Neural network-based state estimation of nonlinear systems: application to fault detection and isolation
Saved in:
| Format: | Book |
|---|---|
| Language: | English |
| Published: |
New York [u.a.]
Springer
2010
|
| Series: | Lecture notes in control and information sciences
395 |
| Subjects: | |
| Online Access: | Inhaltsverzeichnis |
| Physical Description: | XIX, 154 S. Ill., graph. Darst. |
| ISBN: | 9781441914378 |
Staff View
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV036037632 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 100217s2010 ad|| |||| 00||| eng d | ||
| 020 | |a 9781441914378 |9 978-1-4419-1437-8 | ||
| 035 | |a (OCoLC)698858396 | ||
| 035 | |a (DE-599)BSZ315050241 | ||
| 040 | |a DE-604 |b ger |e rakwb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-83 | ||
| 084 | |a SI 845 |0 (DE-625)143198: |2 rvk | ||
| 245 | 1 | 0 | |a Neural network-based state estimation of nonlinear systems |b application to fault detection and isolation |c Heidar A. Talebi ... |
| 264 | 1 | |a New York [u.a.] |b Springer |c 2010 | |
| 300 | |a XIX, 154 S. |b Ill., graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a Lecture notes in control and information sciences |v 395 | |
| 650 | 0 | 7 | |a Neuronales Netz |0 (DE-588)4226127-2 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Nichtlineares System |0 (DE-588)4042110-7 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Neuronales Netz |0 (DE-588)4226127-2 |D s |
| 689 | 0 | 1 | |a Nichtlineares System |0 (DE-588)4042110-7 |D s |
| 689 | 0 | |5 DE-604 | |
| 700 | 1 | |a Talebi, Heidar A. |d 1965- |e Sonstige |0 (DE-588)122392566 |4 oth | |
| 830 | 0 | |a Lecture notes in control and information sciences |v 395 |w (DE-604)BV005848579 |9 395 | |
| 856 | 4 | 2 | |m HBZ Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=018929635&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-018929635 | ||
Record in the Search Index
| _version_ | 1804141064604352512 |
|---|---|
| adam_text | Titel: Neural network-based state estimation of nonlinear systems
Autor: Talebi, Heidar A.
Jahr: 2010
Contents
1 Introduction................................................... i
LI Preamble.................................................. 1
1.2 Background............................................... 7
1.2.1 Multilaycr Neural Networks........................... 7
1.3 Outline................................................... 13
2 Neural Network-Based State Estimation Scheines.................. 15
2.1 Introduction............................................... 15
2.2 Problem Pormulation....................................... 15
2.3 Linear-in-Parameter Neural Network-Based Ohservcr............ 17
2.4 Nonlinear-in-Parameter Neural Network-Based Observer......... 21
2.5 A Gase Study: Application lo State Estimation of Flexible-Joint
Manipulators.............................................. 26
2.5.1 Manipulator Model................................... 27
2.6 Simulation Results......................................... 28
2.6.1 A Single-link Flexible-Joint Manipulator................ 28
2.6.2 A Two-link Flexible-Joint Manipulator.................. 31
2.7 Conclusions............................................... 34
3 Neural Network-Based System Identification Scheines ............. 37
3.1 Introduction............................................... 37
3.2 A Parallel Identification Schcme ............................. 38
3.2.1 LPNN Parallel Idenürier.............................. 40
3.2.2 NLPNN Parallel Identifier............................. 41
3.3 A Series-Parallel Identification Scheine........................ 45
3.4 A Case study. Application to a Flexible-Link Manipulator........ 46
3.5 Simulation Results ......................................... 48
3.5.1 A Two-Link Manipulator............................. 49
3.5.2 The Space Station Remote Manipulator System (SSRMS) . 49
3.5.3 Generalizatkm....................................... 53
3.6 Experimentai Results on a Macro-Micro Manipulator System...... 53
Contents
3.7 Conclusions............................................... 58
An Actuator Fault Detection and Isolation Scheme: Experiments in
Robotic Manipulators.......................................... 61
4.1 Introduction............................................... 61
4.2 Neural Network Structure for Actuator Fault Detection .......... 63
4.3 Case Study 1: Application to Sutellite Attitüde Control Subsystems. 66
4.3.1 System Dynamics.................................... 66
4.3.2 Reaction Wheel Model ............................... 67
4.3.3 Simulation Results................................... 69
4.4 Case Study 2: Application to Robotic Manipulators.............. 71
4.4.1 System Dynamics.................................... 72
4.4.2 Experimentai Setup.................................. 73
4.5 Conclusions............................................... 78
A Robust Actuator Gain Fault Detection and Isolation Scheme ..... 83
5.1 Introduction............................................... 83
5.2 Problem Statement......................................... 84
5.3 Neural Network-Based Fault Detection and Estimation Scheine----- 85
5.3.1 Fault Detection and Isolation Policy..................... 87
5.3.2 Slability Analysis.................................... 87
5.4 A Case Study: Application to a Satellite s Attitüde Control
Subsystem ................................................ 93
5.5 Simulation Results ......................................... 93
5.6 Conclusions............................................... 95
A Robust Sensor and Actuator Fault Detection and Estimation
Approach ..................................................... 99
6.1 Introduction............................................... 99
6.2 Problem Statement ......................................... 100
6.3 Neural Network-Based Fault Detection and Estimation Scheme
for Sensor/Actuator Faults................................... 101
6.3.1 Fault Detection and Isolation Policy..................... 103
6.3.2 System Identification. Fault Detection. and Stabilily Analysis 103
6.4 A Case Study: Application to a Satelltte s Attitüde Control
Subsystem ................................................ 109
6.4.1 Dynamic Modeling................................... 109
6.4.2 Magnctorquer Model cACS Actuator)................... 109
6.4.3 Actuator (Magnctorquer) Fault ........................ 11
6.4.4 Magnetometer Model (ACS Sensor).................... 112
6.5 Simulation Results ......................................... 113
6.6 Conclusions............................................... 117
Contents xi
A Preliminary Defiiiitions.........................................131
A.l Norms....................................................131
A.2 Ultimate Boundedness 11J...................................132
A.3 Positive Real and Strictly Positive Real [2| .....................132
B Flexible-Joint Manipulator Model ...............................133
B. 1 Harmonie Drive............................................133
B.2 Flexible-joint Manipulator Dynamics..........................136
B.2.1 Dynamic Model of a Two-Link Planar Manipulator L3J.....137
B.2.2 The Effect of Joint Flexibility on Manipulator Model [3]... 139
C Neural Network Learning Rules for Theorem 6.1..................141
D Stability Conditions of Theorem 6.1-Part 2 .......................145
References.....................................................147
Index.............................................................153
List of Figures
1.1 High-gain observer for a System in observability normal form |4|.... 4
1.2 Some common choices for the activation functions of multilayer
neural networks............................................. 9
1.3 A thrce layer neural network................................... 9
1.4 A three laycr neural network training by error BP................. 10
2.1 The structure of the proposett neural network observer............. 17
2.2 The sehematic of flexible-joint manipulator [3]................... 27
2.3 The State responses of the single-link flexible-joint manipulator
using NLPNN............?............. .................... 3«)
2.4 The State responses of the single-link flexible-joint manipulator
using NLPNN after the learning stops.......................... 31
2.5 The State responses of the single-link flexible-joint manipulator to
0. l.wwf 4 0.2.v/n2f + 0.05.« h4i trajcctory......................... 32
2.6 The State responses of the single-link flexible-joint manipulator to
0.075.h m3? trajcctory during recall phasc........................ 33
2.7 The State responses of the tvvo-link flexible-joint manipulator after
learning period...............................................34
2.8 The State responses of the flexible-joint manipulator for NLPNN
and LPNN observer Scheines.................................. 35
1 The structure of neural network identitier (parallel model).......... 39
2 The structure of neural network identifter (series-parallel model t. ... 46
3 Simulation results for a two-Iink manipulator {parallel model)...... 50
4 Simulation results for a iwo-link manipulator (series-parallel model i. 51
.5 Sehematic of Canadann 2(5].................................. 52
6 Simulation results for the SSRMS ta) .......................... 54
7 Simulation results for the SSRMS i h)........................... 55
8 Generaiization results for a two-Iink flexible manipulator.......... 56
9 The actual Macro-Micro Manipulator test-bed................... 57
10 Experimenfal results for the M3 test-bed........................ 59
List of Figures
4.) Neural network estimator for actuator fault detection.............. 64
4.2 Sehematic diagram of the reaction wheel........................ 67
4.3 The responses of eurrent and angular velocities of the wheel in
fault-free Operation.......................................... 71
4.4 The responses of the reaction wheel and the hybrid model in
fault-free Operation.......................................... 72
4.5 Angular velocities of the satellite with constant fault in all actuators . 73
4.6 Angular velocities of the satellite with O.Ol constant fault in Tv ..... 74
4.7 Angular velocities of the satellite with 1 X)N.m constant fault in tx ... 75
4.8 Motor eurrent of the reaction wheel with constant fault in the bus
voltage without control reconfiguration......................... 76
4.9 Motor eurrent of the reaction wheel with constant fault in the bus
voltage with control reconfiguration............................ 77
4.10 Joint positions and velocities in fault-free Operation............... 78
4.11 The Outputs of the neural network estimating unmodeled dynamics. . 79
4.12 The Outputs of the neural network estimating the faults............ 80
4.13 Joint positions and velocities with fault in the first three actuators ... 81
4.14 Joint tracking errors with fault in the tust three actuators........... 82
5.1 The neural network-based fault detection and Isolation scheme...... 86
5.2 Actuator fault detection System responses in fault-free Operation---- 96
5.3 Actuator fault detection and Isolation response to a 20% gain fault
in Channel y actuator ........................................ 97
5.4 Actuator fault detection and Isolation response to simultaneous
faults in the Channel x z actuators............................ 98
6.1 Structure of the neural network-based fault detection and isolation
scheme for sensor/actuator faults...............................102
6.2 Principal diagram of a Single coil driver and magnetorquer [6]......110
6.3 Satellite actuai and estimated angular velocities in a fault-free
Operation..................................................117
6.4 The neural networks NN NN2 responses for actuator and sensor
fault detection in a fault-free Operation..........................118
6.5 Satellite actuai and estimated angular velocities for a bias fault in
the Channel .v magnetorquer....................................119
6.6 Actuator fault detection and isolation (NN ) responses for a
constant bius fault in the Channel x magnetorquer. ................120
6.7 Actuator fault detection and isolation (NNO responses
corresponding to simultaneous faults in the Channel x y actuators.. 121
6.8 Satellite actuai and estimated angular velocities for a constant fault
in o: measurement..........................................122
6.9 Sensor fault detection and isolation (NNi) responses for a
(0.03 rad/s) constant fault in (o measurement................. ? ? 123
6.10 Sensor fault detection and isolation (NNi) responses corresponding
to simultaneous faults in to and utz measurements................124
List of Figures xv
6.11 Actuator fault detection and isolation (NN ) responses
corresponding to incipient and abrupt faults in the Channel x y
actuators...................................................125
6.12 Actuator fault detection and isolation (NN]) responses for a small
bias fault in the Channel y magnetorquer ........................126
6.13 The neural networks NN] NNj responses for actuator and sensor
fault detection in a fault-free Operation and in the presence of State
and sensor uncertainties.......................................127
6.14 Actuator fault detection and isolation (NN ) responses in the
presence of State and sensor uncertainties........................128
6.15 Sensor fault detection and isolation (NN]) responses in the presence
of State and sensor uncertainties................................129
6.16 The neural networks /VAri NN2 responses for actuator and sensor
fault detection in a fault-free Operation and in the presence of large
State and sensor uncertainties..................................130
B. 1 Components of harmonic drive [7].............................134
B.2 Principal Operation of harmonic drive [8]........................135
B.3 Two-Iink planar manipulator [3]................................138
B.4 Flexible-joint manipulator model|3J............................139
List of Tables
3.1 The parameters of the actuai robot ............................. 57
4.1 Reaction wheel parameters.................................... 69
|
| any_adam_object | 1 |
| author_GND | (DE-588)122392566 |
| building | Verbundindex |
| bvnumber | BV036037632 |
| classification_rvk | SI 845 |
| ctrlnum | (OCoLC)698858396 (DE-599)BSZ315050241 |
| discipline | Mathematik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01551nam a2200361 cb4500</leader><controlfield tag="001">BV036037632</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">100217s2010 ad|| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781441914378</subfield><subfield code="9">978-1-4419-1437-8</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)698858396</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BSZ315050241</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-83</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">SI 845</subfield><subfield code="0">(DE-625)143198:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Neural network-based state estimation of nonlinear systems</subfield><subfield code="b">application to fault detection and isolation</subfield><subfield code="c">Heidar A. Talebi ...</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">New York [u.a.]</subfield><subfield code="b">Springer</subfield><subfield code="c">2010</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XIX, 154 S.</subfield><subfield code="b">Ill., graph. Darst.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Lecture notes in control and information sciences</subfield><subfield code="v">395</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Nichtlineares System</subfield><subfield code="0">(DE-588)4042110-7</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Nichtlineares System</subfield><subfield code="0">(DE-588)4042110-7</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Talebi, Heidar A.</subfield><subfield code="d">1965-</subfield><subfield code="e">Sonstige</subfield><subfield code="0">(DE-588)122392566</subfield><subfield code="4">oth</subfield></datafield><datafield tag="830" ind1=" " ind2="0"><subfield code="a">Lecture notes in control and information sciences</subfield><subfield code="v">395</subfield><subfield code="w">(DE-604)BV005848579</subfield><subfield code="9">395</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">HBZ Datenaustausch</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=018929635&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-018929635</subfield></datafield></record></collection> |
| id | DE-604.BV036037632 |
| illustrated | Illustrated |
| indexdate | 2024-07-09T22:09:56Z |
| institution | BVB |
| isbn | 9781441914378 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-018929635 |
| oclc_num | 698858396 |
| open_access_boolean | |
| owner | DE-83 |
| owner_facet | DE-83 |
| physical | XIX, 154 S. Ill., graph. Darst. |
| publishDate | 2010 |
| publishDateSearch | 2010 |
| publishDateSort | 2010 |
| publisher | Springer |
| record_format | marc |
| series | Lecture notes in control and information sciences |
| series2 | Lecture notes in control and information sciences |
| spelling | Neural network-based state estimation of nonlinear systems application to fault detection and isolation Heidar A. Talebi ... New York [u.a.] Springer 2010 XIX, 154 S. Ill., graph. Darst. txt rdacontent n rdamedia nc rdacarrier Lecture notes in control and information sciences 395 Neuronales Netz (DE-588)4226127-2 gnd rswk-swf Nichtlineares System (DE-588)4042110-7 gnd rswk-swf Neuronales Netz (DE-588)4226127-2 s Nichtlineares System (DE-588)4042110-7 s DE-604 Talebi, Heidar A. 1965- Sonstige (DE-588)122392566 oth Lecture notes in control and information sciences 395 (DE-604)BV005848579 395 HBZ Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=018929635&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Neural network-based state estimation of nonlinear systems application to fault detection and isolation Lecture notes in control and information sciences Neuronales Netz (DE-588)4226127-2 gnd Nichtlineares System (DE-588)4042110-7 gnd |
| subject_GND | (DE-588)4226127-2 (DE-588)4042110-7 |
| title | Neural network-based state estimation of nonlinear systems application to fault detection and isolation |
| title_auth | Neural network-based state estimation of nonlinear systems application to fault detection and isolation |
| title_exact_search | Neural network-based state estimation of nonlinear systems application to fault detection and isolation |
| title_full | Neural network-based state estimation of nonlinear systems application to fault detection and isolation Heidar A. Talebi ... |
| title_fullStr | Neural network-based state estimation of nonlinear systems application to fault detection and isolation Heidar A. Talebi ... |
| title_full_unstemmed | Neural network-based state estimation of nonlinear systems application to fault detection and isolation Heidar A. Talebi ... |
| title_short | Neural network-based state estimation of nonlinear systems |
| title_sort | neural network based state estimation of nonlinear systems application to fault detection and isolation |
| title_sub | application to fault detection and isolation |
| topic | Neuronales Netz (DE-588)4226127-2 gnd Nichtlineares System (DE-588)4042110-7 gnd |
| topic_facet | Neuronales Netz Nichtlineares System |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=018929635&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| volume_link | (DE-604)BV005848579 |
| work_keys_str_mv | AT talebiheidara neuralnetworkbasedstateestimationofnonlinearsystemsapplicationtofaultdetectionandisolation |