Iranian Journal of Manufacturing Engineering

Iranian Journal of Manufacturing Engineering

Temporal state-of-health estimation of NiMH batteries using GRU networks and random forest models

Document Type : Original Article

Authors
Maryam Khademi 1
Ali Akbar Kafshkanan 2
Mahmoud Heydari Kia 3
Amirhossein Parivar 3
1 Department of Applied Mathematics, Islamic Azad University South Tehran Branch, Tehran, Iran
2 Department of Electrical Engineering, Iran University of Science & Technology, Tehran, Iran
3 Irankhodro Powertrain Company (IPCO), Tehran, Iran
10.22034/ijme.2026.585187.2190
Abstract
Estimating battery state of health (SOH) is important for the reliable operation of battery management systems, especially in hybrid vehicles using nickel–metal hydride batteries. In this study, a data-driven method is presented for estimating the SOH indicator of a NiMH battery module based on voltage and current data. From a manufacturing perspective, the proposed method can help improve quality control, reduce end-of-line testing time, and decrease dependence on long capacity tests. The data were collected using an experimental instrumentation platform including voltage measurement, current measurement, and load control. The raw data were filtered using physical limits to remove abnormal records while preserving both low-current and higher-current operating regimes. The filtered data were then divided into fixed-length windows, and voltage- and current-related features were extracted. Two models, Random Forest and GRU, were evaluated for SOH indicator estimation. The best GRU performance was obtained at a sequence length of 20, with RMSE = 0.005022, MAE = 0.003012, and R² = 0.996177. Under the same comparison condition, Random Forest achieved RMSE = 0.016402, MAE = 0.003950, and R² = 0.959225. The results showed that both models could estimate the SOH indicator, but GRU provided better performance by using temporal information from consecutive windows. The results also showed that excessively increasing the sequence length did not necessarily improve accuracy and could reduce the performance of the recurrent model.
Keywords
NiMH Battery
SOH Indicator
GRU Network
Random Forest
Quality Control
End-Of-Line Testing
Instrumentation
[1] Yang H, Qiu Y, Guo X. Prediction of state-of-health for nickel-metal hydride batteries by a curve model based on charge-discharge tests. Energies. 2015 Nov 4;8(11):12474-87. doi: 10.3390/en81112322
[2] Kafshkanan AA, Shahabiniya MP, Heydarikia M, Parivar AH, Kharazmi S. State-of-health prediction of nickel–metal hydride battery of Toyota Prius hybrid vehicle using features extracted from charge–discharge curves and machine learning. In: Proceedings of the 14th International Conference on Electrical Engineering, Computer, Mechanics and Artificial Intelligence; 2026 Jun; Mashhad, Iran. [In Persian]
[3] Maghamfar A, Shahbazi M, Hashemi R. Detection and measurement of warping in FDM additive manufacturing process using artificial intelligence and machine vision. Iranian Journal of Manufacturing Engineering. 2025 Feb 19;11(12):1-5. (In Persian). doi: 10.22034/ijme.2024.479491.2011
[4] Zangene Najafi M, Shahbazi M, Niknam SA. Developing surface roughness prediction model using deep convolutional network. Iranian Journal of Manufacturing Engineering. 2025 Jan 20;11(11):26-36. doi: 10.22034/ijme.2024.474664.2000 [In Persian]
[5] Schnell J, Reinhart G. Quality management for battery production: a quality gate concept. Procedia CIRP. 2016 Jan 1;57:568-73. doi: 10.1016/j.procir.2016.11.098
[6] Salkind AJ, Fennie C, Singh P, Atwater T, Reisner DE. Determination of state-of-charge and state-of-health of batteries by fuzzy logic methodology. Journal of Power sources. 1999 Jul 1;80(1-2):293-300. doi: 10.1016/S0378-7753(99)00079-8
[7] Zhang J, Li K. State-of-health estimation for lithium-ion batteries in hybrid electric vehicles—a review. Energies. 2024 Nov 18;17(22):5753. doi: 10.3390/en17225753
[8] Chehab Z, Serrao L, Guezennec YG, Rizzoni G. Aging characterization of nickel: Metal hydride batteries using electrochemical impedance spectroscopy. InASME International Mechanical Engineering Congress and Exposition 2006 Jan 1 (Vol. 47683, pp. 343-349). doi: 10.1115/IMECE2006-14608
[9] Dong Q, Liu Z, Wang H, Wang L, Dong R, Lv L. SOH Estimation of Lithium Battery Under Improved CNN-BIGRU-Attention Model Based on Hiking Optimization Algorithm. World Electric Vehicle Journal. 2025 Aug 25;16(9):487. doi: 10.3390/wevj16090487
[10] Yamashita A, Berg S, Figgemeier E. Unsupervised learning of charge-discharge cycles from various lithium-ion battery cells to visualize dataset characteristics and to interpret model performance. Energy and AI. 2024 Sep 1;17:100409. doi: 10.1016/j.egyai.2024.100409
[11] Severson KA, Attia PM, Jin N, Perkins N, Jiang B, Yang Z, Chen MH, Aykol M, Herring PK, Fraggedakis D, Bazant MZ. Data-driven prediction of battery cycle life before capacity degradation. Nature energy. 2019 May;4(5):383-91. doi: 10.1038/s41560-019-0356-8
[12] Klass V, Behm M, Lindbergh G. A support vector machine-based state-of-health estimation method for lithium-ion batteries under electric vehicle operation. Journal of Power Sources. 2014 Dec 15;270:262-72. doi: 10.1016/j.jpowsour.2014.07.116
[13] Yang N, Song Z, Hofmann H, Sun J. Robust State of Health estimation of lithium-ion batteries using convolutional neural network and random forest. Journal of Energy Storage. 2022 Apr 1;48:103857. doi: 10.1016/j.est.2021.103857
[14] Wang X, Hu B, Su X, Xu L, Zhu D. State of health estimation for lithium-ion batteries using random forest and gated recurrent unit. Journal of Energy Storage. 2024 Jan 15;76:109796. doi: 10.1016/j.est.2023.109796
[15] Wu Y, Rao B, Tian J, Du J, Jiang J. SSA-BiLSTM Model-Based SOH Estimation for Lithium-Ion Batteries. Energies. 2026 Mar 17;19(6):1499. doi: 10.3390/en19061499
[16] Huang Z, Dang L, Xie Y, Ma W, Chen B. Gate recurrent unit network based on hilbert-schmidt independence criterion for state-of-health estimation. arXiv preprint arXiv:2303.09497. 2023 Mar 16. doi: 10.48550/arXiv.2303.09497
[17] Uddin K, Schofield J, Widanage WD. State of health estimation of lithium-ion batteries in vehicle-to-grid applications using recurrent neural networks for learning the impact of degradation stress factors. arXiv preprint arXiv:2205.07561. 2022 May 16. doi: 10.48550/arXiv.2205.07561