Springer A Neural Network Approach to Fluid Quantity Measurement in Dynamic Environments

This book discusses effects of temperature variations and contamination on the capacitive sensor, and applies a network based classification technique to predict the actual quantity of the fluid contained in a tank under sloshing conditions. From the Back Cover Sloshing causes liquid to fluctuate, making accurate level readings difficult to obtain in dynamic environments. The measurement system described uses a single-tube capacitive sensor to obtain an instantaneous level reading of the fluid surface, thereby accurately determining the fluid quantity in the presence of slosh. A neural network based classification technique has been applied to predict the actual quantity of the fluid contained in a tank under sloshing conditions.   In A neural network approach to fluid quantity measurement in dynamic environments, effects of temperature variations and contamination on the capacitive sensor are discussed, and the authors propose that these effects can also be eliminated with the proposed neural network based classification system. To examine the performance of the classification system, many field trials were carried out on a running vehicle at various tank volume levels that range from 5 L to 50 L. The effectiveness of signal enhancement on the neural network based signal classification system is also investigated. Results obtained from the investigation are compared with traditionally used statistical averaging methods, and proves that the neural network based measurement system can produce highly accurate fluid quantity measurements in a dynamic environment. Although in this case a capacitive sensor was used to demonstrate measurement system this methodology is valid for all types of electronic sensors. The approach demonstrated in A neural network approach to fluid quantity measurement in dynamic environments can be applied to a wide range of fluid quantity measurement applications in the automotive, naval and aviation industries to produce accurate fluid level readings. Students, lecturers, and experts will find the description of current research about accurate fluid level measurement in dynamic environments using neural network approach useful. About the Author Dr Edin Terzic is the Chief Manufacturing Engineer – Asia Pacific & 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 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 commercialising most of his research. Areas of research include: artificial neural networks, intelligent sensors and non-contact inspection.   Dr Jenny Terzic is the Senior Manager and RLE Business Leader at Ford Motor Company - Asia Pacific and Africa. 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 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 non-contact 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 Austra