Use of modern algorithms for multi-parameter optimization and intelligent modelling of sustainable battery performance


Afzal A., Buradi A., Jilte R., Sundara V., Shaik S., Ağbulut Ü., ...Daha Fazla

Journal of Energy Storage, cilt.73, 2023 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 73
  • Basım Tarihi: 2023
  • Doi Numarası: 10.1016/j.est.2023.108910
  • Dergi Adı: Journal of Energy Storage
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC
  • Anahtar Kelimeler: Battery temperature, Fitness functions, Heat, Modelling, Optimization algorithms, Predictions
  • Yıldız Teknik Üniversitesi Adresli: Hayır

Özet

The focus of this computational work is to predict and optimize the battery thermal performance indicators for its sustainable operation using different meta-heuristic optimization algorithms and machine learning models. The contribution of this work is two-fold, first, the heat removal ability from battery indicated by average Nusselt number (Nuavg) and hotspots (MaxT) to avoid battery thermal runaway are optimized as single objective optimization (SOO) and as multi-level objective optimization (MOO) problem. Second, intelligent algorithms: Gradient boosting (GB) algorithm and Gaussian process regressor (GPR) algorithm are used for modelling of Nuavg and MaxT. For SOO, Multi-verse optimization (MVO) and Grey wolf optimization (GWO) algorithms are used for individual battery performance indicators. Similarly, the enhanced version of MVO and GWO for MOO (MMVO and MGWO) algorithms is customized. Each algorithm is operated for five cycles and 100 iterations in each cycle of execution. In GB algorithm the effect of different loss functions and in GPR algorithm the effect of parameter alpha (α) is analyzed. SOO gives highest fitness of Nuavg and lowest hotspots occurrence from both the algorithms with same converged positions of operating parameters. MMVO and MGWO relatively provide lower Nuavg with MaxT in the same range of SOO. The MOO provides different set of particle positions compared to SOO. MGWO algorithm has outperformed in providing the best non-dominated solution. The GB and GPR algorithm are good enough for the forecasting of battery thermal parameters. GPR is even accurate, however the range of α is important during training and testing. The best Nuavg obtained from SOO using MVO algorithm is around 82.06 while MaxT is 0.34. The same from GWO algorithm is 82.05 and 0.33 respectively. MGWO algorithm in MOO provides Nuavg and MaxT around 75.57 and 0.34 while MMWO provides 66.76 and 0.33 respectively. GPR algorithm gives accuracy as close as 98 % for MaxT while it gives 94 % accuracy for Nuavg. On the other hand GB algorithm gives 99 % and 97.5 % accuracy for MaxT and Nuavg respectively.