Noise Elimination of Reciprocating Compressors Using FEM, Neural Networks Method, and the GA Method

• Published in: Archives of acoustics 2017-06, Vol.42 (2), p.189-197
• Main Authors: Chang, Ying-Chun, Chiu, Min-Chie, Xie, Ji-Lin
• Format: Article
• Language: English
• Subjects: Abatement; Acoustic emission; Acoustic noise; Artificial neural networks; Commercialization; Finite element method; genetic algorithm; Genetic algorithms; group method of data handling; Mathematical analysis; Mathematical models; Neural networks; Noise control; optimization; polynomial neural network model; reciprocating compressor; Reciprocating compressors; Shape optimization
• ISSN: 2300-262X; 0137-5075; 2300-262X
• DOI: 10.1515/aoa-2017-0021

Industry often utilizes acoustical hoods to block noise emitted from reciprocating compressors. How-ever, the hoods are large and bulky. Therefore, to diminish the size of the compressor, a compact discharge muffler linked to the compressor outlet is considered. Because the geometry of a reciprocating compressor is irregular, COMSOL, a finite element analysis software, is adopted. In order to explore the acoustical performance, a mathematical model is established using a finite element method via the COMSOL commercialized package. Additionally, to facilitate the shape optimization of the muffler, a polynomial neural network model is adopted to serve as an objective function; also, a Genetic Algorithm (GA) is linked to the OBJ function. During the optimization, various noise abatement strategies such as a reverse expansion chamber at the outlet of the discharge muffler and an inner extended tube inside the discharge muffler, will be assessed by using the artificial neural network in conjunction with the GA optimizer. Consequently, the discharge muffler that is optimally shaped will decrease the noise of the reciprocating compressor.