The Development of Neural Network Based System Identification ...

More documents

Recommendations

Info

144 CHAPTER 5 NN BASED SYSTEM IDENTIFICATION: RESULTS AND DISCUSSION 5.5 MODEL PERFORMANCE COMPARISON USING OFF-LINE TRAINING The prediction performance among three NN architectures proposed in this work is compared by collecting the error statistics that have been generated in the Figure 5.6, 5.11 and 5.15. The NN models performance comparison is made based on the optimal network structures obtained from these figures. Results point that the prediction from NNARX architecture using the MLP network produce prediction quality with a total RMSE percentage of 10.11%. The HMLP network offers prediction with slight performance improvement than the MLP (9.82%) while the modified Elman network gives the lowest prediction quality (15.78%). Results from Table 5.3, 5.6 and 5.9 indicate that the average RMSE and confidence limit values from the weights are able to produce prediction that adequately fit with the test data. From the results, the prediction performance from the optimised structure of the MLP, HMLP and modified Elman networks are shown to be robust from large variation of weights values. Therefore, it can be conclude that NN training from off-line training method such as LM algorithm would produce weights set that can produce quite large latitude of value but still able to produce a satisfactory prediction performance. 5.6 ON-LINE SYSTEM IDENTIFICATION In this section, the on-line training proposed in Section 4.3.5 is implemented to identify the attitude dynamics of the UAS helicopter model using the MLP network. The suitable regression vector structure and hidden neurons size for recursive NNARX model can be determined using the k-fold cross validation technique previously discussed. Using results from the off-line system identification, network structure with n y = 3 and n u = 1 is used as the basic model structure for comparing the generalisation performance of the recursive Gauss-Newton (rGN) method with off-line training method. The comparison also utilises the k-fold cross validation method to identify the efficiency of the selected neural network training methods in estimating the attitude dynamics of the helicopter. To compare the generalisation performance of the rGN
5.6 ON-LINE SYSTEM IDENTIFICATION 145 10 2 Hidden Neurons Size rGN with MLP Offline LM with MLP RMSE (%) 10 1 10 0 1 2 3 4 5 6 7 8 9 10 Figure 5.18 The percentage of Root Mean Square Error (RMSE) comparison plot for off-line Levenberg-Marquardt (LM) and recursive Gauss-Newton (rGN) training methods. method against the off-line LM method, the training of rGN is repeated several times on a finite data set (repeated recursive training) instead of assuming that the data set increases with time as in the recursive training scheme. The general implementation of the repeated recursive training is previously illustrated in Figure 4.10. After reaching the maximum iterations or performance index threshold, the resulting parameter vector θ is then selected for cross validation. The rGN method’s training parameters are initialised as Q(0) = 25I, λ 0 = 0.99 and λ(0) = 0.997. Figure 5.18 indicates the generalisation error plot for repeated rGN and off-line LM methods. The recursive training algorithm (rGN) exhibits a slightly higher generalisation error in cross validation compared with the off-line method. This indicates that training performed over a large data set would give better generalisation performance over the recursive method. Even though the generalisation error of rGN is slightly higher than off-line LM, the rGN is more adaptive to the changes in dynamic properties. As a comparative study of the adaptability between off-line LM and rGN methods, the roll rate measurement from a new data set is considered. Figure 5.19 shows the prediction from a pre-trained
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: 4.3 SYSTEM IDENTIFICATION WITH NEUR
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 175: 5.4 OFF-LINE BASED SYSTEM IDENTIFIC
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 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?