复杂系统多传感器数据智能融合方法研究

doi:10.3901/JME.2025.04.067

摘要/Abstract

摘要： 如何将复杂系统中各种传感器测量信息进行有效融合，从而形成系统智能控制的依据，是当前智能化领域研究的热点。传统的多传感器数据融合结构一旦确定便无法改变，既缺少足够的弹性计算能力保障，限制其他传感器的加入，也阻碍系统多传感器网络的构建。为了能够形成传感器网络以汇聚全面的系统数据，提出数据智能融合方法。首先借鉴云计算中的数据池思想，在架构上设计基于数据池的数据流动结构，传感器测量信息被汇聚在数据池中，相关算法被视同为服务，解决了数据处理的弹性计算能力问题；其次，经服务处理后的数据池数据，按需求被推送到控制系统，保证了数据处理与控制分离，形成以数据池为中心的星状传感器网络；最后，设计基于检测信号的通用非模型数据融合算法框架，通过信号分解后的系数进行拟合，再利用重构信号进行状态修正，完全摆脱了对系统模型的依赖，将数据融合计算形成了服务，大大降低了后期由于传感器引入对系统控制的影响。通过从设计思想、结构演进过程和特性分析对数据智能融合方法的分析表明，其具备较高的可行性和有效性。该方法的提出可以为我国复杂系统智能控制领域研究提供一条新的思路。

关键词: 数据池, 智能控制, 非模型, 多传感器, 数据融合

Abstract: How to effectively integrate various sensor measurement information in complex systems to form the basis for intelligent control of the system is currently a hot research topic in the field of intelligence. Once the traditional multi-sensor data fusion structure is determined, it cannot be changed which lacks sufficient elastic computing power to ensure the addition of other sensors, and also hinders the construction of the system’s multi-sensor network. In order to form a sensor network to gather comprehensive system data, firstly, a data flow structure based on a data pool is designed on the architecture. So the sensor measurement information is aggregated in the data pool, and related algorithms are treated as services, solving the problem of elastic computing power in data processing; Secondly, the data processed by the service is pushed to the control system according to demand, separating data processing from control, forming a star shaped sensor network centered on the data pool; Finally, an universal non-model data fusion algorithm framework based on detection signals was designed. Which the coefficients after signal decomposition were fitted, and the reconstructed signals were used for state correction, completely eliminating the dependence on the system model and greatly reducing the impact of sensor entering control system. At last, summarized the feasibility and effectiveness of the method from the perspective of design philosophy, structural evolution process, and characteristic analysis. The proposal of this method can provide a new approach for the research of intelligent control of complex systems.

Key words: data pool, intelligent control, non-model, multi-sensor, data fusion

中图分类号:

V464

黄莹. 复杂系统多传感器数据智能融合方法研究[J]. 机械工程学报, 2025, 61(4): 67-73.

HUANG Ying. Research on Intelligent Fusion Method for Multi Sensor Data in Complex Systems[J]. Journal of Mechanical Engineering, 2025, 61(4): 67-73.

参考文献

[1] HUANG Ying. Research on an intelligent structure for push control of multi-center cloud data pool[C]//20235th International Conference on Intelligent Control，Measurement and Signal Processing (ICMSP)，Chengdu，China. NewYork:IEEE，2023:1084-1089.
[2] 黄莹，卢秉恒，赵万华. 云计算在智能机床控制体系中的应用探析[J]. 机械工程学报，2018，54(8):210-216. HUANG Ying，LU Bingheng，ZHAO Wanhua. Application analysis of cloud computing in intelligent machine tool control system[J]. Journal of Mechanical Engineering，2018，54(8):210-216.
[3] 陈吉红，杨建中，周会成. 新一代智能化数控系统[M]. 北京:清华大学出版社，2021. Chen Jihong，Yang Jianzhong，Zhou Huicheng. New generation intelligent CNC system[M]. Beijing:Tsinghua University Press，2021.
[4] Huang Ying，Zhao Wanhua，LU Bingheng. A novel methodology on the state estimation of the machine tools based on the multi-sensor information fusion in time-frequency space[C]//2013 IEEE International Symposium on Assembly and Manufacturing (ISAM)，Xi’an，China. NewYork:IEEE，2013:352-356.
[5] 苏有能. 对开放式数控系统的研究综述[J]. 硅谷，2008(6):128. SU Youneng. A review of research on open CNC systems[J]. Silicon Valley，2008(6):128.
[6] 胡泊. 基于开放式数控系统的体系结构及恒力铣削技术研究[D]. 哈尔滨:哈尔滨工业大学，2011. Hu Bo. Research on architecture and constant force milling technology based on open CNC system[D]. Harbin:Harbin Institute of Technology，2011.
[7] 张浩，唐敦兵，郑庆康. 基于运动控制卡的多轴联动控制系统设计[J]. 机械制造与自动化，2018，47(1):184-186. Zhang Hao，Tang Dunbing，Zheng Qingkang. Design of multi axis linkage control system based on motion control card[J]. Mechanical Manufacturing and Automation，2018，47(1):184-186
[8] 何琳，许阳，陈幼平，等. 基于软件芯片库的开放式数控系统重构[J]. 机械与电子，2001(2):44-48. He Lin，Xu Yang，Chen Youping，et al. Reconstruction of open CNC system based on software chip library[J]. Mechanical and Electronics，2001(2):44-48
[9] 黄振庭，刘建群，程帅，等. 基于UMAC的高精密机床开放式数控系统的开发[J]. 组合机床与自动化加工技术，2019(10):57-59，64. Huang Zhenting，Liu Jianqun，Cheng Shuai，et al. Development of open CNC system for high precision machine tool based on UMAC[J]. Combination Machine Tool and Automation Processing Technology，2019(10):57-59，64.
[10] 李备备. 面向航空制造的总线式高档数控系统关键技术的研究[D]. 北京:中国科学院大学，2019. Li Beibei. Research on key technologies of bus based high end CNC system for aviation manufacturing[D]. Beijing:University of Chinese Academy of Sciences，2019.
[11] 陶瞩，高赛赛，黄莹. 基于时频空间的非模型组合导航滤波方法[J]. 计算机测量与控制，2019，27(8):258-261. Tao Zhu，Gao Saisai，Huang Ying. Non model integrated navigation filtering method based on time-frequency space[J]. Computer Measurement and Control，2019，27(8):258-261.
[12] Pimenov D Y，Bustillo A，Wojciechowski S，et al. Artificial intelligence systems for tool condition monitoring in machining:Analysis and critical review[J]. Journal of Intelligent Manufacturing，2023，34(5):2079-2121.
[13] Segreto T，Teti R. Data quality evaluation for smart multi-sensor process monitoring using data fusion and machine learning algorithms[J]. Production Engineering，2023，17(2):197-210.
[14] Zhang Zhao，Jiang Feng，LUO Ming，et al. Geometric error measuring，modeling，and compensation for CNC machine tools:A review[J]. Chinese Journal of Aeronautics，2024，37(2):163-198.
[15] Cai Y，XIONG J，Chen H，et al. A review of in-situ monitoring and process control system in metal-based laser additive manufacturing[J]. Journal of Manufacturing Systems，2023，70:309-326.
[16] 陆小虎. 开放式数控系统网络化平台关键技术研究与应用[D]. 北京:中国科学院大学，2015. Lu Xiaohu. Research and application on key technologies ofnetwork platform for open CNC system[D]. Beijing:University of Chinese Academy of Sciences，2015.
[17] Tingarikar G，Choudhury A. Vibration analysis-based fault diagnosis of a dynamically loaded bearing with distributed defect[J]. Arabian Journal for Science and Engineering，2022，47(7):8045-8058.
[18] Goyal D，Mongia C，Sehgal S. Applications of digital signal processing in monitoring machining processes and rotary components:A review[J]. IEEE Sensors Journal，2021，21(7):8780-8804.
[19] Tran M Q，Liu M K，Elsisi M. Effective multi-sensor data fusion for chatter detection in milling process[J]. ISA Transactions，2022，125:514-527.
[20] Huang Y C，Liao H S. Building prediction model for a machine tool with genetic algorithm optimization on a general regression neural network[J]. Journal of Intelligent & Fuzzy Systems，2020，38(2):2347-2357.
[21] Chua Z Y，Ahn I H，Moon S K. Process monitoring and inspection systems in metal additive manufacturing:Status and applications[J]. International Journal of Precision Engineering and Manufacturing-Green Technology，2017，4:235-245.
[22] Xu Y，Gui L，XIE T. Intelligent recognition method of turning tool wear state based on information fusion technology and BP neural network[J]. Shock and Vibration，2021，2021:1-10.
[23] Zhang X，Gan H. STF-Net:An improved depth network based on spatio-temporal data fusion for PM2. 5 concentration prediction[J]. Future Generation Computer Systems，2023，144:37-49.
[24] La Fé-Perdomo I，Ramos-Grez J，Mujica R，et al. Surface roughness Ra prediction in selective laser melting of 316L stainless steel by means of artificial intelligence inference[J]. Journal of King Saud University-Engineering Sciences，2023，35(2):148-156.
[25] Liu Zhijian，Tang Haotian，Amini A，et al. Bevfusion:Multi-task multi-sensor fusion with unified bird's-eye view representation[C]//2023 IEEE International Conference on Robotics and Automation (ICRA)，September 29 May. 2 June 2023，2023，ExCeL，London. NewYork:IEEE，2023:2774-2781.