{"corpus_id":119794333,"paper_sha":"ddffb944d989cb19c86802631a5837ff1bf125b8","doi":"10.2514/2.4029","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":3042669952,"dblp_id":null,"acl_id":null,"title":"Nonlinear flight control using neural networks","year":1994,"publication_date":"1994-08-01","venue":"","journal":{"name":"Journal of Guidance Control and Dynamics","pages":"26-33","volume":"20"},"journal_issn":null,"journal_title":null,"publication_types":[],"pubmed_pub_types":null,"s2_fields_of_study":["Computer Science","Engineering"],"reference_count":12,"citation_count":634,"influential_citation_count":18,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"The theoretical developmentofa direct adaptivetracking controlarchitectureusingneuralnetworks ispresented. Emphasis is placed on utilization of neural networks in a  ight control architecture based on feedback linearization of the aircraft dynamics. Neural networks are used to represent the nonlinear inverse transformation needed for feedback linearization. Neural networks may be Ž rst trained off line using a nominalmathematicalmodel, which provides an approximate inversion that can accommodate the total  ight envelope. Neural networks capable of on-line learning are required to compensate for inversion error, which may arise from imperfect modeling, approximate inversion, or sudden changes in aircraft dynamics. A stable weights adjustment rule for the on-line neural network is derived. Under mild assumptions on the nonlinearities representing the inversion error, the adaptation algorithm ensures that all of the signals in the loop are uniformly bounded and that the weights of the on-line neural network tend to constant values. Simulation results for an F-18 aircraft model are presented to illustrate the performance of the on-line neural network based adaptation algorithm.","claims":[{"public_id":"cl_85edd5e32ce9ec5e4fc4422866675ae3","status":"active","text":"A direct adaptive tracking control architecture using neural networks is developed for nonlinear flight control based on feedback linearization.","confidence":0.98,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_85edd5e32ce9ec5e4fc4422866675ae3"},{"public_id":"cl_c683fc2972d963ffdde5ee0069df49bb","status":"active","text":"An online neural network with a derived stable weights adjustment rule compensates for inversion error from imperfect modeling, approximate inversion, or sudden changes in aircraft dynamics.","confidence":0.96,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_c683fc2972d963ffdde5ee0069df49bb"},{"public_id":"cl_9ee6e5bf1ddd94da4360911ab87b36f9","status":"active","text":"Neural networks are used to represent the nonlinear inverse transformation required by the feedback-linearized aircraft dynamics.","confidence":0.97,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_9ee6e5bf1ddd94da4360911ab87b36f9"},{"public_id":"cl_733247ccd586d2fa1859fe7a1afcf0a1","status":"active","text":"Offline training with a nominal mathematical model provides an approximate inversion that can cover the total flight envelope.","confidence":0.91,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_733247ccd586d2fa1859fe7a1afcf0a1"},{"public_id":"cl_45d9b952c2624b0bc3042715817f5786","status":"active","text":"Simulation results for an F-18 aircraft model illustrate the performance of the online neural-network adaptation algorithm.","confidence":0.93,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_45d9b952c2624b0bc3042715817f5786"},{"public_id":"cl_476c78a40c6fc776be2d6b300b94fce9","status":"active","text":"Under mild assumptions on the inversion-error nonlinearities, the adaptation algorithm keeps all loop signals uniformly bounded and drives the online neural-network weights to constant values.","confidence":0.95,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_476c78a40c6fc776be2d6b300b94fce9"}],"concepts":[{"public_id":"co_197eba0cf75ce455d42d415a600e0aac","status":"active","name":"simulation results","description":"Numerical evaluation outcomes used to demonstrate controller behavior.","types":["evaluation result"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_197eba0cf75ce455d42d415a600e0aac"},{"public_id":"co_1a1fc6aa35e2f990e22bcc1cd65483d6","status":"active","name":"feedback linearization","description":"A control design approach that cancels nonlinear dynamics to obtain a linearized closed-loop system.","types":["control method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1a1fc6aa35e2f990e22bcc1cd65483d6"},{"public_id":"co_1e63bdb6c1ab940824aed357ccc6481d","status":"active","name":"offline training","description":"Prior training of the neural network using a model before online operation.","types":["training procedure"],"aliases":["off-line training"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1e63bdb6c1ab940824aed357ccc6481d"},{"public_id":"co_2ed99652805f18c026659701faef8336","status":"active","name":"adaptation algorithm","description":"The online learning and parameter-update procedure used by the controller.","types":["algorithm"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_2ed99652805f18c026659701faef8336"},{"public_id":"co_557985f8f353f9b1d8958ad358817a3f","status":"active","name":"uniformly bounded signals","description":"Closed-loop signals whose magnitudes remain bounded by a finite limit over time.","types":["stability property"],"aliases":["bounded signals"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_557985f8f353f9b1d8958ad358817a3f"},{"public_id":"co_62d872589d72b15619fe4775c6bd6fe9","status":"active","name":"online neural network","description":"A neural network that continues adapting during flight control operation.","types":["method"],"aliases":["on-line neural network"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_62d872589d72b15619fe4775c6bd6fe9"},{"public_id":"co_719595c03405b09c9a28d7ac2fddeb89","status":"active","name":"stable weights adjustment rule","description":"An update law for neural-network parameters designed to maintain stability.","types":["learning rule"],"aliases":["weights adjustment rule"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_719595c03405b09c9a28d7ac2fddeb89"},{"public_id":"co_851e39d1fd23bed04cad86ca4cd3b912","status":"active","name":"inversion-error nonlinearities","description":"Nonlinear terms associated with the inversion error in the control loop.","types":["mathematical structure"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_851e39d1fd23bed04cad86ca4cd3b912"},{"public_id":"co_95a79d2b0ece3b7e0d8611df39c89bdd","status":"active","name":"direct adaptive tracking control architecture","description":"A control framework that adapts its parameters online to make an aircraft follow desired trajectories.","types":["method"],"aliases":["adaptive tracking control architecture"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_95a79d2b0ece3b7e0d8611df39c89bdd"},{"public_id":"co_a4e0aa50f9abbbcecc93e6cbbf04f0b9","status":"active","name":"aircraft dynamics","description":"The nonlinear dynamic behavior of the aircraft being controlled.","types":["system dynamics"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_a4e0aa50f9abbbcecc93e6cbbf04f0b9"},{"public_id":"co_ad5ea1436ea5730ecbd825c25f2fbe82","status":"active","name":"total flight envelope","description":"The full range of operating conditions for the aircraft.","types":["operating domain"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ad5ea1436ea5730ecbd825c25f2fbe82"},{"public_id":"co_dee741097df30d3715b650f33341894a","status":"active","name":"neural networks","description":"Computational models used here to approximate nonlinear mappings in the control system.","types":["method"],"aliases":["NNs"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_dee741097df30d3715b650f33341894a"},{"public_id":"co_e5a4e4ae90beb4a4a327f218fe1dbc21","status":"active","name":"F-18 aircraft model","description":"A simulation model of an F-18 aircraft used to evaluate the control method.","types":["simulation model"],"aliases":["F-18 model"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_e5a4e4ae90beb4a4a327f218fe1dbc21"},{"public_id":"co_e6de3895592e372373138ccfd49f5745","status":"active","name":"nominal mathematical model","description":"An approximate model of the aircraft dynamics used for offline neural-network training.","types":["model"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_e6de3895592e372373138ccfd49f5745"},{"public_id":"co_eb9b39a3e5d25ff9656eb9d7f55d55b2","status":"active","name":"nonlinear inverse transformation","description":"The inverse mapping of the aircraft nonlinear dynamics needed for feedback linearization.","types":["mathematical transformation"],"aliases":["inverse transformation"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_eb9b39a3e5d25ff9656eb9d7f55d55b2"},{"public_id":"co_f2fe535c26f789c58857abba7dcf1e91","status":"active","name":"inversion error","description":"The mismatch between the true nonlinear inverse transformation and its approximation.","types":["error"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_f2fe535c26f789c58857abba7dcf1e91"}],"external_ids":{"DOI":"10.2514/2.4029","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":3042669952,"DBLP":null,"ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/119794333","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":631134,"paper_uid":"c96aa61e-4989-4cfb-ab92-73b9ec76b61b","canonical_identity":{"paper_id":631134,"paper_uid":"c96aa61e-4989-4cfb-ab92-73b9ec76b61b","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/119794333"}