Title :
Non-intrusive pressure measurement system: analysis of characteristics using neural networks
Author :
Yu, Feng ; Gupta, Naren ; Hoy, Jay
Author_Institution :
Sch. of Eng., Napier Univ., Edinburgh, UK
Abstract :
Non-intrusive measurement of pressure using ultrasonics is specifically designed for rapid diagnosis of hydraulic equipment where the conventional measurement instruments fail to make the necessary pressure readings within the sealed pipes. By applying the neural networks, the direct model and the inverse model of the non-intrusive measurement system have been built, which can be utilized to analyze the input-output characteristics of the system and provide an effective means for direct digital readings of the measurand. The modelling results have shown the effectiveness of the proposed modelling method with a low cost of computational complexity for easy implementation in a microcontroller.
Keywords :
computational complexity; microcontrollers; neural nets; pressure measurement; ultrasonic measurement; computational complexity; direct digital readings; direct model; hydraulic equipment; input-output characteristics; inverse model; measurement instruments; microcontroller; neural networks; nonintrusive pressure measurement; pressure readings; rapid diagnosis; sealed pipes; Acoustic measurements; Condition monitoring; Costs; Hydraulic systems; Instruments; Inverse problems; Neural networks; Neurons; Performance evaluation; Pressure measurement;
Conference_Titel :
Instrumentation and Measurement Technology Conference, 2004. IMTC 04. Proceedings of the 21st IEEE
Print_ISBN :
0-7803-8248-X
DOI :
10.1109/IMTC.2004.1351064