DEVELOPMENT OF ARTIFICIAL INTELLIGENCE MOD- ELS FOR PREDICTING NOISE LEVEL IN TYPICAL INDUSTRIAL WORKROOMS

Noise prediction techniques are considered to be an important tool for evaluating cost- effective noise control measures so that, more acceptable situations can be fmally obtained in workrooms. One of the most important issues in this regard is the development of accurate methods for analysis of the complex relationships among acoustic features affecting noise level in workrooms. In this study, artificial neural networks and advanced fuzzy techniques were employed to develop relatively accurate models for noise prediction in noisy industrial workrooms. The main acoustic features and noise levels were determined from 60 embroidery workrooms. Prediction errors, of all structures associated with networks and fuzzy models were approximately similar and within the acceptable level (lower than one dB). Neuro-fuzzy model could slightly improve the accuracy of noise prediction compared with networks. The results confirmed that the developed models as useful tools give professionals the opportunity to have an optimum decision about the effectiveness of acoustic treatment scenarios in embroidery workrooms.