DocumentCode
2843301
Title
A study of expert control system of oil pump energy-saving based on genetic neural network
Author
Ping, He ; Min, Li ; Yuheng, Qian
Author_Institution
Harbin Inst. of Technol., Harbin, China
fYear
2009
fDate
17-19 June 2009
Firstpage
5441
Lastpage
5444
Abstract
In order to deal with the problem of light load operation of most oil pumps in oil fields, an oil pump energy-saving ldquointermittent start-stoprdquo operation method based on genetic neural network and expert control is proposed in this paper. At first, the structure of fuzzy neural network reasoning machine based on rules is introduced in the paper, which is used as an inference engine to deal with the difficulty of acquiring knowledge and the weak inference. To improve the performance of the system, the genetic algorithm is used to make the off-line training of the inference engine, and the rule inference of traditional expert system is used for the transparency of system with agility in system. Finally, the structure of genetic neural network expert control system is given and used in oil pump control that achieves the desired energy-saving effects.
Keywords
control engineering computing; expert systems; fuzzy control; fuzzy neural nets; genetic algorithms; inference mechanisms; mechanical engineering computing; neurocontrollers; oil technology; pumps; expert control system; fuzzy neural network reasoning machine; genetic algorithm; genetic neural network; inference engine; intermittent start-stop operation method; light load operation; oil fields; oil pump energy-saving; rule inference; traditional expert system; weak inference; Control systems; Engines; Expert systems; Fuzzy control; Fuzzy neural networks; Genetic algorithms; Lighting control; Neural networks; Petroleum; Pumps; Expert Control; Fuzzy Neural Network; Genetic Algorithm; Oil Pump Energy-Saving;
fLanguage
English
Publisher
ieee
Conference_Titel
Control and Decision Conference, 2009. CCDC '09. Chinese
Conference_Location
Guilin
Print_ISBN
978-1-4244-2722-2
Electronic_ISBN
978-1-4244-2723-9
Type
conf
DOI
10.1109/CCDC.2009.5195163
Filename
5195163
Link To Document