SavedAdd your journal

Journals / Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi / 2026 / Cilt: 18

Torque estimation using industrial sensor data: A comparative analysis of deep learning, machine learning, and hyperparameter optimization approaches

Endüstriyel sensör verileriyle tork tahmini: Derin öğrenme, makine öğrenmesi ve hiperparametre optimizasyonu yaklaşımlarının karşılaştırmalı analizi

Merve Yağmurcu(Sivas Cumhuriyet Üniversitesi)0009-0000-5749-4337
Kemal Adem(SİVAS CUMHURİYET ÜNİVERSİTESİ)0000-0002-3752-7354
Sibel Arslan(SİVAS CUMHURİYET ÜNİVERSİTESİ)0000-0003-3626-553X
Pages
—
Publication Date
2026-09-28
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Experimental results showed that recurrent deep learning models generally achieved the highest prediction performance under the applied experimental setting.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Predictive maintenance is an important approach for reducing unexpected failures and improving operational reliability in industrial systems.
📊
Key Findings & Data:In this study, deep learning and machine learning models were comparatively evaluated for torque estimation using the AI4I 2020 predictive maintenance dataset.
💡
Conclusion & Impact:Experimental results showed that recurrent deep learning models generally achieved the highest prediction performance under the applied experimental setting.
🔬Design:Modeling & Simulation
📍Scope:2020 Verileri
⚙️Variables:Tork tahmini · öngörücü bakım · derin öğrenme

Abstract

Predictive maintenance is an important approach for reducing unexpected failures and improving operational reliability in industrial systems. In this study, deep learning and machine learning models were comparatively evaluated for torque estimation using the AI4I 2020 predictive maintenance dataset. Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) architectures were analyzed together with conventional regression models, including Random Forest, Extra Trees, Gradient Boosting, Support Vector Regression, Ridge Regression, K-Nearest Neighbor, Linear Regression, and Decision Tree. Random Search, Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and model-specific optimization strategies were applied to examine the effect of hyperparameter optimization. Experimental results showed that recurrent deep learning models generally achieved the highest prediction performance under the applied experimental setting. The Random Search-optimized LSTM model obtained the best numerical result with R² = 0.8363, RMSE = 4.0170, and MAE = 3.0004. However, the effect of optimization was model-dependent. While optimization provided limited improvement in recurrent deep learning models, it produced more visible gains in some machine learning models, particularly Support Vector Regression and Gradient Boosting. The findings indicate that model selection and optimization strategy should be evaluated together in sensor-based torque estimation problems.

Özet

Öngörücü bakım, endüstriyel sistemlerde beklenmeyen arızaların azaltılması ve operasyonel güvenilirliğin artırılması açısından önemli bir yaklaşımdır. Bu çalışmada, AI4I 2020 öngörücü bakım veri seti kullanılarak tork tahmini için derin öğrenme ve makine öğrenmesi modelleri karşılaştırmalı olarak değerlendirilmiştir. Tekrarlayan Sinir Ağı (RNN), Uzun Kısa Süreli Bellek (LSTM) ve Geçit Kontrollü Yinelemeli Birim (GRU) mimarileri; Random Forest, Extra Trees, Gradient Boosting, Destek Vektör Regresyonu, Ridge Regresyon, K-En Yakın Komşu, Doğrusal Regresyon ve Karar Ağacı regresyon modelleri ile birlikte incelenmiştir. Hiperparametre optimizasyonunun etkisini değerlendirmek amacıyla Random Search, Genetik Algoritma (GA), Parçacık Sürü Optimizasyonu (PSO) ve modele özgü optimizasyon stratejileri uygulanmıştır. Deneysel sonuçlar, uygulanan deneysel kurgu altında tekrarlayan derin öğrenme modellerinin genel olarak en yüksek tahmin performansını elde ettiğini göstermiştir. Random Search ile optimize edilen LSTM modeli R² = 0.8363, RMSE = 4.0170 ve MAE = 3.0004 değerleriyle en yüksek sayısal sonucu elde etmiştir. Bununla birlikte optimizasyonun etkisinin modele bağlı olarak değiştiği görülmüştür. Optimizasyon, tekrarlayan derin öğrenme modellerinde sınırlı düzeyde iyileşme sağlarken, özellikle Destek Vektör Regresyonu ve Gradient Boosting modellerinde daha belirgin performans artışı oluşturmuştur. Sonuçlar sensör tabanlı tork tahmini problemlerinde model seçimi ve optimizasyon stratejisinin birlikte değerlendirilmesi gerektiğini göstermektedir.

🔖

Cite This Article

Yağmurcu, M., Adem, K., Arslan, S. (2026). Torque estimation using industrial sensor data: A comparative analysis of deep learning, machine learning, and hyperparameter optimization approaches. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 18. https://doi.org/10.28948/ngumuh.1893199

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (28)

  1. Z. Li, Q. He and J. Li, “A survey of deep learning-driven architecture for predictive maintenance,” Engineering Applications of Artificial Intelligence, 133, 108285, 2024. https://doi.org/10.1016/j.engappai.2024.108285
  2. O. Khattach, O. Moussaoui and M. Hassine, “End-to-end architecture for real-time IoT analytics and predictive maintenance using stream processing and ML pipelines,” Sensors, 25 (9), 2945, 2025. https://doi.org/10.3390/s25092945
  3. M. A. B. Syed, M. R. Hasan, N. I. Chowdhury, M. H. Rahman and I. Ahmed, “A systematic review of time series algorithms and analytics in predictive maintenance,” Decision Analytics Journal, 15, 100573, 2025. https://doi.org/10.1016/j.dajour.2025.100573
  4. U. Khan, D. S. Cheng, F. Setti, F. Fummi, M. Cristani and L. Capogrosso, “A comprehensive survey on deep learning-based predictive maintenance,” ACM Transactions on Embedded Computing Systems, 25 (2), Article 25, 1-43, 2026. https://doi.org/10.1145/3732287
  5. X. Bampoula, N. Nikolakis and K. Alexopoulos, “Condition monitoring and predictive maintenance of assets in manufacturing using LSTM-autoencoders and transformer encoders,” Sensors, 24 (10), 3215, 2024. https://doi.org/10.3390/s24103215
  6. M. A. K. Raiaan, S. Sakib, N. M. Fahad, A. Al Mamun, M. A. Rahman, S. Shatabda and M. S. H. Mukta, “A systematic review of hyperparameter optimization techniques in convolutional neural networks,” Decision Analytics Journal, 11, 100470, 2024. https://doi.org/10.1016/j.dajour.2024.100470
  7. M. Sharma, I. Kandasamy and W. B. Vasantha, “Emotion quantification and classification using the neutrosophic approach to deep learning,” Applied Soft Computing, 148, 110896, 2023. https://doi.org/10.1016/j.asoc.2023.110896
  8. S. Memiş, F. Ş. Erduran and H. Aydoğan, “Adaptive machine learning approaches utilizing soft decision-making via intuitionistic fuzzy parameterized intuitionistic fuzzy soft matrices,” PeerJ Computer Science, 11, e2703, 2025. https://doi.org/10.7717/peerj-cs.2703
  9. S. Mishra, V. Jain, Y. A. Saraf, I. Kandasamy and W. B. Vasantha, “Deep neuro-fuzzy system for violence detection,” Neurocomputing, 619, 129007, 2025. https://doi.org/10.1016/j.neucom.2024.129007
  10. N. M. Thoppil, V. Vasu and C. S. P. Rao, “Bayesian optimization LSTM/bi-LSTM network with self-optimized structure and hyperparameters for remaining useful life estimation of lathe spindle unit,” Journal of Computing and Information Science in Engineering, 22 (2), 021012, 2022.
  11. S. R. Young, D. C. Rose, T. P. Karnowski, S. H. Lim and R. M. Patton, “Optimizing deep learning hyper-parameters through an evolutionary algorithm,” Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments, pp. 1-5, Austin, TX, USA, 15 November 2015. https://doi.org/10.1145/2834892.2834896
  12. M. Elsisi, M. Q. Tran, K. Mahmoud, M. Lehtonen and M. M. F. Darwish, “Robust design of ANFIS-based blade pitch controller for wind energy conversion systems against wind speed fluctuations,” IEEE Access, 9, 37894-37904, 2021. https://doi.org/10.1109/ACCESS.2021.3063053
  13. AI4I 2020 Predictive Maintenance Dataset, UCI Machine Learning Repository, 2020. https://doi.org/10.24432/C5HS5C (accessed Feb. 19, 2026).
  14. J. Kim, H. Kim, H. Kim, D. Lee and S. Yoon, “A comprehensive survey of deep learning for time series forecasting: Architectural diversity and open challenges,” Artificial Intelligence Review, 58, 216, 2025. https://doi.org/10.1007/s10462-025-11223-9
  15. B. Lim and S. Zohren, “Time-series forecasting with deep learning: A survey,” Philosophical Transactions of the Royal Society A, 379 (2194), 20200209, 2021. https://doi.org/10.1098/rsta.2020.0209
  16. I. Goodfellow, Y. Bengio and A. Courville, Deep Learning. MIT Press, Cambridge, MA, USA, 2016.
  17. Y. Bengio, P. Simard and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE Transactions on Neural Networks, 5 (2), 157-166, 1994. https://doi.org/10.1109/72.279181
  18. R. Pascanu, T. Mikolov and Y. Bengio, “On the difficulty of training recurrent neural networks,” Proceedings of the 30th International Conference on Machine Learning (ICML), vol. 28, no. 3, pp. 1310-1318, Atlanta, GA, USA, 17-19 June 2013.
  19. I. D. Mienye, T. G. Swart and G. Obaido, “Recurrent neural networks: A comprehensive review of architectures, variants, and applications,” Information, 15 (9), 517, 2024. https://doi.org/10.3390/info15090517
  20. S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, 9 (8), 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  21. A. Graves, “Long short-term memory,” in Supervised Sequence Labelling with Recurrent Neural Networks, pp. 37-45, Springer, Berlin, Heidelberg, 2012. https://doi.org/10.1007/978-3-642-24797-2_4
  22. K. Cho, B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” arXiv preprint arXiv:1406.1078, 2014. https://doi.org/10.48550/arXiv.1406.1078
  23. J. Chung, C. Gulcehre, K. Cho and Y. Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling,” arXiv preprint arXiv:1412.3555, 2014.
  24. S. Mohsen, “Recognition of human activity using GRU deep learning algorithm,” Multimedia Tools and Applications, 82 (30), 47733-47749, 2023. https://doi.org/10.1007/s11042-023-15571-y
  25. J. Kennedy and R. Eberhart, “Particle swarm optimization,” Proceedings of ICNN’95 - International Conference on Neural Networks, vol. 4, pp. 1942-1948, Perth, WA, Australia, 1995. https://doi.org/10.1109/ICNN.1995.488968
  26. M. A. Kadi, N. Akkouche, S. Awad, K. Loubar and M. Tazerout, “Kinetic study of transesterification using particle swarm optimization method,” Heliyon, 5 (8), e02146, 2019. https://doi.org/10.1016/j.heliyon.2019.e02146
  27. J. H. Holland, Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. University of Michigan Press, Ann Arbor, MI, USA, 1975.
  28. S. Mirjalili, Evolutionary Algorithms and Neural Networks: Theory and Applications. Springer, Cham, Switzerland, 2019. https://doi.org/10.1007/978-3-319-93025-1