[1]许晓丽,郭旭东,郑文栋,等.基于电容层析成像传感器的非接触材质识别研究[J].智能系统学报,2025,20(5):1232-1242.[doi:10.11992/tis.202408021]
XU Xiaoli,GUO Xudong,ZHENG Wendong,et al.Electrical capacitance tomography sensor for contactless material recognition[J].CAAI Transactions on Intelligent Systems,2025,20(5):1232-1242.[doi:10.11992/tis.202408021]
点击复制
XU Xiaoli,GUO Xudong,ZHENG Wendong,et al.Electrical capacitance tomography sensor for contactless material recognition[J].CAAI Transactions on Intelligent Systems,2025,20(5):1232-1242.[doi:10.11992/tis.202408021]
基于电容层析成像传感器的非接触材质识别研究
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
20
期数:
2025年第5期
页码:
1232-1242
栏目:
吴文俊人工智能科学技术奖论坛
出版日期:
2025-09-05
- Title:
- Electrical capacitance tomography sensor for contactless material recognition
- Keywords:
- electrical capacitance tomography; planar capacitance sensor; sensor modeling; untouched recognition; material recognition; classification algorithm; LightGBM; Bayesian optimization
- 分类号:
- TP391
- 摘要:
- 电容层析成像技术(electrical capacitance tomography, ECT)凭借其快速、非侵入性的特性，有效规避了光学成像技术在识别材料特性时面临的光线干扰难题。然而，传统的ECT传感器的研究主要集中在逆问题上，很少有研究考虑通过物体介电分布实现无损的非接触识别。因此，本文设计了一款平面ECT传感器，用于非接触条件下的材质识别。使用基于贝叶斯的轻量级梯度提升机 (Bayesian-light gradient boosting machine, Bayesian-LightGBM)构建了材质预测模型，利用贝叶斯优化算法显著提升了模型的预测性能。实验结果显示在接触时准确率高达95.83%；在距离传感器20 mm以内的非接触条件下准确率达到85.28%。这意味着机器人能够以非接触、无损的方式精准获取环境中的材质信息，为机器人技术在复杂环境中的应用开辟了新的可能性。
- Abstract:
- Electrical capacitance tomography (ECT), known for its rapid and nonintrusive characteristics, effectively avoids the optical interference problem commonly encountered in material property identification based on optical imaging technologies. However, conventional ECT sensor research has predominantly focused on solving the inverse problem, with limited emphasis on achieving noncontact, nonintrusive material identification through permittivity distribution analysis. To address this gap, this study introduces a planar ECT sensor designed for noncontact material recognition. A material prediction model based on Bayesian-LightGBM is developed, significantly enhancing the predictive performance through Bayesian optimization algorithms. Experimental results demonstrate a high accuracy rate of 95.83% when in contact and 85.28% accuracy within a noncontact range of 20 mm from the sensor. This indicates that robots can precisely acquire material information in the environment in a noncontact and nonintrusive manner, paving the way for new possibilities in the application of robotics technology in complex environments.
- 参考文献/References:
-
[1] KIM K, CHO J, PYO J, et al. Dynamic object recognition using precise location detection and ANN for robot manipulator[C]//2017 International Conference on Control, Artificial Intelligence, Robotics & Optimization. Prague: IEEE, 2017: 237-241.
[2] CH H S, PREETI N, MARRI S P, et al. Real-time object detection using mobile robot captured images: a deep learning approach[C]//2024 3rd International Conference for Innovation in Technology. Bangalore: IEEE, 2024: 1-6.
[3] FENG Lin, LIU Yang, LI Zan, et al. Discriminative bit selection hashing in RGB-D based object recognition for robot vision[J]. Assembly automation, 2019, 39(1): 17-25.
[4] ZHANG Shixin, SHAN Jianhua, SUN Fuchun, et al. Multimode fusion perception for transparent glass recognition[J]. Industrial Robot: the international journal of robotics research and application, 2022, 49(4): 625-633.
[5] 王业飞, 葛泉波, 刘华平, 等. 机器人视觉听觉融合的感知操作系统[J]. 智能系统学报, 2023, 18(2): 381-389.
WANG Yefei, GE Quanbo, LIU Huaping, et al. A perceptual manipulation system for audio-visual fusion of robots[J]. CAAI transactions on intelligent systems, 2023, 18(2): 381-389.
[6] 李彤, 阎宇航, 安静, 等. 基于触觉阵列感知的机器人稳定抓取判别方法[J]. 华中科技大学学报(自然科学版), 2024, 52(5): 136-143.
LI Tong, YAN Yuhang, AN Jing, et al. Discrimination method for robot stable grasping based on tactile array perception[J]. Journal of Huazhong university of science and technology (natural science edition), 2024, 52(5): 136-143.
[7] PARK K, YUK H, YANG M, et al. A biomimetic elastomeric robot skin using electrical impedance and acoustic tomography for tactile sensing[J]. Science robotics, 2022, 7(67): eabm7187.
[8] GUO Hongchen, TAN Yu jun, CHEN Ge, et al. Artificially innervated self-healing foams as synthetic piezo-impedance sensor skins[J]. Nature communications, 2020, 11(1): 5747.
[9] DUAN Xi, TAURAND S, SOLEIMANI M. Artificial skin through super-sensing method and electrical impedance data from conductive fabric with aid of deep learning[J]. Scientific reports, 2019, 9(1): 8831.
[10] LIN Z H, SMITH S. A natural user interface for realistic tactile perception of object surface texture[C]//2017 9th International Conference on Intelligent Human-Machine Systems and Cybernetics. Hangzhou: IEEE, 2017: 370-373.
[11] KOZYR P, SAVELIEV A, KUZNETSOV L. Determining distance to an object and type of its material based on data of capacitive sensor signal and machine learning techniques[C]//2021 International Siberian Conference on Control and Communications. Kazan: IEEE, 2021: 1-5.
[12] ZHENG Enhao, MAI Jingeng, LIU Yuxiang, et al. Forearm motion recognition with noncontact capacitive sensing[J]. Frontiers in neurorobotics, 2018, 12: 47.
[13] ZHAO Jianwei, FANG Jianhua, WANG Shouzhong, et al. Obstacle avoidance of multi-sensor intelligent robot based on road sign detection[J]. Sensors, 2021, 21(20): 6777.
[14] GOMES D F, LIN Zhonglin, LUO Shan. GelTip: a finger-shaped optical tactile sensor for robotic manipulation[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems. Las Vegas: IEEE, 2020: 9903-9909.
[15] ABABEI C, RICHIE J E. Sensor design for inductive proximity and moving direction sensing of metal targets[C]//2021 10th International Conference on Modern Circuits and Systems Technologies. Thessaloniki: IEEE, 2021: 1-4.
[16] ZHANG Bo, XIANG Zemin, ZHU Siwei, et al. Dual functional transparent film for proximity and pressure sensing[J]. Nano research, 2014, 7(10): 1488-1496.
[17] WARSITO W, FAN L S. Dynamics of spiral bubble plume motion in the entrance region of bubble columns and three-phase fluidized beds using 3D ECT[J]. Chemical engineering science, 2005, 60(22): 6073-6084.
[18] OSPINA ACERO D, CHOWDHURY S M, MARASHDEH Q M, et al. Efficient and flexible sensitivity matrix computation for adaptive electrical capacitance volume tomography[J]. IEEE transactions on instrumentation and measurement, 2020, 70: 4502510.
[19] YOUNGQUIST R C, STOREY J M, NURGE M A, et al. A derivation of the electrical capacitance tomography sensitivity matrix[J]. Measurement science and technology, 2023, 34(2): 025404.
[20] 吕海舟, 金鑫, 吴昀, 等. 电容层析成像技术应用于低温流体反演成像的研究现状[J]. 能源工程, 2024, 44(2): 67-76.
LV Haizhou, JIN Xin, WU Yun, et al. State of the art of electrical capacitance tomography applied to cryogenic fluid inversion imaging[J]. Energy engineering, 2024, 44(2): 67-76.
[21] YE Jiamin, WANG Haigang, YANG Wuqiang. Characterization of electrical capacitance tomography sensors with different diameter[J]. IEEE sensors journal, 2014, 14(7): 2240-2251.
[22] 张立峰, 常恩健. 基于多尺度密集连接网络的电容层析成像图像重建[J]. 计量学报, 2024, 45(5): 678-684.
ZHANG Lifeng, CHANG Enjian. Image reconstruction of electrical capacitance tomography based on multi-scale densely connected network[J]. Acta metrologica sinica, 2024, 45(5): 678-684.
[23] YE Z, BANASIAK R, SOLEIMANI M. Planar array 3D electrical capacitance tomography[J]. Insight-non-destructive testing and condition monitoring, 2013, 55(12): 675-680.
[24] MA G, SOLEIMANI M. A versatile 4D capacitive imaging array: a touchless skin and an obstacle-avoidance sensor for robotic applications[J]. Scientific reports, 2020, 10(1): 11525.
[25] HU Xiaohui, YANG Wuqiang. Planar capacitive sensors-designs and applications[J]. Sensor review, 2010, 30(1): 24-39.
[26] LIU Bo, TANG Chenhui, TANG Kaihao, et al. A water fraction measurement method using heuristic-algorithm-based electrical capacitance tomography images post-processing technology[J]. IEEE access, 2020, 8: 206418-206426.
[27] OSPINA-ACERO D, MARASHDEH Q M, TEIXEIRA F L. Relevance vector machine image reconstruction algorithm for electrical capacitance tomography with explicit uncertainty estimates[J]. IEEE sensors journal, 2020, 20(9): 4925-4939.
[28] FANG Weifu. A nonlinear image reconstruction algorithm for electrical capacitance tomography[J]. Measurement science and technology, 2004, 15(10): 2124-2132.
[29] 孙一心, 钟莹, 王向鸿, 等. 电容式触觉传感器信号检测系统的设计[J]. 纳米技术与精密工程, 2015(1): 28-33.
SUN Yixin, ZHONG Ying, WANG Xianghong, et al. Design of signal detection system of capacitive tactile sensor array[J]. Nanotechnology and precision engineering, 2015(1): 28-33.
[30] KE Guolin, MENG Qi, FINLEY T, et al. LightGBM: a highly efficient gradient boosting decision tree[J]. Advances in neural information processing systems, 2017, 30: 1-9.
[31] FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J]. The annals of statistics, 2001, 29(5): 1189-1232.
[32] 丁建立, 孙玥. 基于LightGBM的航班延误多分类预测[J]. 南京航空航天大学学报, 2021, 53(6): 847-854.
DING Jianli, SUN Yue. Multi-classification prediction of flight delay based on LightGBM[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2021, 53(6): 847-854.
[33] MOCKUS J. Application of Bayesian approach to numerical methods of global and stochastic optimization[J]. Journal of global optimization, 1994, 4(4): 347-365.
[34] 李亚茹, 张宇来, 王佳晨. 面向超参数估计的贝叶斯优化方法综述[J]. 计算机科学, 2022, 49(S1): 86-92.
LI Yaru, ZHANG Yulai, WANG Jiachen. Survey on Bayesian optimization methods for hyper-parameter tuning[J]. Computer science, 2022, 49(S1): 86-92.
备注/Memo
收稿日期:2024-8-29。
基金项目:国家自然科学基金国际合作重点项目(62120106005).
作者简介:许晓丽，硕士研究生，主要研究方向为电容传感器、机器人触觉感知。E-mail：suger-xu@hotmail.com。;郭旭东，教授，中国自动化学会智能自动化专业委员会委员，主要研究方向为嵌入式系统设计、智能传感器和智能诊断系统图像处理算法。E-mail：guoxd@usst.edu.cn。;刘华平，教授，中国人工智能学会理事、中国人工智能学会认知系统与信息处理专业委员会秘书长，吴文俊人工智能科学技术奖获得者。主要研究方向为机器人感知、学习与控制和多模态信息融合。主持国家自然科学基金重点项目2项，发表学术论文100 余篇。E-mail：hpliu@tsinghua.edu.cn。
通讯作者:刘华平. E-mail：hpliu@tsinghua.edu.cn
更新日期/Last Update:
2025-09-05