The Development of Neural Network Based System Identification ...

More documents

Recommendations

Info

36 CHAPTER 2 LITERATURE REVIEW properly track the dynamics of the system under consideration. Furthermore, the usage of recursive algorithms such as recursive Gauss-Newton (rGN) or recursive Levenberg- Marquardt (rLM) reduces the computation complexity of the off-line (batch) training method without having to invert the full Hessian matrix in every iteration [Ngia and Sjoberg, 2000]. The implementation of the recursive training using rGN algorithm is proposed in this work and compared with mini-batch LM training to determine the effectiveness of recursive training for real-time NN prediction. 2.4 AUTOMATIC FLIGHT CONTROL SYSTEM Automatic flight control system (AFCS) for helicopter based UAS was traditionally designed using linearisation of rigid body equation of motion at various points throughout the flight envelope [Mettler et al., 2000]. Since we have a collection of linear models that represents a particular flight regime, the gain scheduling approach is the commonly used method to design flight controllers for UAS. The overview of the gain scheduling control approach is shown in Figure 2.7. In this approach, several linear models are obtained from the non-linear model in certain flight conditions. Subsequently, linear controllers are then designed for each different flight conditions such as hovering or forward flight at different velocities. Since we have multiple linear controllers that provide satisfactory control for different operating points, the gain scheduling approach is used to determine the current flight operating region and to activate the appropriate linear controller. Several measured variables from the on-board instrumentation such as airspeed, dynamic pressure or altitude can be used to trigger specific linear controllers relative to the current flight operating region. The complex, inherently unstable and non-linear nature helicopter based UAS present a serious challenge for design and implementation of a control strategy. Typically, the control system architectures for helicopters were primarily based on the stability augmentation systems (SAS), which are concerned with attitude or altitude control and stabilisation. Besides SAS, the AFCS developed for helicopter based UAS can also include other types of control loops including velocity/position control, heading control and 3D trajectory tracking. Throughout the past few decades, a wide range
2.4 AUTOMATIC FLIGHT CONTROL SYSTEM 37 HOVER u = 3 m/s u = 6 m/s u = X m/s Figure 2.7 An overview of gain scheduling control approach. of control methodologies were proposed to address helicopter control problems, which vary from the classical control method to learning based control. Detailed review on the existing control methodologies applied to the unmanned helicopter system is given in Kendoul [2012], Nonami [2010], Valavanis [2007]. These flight controllers are generally classified in three broad categories such as linear flight controllers, model based non-linear controllers and learning based flight controllers. The linear controllers are currently the most favoured methods used by military and industrial research communities due to the simple implementation and intuitive control system structure. There exist many available tools that can be used to refine the controller’s gains and to analyse their performance and robustness. Moreover, the linear controllers have been successfully implemented in UAS applications and have been shown to be effective in numerous flight tests [Mettler, 2003, Valavanis, 2007, Saripalli et al., 2003, Amidi et al., 1999, Kendoul, 2012]. Recent research on helicopter UAS has focussed on the use of linear control theories such as Linear Quadratic Regulator [Shin et al., 2005, Nonami, 2010, Bergerman et al., 2007], H ∞ control [Civita, 2003, Walker, 2003] and Gain Scheduling control [Antunes et al., 2010].
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 59 and 60: 2.3 NEURAL NETWORK BASED SYSTEM IDE
Page 67: 2.3 NEURAL NETWORK BASED SYSTEM IDE
Page 71 and 72: 2.4 AUTOMATIC FLIGHT CONTROL SYSTEM
Page 85: 2.5 SUMMARY 53 design based on the
Page 88 and 89: 56 CHAPTER 3 AERIAL PLATFORM AND CU
Page 109 and 110: Chapter 4 NEURAL NETWORK BASED SYST
Page 111 and 112: 4.2 THE ARTIFICIAL NEURAL NETWORKS
Page 119 and 120:
4.2 THE ARTIFICIAL NEURAL NETWORKS
Page 121 and 122:
4.2 THE ARTIFICIAL NEURAL NETWORKS
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 190 and 191:
Page 192 and 193:
Page 194 and 195:
Page 196 and 197:
Page 198 and 199:
Page 200 and 201:
Page 202 and 203:
Page 204 and 205:
Page 206 and 207:
Page 208 and 209:
Page 210 and 211:
Page 212 and 213:
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 and 238:
7.3 EXPERIMENTAL RESULTS 205 Yaw Ra
Page 239:
7.4 SUMMARY 207 data measured from
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?