AI Summary & Key Takeaways
AI InsightIt was noticed thatthe designed model provided very close results to the actual test results and can be applied successfully.
📌 3 Key Takeaways
Abstract
Ever inreasing demand to raw mineral production stimulates intense use of mining machinery and subsequentlyexposes mining machinery operators to high levels of continuous noise. Long-term exposure to high levels ofcontinuous noise can cause Occupational Hearing Loss (OHL) on operators. In order to certify a good workingenvironment, it is important to estimate real noise levels of opencast mining machines.The aim of this study was to assess exposure levels to continuous noise using the test records of continouos noiseemitted from mining machinery and recommend some actions to reduce it. Artificial neural networks (ANN) tooldeveloped by MATLAB software has been used for these estimates.During the study, consistent personal noise exposure levels emitting from 60 different opencast miningmachinery was recorded. The lowest, highest, average and equivalent noise levels of the machines wererecorded and possible exposure noise-levels (LEX,8H) on operators were calculated.Later, data obtained from tests were used to train the ANN multilayered model by forward-feed-fault-backcirculation algorithm. During modeling of ANN; vehicle types, recording times, ambient temperature andpressure and relative humudity were determined as input parameters. By the help of the model, equivalent andmomentary noise levels prior to maximum level were estimated. Following training and testing of the model, theobtained noise levels were examined by statistical analysis commonly used in ANN models. It was noticed thatthe designed model provided very close results to the actual test results and can be applied successfully.