Noise Prediction in Industrial Workrooms Using Regression Modeling Methods Based on the Dominant Frequency Cutoff Point

Abstract

Noise pollution is one of the major problems in industrial environments. The physiological response to the noise in industrial environments depends on the characteristics of the noise and environment. This study aimed to develop an empirical model for predicting the level of noise in closed industrial spaces using regression modeling based on the dominant frequency cutoff point. After identifying and determining the effective input variables in the prediction of noise level, the relevant data were collected from 56 industrial workrooms and the model was developed using multiple regression technique. The two models were best fitted to estimate the noise level for workrooms with a dominant frequency of less or equal to and more than 250 Hz (R2 = 0.86, R2 = 0.85, respectively). Based on the results of this study, it is less costly and requires less equipment for noise evaluation and monitoring by the mentioned models during the design, implementation, and operation of industrial environments. These experimental models can be used as suitable measures for screening closed industrial spaces and ranking them in terms of the amount of noise pollution.