ENERGY-AWARE CLASSIFICATION OF MACHINE OPERATING STATES FOR EFFICIENT AND SUSTAINABLE PRODUCTION
DOI:
https://doi.org/10.67772/6xs71g72Keywords:
Energy efficiency, Machine-state classification, Sustainable manufacturing, Power consumption, Random ForestAbstract
The monitoring of machines is becoming more energy efficient as it contributes to better production performance and sustainable production. This paper investigated if machine operating states can be identified based on the commonly collected power consumption characteristics. The operating states analysed were: Production, Standby, MachineOn, Alarm, Loading and Tooling (all publicly available discrete manufacturing). Average, minimum and maximum power consumption were selected as main predictive variables, and machine-state recognition was applied using a Random Forest (RF) Classifier. The overall accuracy of the model was 72.26% and the weighted F1-score was 0.760. Production had the best classification performance, followed by Standby and MachineOn, whereas Alarm and Loading and Tooling were more challenging to classify due to high energy patterns overlapping and low energy frequencies of the classes. The average power was the strongest contributor to classification, while the minimum and maximum power were also contributing information for classification. Non-production states were more likely to have a higher percentage of machine time but a lower percentage of total energy use, as production was responsible for 84.75% of estimated energy use and 41.43% of recorded machine time. The results show that simple power consumption parameters can be used for practical machine state monitoring and to help determine operation parameters that are relevant for enhanced energy management, machine utilization, and sustainable production.
References
1. Abadi, M. M. K. F., Liu, C., Zhang, M., Hu, Y., & Xu, Y. (2025). Leveraging AI for energy-efficient manufacturing systems: Review and future prospectives. Journal of Manufacturing Systems, 78, 153-177.
2. Atzeni, D., Ramjattan, R., Figliè, R., Baldi, G., & Mazzei, D. (2023). Data-driven insights through industrial retrofitting: An anonymized dataset with machine learning use cases. Sensors, 23(13), 6078. https://doi.org/10.3390/s23136078
3. Bermeo-Ayerbe, M. A., Ocampo-Martinez, C., & Diaz-Rozo, J. (2022). Data-driven energy prediction modeling for both energy efficiency and maintenance in smart manufacturing systems. Energy, 238, 121691.
4. Cagno, E., Accordini, D., Thollander, P., Andrei, M., Hasan, A. M., Pessina, S., & Trianni, A. (2025). Energy management and industry 4.0: Analysis of the enabling effects of digitalization on the implementation of energy management practices. Applied Energy, 390, 125877.
5. Cooper, C., Zhang, J., Ragai, I., & Gao, R. X. (2024). Multi-sensor fusion and machine learning-driven sequence-to-sequence translation for interpretable process signature prediction in machining. Journal of Manufacturing Systems, 75, 288-298.
6. da Silva, F. S. T., da Costa, C. A., Crovato, C. D. P., & da Rosa Righi, R. (2020). Looking at energy through the lens of Industry 4.0: A systematic literature review of concerns and challenges. Computers & Industrial Engineering, 143, 106426.
7. Geng, D., Evans, S., & Kishita, Y. (2023). The identification and classification of energy waste for efficient energy supervision in manufacturing factories. Renewable and sustainable energy reviews, 182, 113409.
8. Mazzei, D., & Ramjattan, R. (2022). Machine learning for industry 4.0: a systematic review using deep learning-based topic modelling. Sensors, 22(22), 8641.
9. Polenta, A., Tomassini, S., Falcionelli, N., Contardo, P., Dragoni, A. F., & Sernani, P. (2022). A comparison of machine learning techniques for the quality classification of molded products. Information, 13(6), 272.
10. Rai, R., Tiwari, M. K., Ivanov, D., & Dolgui, A. (2021). Machine learning in manufacturing and industry 4.0 applications. International Journal of Production Research, 59(16), 4773-4778.
11. Sarswatula, S. A., Pugh, T., & Prabhu, V. (2022). Modeling energy consumption using machine learning. Frontiers in Manufacturing Technology, 2, 855208.
12. Selvaraj, V., & Min, S. (2023). Real-time fault identification system for a retrofitted ultra-precision CNC machine from equipment's power consumption data: a case study of an implementation. International Journal of Precision Engineering and Manufacturing-Green Technology, 10(4), 925-941.
13. Seyedzadeh, S., Christodoulou, V., Turner, A., & Lotfian, S. (2025). Optimising manufacturing efficiency: a data analytics solution for machine utilisation and production insights. Journal of Manufacturing and Materials Processing, 9(7), 210.
14. Tan, D., Suvarna, M., Tan, Y. S., Li, J., & Wang, X. (2021). A three-step machine learning framework for energy profiling, activity state prediction and production estimation in smart process manufacturing. Applied Energy, 291, 116808.
15. Xu, Z., Selvaraj, V., & Min, S. (2024). State identification of a 5-axis ultra-precision CNC machine tool using energy consumption data assisted by multi-output densely connected 1D-CNN model. Journal of Intelligent Manufacturing, 35(1), 147-160.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
