基于数据空间混合策略的冲压工艺能量图谱构建及成形质量监测

doi:10.3901/JME.260252

机械工程学报 ›› 2026, Vol. 62 ›› Issue (5): 374-389.doi: 10.3901/JME.260252

• 数字化设计与制造 • 上一篇

扫码分享

基于数据空间混合策略的冲压工艺能量图谱构建及成形质量监测

甘雷¹, 王成军¹, 李磊², 徐鸿蒙³, 吴军⁴, 黄海鸿²

1. 安徽理工大学人工智能学院淮南 232001;
2. 合肥工业大学机械工程学院合肥 230009;
3. 南京工程学院机械工程学院南京 211167;
4. 中国科学技术大学管理学院合肥 230026

收稿日期:2024-04-18 修回日期:2025-01-21 发布日期:2026-04-23
作者简介:甘雷,男,1996年出生,博士,讲师。研究方向为可持续制造、数据驱动的冲压成形工艺监测与调控。E-mail:ganlei9696@163.com
黄海鸿(通信作者),男,1980年出生,博士,教授,博士研究生导师。主要从事绿色制造与再制造方面的研究。E-mail:huanghaihong@hfut.edu.cn
基金资助:
安徽理工大学高层次引进人才科研启动基金(2024yjrc12)和国家自然科学基金(U20A20295，52005146)资助项目。

Data Spatial Blending Strategy Based Stamping Process Energy Map for Monitoring the Part Forming Quality

GAN Lei¹, WANG Chengjun¹, LI Lei², XU Hongmeng³, WU Jun⁴, HUANG Haihong²

1. School of Artificial Intelligence, Anhui University of Science and Technology, Huainan 232001;
2. School of Mechanical Engineering, Hefei University of Technology, Hefei 230009;
3. School of Mechanical Engineering, Nanjing Institute of Technology, Nanjing 211167;
4. School of Management, University of Science and Technology, Hefei 230026

Received:2024-04-18 Revised:2025-01-21 Published:2026-04-23

摘要/Abstract

摘要： 监测冲压件成形质量变化，对于避免缺陷产生与资源浪费，实现绿色制造至关重要。模具的封闭性和环境噪声干扰导致图像、振动及压力分布等数据难以准确获取，影响冲压件成形质量的监测精度。已有研究指出，易采集且抗干扰的冲压力在冲压深度上的积分(即工艺能量)与冲压件的厚度变化率之间存在定量变化关系。为此，本文提出了一种通过颜色与深度表征并监测冲压件厚度变化率的冲压工艺能量图谱。图谱以冲压深度与工艺能量分别作为横、纵坐标，将测量厚度变化率根据对应坐标分布于图谱之上。考虑有限测量数据对数据插值预测数据精度的限制，应用一种数据空间混合策略，将数据插值预测的厚度变化率与仿真厚度变化率进行空间加权混合，实现图谱的精确填充与着色。进一步根据厚度变化率阈值曲线，完成图谱质量区域的划分。类车门内板件厚度变化率监测结果显示，图谱监测的平均绝对百分比误差不超过5%，对破裂与起皱的识别准确率超90%。应用图谱进行工艺控制的结果显示，冲压件的最大减薄率降低了14.56%，有效地避免了冲压件的破裂。所提出的冲压工艺能量图谱可实现冲压件成形质量的精确监测，助力高质量、零缺陷生产。

关键词: 冲压工艺能量, 成形质量, 监测图谱, 数据插值, 数据空间混合

Abstract: Monitoring the part quality variation is essential to avoid defects and resource waste for green manufacturing achievement. However, it is difficult to obtain accurate images, vibration, pressure distribution, and other data for the accurate monitoring of the forming quality of stamping parts due to the closed mold and noisy production environment. Existing efforts indicated that the part thickness variation ratio varies quantitatively with process energy, which is the accumulation of punch force over the stamping depth, and it is easy to collect and anti-interference. In this context, a stamping process energy map is proposed to characterize the thickness variation ratio by color and its intensity. The stamping depth and process energy are set as the horizontal and vertical coordinates of the map, respectively. A data interpolation technique is applied to interpolate the measured thickness variation ratio data located in the map. Considering the limitation of finite measurement data on the accuracy of interpolation data, a data spatial blending strategy that weights and blends the interpolated and simulated thickness variation ratio data to fill and color the map followed by the quality zone division according to the threshold curve of thickness variation ratio. To validate the effectiveness, the map was applied to form a downscaling part of a car door. The mean absolute percentage error of the monitored thickness variation ratio was within 5%. The crack and wrinkle identification accuracy is up to 90.63%. The results of applying the map to stamping process control showed a 14.56% reduction in the maximum thinning ratio of the part, which effectively prevents cracking. The proposed stamping process energy map assisted in accurate part quality monitoring and quality improvement in stamping.

Key words: process energy, forming quality, monitoring map, data interpolation, data spatial blending

中图分类号:

TG156

甘雷, 王成军, 李磊, 徐鸿蒙, 吴军, 黄海鸿. 基于数据空间混合策略的冲压工艺能量图谱构建及成形质量监测[J]. 机械工程学报, 2026, 62(5): 374-389.

GAN Lei, WANG Chengjun, LI Lei, XU Hongmeng, WU Jun, HUANG Haihong. Data Spatial Blending Strategy Based Stamping Process Energy Map for Monitoring the Part Forming Quality[J]. Journal of Mechanical Engineering, 2026, 62(5): 374-389.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.260252

http://www.cjmenet.com.cn/CN/Y2026/V62/I5/374

参考文献

[1] 刘培基，刘飞，王旭，等. 绿色制造的理论与技术体系及其新框架[J]. 机械工程学报，2021，57(19):165-179. LIU Peiji，LIU Fei，WANG Xu，et al. The theory and technology system of green manufacturing and their new frameworks[J]. Journal of Mechanical Engineering，2021，57(19):165-179.
[2] FOIVOS P，VICTOR A. Zero defect manufacturing:a complete guide for advanced and sustainable quality management[J]. Journal of Manufacturing Systems，2024，77:764-779.
[3] GUO Yingjian，WANG Can，HAN Sutao，et al. A deep neural network model for parameter identification in deep drawing metal forming process[J]. Journal of Manufacturing Processes，2025，133:380-394.
[4] NAJM S，TRZEPIECINSKI T，IBRAHIM O，et al. Analysis of the friction performance of deep-drawing steel sheets using network models[J]. International Journal of Advanced Manufacturing Technology，2024，132:3757-3769.
[5] LIU Jiahao，JIANG Chen，YANG Xue，et al. Review of the application of acoustic emission technology in green manufacturing[J]. International Journal of Precision Engineering and Manufacturing-Green Technology，2024，11:995-1016.
[6] HE Yike，WU Baotong，MAO Jianhua，et al. An effective MID-based visual defect detection method for specular car body surface[J]. Journal of Manufacturing Systems，2024，72:154-162.
[7] UBHAYARATNE I，PEREIRA M，XIANG Yong，et al. Audio signal analysis for tool wear monitoring in sheet metal stamping[J]. Mechanical Systems and Signal Processing，2017，85:809-826.
[8] BEHRENS B A，HUBNER S，WOLKI K. Acoustic emission-a promising and challenging technique for process monitoring in sheet metal forming[J]. Journal of Manufacturing Processes，2017，29:281-288.
[9] GAO R X，SAH S，Mahayotsanun N. On-line measurement of contact pressure distribution at tool-workpiece interfaces in manufacturing operations[J]. CIRP Annals，2010，59(1):399-402.
[10] SAH S，GAO R X，KURP T. Model-augmented methods for estimation of contact pressure distribution[J]. Journal of Manufacturing Systems，2011，30(4):223-233.
[11] SAH S，GAO R X. An experimental study of contact pressure distribution in panel stamping operations[J]. The International Journal of Advanced Manufacturing Technology，2011，55(1):121-132.
[12] SAH S，MAHAYOTSANUN N，Peshkin M，et al. Pressure and draw-in maps for stamping process monitoring[J]. Journal of Manufacturing Science and Engineering，2016，138(9):091005.
[13] CAO Jian，Brinksmeier E，FU Mingwang，et al. Manufacturing of advanced smart tooling for metal forming[J]. CIRP Annals，2019，68(2):605-628.
[14] LI Lei，HUANG Haihong，ZHAO Fu，et al. Variations of energy demand with process parameters in cylindrical drawing of stainless steel[J]. Journal of Manufacturing Science and Engineering，2019，141(9):091002.
[15] LI Lei，HUANG Haihong，ZHAO Fu，et al. Modeling and analysis of the process energy for cylindrical drawing[J]. Journal of Manufacturing Science and Engineering，2019，141(2):201001.
[16] 甘雷. 面向冲压件厚度变化监测的工艺能量图谱构建关键技术研究[D]. 合肥:合肥工业大学，2023. GAN Lei. Key technology of process energy map construction for thickness variation monitoring in stamping[D]. Hefei:Hefei University of Technology，2023.
[17] RYSER M，PAVEL H，Bambach M. Algorithmic determination of measurement locations for surface point markers in sheet metal forming and application in inverse modelling-a numerical and experimental study[J]. Journal of Materials Processing Technology，2022，312:117848.
[18] WANG Yucheng，TAO Fei，ZHANG Meng，et al. Digital twin enhanced fault prediction for the autoclave with insufficient data[J]. Journal of Manufacturing Systems，2021，60:350-359.
[19] LI Weihan，Rentemeister M，Badeda J，et al. Digital twin for battery systems:cloud battery management system with online state-of-charge and state-of-health estimation[J]. Journal of Energy Storage，2020，30:101557.
[20] GAN Lei，LI Lei，HUANG Haihong. Digital twin-driven sheet metal forming:modeling and application for stamping considering mold wear[J]. Journal of Manufacturing Science and Engineering，2022，144(12):121003.
[21] LIANG Yiyi，FENG Sang，ZHANG Yuxun，et al. A stable diffusion enhanced YOLOV5 model for metal stamped part defect detection based on improved network structure[J]. Journal of Manufacturing Processes，2024，111:21-31.
[22] HUANG Haihong，LV Qingyu，LI Lei，et al. Individually segmented blank holding system driven by electromagnetics for stamping:modeling，validation，and prototype[J]. Journal of Materials Processing Technology，2023，313:117883.
[23] HUANG Haihong，SANG Haojie，LI Lei，et al. High-accuracy control of variable blank holding force driven by electromagnetics based on pulse width modulation with grading voltage and mode matching[J]. Journal of Materials Processing Technology，2023，322:118210.
[24] LI Lei，DENG Yangtong，WANG Yue，et al. Discretized blank holding force driven by electromagnetics:mechanism of thermal effects and deformation[J]. Journal of Materials Processing Technology，2024，331:118493.
[25] LI Lei，HU Guozeng，JIN Rui，et al. Flexible tooling enabled by the electromagnetics with discrete blank holding force:short-time pulse control and forming validation[J]. Journal of Manufacturing Science and Engineering，2025，147(5):051005.

基于数据空间混合策略的冲压工艺能量图谱构建及成形质量监测

Data Spatial Blending Strategy Based Stamping Process Energy Map for Monitoring the Part Forming Quality

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	李雨露, 李俊峰, 万章艺, 魏正英. 基于YOLO算法的激光粉末床熔融成形层形貌分类识别与成形质量预测研究[J]. 机械工程学报, 2026, 62(3): 218-234.
[2]	杜心伟, 魏艳红, 沈泳华, 赵文勇, 刘仁培. 电弧增材制造装备系统与应用的发展现状[J]. 机械工程学报, 2025, 61(6): 92-102.
[3]	贺世伟, 朱丽娜, 张志强, 康嘉杰. 激光电弧复合增材制造铝合金的组织和性能研究[J]. 机械工程学报, 2025, 61(10): 152-163.
[4]	覃林, 张李超, 王森林, 汤名锴, 史玉升. 激光选区熔化区域连续能量调控扫描方法研究[J]. 机械工程学报, 2024, 60(1): 159-169.