Design of Smart Tool Holders and Systems Based on Multi-sensor Information Fusion

doi:10.3969/j.issn.1004-132X.2026.01.019

Abstract

Abstract:

In order to effectively monitor the physical characteristics in machining processes， accurately determine the abnormal machining conditions， and optimize the machining processes， a self-developed multi-source information fusion-based smart tool holder and system was introduced. Based on finite element analysis of force-sensitive components， structure modals and vibrations of tool holders， a system for multi-source sensing smart tool holders was constructed. Combined with methods such as time series neural network modeling of temperature transfer， the online monitoring of cutting forces， vibrations and tool tip cutting temperature was achieved. Test results show that the system reaches a force resolution of approximately 21.1 mN and a relative error of less than 2.5% in predicting transient temperatures of the tool tips， validating the good monitoring capabilities for various physical quantities. Meanwhile， based on the analysis of the characteristics of dynamical physical quantities such as acceleration and force， a probabilistic judgment method for the early warning of abnormal tool collisions was proposed， which may improve the accuracy of judging the normal collision when the tool cuts into the workpiece.

Key words: smart tool holder, cutting force, cutting heat, modal analysis, abnormal warning

摘要：

为有效监测加工过程中的物理特征，准确判断异常工况，优化加工工艺，设计了基于多源传感信息融合的智能刀柄及系统。基于力敏感元件、刀柄结构模态与刀柄振动等有限元分析，构建了多源传感智能刀柄系统；结合温度传递的时间序列神经网络建模等方法，实现了对切削力、振动和刀尖切削温度的在线监测。测试结果表明，系统对力的分辨力约为21.1mN，刀尖瞬态温度预测相对误差小于2.5%，对不同物理量具有良好的监测能力。同时，基于对加速度与力的分析，提出的刀具异常碰撞预警概率判断方法可提高刀具切入工件瞬间正常碰撞的判断准确率。

关键词: 智能刀柄, 切削力, 切削热, 模态分析, 异常预警

CLC Number:

TG506

GAO Yuan, WU Qiwei, SONG Yang, QU Da. Design of Smart Tool Holders and Systems Based on Multi-sensor Information Fusion[J]. China Mechanical Engineering, 2026, 37(1): 184-191.

高远, 吴琦炜, 宋阳, 渠达. 基于多源传感信息融合的智能刀柄及系统的设计[J]. 中国机械工程, 2026, 37(1): 184-191.

Figures/Tables 17

Fig.1 Logical framework for realizing smart tool holder function

Fig.2 Modal analysis of the multi-dimensional force sensor

Fig.3 The first four modal analyses of the mounting base

Fig.4 Smart tool holder calibration experiment and measurement results

Fig.5 Load calibration of smart tool holder

Tab.1 Load calibration and relative error of smart tool holder

序号	重力/N	相对误差/%	序号	重力/N	相对误差/%
1	0	2.89	11	9.799 77	$-$ 0.48
2	0.010 85	2.65	12	19.593 11	$-$ 0.24
3	0.021 14	2.74	13	29.389 97	$-$ 0.06
4	0.050 73	2.69	14	39.194 78	$-$ 0.05
5	0.099 83	2.41	15	48.961 06	$-$ 0.05
6	0.197 83	2.00	16	58.757 93	$-$ 0.05
7	0.491 83	1.48	17	68.552 34	0.09
8	0.981 64	0.60	18	78.349 21	0.05
9	1.961 83	0.25	19	88.144 21	0.04
10	4.901 08	$-$ 0.31

Tab.1 Load calibration and relative error of smart tool holder

序号	重力/N	相对误差/%	序号	重力/N	相对误差/%
1	0	2.89	11	9.799 77	$-$ 0.48
2	0.010 85	2.65	12	19.593 11	$-$ 0.24
3	0.021 14	2.74	13	29.389 97	$-$ 0.06
4	0.050 73	2.69	14	39.194 78	$-$ 0.05
5	0.099 83	2.41	15	48.961 06	$-$ 0.05
6	0.197 83	2.00	16	58.757 93	$-$ 0.05
7	0.491 83	1.48	17	68.552 34	0.09
8	0.981 64	0.60	18	78.349 21	0.05
9	1.961 83	0.25	19	88.144 21	0.04
10	4.901 08	$-$ 0.31

Fig.6 Temperature analysis of tool holder and tool tip

Fig.7 Heat transfer process and trend between the tool holder and the tool tip

Fig.8 Tool tip temperature prediction model architecture based on NARX

Fig.9 Training results of tool tip temperature prediction model based on NARX

Fig.10 Analysis of fitting degree of tool tip temperature prediction model based on NARX

Tab.2 Experimental and predicted values of the temperature of the tool tip

测试值	实验值/℃	预测值/℃	误差
测试值	实验值/℃	预测值/℃	原始值/℃	相对值/%
1	25.49	24.89	$-$ 0.60	$-$ 2.35
2	26.69	26.25	$-$ 0.44	$-$ 1.65
3	62.05	62.30	0.25	0.40
4	70.58	69.78	$-$ 0.80	$-$ 1.13

Tab.2 Experimental and predicted values of the temperature of the tool tip

测试值	实验值/℃	预测值/℃	误差
测试值	实验值/℃	预测值/℃	原始值/℃	相对值/%
1	25.49	24.89	$-$ 0.60	$-$ 2.35
2	26.69	26.25	$-$ 0.44	$-$ 1.65
3	62.05	62.30	0.25	0.40
4	70.58	69.78	$-$ 0.80	$-$ 1.13

Fig.11 Intelligent support system logic diagram

Fig.12 Flow chart of BP neural network algorithm based on genetic algorithm

Fig.13 The result of multi-source information fusion collection

Fig.14 Hardware of the smart tool holder in analyzing crash test.

Fig.15 Analysis of characters extracted from contacting force and vibration acceleration during crash test

References 18

[1]	LI Xuebing， LIU Xianli， YUE Caixu， et al. Systematic Review on Tool Breakage Monitoring Techniques in Machining Operations［J］. International Journal of Machine Tools and Manufacture， 2022， 176： 103882.
[2]	KIM B C， CHO H， KIM D， et al. Design of Slip Detection Sensor for Artificial Skin［C］∥2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence （URAI）. Daejeon， 2012： 510-511.
[3]	陈少波，刘晓东. 新型测力装置［J］. 现代制造工程， 2003（9）： 57-58.
	CHEN Shaobo， LIU Xiaodong. New Force Measuring Device［J］. Modern Manufacturing Engineering， 2003（9）： 57-58.
[4]	尚永艳. 刀柄式压电切削测力仪研究［D］. 大连：大连理工大学， 2014.
	SHANG Yongyan. Research on Piezoelectric Cutting Dynamometer with Tool Handle［D］.Dalian： Dalian University of Technology， 2014.
[5]	解正友. 面向切削过程在线监测的多传感器集成式智能刀柄研究［D］. 哈尔滨：哈尔滨工业大学， 2019.
	XIE Zhengyou. Research on Multi-sensor Integrated Intelligent Tool Holder for Online Monitoring of Cutting Process［D］.Harbin： Harbin Institute of Technology， 2019.
[6]	李文德. 基于声表面波原理的智能刀具系统关键技术研究［D］. 哈尔滨：哈尔滨工业大学， 2013.
	LI Wende. Research on Key Technologies of Intelligent Tool System Based on SAW Principle［D］.Harbin： Harbin Institute of Technology， 2013.
[7]	SUN X， BATEMAN R， CHENG K， et al. Design and Analysis of an Internally Cooled Smart Cutting Tool for Dry Cutting［J］. Proceedings of the Institution of Mechanical Engineers， Part B： Journal of Engineering Manufacture， 2012， 226（4）： 585-591.
[8]	刘强，张海军，刘献礼，等. 智能刀具研究综述［J］. 机械工程学报， 2021， 57（21）： 248-268.
	LIU Qiang， ZHANG Haijun， LIU Xianli， et al. A Review of Research on Intelligent Cutting Tools［J］. Journal of Mechanical Engineering， 2021， 57（21）： 248-268.
[9]	崔云先，张博文，刘义，等. 智能切削刀具发展现状综述［J］. 大连交通大学学报， 2016， 37（6）： 10-14.
	CUI Yunxian， ZHANG Bowen， LIU Yi， et al. Development Status Summary of Smart Cutting Tool［J］. Journal of Dalian Jiaotong University， 2016， 37（6）： 10-14.
[10]	殷增斌，郝肖华，陈为友，等. 一种新型切削温度感知智能刀具研究［J］. 机械工程学报， 2023， 59（1）： 242-248.
	YIN Zengbin， HAO Xiaohua， CHEN Weiyou， et al. Study on a New Type of Cutting Temperature Sensing Smart Tool［J］. Journal of Mechanical Engineering， 2023， 59（1）： 242-248.
[11]	ZHU Lida， LIU Changfu. Recent Progress of Chatter Prediction， Detection and Suppression in Milling［J］. Mechanical Systems and Signal Processing， 2020， 143： 106840.
[12]	CHEN Fan， LIU Guangya. Active Damping of Machine Tool Vibrations and Cutting Force Measurement with a Magnetic Actuator［J］. The International Journal of Advanced Manufacturing Technology， 2017， 89（1）： 691-700.
[13]	刘海军. 面向铣削过程的无线测振刀柄的关键技术研究［D］. 哈尔滨：哈尔滨工业大学， 2015.
	LIU Haijun. Research on Key Technology of Wireless Vibration Measuring Tool Holder for Milling Process［D］.Harbin： Harbin Institute of Technology， 2015.
[14]	陈奇伟. 面向铣削加工的测振刀柄设计与试验研究［D］. 南京：南京航空航天大学， 2019.
	CHEN Qiwei. Design and Experimental Study of Vibration Measuring Tool Holder for Milling［D］.Nanjing： Nanjing University of Aeronautics and Astronautics， 2019.
[15]	YANG Zhaojun， KAN Yingnan， CHEN Fei， et al. Bayesian Reliability Modeling and Assessment Solution for NC Machine Tools under Small-sample Data［J］. Chinese Journal of Mechanical Engineering， 2015， 28（6）： 1229-1239.
[16]	HOROVÁ I， KOLÁČEK J， ZELINKA J. Kernel Smoothing in MATLAB： Theory and Practice of Kernel Smoothing［M］. Singapore： World Scientific， 2012
[17]	WUNSCH A， LIESCH T， BRODA S. Forecasting Groundwater Levels Using Nonlinear Autoregressive Networks with Exogenous Input （NARX）［J］. Journal of Hydrology， 2018， 567： 743-758.
[18]	CAO Huajun， LIU Lei， WU Bo， et al. Process Optimization of High-speed Dry Milling UD-CF/PEEK Laminates Using GA-BP Neural Network［J］. Composites Part B： Engineering， 2021， 221： 109034.