Brilliance: Research of Artificial Intelligence
Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026

Noise Source Identification in Industrial Machinery Using Acoustic Analysis

Abdulqadir M. Alhadar (Department of Mechanical Engineering, The Higher Institute of Science and Technology Tamzawa Al-Shati, Fezzan, Libya)
Osamah Ibrahim Ali Barka (Department of Mechanical Engineering, The Higher Institute of Science and Technology Tamzawa Al-Shati, Fezzan, Libya)
Musbag Ahedery (Department of Mechanical Engineering, The Higher Institute of Science and Technology Tamzawa Al-Shati, Fezzan, Libya)
Omer I. A. Hmellah (Department of Mechanical Engineering, The Higher Institute of Science and Technology Tamzawa Al-Shati, Fezzan, Libya)
Nuri Salem Ali Abosetha (Department of Mechanical Engineering, The Higher Institute of Science and Technology Tamzawa Al-Shati, Fezzan, Libya)



Article Info

Publish Date
02 Jun 2026

Abstract

Industrial machinery can generate occupational noise that affects worker safety and machine reliability, yet general noise measurement does not show which component is responsible for the strongest sound. Objective: This study improves noise source identification in industrial machinery by combining acoustic signal analysis, frequency spectrum interpretation, and component level comparison for four representative machines. Methods: A lathe, a multi-spindle drilling machine, a cigarette manufacturing machine, and a pasta packaging machine were examined. Measurements were taken near motors, gearboxes, cutting zones, drilling heads, rollers, reels, and a packaging cutter using a calibrated sound level meter and a condenser microphone. Recorded signals were evaluated through waveform observation, dominant frequency estimation, and repeated component ranking. Results: The highest measured levels were produced by electric motor noise in the cigarette machine, lathe, and drilling machine, with values of 101.4, 101.6, and 103.5 decibels respectively. Gearboxes, rollers, reels, drilling heads, and the cutter also produced meaningful noise, but most were lower than the corresponding motors. The frequency spectrum showed distinctive tonal or cyclic components for each machine part. Conclusion: The method provides a practical route for locating dominant noise sources, prioritizing maintenance, and reducing occupational noise through targeted control of motors, transmissions, and cutting mechanisms.

Copyrights © 2026






Journal Info

Abbrev

brilliance

Publisher

Subject

Decision Sciences, Operations Research & Management Mathematics Other

Description

Brilliance: Research of Artificial Intelligence is The Scientific Journal. Brilliance is published twice in one year, namely in February, May and November. Brilliance aims to promote research in the field of Informatics Engineering which focuses on publishing quality papers about the latest ...