Prediction Models with Multiple Linear Regression for Improving Acoustic Performance of Textile Industry Plants
In industrial plants noise is a major threat to the mental and physical health of employees. The risk increases more due to the presence of high noise sources and the presence of too many employees in textile industry plants. This paper aims to predict the consequences of variables that may arise in...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Fundamental Technological Research Polish Academy of Sciences
2025-01-01
|
| Series: | Archives of Acoustics |
| Subjects: | |
| Online Access: | https://acoustics.ippt.pan.pl/index.php/aa/article/view/3867 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In industrial plants noise is a major threat to the mental and physical health of employees. The risk increases more due to the presence of high noise sources and the presence of too many employees in textile industry plants. This paper aims to predict the consequences of variables that may arise in the plants for acoustic improvement in textile industry plants. For this purpose, scenario plants have been created according to architectural properties and source-transmission path-receiver characteristics. The acoustic analyses of the scenario plants were performed in the ODEON Auditorium, and A-weighted sound pressure level (LA), noise reduction (NR), and reverberation time (RT) were determined. From the data, prediction equations were created with a multiple linear regression (MLR) model. To test the prediction equations, acoustic measurements were made, and acoustics improvements were carried out at a textile industry plant located in Türkiye. When the obtained results, the success, validity, and reliability of the prediction method are provided. In conclusion, the effect of architectural properties and the surface absorption on acoustic improvements in the textile industry was revealed. It was emphasized that prediction methods can be used to determine the effectiveness of interventions that can be applied in different facilities and can be improved in future studies. |
|---|---|
| ISSN: | 0137-5075 2300-262X |