Appendices Appendix A: List of Publications The following papers highlight the findings of this research. These articles were published in reputed journals during the course of this research program. 1. Terzic, Edin, Nagarajah, Romesh, and Alamgir, Muhammad. A neural network approach to fluid quantity measurement in dynamic environments, Mechatronics; vol. 21, no. 1, pp. 145 155, Feb 2011. 2. Terzic, Edin, Nagarajah, C. Romesh, and Alamgir, Muhammad. Capacitive sensor-based fluid level measurement in a dynamic environment using neural network, Engineering Applications of Artificial Intelligence; vol. 23, no. 4, pp. 614 619, June 2010. 3. Terzic, Edin, Nagarajah, Romesh, and Alamgir, Muhammad. A Neural Network Approach to Fluid Level Measurement in Dynamic Environments Using a Single Capacitive Sensor, Sensors & Transducers Journal; vol. 114, no. 3, pp. 41 55, March 2010 133
134 Appendices Appendix B: EXXSOL D-40 Fluid Specification The following table provides detailed specifications for the Exxsol D-40 type Stoddard solvent used in the experimentations [1]. Table B.1 Exxsol D-40 fluid specifications Property Units Typical values Test method Distillation range C ASTM D 86 IBP 164 DP 192 Flash point C 48 ASTM D 56 Density @ 15 C kg/dm 3 0.772 ASTM D 4052 Viscosity @ 25 C mm 2 /s 1.30 ASTM D 445 Evaporation rate (n-buac = 100) 15 EMC-AP-F01 KB value 32 ASTM D 1133 Aniline point C 70 ASTM D 611 Aromatic content wt% 0.08 AM-S 140.31 Colour (Saybolt)?30 ASTM D 156 Bromine index mg/100 g 15 ASTM D 2710 Surface tension @ 25 C mn/m 24.7 EC-M-F02 (Wilhelmy Plate) Refractive index @ 20 C 1.428 ASTM D 1218 Reference 1. Corporation, Exxon Mobil. Aliphatics Fluids (Exxsol Series) Grades & Datasheets. Exxon Mobil Corporation; [cited]; Available from: http://www.exxonmobilchemical.com/public_ Products/Fluids/Aliphatics/Worldw ide/grades_and_datasheets/fluids_aliphatics_exxsolsbp_ Grades_WW.asp.
About the Authors Dr. Edin Terzic is the Chief Manufacturing Engineer Asia Pacific and Managing Director (CEO) of Powertrain at Delphi Automotive Systems Australia. He holds a Bachelor of Mechanical Engineering (with honors), Master of Engineering in Computer Integrated Manufacturing, and PhD in Automotive Engineering from Swinburne University of Technology. He has published a number of technical papers in the area of Engineering Applications of Artificial Intelligence. He also holds several international patents in the area of automotive engineering and had success in commercializing most of his research. Areas of research include: artificial neural networks, intelligent sensors and non-contact inspection. Dr. Jenny Terzic is the Director of Corporate Quality at Iveco Trucks Australia (Fiat Group). She holds a Bachelor of Mechanical Engineering (with honors), Master of Engineering in Computer Integrated Manufacturing and PhD in Automotive Engineering from Swinburne University of Technology. She has a published number of technical papers in the area of Engineering Applications of Artificial Intelligence. Areas of research include: support vector machines, artificial neural networks, advance signal processing, intelligent sensors, and noncontact inspection. Prof. Romesh Nagarajah is the Professor of Mechanical Engineering at Swinburne University of Technology. He leads an internationally recognized research group working in the fields of Non-Contact Inspection and Intelligent Sensing. Professor Nagarajah has several international patents and has published over 150 international journal, conference, and technical papers in intelligent sensing and non-contact inspection. He has received several grants from the Australian Research Council and the automotive industry to develop intelligent sensing systems for process monitoring and non-contact inspection. Muhammad Alamgir is a Software Engineer at Vipac Engineers and Scientists. He has graduated in Computer Systems Engineering from RMIT University. He has been developing microcontroller-based sensors and instruments, and has also been involved in smart-sensor-based projects, incorporating Artificial Intelligencebased techniques, at Delphi Automotive Systems, Australia. 135
Index A Analog waveform, 40 Artificial neural network, 4, 45, 49, 57, 69, 71, 84, 129 Averaging, 4, 29, 32, 33, 86, 102 B Backpropagation neural network, 69, 71, 82, 87, 100 C Capacitance, 12, 13 Capacitive sensor, 3, 12 Contamination, 4, 26 D Dampening, 29 Design of experiments, 5 Dielectric constant, 3, 12, 15 Dielectric strength, 15 Discrete cosine transform (DCT), 41, 42 Discrete sine transform (DST), 43 Distributed time delay neural network, 51, 84, 91 Dynamic neural network, 49 E Exxsol D-40, 134 F Fast fourier transform (FFT), 41 Feature extraction, 39, 41 Feed forward network, 49 Fisher discriminant analysis (FDA), 41 Focused time delay neural network, 51 Frequency coefficients, 58, 99 Full factorial matrix, 83 H Hidden layer, 49 I Independent component analysis (ICA), 41 Input layer, 49 Interaction plots, 67, 96 L Labview, 86 Learning rule, 52 Linear transfer function, 47 Low pass filter, 40 M Main effect plots, 67, 95 Matlab, 92 Moving mean, 5, 117 Moving median, 5, 117 137
138 Index N NARX neural network, 52, 85, 91 Network weights, 114 Neural network validation, 101, 115 Neuron model, 45 O Output layer, 49 P Perceptron neuron, 48 Principle component analysis (PCA), 41 Purelin, 87 Signal smoothing, 5 Sloshing, 4, 29 Supervised classification, 44 Supervised learning, 52 T Tansig, 87 Threshold transfer function, 47 Tilt sensor, 30 U Unsupervised classification, 44 Unsupervised learning, 53 R Recurrent neural network, 51 V Validation error, 118 S Sigmoid function, 47 Sigmoidal function, 5 Signal classification, 44 Signal filtration, 9 W Wavelet filter, 5 Wavelet transform (WT), 41, 43 Weights, 45