The Multi-agent System for the Intelligent Design of Taper Ball Endmill

doi:10.3901/JME.260618

Abstract

Abstract: With breakthroughs in technologies such as large language models, retrieval-augmented generation, and function calling, AI is progressively mastering the complex skills and expertise required in manufacturing, laying the foundation for its deep integration into industrial scenarios. Accordingly, a multi-agent system for the design of cutting tool, driven by large language models, is proposed. Leveraging the advantages of intelligent agents, it restructures the architecture of traditional tool design software and significantly improves the efficiency of cutting tool design. Meanwhile, the multi-agent system is divided into the task extraction agent and task agents, enabling the decomposition of tool design tasks. Taking the taper ball endmill as an example, the multi-agent system for tool design was implemented. First, the technical strengths of agent are deeply integrated with the core elements of tool design to construct the framework of the multi-agent system for taper ball endmill design. Then, the task extraction agent was established to perform information extraction and task planning based on the input cutting tool design requirements. Subsequently, decision-making tools for optimal tool materials and coatings, as well as the optimization tool for geometry parameters, are established and integrated with large language models to form the task agents, thereby building the capabilities of multi-agent system in the field of tool design. Finally, the multi-agent system is implemented using technologies such as Microsoft C# and the DeepSeek large language model, and its effectiveness is validated through a case study involving the design of a taper ball endmill for the precision machining of titanium alloy impellers.

Key words: taper ball endmill, DeepSeek large model, multi-agent system, intelligent design of cutting tool

CLC Number:

TG501

WANG Hongyang, LIU Xianli, YUE Caixu, FAN Mengchao, MAO Xinhui, HU Zihao, SUN Yaxun, CHEN Yang. The Multi-agent System for the Intelligent Design of Taper Ball Endmill[J]. Journal of Mechanical Engineering, 2026, 62(15): 154-170.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.cjmenet.com.cn/EN/10.3901/JME.260618

http://www.cjmenet.com.cn/EN/Y2026/V62/I15/154

References

[1] STABLER G V. The fundamental geometry of cutting tools[J]. Proceedings of the Institution of Mechanical Engineers，1951，165(1)：14-26.
[2] MOUFKI A，DUDZINSKI D，MOLINARI A，et al. Thermoviscoplastic modelling of oblique cutting：Forces and chip flow predictions[J]. International Journal of Mechanical Sciences，2000，42(6)：1205-1232.
[3] KIM G M，CHO P J，CHU C N. Cutting force prediction of sculptured surface ball-end milling using Z-map[J]. International Journal of Machine Tools and Manufacture，2000，40(2)：277-291.
[4] WEI Z C，WANG M J，ZHU J N，et al. Cutting force prediction in ball end milling of sculptured surface with Z-level contouring tool path[J]. International Journal of Machine Tools and Manufacture，2011，51(5)：428-432.
[5] XU Jinting，ZHANG Hai，SUN Yuwen. Swept surface-based approach to simulating surface topography in ball-end CNC milling[J]. The International Journal of Advanced Manufacturing Technology，2018，98：107-118.
[6] LOTFI S，RAMI B，MAHER B，et al. Cutter-workpiece engagement calculation in 3-axis ball end milling considering cutter runout[J]. Journal of Manufacturing Processes，2019，41：74-82.
[7] MARTELLOTTI M E. An analysis of the milling process[J]. Transactions of the ASME，1941，63(8)：677-695.
[8] YUAN Yanjie，JING Xiubing，EHMANN K F，et al. Modeling of cutting forces in micro end-milling[J]. Journal of Manufacturing Processes，2018，31：844-858.
[9] LAMIKIZ A，LÓPEZ DE LACALLE L N，SÁNCHEZ J A，et al. Cutting force estimation in sculptured surface milling[J]. International Journal of Machine Tools and Manufacture，2004，44(14)：1511-1526.
[10] CHEN Yonghui，LU Juan，DENG Qilin，et al. Modeling study of milling force considering tool runout at different types of radial cutting depth[J]. Journal of Manufacturing Processes，2022，76：486-503.
[11] FERRY W B，ALTINTAS Y. Virtual five-axis flank milling of jet engine impellers—Part I：Mechanics of five-axis flank milling[J]. Journal of Manufacturing Science and Engineering，2008，130(1)：339-353.
[12] FAN Mengchao，BI Chunxu，LIU Xianli，et al. Effects of tool structure factor，cutting orientations，and cutting parameters of double-arc milling cutter on cutting force[J]. The International Journal of Advanced Manufacturing Technology，2024，134(9)：4701-4716.
[13] SHAN Chenwei，ZHANG Xu，SHEN Bin，et al. An improved analytical model of cutting temperature in orthogonal cutting of Ti6Al4V[J]. Chinese Journal of Aeronautics，2019，32(3)：759-769.
[14] ZHANG Jingjie，LIU Zhanqiang，XU Chonghai，et al. Modeling and prediction of cutting temperature in machining H13 hard steel with multilayer coated cutting tools[J]. The International Journal of Advanced Manufacturing Technology，2021，115(11)：3731-3739.
[15] VEIGA F，ARIZMENDI M，JIMÉNEZ A，et al. Analytical thermal model of orthogonal cutting process for predicting the temperature of cutting tool with temperature-dependent thermal conductivity[J]. International Journal of Mechanical Sciences，2021，204：1-20.
[16] ZHANG Ziqi，LIU Zhanqiang，REN Xiaoping，et al. Prediction of tool wear rate and tool wear during dry orthogonal cutting of Inconel 718[J]. Metals，2023，13(7)：1-39.
[17] ZHAO H，BARBER G C，ZOU Q. A study of flank wear in orthogonal cutting with internal cooling[J]. Wear，2002，253(9)：957-962.
[18] 赵敏. 超硬刀具高速切削钛合金的性能研究[D]. 大连：大连理工大学，2022. ZHAO Min. Research on the performance of superhard cutting tool in high-speed cutting of titanium alloy TC4[D]. Dalian：Dalian University of Technology，2022.
[19] 张金明. 球头铣刀钛合金螺旋铣孔切削性能分析与切削参数优化研究[D]. 沈阳：东北大学，2020. ZHANG Jinming. Study on cutting characteristics and parameter optimization in helical milling of titanium alloy using ball-end milling cutter[D]. Shenyang：Northeastern University，2020.
[20] LIN Zhi，YUE Caixu，HU Desheng，et al. Research and development of parametric design platform for series complex cutting tools[J]. The International Journal of Advanced Manufacturing Technology，2022，121(9)：6325-6340.
[21] CHEN Hanshi. A new method of modeling flank and fillet rake surfaces of fillet end-mills[D]. Montreal：Concordia University，2015.
[22] WANG Dazhong，CHEN Feiyang，WU Shujing，et al. Study on the mechanism of cutting Ti6Al4V with complex microstructure cutting tools[J]. The International Journal of Advanced Manufacturing Technology，2024，(11/12)：1-14.
[23] CHEN Zhigao，DING Fei，ZHANG Zhichao，et al. The study on the effect of various tool wear indicators on the machining of MMCs[J]. Journal of Materials Research and Technology，2024，30：231-244.
[24] LI Xuebing，LIU Xianli，YUE Caixu，et al. A data-driven approach for tool wear recognition and quantitative prediction based on radar map feature fusion[J]. Measurement，2021，185：1-14.
[25] WEI Xudong，LIU Xianli，YUE Caixu，et al. Tool wear state recognition based on feature selection method with whitening variational mode decomposition[J]. Robotics and Computer-Integrated Manufacturing，2022，77：1-12.
[26] SIYAMBAS Y，AKDULUM A，CAKIROGLU R，et al. Estimation of cutting temperature using machine learning based on signal information received from power analyzer in vortex machining conditions[J]. Journal of Manufacturing Processes，2025，137：100-112.
[27] WU Pengcheng，HE Yan，LI Yufeng，et al. Online prediction of cutting temperature using self-adaptive local learning and dynamic CNN[J]. IEEE Transactions on Industrial Informatics，2022，18(12)：8629-8640.
[28] SHARMA M K，ALKHAZALEH H A，ASKAR S，et al. FEM-supported machine learning for residual stress and cutting force analysis in micro end milling of aluminum alloys[J]. International Journal of Mechanics and Materials in Design，2024，20(5)：1077-1098.
[29] LEE K，YU Zhengxiao，LAI Zenhao，et al. Derivation of physical equations for high-speed laser welding using large language models[J]. International Journal of Machine Tools and Manufacture，2025：1-14.
[30] GARCIA C I，DIBATTISTA M A，LETELIER T A，et al. Framework for LLM applications in manufacturing[J]. Manufacturing Letters，2024，41：253-263.
[31] XIE Yanling，LIU Jihong，WANG Ruiwen，et al. Rapid generation method of process routes based on multi-agent collaboration with LLMs[J]. Advanced Engineering Informatics，2025，68：1-18.
[32] NAGHAVI K K，PATEL A，MALHOTRA R，et al. Large language models for extrapolative modeling of manufacturing processes[J]. Journal of Intelligent Manufacturing，2025：1-29.
[33] 刘献礼，计伟，范梦超，等. 基于特征的刀具“形-性-用”一体化设计方法[J]. 机械工程学报，2016，52(11)：146-153. LIU Xianli，JI Wei，FAN Mengchao，et al. Feature based cutting tool “shape-performance-application” integrating design approach[J]. Journal of Mechanical Engineering，2016，52(11)：146-153.
[34] WANG Hongyang，LIU Xianli，YUE Caixu，et al. An accurate mathematical model for ball end mills with chisel edge[J]. The International Journal of Advanced Manufacturing Technology，2024，131(12)：5729- 5743.