[1]陈德旺,王蕊,孔令坤,等.基于模糊系统的第三代人工智能[J].智能系统学报,2025,20(5):1071-1081.[doi:10.11992/tis.202407011]
CHEN Dewang,WANG Rui,KONG Lingkun,et al.Third-generation artificial intelligence based on fuzzy systems[J].CAAI Transactions on Intelligent Systems,2025,20(5):1071-1081.[doi:10.11992/tis.202407011]
点击复制
CHEN Dewang,WANG Rui,KONG Lingkun,et al.Third-generation artificial intelligence based on fuzzy systems[J].CAAI Transactions on Intelligent Systems,2025,20(5):1071-1081.[doi:10.11992/tis.202407011]
基于模糊系统的第三代人工智能
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
20
期数:
2025年第5期
页码:
1071-1081
栏目:
综述
出版日期:
2025-09-05
- Title:
- Third-generation artificial intelligence based on fuzzy systems
- Keywords:
- third-generation artificial intelligence; fuzzy systems; three-space fusion model; knowledge-driven; data-driven; universal approximation; fuzzy expert systems; data-driven fuzzy system identification
- 分类号:
- TP39
- 摘要:
- 人工智能经历了第一代人工智能和第二代人工智能2个发展阶段，2个阶段的人工智能分别运用以控制逻辑为核心的知识驱动和以数据学习为核心的数据驱动建构算法系统，以模拟人类的生物智能。2种路径各有优势，但存在算力有限和可解释性缺陷等缺点，第三代人工智能理论与方法正致力于发展抗噪、鲁棒且可解释的人工智能。为实现这一目标，详细讨论了基于知识驱动和数据驱动相融合的第三代人工智能的建模方法，并在此第三代人工智能的基础上，探讨将模糊系统与第三代人工智能相结合，充分利用模糊系统鲁棒性与可解释性强的优势，推动第三代人工智能的发展，希望对未来第三代人工智能发展具有一定借鉴意义。
- Abstract:
- Artificial Intelligence (AI) has undergone two stages of development. The first-generation AI relied on knowledge-driven algorithmic systems focused on control logic, while the second-generation AI shifted toward data-driven systems emphasizing data learning to simulate the biological intelligence of human beings. Both approaches have their strengths. However, they face limitations such as limited computational power and issues with interpretability. To address these shortcomings, third-generation AI theories and methodologies aim to develop systems that are noise-resistant, robust, and interpretable. This paper discusses the modeling methods for third-generation AI, which are based on integrating knowledge-driven and data-driven approaches. It also examines the potential of combining third-generation AI with fuzzy systems. By leveraging the robust and interpretable characteristics of fuzzy systems, the advancement of third-generation AI can be further accelerated. The insights presented offer a valuable reference for shaping the future development of third-generation AI.
- 参考文献/References:
-
[1] 郑南宁. 人工智能新时代[J]. 智能科学与技术学报, 2019(1): 1-3.
ZHENG Nanning. The new era of artificial intelligence[J]. Chinese journal of intelligent science and technology, 2019(1): 1-3.
[2] ZADEH L A. Fuzzy sets[J]. Information and control, 1965, 8(3): 338-353.
[3] WANG Lixin. Fuzzy systems are universal approximators[C]//IEEE International Conference on Fuzzy Systems. San Diego: IEEE, 1992: 1163-1170.
[4] KOSKO B. Fuzzy systems as universal approximators[J]. IEEE transactions on computers, 1994, 43(11): 1329-1333.
[5] 刘慧林, 冯汝鹏, 胡瑞栋, 等. 模糊系统作为通用逼近器的10年历程[J]. 控制与决策, 2004, 19(4): 367-371.
LIU Huilin, FENG Rupeng, HU Ruidong, et al. Decennary development of fuzzy systems as universal approximators[J]. Control and decision, 2004, 19(4): 367-371.
[6] CASTRO J L. Fuzzy logic controllers are universal approximators[J]. IEEE transactions on systems, man, and cybernetics, 1995, 25(4): 629-635.
[7] JANG J R, SUN C T. Functional equivalence between radial basis function networks and fuzzy inference systems[J]. IEEE transactions on neural networks, 1993, 4(1): 156-159.
[8] PARK J, SANDBERG I W. Universal approximation using radial-basis-function networks[J]. Neural computation, 1991, 3(2): 246-257.
[9] ZENG Xiaojun, SINGH M G. Approximation theory of fuzzy systems-MIMO case[J]. IEEE transactions on fuzzy systems, 1995, 3(2): 219-235.
[10] 陈德旺, 蔡际杰, 黄允浒. 面向可解释性人工智能与大数据的模糊系统发展展望[J]. 智能科学与技术学报, 2019, 1(4): 327-334.
CHEN Dewang, CAI Jijie, HUANG Y (H /X). Development prospect of fuzzy system oriented to interpretable artificial intelligence and big data[J]. Chinese journal of intelligent science and technology, 2019, 1(4): 327-334.
[11] FERNANDEZ A, HERRERA F, CORDON O, et al. Evolutionary fuzzy systems for explainable artificial intelligence: why, when, what for, and where to?[J]. IEEE computational intelligence magazine, 2019, 14(1): 69-81.
[12] CAO Jin, ZHOU Ta, ZHI Shaohua, et al. Fuzzy inference system with interpretable fuzzy rules: advancing explainable artificial intelligence for disease diagnosis: a comprehensive review[J]. Information sciences, 2024, 662: 120212.
[13] 刘福才, 陈超, 邵慧, 等. 模糊系统万能逼近理论研究综述[J]. 智能系统学报, 2007, 2(1): 25-34.
LIU Fucai, CHEN Chao, SHAO Hui, et al. Researches for universal approximation of fuzzy systems: a survey[J]. CAAI transactions on intelligent systems, 2007, 2(1): 25-34.
[14] SUN Changle, LI Haitao. Construction of universal approximators for multi-input single-output hierarchical fuzzy systems[J]. IEEE transactions on fuzzy systems, 2023, 31(12): 4170-4179.
[15] 游文虎, 王茂, 施佳. PIE+MOM的Mamdani模糊系统通用逼近性充要条件[J]. 哈尔滨工业大学学报, 2014, 46(11): 1-7.
YOU Wenhu, WANG Mao, SHI Jia. Sufficient and necessary condition of Mamdani fuzzy systems with PIE and MOM as universal approximators[J]. Journal of Harbin Institute of Technology, 2014, 46(11): 1-7.
[16] 王宁, 谭跃, 王丹, 等. 一般齐次T-S模糊系统的逼近性能[J]. 智能系统学报, 2010, 5(5): 436-442.
WANG Ning, TAN Yue, WANG Dan, et al. Study on approximation capabilities of general homogenous T-S fuzzy systems[J]. CAAI transactions on intelligent systems, 2010, 5(5): 436-442.
[17] SHEN Hanhan, PAN Xiaodong, PENG Xiaoyu, et al. A new type of fuzzy systems in terms of vague partitions[J]. Journal of intelligent & fuzzy systems, 2023, 44(6): 9545-9563.
[18] ZENG Xiaojun, SINGH M G. Approximation accuracy analysis of fuzzy systems as function approximators[J]. IEEE transactions on fuzzy systems, 1996, 4(1): 44-63.
[19] ZENG Xiaojun, SINGH M G. A relationship between membership functions and approximation accuracy in fuzzy systems[J]. IEEE transactions on systems, man, and cybernetics, part B (cybernetics), 1996, 26(1): 176-180.
[20] WANG Lixin, WEI Chen. Approximation accuracy of some neuro-fuzzy approaches[J]. IEEE transactions on fuzzy systems, 2000, 8(4): 470-478.
[21] YAN Wen, ZHAO Tao, GONG Xin. An explicit-time and explicit-accuracy control for a state-constrained nonstrict-feedback uncertain system based on adaptive fuzzy dynamic-approximation[J]. Journal of the franklin institute, 2023, 360(9): 6425-6462.
[22] RAJA P, AGHILI-ASHTIANI A. G-normal fuzzy relational models are universal approximators[J]. Fuzzy sets and systems, 2023, 471: 108682.
[23] TAO Yujie, SUO Chunfeng, WANG Guijun. Approximation factor of the piecewise linear functions in Mamdani fuzzy system and its realization process[J]. Journal of intelligent & fuzzy systems, 2021, 41(6): 6859-6873.
[24] 李峰, 王琦, 胡健雄, 等. 数据与知识联合驱动方法研究进展及其在电力系统中应用展望[J]. 中国电机工程学报, 2021, 41(13): 4377-4389.
LI Feng, WANG Qi, HU Jianxiong, et al. Combined data-driven and knowledge-driven methodology research advances and its applied prospect in power systems[J]. Proceedings of the CSEE, 2021, 41(13): 4377-4389.
[25] 王飞跃, 缪青海. 人工智能驱动的科学研究新范式: 从AI4S到智能科学[J]. 中国科学院院刊, 2023, 38(4): 536-540.
WANG Feiyue, MIAO Qinghai. Bulletin of Chinese academy of sciences, 2023, 38(4): 536-540.
[26] ZHENG Ying, CHEN Haoyu, DUAN Qingyang, et al. Leveraging domain knowledge for robust deep reinforcement learning in networking[C]//IEEE Conference on Computer Communications. Vancouver: IEEE, 2021: 1-10.
[27] 金哲, 张引, 吴飞, 等. 数据驱动与知识引导结合下人工智能算法模型[J]. 电子与信息学报, 2023, 45(7): 2580-2594.
JIN Zhe, ZHANG Yin, WU Fei, et al. Artificial intelligence algorithms based on data-driven and knowledge-guided models[J]. Journal of electronics & information technology, 2023, 45(7): 2580-2594.
[28] 万超. 知识驱动与数据驱动系统构建综述[J]. 长江信息通信, 2021(4): 145-147.
WAN Chao. Summary of knowledge-driven and data-driven system construction[J]. Changjiang information & communications, 2021(4): 145-147.
[29] XIE Xiaozheng, NIU Jianwei, LIU Xuefeng, et al. A survey on incorporating domain knowledge into deep learning for medical image analysis[J]. Medical image analysis, 2021, 69: 101985.
[30] 杨浩, 王佳怡, 易文飞, 等. 知识–数据融合驱动的配电网光伏逆变器 电压/无功优化自适应控制[J/OL]. 中国电机工程学报.https://doi.org/10.13334/j.0258-8013.pcsee.241838 .
YANG Hao , WANG Jiayi , YI Wenfei, et al. Hybrid knowledge-data driven adaptive voltage/var optimization control of photovoltaic inverters in distribution networks[J/OL]. Proceedings of the CSEE.https://doi.org/10.13334/j.0258-8013.pcsee.241838 .
[31] 张钹, 朱军, 苏航. 迈向第三代人工智能[J]. 中国科学(信息科学), 2020, 50(9): 1281-1302.
ZHANG Bo, ZHU Jun, SU Hang. Toward the third generation of artificial intelligence[J]. Scientia sinica (informationis), 2020, 50(9): 1281-1302.
[32] NURMINEN J K, KARONEN O, H?T?NEN K. What makes expert systems survive over 10 years: empirical evaluation of several engineering applications[J]. Expert systems with applications, 2003, 24(2): 199-211.
[33] KANDEL A. Fuzzy expert systems[M]. Boca Raton: CRC press, 1991.
[34] ROBINSON J A. A machine-oriented logic based on the resolution principle[J]. Journal of the ACM, 1965, 12(1): 23-41.
[35] ESLAMI E, BUCKLEY J J. Inverse approximate reasoning[J]. Fuzzy sets and systems, 1997, 87(2): 155-158.
[36] JANG J R. ANFIS: adaptive-network-based fuzzy inference system[J]. IEEE transactions on systems, man, and cybernetics, 1993, 23(3): 665-685.
[37] CORDON O, HERRERA F, GOMIDE F, et al. Ten years of genetic fuzzy systems: current framework and new trends[C]//Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference. Vancouver: IEEE, 2001: 1241-1246.
[38] 孙富春, 罗敏楠. 模糊系统建模综述[J]. 杭州电子科技大学学报, 2015, 35(5): 1-6.
SUN Fuchun, LUO Minnan. A review of fuzzy system modeling[J]. Journal of Hangzhou Dianzi University, 2015, 35(5): 1-6.
[39] JAKUBEK S, HAMETNER C, KEUTH N. Total least squares in fuzzy system identification: an application to an industrial engine[J]. Engineering applications of artificial intelligence, 2008, 21(8): 1277-1288.
[40] YEN J, WANG L. Simplifying fuzzy rule-based models using orthogonal transformation methods[J]. IEEE transactions on systems, man, and cybernetics Part B, Cybernetics, 1999, 29(1): 13-24.
[41] CORDON O, HERRERA F, DEL JESUS M J, et al. A multiobjective genetic algorithm for feature selection and granularity learning in fuzzy-rule based classification systems[C]//Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference. Vancouver: IEEE, 2002: 1253-1258.
[42] ISHIBUCHI H, YAMAMOTO T. Fuzzy rule selection by multi-objective genetic local search algorithms and rule evaluation measures in data mining[J]. Fuzzy sets and systems, 2004, 141(1): 59-88.
- 相似文献/References:
-
[1]孙富春,杨 晋,刘华平.SISO Mamdani模糊系统作为函数逼近器的必要条件[J].智能系统学报,2009,4(4):288.
SUN Fu-chun,YANG Jin,LIU Hua-ping.Preconditions for SISO Mamdani fuzzy systems to perform as function approximators[J].CAAI Transactions on Intelligent Systems,2009,4():288.
[2]蒋云良,印泽宗,张雄涛,等.高阶Takagi-Sugeno-Kang模糊知识蒸馏分类器及其在脑电信号分类中的应用[J].智能系统学报,2024,19(6):1419.[doi:10.11992/tis.202307029]
JIANG Yunliang,YIN Zezong,ZHANG Xiongtao,et al.TSK fuzzy distillation classifier with negative Euclidean probability and High-order fuzzy dark knowledge transfer and its application on EEG signals classification[J].CAAI Transactions on Intelligent Systems,2024,19():1419.[doi:10.11992/tis.202307029]
[3]张雄涛,陈天宇,赵康,等.基于多教师自适应知识蒸馏的TSK模糊分类器[J].智能系统学报,2025,20(5):1136.[doi:10.11992/tis.202410028]
ZHANG Xiongtao,CHEN Tianyu,ZHAO Kang,et al.TSK fuzzy classifier based on multi-teacher adaptive knowledge distillation[J].CAAI Transactions on Intelligent Systems,2025,20():1136.[doi:10.11992/tis.202410028]
备注/Memo
收稿日期:2024-7-8。
基金项目:福建省第三批创新之星人才计划项目 (003002)；福建省财政厅教育科研专项资金项目 (GY-Z21001)；福建理工大学科研基金项目 (GY-Z22071).
作者简介:陈德旺，教授，博士，电气电子工程师学会(IEEE) 高级会员、中国自动化学会高级会员，主要研究方向为人工智能算法、模糊系统和智能交通系统。发表学术论文200余篇，出版学术专著4部，出版科普专著2部。E-mail：dwchen@fjut.edu.cn。;王蕊，硕士研究生，主要研究方向为模糊系统、列车运行时刻表优化。E-mail：wangrui175@163.com。;孔令坤，博士研究生，主要研究方向为柔性生产线控制与通信优化。E-mail：klk@126.com。
通讯作者:陈德旺. E-mail：dwchen@fjut.edu.cn
更新日期/Last Update:
2025-09-05