DOI: https://doi.org/10.32515/2664-262X.2024.10(41).2.142-151
Increasing the Reliability and Efficiency of Production Lines Using Artificial Intelligence Methods Using Acoustic Signal Monitoring
About the Authors
С.Г. Ковальов, Doctoral student, PhD in Technics (Candidate of Technics Sciences), Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, e-mail: kovalyovserggr@ukr.net, ORCID ID: 0009-0002-3922-8697
Viktor Aulin, Professor, Doctor in Technics (Doctor of Technic Sciences), Central Ukraіnian National Technical University, Kropyvnytskyi, Ukraine, e-mail: AulinVV@gmail.com, ORCID ID: 0000-0003-2737-120X
Andriy Hrynkiv, Senior Researcher, PhD in Technics (Candidate of Technics Sciences), Central Ukraіnian National Technical University, Kropyvnytskyi, Ukraine, e-mail: avgrinkiv@gmail.com, ORCID ID: 0000-0002-1888-6685
В.В. Варваров, PhD in Technics (Candidate of Technics Sciences), Kharkiv National Ivan Kozhedub Air Force University, Kharkiv, Ukraine, e-mail: varvarov_@ukr.net, ORCID ID: 0000-0003-1273-5605
Abstract
The article provides an in-depth analysis of a method to improve the reliability and efficiency of automated production lines by reducing maintenance costs and minimizing downtime using artificial intelligence algorithms. The method involves the application of acoustic spectra generated by the production line nodes during operation to establish a correlation with the reliability and efficiency of these lines. A model for representing acoustic spectra as a two-dimensional data array, which captures the change in acoustic spectra over time, has been proposed. The format of acoustic spectra as two-dimensional data is used to recognize equipment operation patterns. To recognize these patterns, the use of a convolutional neural network is proposed, and its software model has been developed, allowing simulation and assessment of the accuracy of using machine learning methods.
Additionally, the article highlights the results of the functioning of the developed neural network, which indicate a significant correlation between the measured acoustic spectra of the production line equipment and its reliability and efficiency indicators. The importance of this approach lies in the ability to timely detect potential problems and quickly eliminate them, which in turn contributes to reducing maintenance costs and increasing productivity.
Moreover, the implementation of this method can significantly impact the overall efficiency of production processes, providing more accurate and reliable monitoring of equipment conditions. Further research may be directed towards improving the proposed models and algorithms, as well as developing new approaches to the analysis and interpretation of acoustic spectra.
Furthermore, the integration of such advanced technologies into the production environment demonstrates a progressive shift towards more intelligent and autonomous manufacturing systems. These advancements not only enhance the performance and sustainability of industrial operations but also pave the way for future innovations. By continually refining the models and algorithms used in acoustic spectrum analysis, industries can achieve higher levels of precision in fault detection and maintenance planning. This proactive approach ensures that equipment operates at optimal levels, thereby extending its lifespan and reducing unexpected downtime. Overall, the adoption of AI-driven methodologies in industrial settings represents a significant leap forward in modernizing production lines and achieving unprecedented levels of operational excellence.
Keywords
reliability of operation, efficiency of operation, automated production lines, acoustic spectrum, machine learning, convolutional networks
Full Text:
PDF
References
1. Zhiqiang Gao, Qi Chang, Yu Deng, Wei Liu, Pengfei M, Pu Zhou, & Lei Si. (2025) “Tilt noise extraction method based on fourier transform and fitting of 2D images”. Optics Communications. Volume 577, March 2025, 131372. URL: https://doi.org/10.1016/j.optcom.2024.131372 [in English].
2. Aulin V.V., Hrynkiv A.V., Lysenko S.V., & Holub D.V. Synergetics of increasing machine reliability using Markov process models. Prospects and trends in the development of structures and technical service of agricultural machines and tools: collection of materials of the participants of the V All-Ukrainian Scientific and Practical Conference. Zhytomyr: Zhytomyr Agrotechnical College, 2019. P. 242-245. [in Ukrainian].
3. Aulin V.V., Hrynkiv A. V., Holovaty A. O., Lysenko S. V., Holub D. V., Kuzyk O. V., & Tykhy A. A. Methodological foundations of design and functioning of intelligent transport and production systems: monograph under the general editorship of Dr. Tech., Prof. Aulina V. V. Kropyvnytskyi: Publisher Lysenko V. F., 2020. 428p. [in Ukrainian].
4. Kenta Ohira, Toru Ohira. Solving a delay differential equation through the Fourier transform. Physics Letters A. Volume 531, 28 January 2025, Page 130138. URL: https://doi.org/10.1016/j.physleta.2024.130138. [in English].
5. Mehieddine Derbas, Stephan Frömel-Frybort, Hans-Christian Möhring, Martin Riegler. Accelerated Singular Spectrum Analysis and Machine Learning to investigate wood machining acoustics. Mechanical Systems and Signal Processing. Volume 223, 15 January 2025, 111879. URL: https://doi.org/10.1016/j.ymssp.2024.111879. [in English].
6. V.V. Aulin, S.G. Kovalev, A.V. Hrynkiv, & V.V. Varvarov. Algorithm for optimizing the reliability of functioning and efficiency of the use of production equipment using artificial intelligence methods. Collection of scientific papers "Central Ukrainian Scientific Bulletin. Technical Sciences". Issue 10 (41), part I. Kropyvnytskyi.. 2024, P. 60-67. [in Ukrainian].
7. Kovalev S.G. & Kovalev Yu.G. Features of the implementation of the artificial neural network model by hardware means. "Science and Technology Today" (Series "Pedagogy", Series "Law", Series "Economics", Series "Physical and Mathematical Sciences", Series "Technology")": journal. 2024. No. 6(34) 2024. P. 1131. URL: DOI: https://doi.org/10.52058/2786-6025-2024-6(34) [in Ukrainian].
8. Tao Liu, Xinsan Li, Junshuai Sun, Mindong Lyu. Shaoze Yan A post-processing method called Fourier transform based on local maxima of autocorrelation function for extracting fault feature of bearings. Advanced Engineering Informatics. Volume 62, Part B, October 2024, 102766 URL: https://doi.org/10.1016/j.aei.2024.102766. [in English].
9. Xuanqi Lin, Yong Zhang, Shun Wang, Yongli Hu, Baocai Yin. Multi-scale wavelet transform enhanced graph neural network for pedestrian trajectory prediction. Physica A: Statistical Mechanics and its Applications. Volume 659, 1 February 2025, 130319. URL: https://doi.org/10.1016/j.physa.2024.130319.
10. Seong-Heon Seo. Instantaneous frequency estimation by interpolating continuous wavelet transform coefficients. Digital Signal Processing.Volume 159, April 2025, 104989. URL: https://doi.org/10.1016/j.dsp.2025.104989. [in English].
11. Elizabeth Shoop, Suzanne J. Matthews, Richard Brown, Joel C. Adams. Hands-on parallel & distributed computing with Raspberry Pi devices and clusters. Journal of Parallel and Distributed Computing. Volume 196, February 2025, 104996. URL: https://doi.org/10.1016/j.jpdc.2024.104996. [in English].
12. M.D. Rakesh, M. & Jeevankumar, S.B. Rudraswamy. Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor. Smart Agricultural Technology. Volume 10, March 2025, 100714. URL: https://doi.org/10.1016/j.atech.2024.100714. [in English].
13. Luca Barillaro. Deep Learning Platforms: TensorFlow. Reference Module in Life Sciences. 2024. URL: https://doi.org/10.1016/B978-0-323-95502-7.00167-6. [in English].
14. Luca Barillaro. Deep Learning Platforms: Keras. Reference Module in Life Sciences 2024. URL: https://doi.org/10.1016/B978-0-323-95502-7.00092-0. [in English].
15. Sharnil Pandya, Hemant Ghayvat. Ambient acoustic event assistive framework for identification, detection, and recognition of unknown acoustic events of a residence. Advanced Engineering Informatics. Volume 47, January 2021, 101238. URL: https://doi.org/10.1016/j.aei.2020.101238. [in English].
Citations
1. Zhiqiang Gao, Qi Chang, Yu Deng, Wei Liu, Pengfei M, Pu Zhou, Lei Si. “Tilt noise extraction method based on fourier transform and fitting of 2D images”. Optics Communications. Volume 577, March 2025, 131372. URL: https://doi.org/10.1016/j.optcom.2024.131372
2. Аулін В.В., Гриньків А.В., Лисенко С.В., Голуб Д.В. Синергетика підвищення надійності машин використанням моделей марківських процесів. Перспективи і тенденції розвитку конструкцій та технічного сервісу сх машин і знарядь: зб. матеріалів доп. учасн. V Всеукраїнської науково-практичної конф. Житомир: Житомирський агротехнічний коледж, 2019. С. 242-245.
3. Аулін В. В., Гриньків А. В., Головатий А. О., Лисенко С. В., Голуб Д. В., Кузик О.В., Тихий А. А. Методологічні основи проектування та функціонування інтелектуальних транспортних і виробничих систем: монографія під заг. ред. д.т.н., проф. Ауліна В.В. Кропивницький: Видавець Лисенко В.Ф., 2020. 428с.
4. Kenta Ohira, Toru Ohira. Solving a delay differential equation through the Fourier transform. Physics Letters A. Volume 531, 28 January 2025, Page 130138. URL: https://doi.org/10.1016/j.physleta.2024.130138.
5. Mehieddine Derbas, Stephan Frömel-Frybort, Hans-Christian Möhring, Martin Riegler. Accelerated Singular Spectrum Analysis and Machine Learning to investigate wood machining acoustics. Mechanical Systems and Signal Processing. Volume 223, 15 January 2025, 111879. URL: https://doi.org/10.1016/j.ymssp.2024.111879.
6. В.В. Аулін, С.Г. Ковальов, А.В. Гриньків, В.В. Варваров. Алгоритм оптимізації надійності функціонування та ефективності використання виробничого обладнання методами штучного інтелекту. Збірник наукових праць «Центральноукраїнський науковий вісник. Технічні науки». Вип.10 (41), ч. I. Кропивницький. 2024, С. 60-67.
7. Ковальов С.Г. Ковальов Ю.Г. Особливості реалізація моделі штучної нейронної мережі апаратними засобами. «Наука і технікасьогодні» (Серія «Педагогіка», Серія «Право», Серія «Економіка», Серія «Фізико-математичнінауки», Серія «Техніка»)»: журнал. 2024. No6(34) 2024. С. 1131. URL: DOI: https://doi.org/10.52058/2786-6025-2024-6(34)
8. Tao Liu, Xinsan Li, Junshuai Sun, Mindong Lyu. Shaoze Yan A post-processing method called Fourier transform based on local maxima of autocorrelation function for extracting fault feature of bearings. Advanced Engineering Informatics. Volume 62, Part B, October 2024, 102766 URL: https://doi.org/10.1016/j.aei.2024.102766.
9. Xuanqi Lin, Yong Zhang, Shun Wang, Yongli Hu, Baocai Yin. Multi-scale wavelet transform enhanced graph neural network for pedestrian trajectory prediction. Physica A: Statistical Mechanics and its Applications. Volume 659, 1 February 2025, 130319. URL: https://doi.org/10.1016/j.physa.2024.130319.
10. Seong-Heon Seo. Instantaneous frequency estimation by interpolating continuous wavelet transform coefficients. Digital Signal Processing.Volume 159, April 2025, 104989. URL: https://doi.org/10.1016/j.dsp.2025.104989.
11. Elizabeth Shoop, Suzanne J. Matthews, Richard Brown, Joel C. Adams. Hands-on parallel & distributed computing with Raspberry Pi devices and clusters. Journal of Parallel and Distributed Computing. Volume 196, February 2025, 104996. URL: https://doi.org/10.1016/j.jpdc.2024.104996.
12. M.D. Rakesh, M. Jeevankumar, S.B. Rudraswamy. Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor. Smart Agricultural Technology. Volume 10, March 2025, 100714. URL: https://doi.org/10.1016/j.atech.2024.100714.
13. Luca Barillaro. Deep Learning Platforms: TensorFlow. Reference Module in Life Sciences. 2024. URL: https://doi.org/10.1016/B978-0-323-95502-7.00167-6.
14. Luca Barillaro. Deep Learning Platforms: Keras. Reference Module in Life Sciences 2024. URL: https://doi.org/10.1016/B978-0-323-95502-7.00092-0.
15. Sharnil Pandya, Hemant Ghayvat. Ambient acoustic event assistive framework for identification, detection, and recognition of unknown acoustic events of a residence. Advanced Engineering Informatics. Volume 47, January 2021, 101238. URL: https://doi.org/10.1016/j.aei.2020.101238.
Copyright (c) 2024 Serhii Kovalov, Viktor Aulin, Andrii Hrynkiv, Valerii Varvarov
Increasing the Reliability and Efficiency of Production Lines Using Artificial Intelligence Methods Using Acoustic Signal Monitoring
About the Authors
С.Г. Ковальов, Doctoral student, PhD in Technics (Candidate of Technics Sciences), Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, e-mail: kovalyovserggr@ukr.net, ORCID ID: 0009-0002-3922-8697
Viktor Aulin, Professor, Doctor in Technics (Doctor of Technic Sciences), Central Ukraіnian National Technical University, Kropyvnytskyi, Ukraine, e-mail: AulinVV@gmail.com, ORCID ID: 0000-0003-2737-120X
Andriy Hrynkiv, Senior Researcher, PhD in Technics (Candidate of Technics Sciences), Central Ukraіnian National Technical University, Kropyvnytskyi, Ukraine, e-mail: avgrinkiv@gmail.com, ORCID ID: 0000-0002-1888-6685
В.В. Варваров, PhD in Technics (Candidate of Technics Sciences), Kharkiv National Ivan Kozhedub Air Force University, Kharkiv, Ukraine, e-mail: varvarov_@ukr.net, ORCID ID: 0000-0003-1273-5605
Abstract
Keywords
Full Text:
PDFReferences
1. Zhiqiang Gao, Qi Chang, Yu Deng, Wei Liu, Pengfei M, Pu Zhou, & Lei Si. (2025) “Tilt noise extraction method based on fourier transform and fitting of 2D images”. Optics Communications. Volume 577, March 2025, 131372. URL: https://doi.org/10.1016/j.optcom.2024.131372 [in English].
2. Aulin V.V., Hrynkiv A.V., Lysenko S.V., & Holub D.V. Synergetics of increasing machine reliability using Markov process models. Prospects and trends in the development of structures and technical service of agricultural machines and tools: collection of materials of the participants of the V All-Ukrainian Scientific and Practical Conference. Zhytomyr: Zhytomyr Agrotechnical College, 2019. P. 242-245. [in Ukrainian].
3. Aulin V.V., Hrynkiv A. V., Holovaty A. O., Lysenko S. V., Holub D. V., Kuzyk O. V., & Tykhy A. A. Methodological foundations of design and functioning of intelligent transport and production systems: monograph under the general editorship of Dr. Tech., Prof. Aulina V. V. Kropyvnytskyi: Publisher Lysenko V. F., 2020. 428p. [in Ukrainian].
4. Kenta Ohira, Toru Ohira. Solving a delay differential equation through the Fourier transform. Physics Letters A. Volume 531, 28 January 2025, Page 130138. URL: https://doi.org/10.1016/j.physleta.2024.130138. [in English].
5. Mehieddine Derbas, Stephan Frömel-Frybort, Hans-Christian Möhring, Martin Riegler. Accelerated Singular Spectrum Analysis and Machine Learning to investigate wood machining acoustics. Mechanical Systems and Signal Processing. Volume 223, 15 January 2025, 111879. URL: https://doi.org/10.1016/j.ymssp.2024.111879. [in English].
6. V.V. Aulin, S.G. Kovalev, A.V. Hrynkiv, & V.V. Varvarov. Algorithm for optimizing the reliability of functioning and efficiency of the use of production equipment using artificial intelligence methods. Collection of scientific papers "Central Ukrainian Scientific Bulletin. Technical Sciences". Issue 10 (41), part I. Kropyvnytskyi.. 2024, P. 60-67. [in Ukrainian].
7. Kovalev S.G. & Kovalev Yu.G. Features of the implementation of the artificial neural network model by hardware means. "Science and Technology Today" (Series "Pedagogy", Series "Law", Series "Economics", Series "Physical and Mathematical Sciences", Series "Technology")": journal. 2024. No. 6(34) 2024. P. 1131. URL: DOI: https://doi.org/10.52058/2786-6025-2024-6(34) [in Ukrainian].
8. Tao Liu, Xinsan Li, Junshuai Sun, Mindong Lyu. Shaoze Yan A post-processing method called Fourier transform based on local maxima of autocorrelation function for extracting fault feature of bearings. Advanced Engineering Informatics. Volume 62, Part B, October 2024, 102766 URL: https://doi.org/10.1016/j.aei.2024.102766. [in English].
9. Xuanqi Lin, Yong Zhang, Shun Wang, Yongli Hu, Baocai Yin. Multi-scale wavelet transform enhanced graph neural network for pedestrian trajectory prediction. Physica A: Statistical Mechanics and its Applications. Volume 659, 1 February 2025, 130319. URL: https://doi.org/10.1016/j.physa.2024.130319.
10. Seong-Heon Seo. Instantaneous frequency estimation by interpolating continuous wavelet transform coefficients. Digital Signal Processing.Volume 159, April 2025, 104989. URL: https://doi.org/10.1016/j.dsp.2025.104989. [in English].
11. Elizabeth Shoop, Suzanne J. Matthews, Richard Brown, Joel C. Adams. Hands-on parallel & distributed computing with Raspberry Pi devices and clusters. Journal of Parallel and Distributed Computing. Volume 196, February 2025, 104996. URL: https://doi.org/10.1016/j.jpdc.2024.104996. [in English].
12. M.D. Rakesh, M. & Jeevankumar, S.B. Rudraswamy. Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor. Smart Agricultural Technology. Volume 10, March 2025, 100714. URL: https://doi.org/10.1016/j.atech.2024.100714. [in English].
13. Luca Barillaro. Deep Learning Platforms: TensorFlow. Reference Module in Life Sciences. 2024. URL: https://doi.org/10.1016/B978-0-323-95502-7.00167-6. [in English].
14. Luca Barillaro. Deep Learning Platforms: Keras. Reference Module in Life Sciences 2024. URL: https://doi.org/10.1016/B978-0-323-95502-7.00092-0. [in English].
15. Sharnil Pandya, Hemant Ghayvat. Ambient acoustic event assistive framework for identification, detection, and recognition of unknown acoustic events of a residence. Advanced Engineering Informatics. Volume 47, January 2021, 101238. URL: https://doi.org/10.1016/j.aei.2020.101238. [in English].
Citations
1. Zhiqiang Gao, Qi Chang, Yu Deng, Wei Liu, Pengfei M, Pu Zhou, Lei Si. “Tilt noise extraction method based on fourier transform and fitting of 2D images”. Optics Communications. Volume 577, March 2025, 131372. URL: https://doi.org/10.1016/j.optcom.2024.131372
2. Аулін В.В., Гриньків А.В., Лисенко С.В., Голуб Д.В. Синергетика підвищення надійності машин використанням моделей марківських процесів. Перспективи і тенденції розвитку конструкцій та технічного сервісу сх машин і знарядь: зб. матеріалів доп. учасн. V Всеукраїнської науково-практичної конф. Житомир: Житомирський агротехнічний коледж, 2019. С. 242-245.
3. Аулін В. В., Гриньків А. В., Головатий А. О., Лисенко С. В., Голуб Д. В., Кузик О.В., Тихий А. А. Методологічні основи проектування та функціонування інтелектуальних транспортних і виробничих систем: монографія під заг. ред. д.т.н., проф. Ауліна В.В. Кропивницький: Видавець Лисенко В.Ф., 2020. 428с.
4. Kenta Ohira, Toru Ohira. Solving a delay differential equation through the Fourier transform. Physics Letters A. Volume 531, 28 January 2025, Page 130138. URL: https://doi.org/10.1016/j.physleta.2024.130138.
5. Mehieddine Derbas, Stephan Frömel-Frybort, Hans-Christian Möhring, Martin Riegler. Accelerated Singular Spectrum Analysis and Machine Learning to investigate wood machining acoustics. Mechanical Systems and Signal Processing. Volume 223, 15 January 2025, 111879. URL: https://doi.org/10.1016/j.ymssp.2024.111879.
6. В.В. Аулін, С.Г. Ковальов, А.В. Гриньків, В.В. Варваров. Алгоритм оптимізації надійності функціонування та ефективності використання виробничого обладнання методами штучного інтелекту. Збірник наукових праць «Центральноукраїнський науковий вісник. Технічні науки». Вип.10 (41), ч. I. Кропивницький. 2024, С. 60-67.
7. Ковальов С.Г. Ковальов Ю.Г. Особливості реалізація моделі штучної нейронної мережі апаратними засобами. «Наука і технікасьогодні» (Серія «Педагогіка», Серія «Право», Серія «Економіка», Серія «Фізико-математичнінауки», Серія «Техніка»)»: журнал. 2024. No6(34) 2024. С. 1131. URL: DOI: https://doi.org/10.52058/2786-6025-2024-6(34)
8. Tao Liu, Xinsan Li, Junshuai Sun, Mindong Lyu. Shaoze Yan A post-processing method called Fourier transform based on local maxima of autocorrelation function for extracting fault feature of bearings. Advanced Engineering Informatics. Volume 62, Part B, October 2024, 102766 URL: https://doi.org/10.1016/j.aei.2024.102766.
9. Xuanqi Lin, Yong Zhang, Shun Wang, Yongli Hu, Baocai Yin. Multi-scale wavelet transform enhanced graph neural network for pedestrian trajectory prediction. Physica A: Statistical Mechanics and its Applications. Volume 659, 1 February 2025, 130319. URL: https://doi.org/10.1016/j.physa.2024.130319.
10. Seong-Heon Seo. Instantaneous frequency estimation by interpolating continuous wavelet transform coefficients. Digital Signal Processing.Volume 159, April 2025, 104989. URL: https://doi.org/10.1016/j.dsp.2025.104989.
11. Elizabeth Shoop, Suzanne J. Matthews, Richard Brown, Joel C. Adams. Hands-on parallel & distributed computing with Raspberry Pi devices and clusters. Journal of Parallel and Distributed Computing. Volume 196, February 2025, 104996. URL: https://doi.org/10.1016/j.jpdc.2024.104996.
12. M.D. Rakesh, M. Jeevankumar, S.B. Rudraswamy. Implementation of real time root crop leaf classification using CNN on raspberry-Pi microprocessor. Smart Agricultural Technology. Volume 10, March 2025, 100714. URL: https://doi.org/10.1016/j.atech.2024.100714.
13. Luca Barillaro. Deep Learning Platforms: TensorFlow. Reference Module in Life Sciences. 2024. URL: https://doi.org/10.1016/B978-0-323-95502-7.00167-6.
14. Luca Barillaro. Deep Learning Platforms: Keras. Reference Module in Life Sciences 2024. URL: https://doi.org/10.1016/B978-0-323-95502-7.00092-0.
15. Sharnil Pandya, Hemant Ghayvat. Ambient acoustic event assistive framework for identification, detection, and recognition of unknown acoustic events of a residence. Advanced Engineering Informatics. Volume 47, January 2021, 101238. URL: https://doi.org/10.1016/j.aei.2020.101238.