error Prediction Based on Multi-source Information Fusion and Ensemble Learning[J]. China Mechanical Engineering, 2025, 36(06): 1261-1268.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.cmemo.org.cn/CN/10.3969/j.issn.1004-132X.2025.06.013

https://www.cmemo.org.cn/CN/Y2025/V36/I06/1261

参考文献

［1］岳彩旭, 张俊涛, 刘献礼，等. 薄壁件铣削过程加工变形研究进展［J］. 航空学报, 2022, 43(4):106-131.
YUE Caixu, ZHANG Juntao, LIU Xianli, et al. Research Progress on Machining Deformation during Milling of Thin-walled Parts［J］. Acta Aeronauticaet Astronautica Sinica, 2022, 43(4):106-131.
［2］刘醒彦. 基于变形力监测数据的航空结构件加工变形预测与控制方法［D］. 南京：南京航空航天大学, 2020.
LIU Xingyan. Machining Deformation Prediction and Control of Aerospace Structural Parts Based on Deformation Force Monitor Data［D］. Nanjing： Nanjing University of Aeronautics and Astronautics, 2020.
［3］YI J, WANG X B, JIAO L, et al. Research on Deformation Law and Mechanism for Milling Micro Thin Wall with Mixed Boundaries of Titanium Alloy in Mesoscale［J］. Thin-walled Structures, 2019, 144:106329.
［4］李曦, 袁军堂, 汪振华，等. 基于Rayleigh-Ritz法的钛合金薄壁件非均匀余量加工变形控制研究［J］. 中国机械工程, 2020, 31(11):1378-1385.
LI Xi, YUAN Juntang, WANG Zhenhua, et al. Study on Deformation Control of Thin-walled Titanium Alloy Parts in Non-uniform Allowance Machining Based on Rayleigh-Ritz Method［J］. China Mechanical Engineering, 2020, 31(11):1378-1385.
［5］YUE C X, CHEN Z T, LIANG S Y, et al. Modeling Machining Errors for Thin-walled Parts According to Chip Thickness［J］. International Journal of Advanced Manufacturing Technology, 2019, 103(14):91-100.
［6］SUN H, ZHAO S Q, PENG F Y, et al. In-situ prediction of Machining Errors of Thin-walled Parts:an Engineering Knowledge Based Sparse Bayesian Learning Approach［J］. Journal of Intelligent Manufacturing, 2024, 35(1):387-411.
［7］王骏腾. 薄壁件铣削残余应力变形的感知预测与工艺优化方法［D］.西安：西北工业大学, 2018.
WANG Junteng. Research on Prediction and Optimization Method of Deformation Induced by Residual Stresses in Milling of Thin-walledParts［D］. Xian：Northwestern Polytechnical University, 2018.
［8］GE G Y, DU Z C, YANG J G. Rapid Prediction and Compensation Method of Cutting Force-induced Error for Thin-walled Workpiece［J］. International Journal of Advanced Manufacturing Technology, 2020, 106(11/12):5453-5462.
［9］朱卫华, 王宗园, 任军学，等. TC4钛合金薄壁件铣削残余应力变形研究［J］. 组合机床与自动化加工技术, 2020 (12):70-72.
ZHU Weihua, WANG Zongyuan, REN Junxue, et al. Study on Milling Residual Stress and Deformation of TC4 Titanium Alloy Thin Plate Parts［J］. Modular Machine Tool & Automatic Manufacturing Technique, 2020(12):70-72.
［10］ZHANG Z X, ZHANG Z, ZHANG D H, et al. Milling Distortion Prediction for Thin-walled Component Based on the Average MIRS in Specimen Machining［J］. International Journal of Advanced Manufacturing Technology, 2020, 111(11/12):3379-3392.
［11］LI B H, DENG H B, HUI D, et al. A Semi-analytical Model for Predicting the Machining Deformation of Thin-walled Parts Considering Machining-induced and Blank Initial Residual Stress［J］. International Journal of Advanced Manufacturing Technology, 2020, 110(1/2):139-161.
［12］CHEN Z T, YUE C X, LIANG S Y, et al. Iterative from Error Prediction for Side-milling of Thin-walled Parts［J］. International Journal of Advanced Manufacturing Technology, 2020, 107(9/10):4173-4189.
［13］SHI D M, HUANG T, ZHANG X M, et al. An Explicit Coupling Model for Accurate Prediction of Force-induced Deflection in Thin-walled Workpiece Milling［J］. Journal of Manufacturing Science and Engineering—Transactions of the ASME, 2022, 144(8):081005.
［14］丛靖梅, 莫蓉, 吴宝海，等. 薄壁件残余应力变形仿真预测与切削参数优化［J］. 机械科学与技术, 2019, 38(2):205-210.
CONG Jingmei, MO Rong, WU Baohai, et al. Prediction of Deformation Induced by Residual Stress in Milling of Thin-walled Part and Optimization of Cutting Parameters［J］. Mechanical Science and Technology for Aerospace Engineering, 2019, 38(2):205-210.
［15］田海东. 铝合金薄壁结构件铣削变形预测与工艺参数优化［D］. 济南：山东大学, 2020.
TIAN Haidong. Prediction of Milling Deformation and Optimization of Process Parameters of Aluminum Alloy Thin-walled StructuralParts［D］. Jinan：Shandong University, 2020.
［16］WHITEHOUSE D. Surfaces—a Link between Manufacture and Function［J］. Proceedings of the Institution of Mechanical Engineers, 1978, 192(1):179-188.
［17］张智, 刘成颖, 刘辛军，等. 采用小波包能量熵的铣削振动状态分析方法研究［J］. 机械工程学报, 2018, 54(21):57-62.
ZHANG Zhi, LIU Chengying, LIU Xinjun, et al. Analysis of Milling Vibration State Based on the Energy Entropy of WPD［J］. Chinese Journal of Mechanical Engineering, 2018, 54(21):57-62.

[1]	石龙, 周鹤翔, 李洲龙. 基于模糊线性自抗扰的薄壁件机器人铣削切深控制[J]. 中国机械工程, 2025, 36(04): 671-680.
[2]	张珞1, 刘明明2, 陈锐敏1, 但鹏1, 郭楠1. 激光选区熔化成形大尺寸薄壁件变形控制仿真与试验研究[J]. 中国机械工程, 2024, 35(09): 1653-1658，1709.
[3]	钱栊, 张立强, 高秋阁, 杨杰. 基于奇异避免的薄壁件镜像铣削加工路径优化[J]. 中国机械工程, 2023, 34(05): 576-583，594.
[4]	张瑾, 韩福柱, . 电弧铣削加工间隙电压预测模型的建立与研究[J]. 中国机械工程, 2022, 33(16): 1891-1896.
[5]	李敏波, 董伟伟. 面向不平衡数据集的汽车零部件质量预测[J]. 中国机械工程, 2022, 33(01): 88-96.
[6]	黎宇嘉, 黄兵, 鲁娟, 钟奇憬, 陈超逸, 廖小平, 马俊燕. 基于有限元模拟的Ti6Al4V铣削过程参数多目标优化[J]. 中国机械工程, 2021, 32(13): 1555-1561,1570.
[7]	阮大文, 茅健, 刘钢, 马丽. [误差建模及精度保证方法]双五轴数控铣削机床旋转轴误差辨识方法[J]. 中国机械工程, 2020, 31(13): 1548-1554.
[8]	李曦;袁军堂;汪振华;章波. 基于Rayleigh-Ritz法的钛合金薄壁件非均匀余量加工变形控制研究[J]. 中国机械工程, 2020, 31(11): 1378-1385.
[9]	吕树杰;李郝林. 数控型腔铣削加工稳定性预测[J]. 中国机械工程, 2019, 30(18): 2236-2241.
[10]	尚宝平1;闫富宏1;刘高峰2;陈振中3;邱浩波4;李晓科1. 基于近似模型的铣削工艺参数可靠性设计优化[J]. 中国机械工程, 2019, 30(04): 480-485,493.
[11]	王仲奇;李诚;杨勃;杨元. 基于花授粉算法的曲面薄壁件定位布局优化[J]. 中国机械工程, 2017, 28(18): 2231-2236.
[12]	李玉昆, 李永泉, 佘亚中, 张立杰, . 3-UPS/S并联稳定平台满载工况误差分析与运动学标定[J]. 中国机械工程, 2017, 28(08): 958-965.
[13]	曾莎莎, 彭卫平, 雷金. 基于混合算法的薄壁件铣削加工工艺参数优化[J]. 中国机械工程, 2017, 28(07): 842-845,851.
[14]	朱绍维, 李卫东, 汤立民, 杜丽. ARTIS刀具监控系统在航空结构件铣削加工中的应用[J]. 中国机械工程, 2016, 27(15): 2040-2043.
[15]	乔凯, 舒小平. 薄壁件加工变形误差预估及补偿的集成[J]. 中国机械工程, 2015, 26(21): 2895-2900.

基于多源信息融合和集成学习的薄壁件铣削加工变形误差预测

Thin-walled Workpiece Milling Deformation Error Prediction Based on Multi-source Information Fusion and Ensemble Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics