神经网络类机理建模下的持续自学习控制
针对未知、时变复杂动力学系统在基于模型的控制中的动态建模问题,本文采用前向全连接神经网络对动力学系统进行数据驱动下的非机理拟合建模.通过动态线性化和归一化/反归一化数据处理,基于前向传播算法,将神经网络的网络拓扑计算过程转化成动力学系统机理模型的同构等价表达形式.与基于模型的预测与反演控制相结合,提出了神经网络类机理建模下的持续自学习控制方法,探索了神经网络在动力学系统建模与控制中的可解释性问题.以机械臂为控制对象的仿真结果表明,神经网络类机理模型与机理模型在形式上同构,在参数上近似或等价,可用于控制系统控制品质的定性、定量分析.持续自学习控制对非线性未知、时变复杂系统具有较好的动态适应能力....
Saved in:
| Published in | 控制理论与应用 Vol. 41; no. 5; pp. 885 - 894 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
上海航天控制技术研究所,上海 201109
01.05.2024
上海市空间智能控制技术重点实验室,上海 201109%上海航天控制技术研究所,上海 201109 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1000-8152 |
| DOI | 10.7641/CTA.2023.20771 |
Cover
| Abstract | 针对未知、时变复杂动力学系统在基于模型的控制中的动态建模问题,本文采用前向全连接神经网络对动力学系统进行数据驱动下的非机理拟合建模.通过动态线性化和归一化/反归一化数据处理,基于前向传播算法,将神经网络的网络拓扑计算过程转化成动力学系统机理模型的同构等价表达形式.与基于模型的预测与反演控制相结合,提出了神经网络类机理建模下的持续自学习控制方法,探索了神经网络在动力学系统建模与控制中的可解释性问题.以机械臂为控制对象的仿真结果表明,神经网络类机理模型与机理模型在形式上同构,在参数上近似或等价,可用于控制系统控制品质的定性、定量分析.持续自学习控制对非线性未知、时变复杂系统具有较好的动态适应能力. |
|---|---|
| AbstractList | 针对未知、时变复杂动力学系统在基于模型的控制中的动态建模问题,本文采用前向全连接神经网络对动力学系统进行数据驱动下的非机理拟合建模.通过动态线性化和归一化/反归一化数据处理,基于前向传播算法,将神经网络的网络拓扑计算过程转化成动力学系统机理模型的同构等价表达形式.与基于模型的预测与反演控制相结合,提出了神经网络类机理建模下的持续自学习控制方法,探索了神经网络在动力学系统建模与控制中的可解释性问题.以机械臂为控制对象的仿真结果表明,神经网络类机理模型与机理模型在形式上同构,在参数上近似或等价,可用于控制系统控制品质的定性、定量分析.持续自学习控制对非线性未知、时变复杂系统具有较好的动态适应能力. |
| Abstract_FL | Aiming at the problem of dynamic modeling of unknown and time-varying complex dynamic systems in model-based control,a forward fully connected neural network is used to model the dynamic system with data-driven non mechanism fitting.Through dynamic linearization and normalization/anti normalization data processing,based on the forward propagation algorithm,the topological calculation process of neural network is transformed into isomorphic equivalent expression of dynamic system mechanism model.Combined with model-based prediction and inversion con-trol,a continuous self-learning control method based on the neural network mechanism modeling is proposed,and the interpretability of neural network in dynamic system modeling and control is explored.The simulation results with the manipulator as the control object show that the neural network mechanism model is similar to the mechanism model in form,approximate or equivalent in parameters,and can be used for the qualitative and quantitative analysis of the control quality of the control system.Continuous self-learning control has good dynamic adaptability to nonlinear unknown and time-varying complex systems. |
| Author | 张万超 何永宁 谭天乐 周恒杰 |
| AuthorAffiliation | 上海航天控制技术研究所,上海 201109;上海市空间智能控制技术重点实验室,上海 201109%上海航天控制技术研究所,上海 201109 |
| AuthorAffiliation_xml | – name: 上海航天控制技术研究所,上海 201109;上海市空间智能控制技术重点实验室,上海 201109%上海航天控制技术研究所,上海 201109 |
| Author_FL | ZHANG Wan-chao ZHOU Heng-jie HE Yong-ning TAN Tian-le |
| Author_FL_xml | – sequence: 1 fullname: TAN Tian-le – sequence: 2 fullname: ZHANG Wan-chao – sequence: 3 fullname: HE Yong-ning – sequence: 4 fullname: ZHOU Heng-jie |
| Author_xml | – sequence: 1 fullname: 谭天乐 – sequence: 2 fullname: 张万超 – sequence: 3 fullname: 何永宁 – sequence: 4 fullname: 周恒杰 |
| BookMark | eNotjz1Lw1AYhe9QwVq7-htcUt_3fuStYwl-QcGlzuXG5IoabsEgEjdBVFCsrlJEBz8QOriINvhvmlx_hgFdzhkOPIdnjtXswMaMLSC0yJe4FPQ6LQ5cVEGENVZHAPDaqPgsa6bpbgiACJwU1pnvnu5dPnTfty4fufe8HE3czVmRT8rXx-nnpbs7La9OXD7-OX8rxs_Tr4fy-qW4-JhnM0Ynadz87wbbWl3pBeted3NtI-h0vRRBoBe2fRlpPwqXBQ-lb4gUGKkjKdQ2VySqKSIdSxIxmdBopTiSkDFGgpQkLhps8Y97pK3Rdqe_Nzg8sNVjf_84SbIsqzwlqMpH_ALs2FxO |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.7641/CTA.2023.20771 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| DocumentTitle_FL | Continuous self-learning control under transformation of neural network into isomorphic eauivalent form of mechanism model |
| EndPage | 894 |
| ExternalDocumentID | kzllyyy202405011 |
| GroupedDBID | -01 -0Y 2B. 4A8 5XA 5XJ 92H 92I 93N ABJNI ACGFS ALMA_UNASSIGNED_HOLDINGS CCEZO CCVFK CUBFJ CW9 PSX TCJ TGT U1G U5S UY8 |
| ID | FETCH-LOGICAL-s1031-b864da6db932b46f7750f4ad435c2573a6dd7ae473e7fbfa5521734e1d3754723 |
| ISSN | 1000-8152 |
| IngestDate | Thu May 29 04:08:30 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Keywords | continuous self-learning control 非机理建模 model prediction and inversion control 时变系统 black box system 神经网络建模 机械臂控制 neural network modeling manipulator control 模型预测与反演控制 持续自学习控制 黑箱系统 同构等价表达 non mechanism modeling time varying system isomorphic equivalent expression |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1031-b864da6db932b46f7750f4ad435c2573a6dd7ae473e7fbfa5521734e1d3754723 |
| PageCount | 10 |
| ParticipantIDs | wanfang_journals_kzllyyy202405011 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-05-01 |
| PublicationDateYYYYMMDD | 2024-05-01 |
| PublicationDate_xml | – month: 05 year: 2024 text: 2024-05-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 控制理论与应用 |
| PublicationTitle_FL | Control Theory & Applications |
| PublicationYear | 2024 |
| Publisher | 上海航天控制技术研究所,上海 201109 上海市空间智能控制技术重点实验室,上海 201109%上海航天控制技术研究所,上海 201109 |
| Publisher_xml | – name: 上海航天控制技术研究所,上海 201109 – name: 上海市空间智能控制技术重点实验室,上海 201109%上海航天控制技术研究所,上海 201109 |
| SSID | ssib001102751 ssib002258297 ssib023646306 ssib057620041 ssib051372463 ssj0042201 ssib023167526 |
| Score | 2.4465206 |
| Snippet | 针对未知、时变复杂动力学系统在基于模型的控制中的动态建模问题,本文采用前向全连接神经网络对动力学系统进行数据驱动下的非机理拟合建模.通过动态线性化和归一化/反归一... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 885 |
| Title | 神经网络类机理建模下的持续自学习控制 |
| URI | https://d.wanfangdata.com.cn/periodical/kzllyyy202405011 |
| Volume | 41 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVEBS databaseName: Inspec with Full Text issn: 1000-8152 databaseCode: ADMLS dateStart: 20170701 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text omitProxy: false ssIdentifier: ssib057620041 providerName: EBSCOhost |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1Na9VAcKntRQ_iJ35TwT3Jq8lmP4-b91KKWC-20FtJXvIULE-w7eH1JogKih9XKaIHPxB68CLah_-mffFnOLPZNmnroXpZNrszO7Mz2cxsktkh5FpWSGUYK1q6x0yLS9jupCaXLXBFtGAmLboCA4Vnb8uZeX5zQSyMHRk0_lpaXcmmumt_jSv5H61CG-gVo2T_QbO7g0ID1EG_UIKGoTyUjmmiqBXUJFiJY6qnXaVDTehbTNtVQqwnEi9jiy0moFrSRGA7tkhqNbWAxWmsqY4djKWaY5dug7_pB7QdmgAA0LWIDpdWOixDbeCAE2oVdmlNY9n0fQ_2NjgB6onjpGIgcbxZariD4cDezq2BsHHgGAH60GM8fRPUIIDcdgxVwymHBORFDcKdoARyBcMBFA6XUB02RwFBgmCQ8ZAa5kTYAfDmuxLG6z8T3d29Q9SJNQZOHHWYsBdZxfJBWUhE0YHXk3W6hClUIgAUD2MQhrUPUrnuvCzTMDMYz69DsccOVQeA-fUmGkZFe-F4_6RKCr3f9CnJ0fS15-wUzDyCQlW5bfYdJ35_bWlpMBigdAIRYFT8BFNSsnEyYTuzt-7UvnSIX7Qbvh0TGIa9c83wCAVR--6YiEBG9Sd7EUaKNVItwL4Wl-7u_1ecMZebfFcU1YmqOI0beyfhwun6vbR_t-H5zZ0gx_2WbdJW6-8kGVu7d4ocaxzkeZrI8uO7cviq_PWmHK6X34aj9c3y9ZPt4eboy4etH8_Lt49HLx6Vw43fT79ub3za-vl-9PLz9rPvZ8j8dDLXnmn5jCStZUyH0sq05Hkq8wx2PRmXPQX-do-nOew5umD7IujKVVpwFRWql_VSAc6xingR5phpWrHoLBnvP-gX58hkIQqZh4HqpgZfw6Y60-D9826ea5aCmTxPrvpZL_onzvLift1dOATMRXK0XgmXyPjKw9XiMvjRK9kVr_E_7p6Scg |
| linkProvider | EBSCOhost |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%B1%BB%E6%9C%BA%E7%90%86%E5%BB%BA%E6%A8%A1%E4%B8%8B%E7%9A%84%E6%8C%81%E7%BB%AD%E8%87%AA%E5%AD%A6%E4%B9%A0%E6%8E%A7%E5%88%B6&rft.jtitle=%E6%8E%A7%E5%88%B6%E7%90%86%E8%AE%BA%E4%B8%8E%E5%BA%94%E7%94%A8&rft.au=%E8%B0%AD%E5%A4%A9%E4%B9%90&rft.au=%E5%BC%A0%E4%B8%87%E8%B6%85&rft.au=%E4%BD%95%E6%B0%B8%E5%AE%81&rft.au=%E5%91%A8%E6%81%92%E6%9D%B0&rft.date=2024-05-01&rft.pub=%E4%B8%8A%E6%B5%B7%E8%88%AA%E5%A4%A9%E6%8E%A7%E5%88%B6%E6%8A%80%E6%9C%AF%E7%A0%94%E7%A9%B6%E6%89%80%2C%E4%B8%8A%E6%B5%B7+201109&rft.issn=1000-8152&rft.volume=41&rft.issue=5&rft.spage=885&rft.epage=894&rft_id=info:doi/10.7641%2FCTA.2023.20771&rft.externalDocID=kzllyyy202405011 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fkzllyyy%2Fkzllyyy.jpg |