The Development of Neural Network Based System Identification ...

More documents

Recommendations

Info

206 CHAPTER 7 FLIGHT CONTROL SYSTEM DESIGN: RESULTS AND DISCUSSION 7.4 SUMMARY The flight test results for the unmanned helicopter system controlled by multiple NNAPC controllers are presented in this chapter. The automatic hovering flight controllers are designed according to the TITO architecture which result in three NNAPC controllers i.e. the coupled roll-pitch controller, the yaw rate controller and the altitude speed controller. Several flight tests have been conducted in the early parts of controller development to identified the control tuning parameters such as r w , N p , K Ψ and K w that would produced satisfactory control performance. The HMLP network presented in the Subsection 4.2.2 is used in the NNAPC controller prediction due the network capability to model the flight dynamics with fewer weight connections compared with the standard MLP network. The control tuning results show that tuning parameters such as r w = 1.5, N p = 10, K Ψ = 1.0 and K w = 0.75 produce the best flight control response compared with other tuning setting. Using the tuning parameters identified from the control tuning tests, a full 4 DOF NNAPC controller is successfully realised in the hovering flight condition with good compensation performance. In the hovering flight test, the unmanned helicopter is commanded to track a step response in altitude for a duration of 19.8 s while stabilising the helicopter in roll, pitch and yaw channels. After the successful implementation of the 4 DOF flight controllers, the NNAPC controllers are further tested under the physical parameter variations that involve changes in the collective pitch curve setting, throttle curve setting and the test rig’s counterbalance weight. The changes in the counterbalance weight can be equated to the changes in the unmanned helicopter payload during flight. Similar to the approach taken by Samal [2009], the changes in both collective and throttle curves of the helicopter blades are used as the test reference. In real flight condition, the total lift and drag forces acting on the helicopter vary during different flight and environment conditions. This can be treated similarly in the indoor test by setting changes in the collective pitch and throttle setting during flight. The performance of the NNAPC-Offline controller is then compared with the NNAPC-Online controller under parameter variation tests. The off-line NN model and the initial model for recursive HMLP are obtained using the
7.4 SUMMARY 207 data measured from the previous parameter settings before changes is made. From the findings of the above studies, it can be concluded that the recursive NN model improved the NNAPC-Offline controller performance under the new parameter variations. This is due to the ability of the recursive NN model to track the time varying parameters of the helicopter dynamics. Since the off-line NN model is not trained with the new changes in physical parameter values, a significant model mismatch can occurs and this would affect the accuracy of the NNAPC controller’s prediction, thus contributing to the deteriorating performance of the NNAPC-Offline controller. Finally, the performance of the NNAPC controllers was further tested under input disturbances after tracking the given references. The proposed NNAPC approaches with either offline or online NN model were found to be efficient in compensating the effect of the input disturbances. Performance comparison between the NNAPC- Online and NNAPC-Offline controllers shows that the NNAPC-Online controllers offer improvement in regulating the input disturbance effects, particularly in the pitch and yaw axes. Despite the reported effectiveness of the NNAPC-Online controller in handling parameter variations and input disturbance effects, the good performance of the NNAPC- Online controller was obtained at the expense of increased computational load compared with the NNAPC-Offline scheme. However, this is justifiable for such a critical and challenging dynamic process. The computational load of the NNAPC-Online scheme can be implemented within given computational resources if appropriate selection of tuning options is made by users. Nevertheless, several suggestions are made in the next chapter on several options to improve the execution speed of the NNAPC-Online control scheme.
Page 1:
The Development of Neural Network B
Page 5 and 6:
ABSTRACT This thesis presents the d
Page 7:
vii the MLP network, the prediction
Page 11:
PUBLICATIONS The following is a lis
Page 14 and 15:
xiv TABLE OF CONTENTS CHAPTER 4 CHA
Page 17 and 18:
LIST OF FIGURES 1.1 Examples of typ
Page 19 and 20:
LIST OF FIGURES xix 3.13 Overview o
Page 21 and 22:
LIST OF FIGURES xxi 5.2 The predict
Page 23 and 24:
LIST OF FIGURES xxiii 5.13 The pred
Page 25 and 26:
LIST OF FIGURES xxv 7.1 The locatio
Page 27 and 28:
LIST OF TABLES 3.1 The specificatio
Page 29 and 30:
NOMENCLATURE AFCS Automatic Flight
Page 31:
LIST OF TABLES xxxi NNARX QP RBF RC
Page 34 and 35:
2 CHAPTER 1 INTRODUCTION Surveillan
Page 36 and 37:
4 CHAPTER 1 INTRODUCTION is then de
Page 38 and 39:
6 CHAPTER 1 INTRODUCTION the dynami
Page 40 and 41:
8 CHAPTER 1 INTRODUCTION models [Sa
Page 42 and 43:
10 CHAPTER 1 INTRODUCTION improved
Page 44 and 45:
12 CHAPTER 1 INTRODUCTION Chapter 3
Page 47 and 48:
Chapter 2 LITERATURE REVIEW The pur
Page 49 and 50:
2.1 INTRODUCTION 17 • Inefficient
Page 51 and 52:
2.1 INTRODUCTION 19 Figure 2.2 The
Page 53 and 54:
2.2 HELICOPTER DYNAMICS MODELLING A
Page 55 and 56:
Page 57 and 58:
Page 59 and 60:
2.3 NEURAL NETWORK BASED SYSTEM IDE
Page 61 and 62:
Page 63 and 64:
Page 65 and 66:
Page 67 and 68:
Page 69 and 70:
2.4 AUTOMATIC FLIGHT CONTROL SYSTEM
Page 71 and 72:
Page 73 and 74:
Page 75 and 76:
Page 77 and 78:
Page 79 and 80:
Page 81 and 82:
Page 83 and 84:
Page 85:
2.5 SUMMARY 53 design based on the
Page 88 and 89:
56 CHAPTER 3 AERIAL PLATFORM AND CU
Page 90 and 91:
Page 92 and 93:
Page 94 and 95:
Page 96 and 97:
Page 98 and 99:
Page 100 and 101:
Page 102 and 103:
Page 104 and 105:
Page 106 and 107:
Page 109 and 110:
Chapter 4 NEURAL NETWORK BASED SYST
Page 111 and 112:
4.2 THE ARTIFICIAL NEURAL NETWORKS
Page 113 and 114:
Page 115 and 116:
Page 117 and 118:
Page 119 and 120:
Page 121 and 122:
Page 123 and 124:
4.3 SYSTEM IDENTIFICATION WITH NEUR
Page 125 and 126:
Page 127 and 128:
Page 129 and 130:
Page 131 and 132:
Page 133 and 134:
Page 135 and 136:
Page 137 and 138:
Page 139 and 140:
Page 141 and 142:
Page 143 and 144:
Page 145 and 146:
Page 147 and 148:
Page 149 and 150:
4.4 SUMMARY 117 Segment 1 Segment 2
Page 151 and 152:
Chapter 5 NN BASED SYSTEM IDENTIFIC
Page 153 and 154:
5.2 OFF-LINE BASED SYSTEM IDENTIFIC
Page 155 and 156:
Page 157 and 158:
Page 159 and 160:
Page 161 and 162:
Page 163 and 164:
Page 165 and 166:
Page 167 and 168:
Page 169 and 170:
Page 171 and 172:
Page 173 and 174:
Page 175 and 176:
Page 177 and 178:
5.6 ON-LINE SYSTEM IDENTIFICATION 1
Page 179 and 180:
5.6 ON-LINE SYSTEM IDENTIFICATION 1
Page 181 and 182:
5.7 MODEL PERFORMANCE COMPARISON US
Page 183 and 184:
5.8 SUMMARY 151 methods such as wei
Page 185:
5.8 SUMMARY 153 would enable the im
Page 188 and 189: 156 CHAPTER 6 NEURAL NETWORK BASED
Page 215 and 216: Chapter 7 FLIGHT CONTROL SYSTEM DES
Page 217 and 218: 7.2 FLIGHT TESTS IMPLEMENTATION 185
Page 219 and 220: 7.3 EXPERIMENTAL RESULTS 187 1 0.8
Page 221 and 222: 7.3 EXPERIMENTAL RESULTS 189 Longit
Page 223 and 224: 7.3 EXPERIMENTAL RESULTS 191 Pitch
Page 225 and 226: 7.3 EXPERIMENTAL RESULTS 193 Flight
Page 227 and 228: 7.3 EXPERIMENTAL RESULTS 195 140 Ya
Page 229 and 230: 7.3 EXPERIMENTAL RESULTS 197 indica
Page 231 and 232: 7.3 EXPERIMENTAL RESULTS 199 20 100
Page 233 and 234: 7.3 EXPERIMENTAL RESULTS 201 Yaw Ra
Page 235 and 236: 7.3 EXPERIMENTAL RESULTS 203 mainta
Page 237: 7.3 EXPERIMENTAL RESULTS 205 Yaw Ra
Page 242 and 243: 210 CHAPTER 8 CONCLUSIONS AND FUTUR
Page 244 and 245: 212 CHAPTER 8 CONCLUSIONS AND FUTUR
Page 246 and 247: 214 REFERENCES B. W. Bequette. Non-
Page 248 and 249: 216 REFERENCES Konstantinos Dalamag
Page 250 and 251: 218 REFERENCES Wayne Johnson. Helic
Page 252 and 253: 220 REFERENCES B. Mettler, Mark B.
Page 254 and 255: 222 REFERENCES V. R. Puttige and S.
Page 256 and 257: 224 REFERENCES D.H. Shim. Hierarchi
Page 258 and 259: 226 REFERENCES Nikos Vitzilaios and
show all

The Development of Neural Network Based System Identification ...

Create successful ePaper yourself

Delete template?

Save as template?