Soft Sensors for State of Charge, State of Energy, and Power Loss in Formula Student Electric Vehicle
Abstract
:1. Introduction
2. Methodology
2.1. FSEV Battery Pack Modelling
2.2. Soft-Sensor Design
- Load the input current profile and SOC/SOE/PL dataset for the FSEV battery pack considered in the current study.
- Partition the dataset into training, validation, and testing sets. The total dataset available for the current study was partitioned 70% for training, and 15% each for validation and testing (Table 4).
- Select the neural-network architecture for predictive modelling (two-layer feedforward network with sigmoid transfer function in the hidden layer and a linear transfer function in the output layer).
- Select the number of hidden neurons (selected as 10 in the present work).
- Train the neural network using a supervised learning algorithm (Levenberg–Marquardt).
- Validate and test the trained neural network.
- Retrain the network if performance is poor in terms of the R-squared value of the testing dataset.
Levenberg–Marquardt Training Algorithm
3. Results and Discussion
3.1. State of Charge Soft Sensor
3.2. State of Energy Soft Sensor
3.3. Power-Loss Soft Sensor
4. Conclusions
- Testing dataset accuracy of the proposed FSEV SOC, SOE, PL soft sensors was 99.96%, 99.96%, and 99.99%, respectively.
- The MSEs of testing dataset partitions for the SOC, SOE, PL soft sensors were 8.34 × , 7.4774 and 5.55 × , respectively.
- The R-squared prediction metrics of the proposed ANN-based soft sensors were superior to the R-squared values of the linear or nonlinear regression models and FIT% of the system identification-based parametric models.
- The mean squared errors of the parametric model structures were lower than those of the ANN and linear or nonlinear regression models (except for the OE 221 PL parametric model).
- The best validation performance (MSE) for the SOC, SOE, PL soft sensors was 8.3017 × at epoch 25, 7.4901 × at epoch 32, and 5.7628 × at epoch 205, respectively.
- The SOC and SOE dropped from 97% to 93.5% and 97% to 93.8%, respectively, during the FSEV running time of 118 s (one lap time).
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Tran, M.K.; Akinsanya, M.; Panchal, S.; Fraser, R.; Fowler, M. Design of a Hybrid Electric Vehicle Powertrain for Performance Optimization Considering Various Powertrain Components and Configurations. Vehicles 2021, 3, 20–32. [Google Scholar] [CrossRef]
- Pappalardo, C.; Lombardi, N.; Guida, D. A model-based system engineering approach for the virtual prototyping of an electric vehicle of class l7. Eng. Lett. 2020, 28, 215–234. [Google Scholar]
- Vita, V.; Koumides, P. Electric vehicles and distribution networks: Analysis on vehicle to grid and renewable energy sources integration. In Proceedings of the 2019 11th Electrical Engineering Faculty Conference (BulEF), Varna, Bulgaria, 11–14 September 2019; pp. 1–4. [Google Scholar]
- Sen, C.; Kar, N.C. Battery pack modeling for the analysis of battery management system of a hybrid electric vehicle. In Proceedings of the 2009 IEEE Vehicle Power and Propulsion Conference, Dearborn, MI, USA, 7–10 September 2009; pp. 207–212. [Google Scholar] [CrossRef]
- Jaguemont, J.; Boulon, L.; Dubé, Y. Characterization and Modeling of a Hybrid-Electric-Vehicle Lithium-Ion Battery Pack at Low Temperatures. IEEE Trans. Veh. Technol. 2016, 65, 1–14. [Google Scholar] [CrossRef] [Green Version]
- Cui, W.H.; Wang, J.S.; Chen, Y.Y. Equivalent circuit model of lead-acid battery in energy storage power station and its state-of-charge estimation based on extended kalman filtering method. Eng. Lett. 2018, 26, 504–517. [Google Scholar]
- Li, J.; Mazzola, M.S. Accurate battery pack modeling for automotive applications. J. Power Source 2013, 237, 215–228. [Google Scholar] [CrossRef]
- Liu, C.; Liu, W.; Wang, L.; Hu, G.; Ma, L.; Ren, B. A new method of modeling and state of charge estimation of the battery. J. Power Sources 2016, 320, 1–12. [Google Scholar] [CrossRef]
- Ting, T.; Man, K.; Lei, C.U.; Lu, C. State-of-charge for battery management system via Kalman filter. Eng. Lett. 2014, 22, 75–82. [Google Scholar]
- Shah, P.; Sekhar, R. Closed Loop System Identification of a DC Motor using Fractional Order Model. In Proceedings of the 2019 International Conference on Mechatronics, Robotics and Systems Engineering (MoRSE), Bali, Indonesia, 4–6 December 2019; pp. 69–74. [Google Scholar]
- Sekhar, R.; Singh, T.; Shah, P. Complex Order PIα+jβDγ+jθ Design for Surface Roughness Control in Machining CNT Al-Mg Hybrid Composites. Adv. Sci. Technol. Eng. Syst. J. (ASTESJ) 2020, 5, 299–306. [Google Scholar] [CrossRef]
- Sekhar, R.; Singh, T. Determination of Johnson Cook Parameters in Turning of Micro and Nano Reinforced Aluminum Composites using Trust Region Reflective Algorithm. Int. J. Innov. Technol. Explor. Eng. 2019, 8, 1712–1716. [Google Scholar] [CrossRef]
- Sekhar, R.; Shah, P. Predictive Modeling of a Flexible Robotic Arm using Cohort Intelligence Socio-Inspired Optimization. In Proceedings of the 2020 1st International Conference on Information Technology, Advanced Mechanical and Electrical Engineering (ICITAMEE), Yogyakarta, Indonesia, 13–14 October 2020; pp. 193–198. [Google Scholar] [CrossRef]
- Sekhar, R.; Singh, T.; Shah, P. System identification of tool chip interface friction while machining CNT-Mg-Al composites. AIP Conf. Proc. 2021, 2317, 1–9. [Google Scholar] [CrossRef]
- Sekhar, R.; Singh, T.; Shah, P. ARX/ARMAX Modeling and Fractional Order Control of Surface Roughness in Turning Nano-Composites. In Proceedings of the 2019 International Conference on Mechatronics, Robotics and Systems Engineering (MoRSE), Bali, Indonesia, 4–6 December 2019; pp. 97–102. [Google Scholar] [CrossRef]
- Sekhar, R.; Singh, T.; Shah, P. Micro and Nano Particle Composite Machining: Fractional Order Control of Surface Roughness. In Proceedings of the Third International Conference on Powder, Granule and Bulk Solids: Innovations and Applications PGBSIA 2020, Patiala, India, 26–28 February 2020; pp. 35–42. [Google Scholar]
- Shah, P.; Sekhar, R. Predictive Modeling and Control of Clamp Load Loss in Bolted Joints Based on Fractional Calculus. In Advances in Computing and Network Communications; Thampi, S.M., Gelenbe, E., Atiquzzaman, M., Chaudhary, V., Li, K.C., Eds.; Springer: Singapore, 2021; pp. 15–32. [Google Scholar]
- Shah, P.; Sekhar, R.; Singh, P. Predictive Modeling of A Bio-Fuelled Diesel Engine Using System Identification Approach. In Proceedings of the International Conference on Renewable Energy: Generation and Applications (ICREGA), Al Ain, United Arab Emirates, 2–4 February 2021; pp. 95–100. [Google Scholar] [CrossRef]
- Sekhar, R.; Singh, T.; Shah, P. Machine learning based predictive modeling and control of surface roughness generation while machining micro boron carbide and carbon nanotube particle reinforced Al-Mg matrix composites. Part. Sci. Technol. 2021, 1–18. [Google Scholar] [CrossRef]
- Jatti, V.S.; Sekhar, R.; Shah, P. Machine Learning Based Predictive Modeling of Ball Nose End Milling using Exogeneous Autoregressive Moving Average Approach. In Proceedings of the 2021 IEEE 12th International Conference on Mechanical and Intelligent Manufacturing Technologies (ICMIMT), Cape Town, South Africa, 13–15 May 2021; pp. 68–72. [Google Scholar]
- Shah, P.; Sekhar, R.; Kulkarni, A.J.; Siarry, P. Metaheuristic Algorithms in Industry 4.0; CRC Press: Boca Raton, FL, USA, 2021. [Google Scholar]
- Li, C.; Xiao, F.; Fan, Y. An Approach to State of Charge Estimation of Lithium-Ion Batteries Based on Recurrent Neural Networks with Gated Recurrent Unit. Energies 2019, 12, 1592. [Google Scholar] [CrossRef] [Green Version]
- Castano, S.; Gauchia, L.; Voncila, E.; Sanz, J. Dynamical modeling procedure of a Li-ion battery pack suitable for real-time applications. Energy Convers. Manag. 2015, 92, 396–405. [Google Scholar] [CrossRef]
- Zhang, L.; Hu, X.; Wang, Z.; Sun, F.; Dorrell, D.G. Fractional-order modeling and State-of-Charge estimation for ultracapacitors. J. Power Sources 2016, 314, 28–34. [Google Scholar] [CrossRef]
- Xiao, R.; Shen, J.; Li, X.; Yan, W.; Pan, E.; Chen, Z. Comparisons of Modeling and State of Charge Estimation for Lithium-Ion Battery Based on Fractional Order and Integral Order Methods. Energies 2016, 9, 184. [Google Scholar] [CrossRef]
- Meng, J.; Luo, G.; Ricco, M.; Swierczynski, M.; Stroe, D.I.; Teodorescu, R. Overview of Lithium-Ion Battery Modeling Methods for State-of-Charge Estimation in Electrical Vehicles. Appl. Sci. 2018, 8, 659. [Google Scholar] [CrossRef] [Green Version]
- He, W.; Williard, N.; Chen, C.; Pecht, M. State of charge estimation for Li-ion batteries using neural network modeling and unscented Kalman filter-based error cancellation. Int. J. Electr. Power Energy Syst. 2014, 62, 783–791. [Google Scholar] [CrossRef]
- Charkhgard, M.; Farrokhi, M. State-of-Charge Estimation for Lithium-Ion Batteries Using Neural Networks and EKF. IEEE Trans. Ind. Electron. 2010, 57, 4178–4187. [Google Scholar] [CrossRef]
- Chemali, E.; Kollmeyer, P.J.; Preindl, M.; Emadi, A. State-of-charge estimation of Li-ion batteries using deep neural networks: A machine learning approach. J. Power Source 2018, 400, 242–255. [Google Scholar] [CrossRef]
- Li, I.; Wang, W.; Su, S.; Lee, Y. A Merged Fuzzy Neural Network and Its Applications in Battery State-of-Charge Estimation. IEEE Trans. Energy Convers. 2007, 22, 697–708. [Google Scholar] [CrossRef]
- Weigert, T.; Tian, Q.; Lian, K. State-of-charge prediction of batteries and battery–supercapacitor hybrids using artificial neural networks. J. Power Source 2011, 196, 4061–4066. [Google Scholar] [CrossRef]
- Offer, G.J.; Yufit, V.; Howey, D.A.; Wu, B.; Brandon, N.P. Module design and fault diagnosis in electric vehicle batteries. J. Power Source 2012, 206, 383–392. [Google Scholar] [CrossRef] [Green Version]
- Carraro, E.; Degano, M.; Morandin, M.; Bianchi, N. Formula SAE electric competition: Electrical motor design. In Proceedings of the 2013 International Electric Machines Drives Conference, Chicago, IL, USA, 12–15 May 2013; pp. 1142–1148. [Google Scholar] [CrossRef]
- Munaro, M.; Bianchi, N.; Meneghetti, G. The Formula SAE Electric Vehicle Competition: A High-Torque Density Permanent Magnet Motor. IEEE Ind. Appl. Mag. 2020, 26, 76–86. [Google Scholar] [CrossRef]
- Zhang, Y.; Xiong, R.; He, H.; Shen, W. Lithium-Ion Battery Pack State of Charge and State of Energy Estimation Algorithms Using a Hardware-in-the-Loop Validation. IEEE Trans. Power Electron. 2017, 32, 4421–4431. [Google Scholar] [CrossRef]
- Zhang, W.; Shi, W.; Ma, Z. Adaptive unscented Kalman filter based state of energy and power capability estimation approach for lithium-ion battery. J. Power Source 2015, 289, 50–62. [Google Scholar] [CrossRef]
- He, H.; Zhang, Y.; Xiong, R.; Wang, C. A novel Gaussian model based battery state estimation approach: State-of-Energy. Appl. Energy 2015, 151, 41–48. [Google Scholar] [CrossRef]
- Zheng, L.; Zhu, J.; Wang, G.; He, T.; Wei, Y. Novel methods for estimating lithium-ion battery state of energy and maximum available energy. Appl. Energy 2016, 178, 1–8. [Google Scholar] [CrossRef]
- Li, K.; Wei, F.; Tseng, K.J.; Soong, B.H. A Practical Lithium-Ion Battery Model for State of Energy and Voltage Responses Prediction Incorporating Temperature and Ageing Effects. IEEE Trans. Ind. Electron. 2018, 65, 6696–6708. [Google Scholar] [CrossRef]
- Lin, C.; Mu, H.; Xiong, R.; Cao, J. Multi-model probabilities based state fusion estimation method of lithium-ion battery for electric vehicles: State-of-energy. Appl. Energy 2017, 194, 560–568. [Google Scholar] [CrossRef]
- Zhang, X.; Wang, Y.; Wu, J.; Chen, Z. A novel method for lithium-ion battery state of energy and state of power estimation based on multi-time-scale filter. Appl. Energy 2018, 216, 442–451. [Google Scholar] [CrossRef]
- Li, X.; Pan, K.; Fan, G.; Lu, R.; Zhu, C.; Rizzoni, G.; Canova, M. A physics-based fractional order model and state of energy estimation for lithium ion batteries. Part II: Parameter identification and state of energy estimation for LiFePO4 battery. J. Power Source 2017, 367, 202–213. [Google Scholar] [CrossRef]
- Apostolaki-Iosifidou, E.; Codani, P.; Kempton, W. Measurement of power loss during electric vehicle charging and discharging. Energy 2017, 127, 730–742. [Google Scholar] [CrossRef]
- Category Archives: Rules. Available online: https://www.formulabharat.com/category/rules/ (accessed on 6 August 2021).
- Technical Data and Manual for EMRAX Motors/Generators. Available online: https://emrax.com/wp-content/uploads/2017/10/user_manual_for_emrax_motors.pdf (accessed on 6 August 2021).
- Battery Pack Design Validation and Assembly Guide A123 Systems AMP20M1HD-A Nanophosphate Cell. Available online: https://www.buya123products.com/uploads/vipcase/b24d4f5b63934c59d43e93b3bb4db60a.pdf (accessed on 6 August 2021).
- Panchal, S.; Mcgrory, J.; Kong, J.; Fraser, R.; Fowler, M.; Dincer, I.; Agelin-Chaab, M. Cycling degradation testing and analysis of a LiFePO4 battery at actual conditions. Int. J. Energy Res. 2017, 41, 2565–2575. [Google Scholar] [CrossRef]
- Saidani, F.; Hutter, F.X.; Scurtu, R.G.; Braunwarth, W.; Burghartz, J.N. Lithium-ion battery models: A comparative study and a model-based powerline communication. Adv. Radio Sci. 2017, 15, 83–91. [Google Scholar] [CrossRef] [Green Version]
- Weber, T.; Sossenheimer, J.; Schäfer, S.; Ott, M.; Walther, J.; Abele, E. Machine Learning based System Identification Tool for data-based Energy and Resource Modeling and Simulation. In Proceedings of the Procedia CIRP, 26th CIRP Conference on Life Cycle Engineering (LCE) Purdue University, West Lafayette, IN, USA, 7–9 May 2019. [Google Scholar] [CrossRef]
- Nguyen-Truong, H.T.; Le, H.M. An implementation of the Levenberg–Marquardt algorithm for simultaneous-energy-gradient fitting using two-layer feed-forward neural networks. Chem. Phys. Lett. 2015, 629, 40–45. [Google Scholar] [CrossRef]
- El-Banbi, A.; Alzahabi, A.; El-Maraghi, A. Artificial Neural Network Models for PVT Properties; Gulf Professional Publishing: Oxford, UK, 2018; pp. 225–247. [Google Scholar] [CrossRef]
- Jenkal, S.; Kourchi, M.; Rachdy, A.; Oussalem, O.; Ajaamoum, M.; Oubella, M. Modeling a photovoltaic emulator using four methods and buck-boost converter. Eng. Lett. 2021, 29, 408–415. [Google Scholar]
- Dahunsi, O.; Pedro, J. Neural network-based identification and approximate predictive control of a servo-hydraulic vehicle suspension system. Eng. Lett. 2010, 18, 4. [Google Scholar]
- Quesada, A. 5 Algorithms to Train a Neural Network. Available online: https://www.neuraldesigner.com/blog/5_algorithms_to_train_a_neural_network#Levenberg-Marquardt (accessed on 15 March 2021).
- Mathworks, L. Levenberg-Marquardt Backpropagation. Available online: https://in.mathworks.com/help/deeplearning/ref/trainlm.html (accessed on 16 March 2021).
- Paolucci, R. Linear Regression v.s. Neural Networks. 2020. Available online: https://towardsdatascience.com/linear-regression-v-s-neural-networks-cd03b29386d4 (accessed on 16 March 2021).
Parameter/Specification | Value | Parameter/Specification | Value |
---|---|---|---|
Vehicle Mass | 300 kg | Tire Rolling Drag | 0.03 |
Drag coefficient | 0.7 | Power Scaling Factor | 95% |
Downforce coefficient | 0.5 | Aero Scaling Factor | 90% |
Frontal area | 0.9 m | Grip Scaling Factor | 90% |
Drivetrain efficiency | 90% | Mass Lateral Friction | 260 kg |
Tire rolling radius | 0.203 m | Mass Longitudinal Friction | 260 kg |
Air density | 1.23 kg/m | Aero Efficiency | 0.7142 |
Final drive ratio | 5 | Motor Thermal Efficiency | 80% |
Longitudinal friction | 1.4 | Motor Torque Data | 90 N·m |
Lateral friction | 1.5 | Motor RPM Data | 6500 rpm |
Parameter | Lower Limit | Upper Limit |
---|---|---|
Charge current | 0 A | 40 A |
Discharge current | 0 A | 300 A |
Cell voltage | 2 V | 3.65 V |
Cell temperature | 0 °C | 55 °C |
Specifications | Value |
---|---|
Drive cycle distance | 22 km |
Pack voltage | 300 V |
Range | 22 km |
Cell voltage nominal | 3.3 V |
Cell capacity | 20 Ah |
Pack capacity | 20 Ah |
Dataset Partitions | Number of Samples | Data% |
---|---|---|
Training | 82,132 | 70 |
Validation | 17,600 | 15 |
Testing | 17,600 | 15 |
Total | 117,332 | 100 |
Training Method | Levenberg-Marquardt |
---|---|
Sample division | as shown in Table 4 |
Activation function () | Sigmoid function |
Activation function () | Linear function |
Initial weights and bias | zero |
Input layer nodes | 2 |
Output layer nodes | 1 |
Hidden layer nodes | 10 |
Performance index | Mean squared error (MSE) |
Sr. No. | Stopping Criteria | Settings |
---|---|---|
1. | Maximal epochs | 1000 |
2. | Maximal training time | ∞ |
3. | Performance goal | 0 |
4. | Minimal performance gradient | 1.00 × |
5. | Maximal | 1.00 × |
6. | Maximal validation fails | 6 |
Sr. No. | Model Name | Model Structure |
---|---|---|
1 | Output error (OE) | y(t) = [B(z)/F(z)]u(t) + e(t) |
2 | Autoregressive moving average with exogenous input (ARMAX) | A(z)y(t) = B(z)u(t) + [C(z)/(1 − z)]e(t) |
3 | Box Jenkins (BJ) | y(t) = [B(z)/F(z)]u(t) + [C(z)/D(z)]e(t) |
4 | Autoregressive with exogenous input (ARX) | A(z)y(t) = B(z)u(t) + e(t) |
Weight | Value | Weight | Value | Weight | Value | Bias | Value |
---|---|---|---|---|---|---|---|
−6.7388 | 0.1385 | −0.3445 | 5.2081 | ||||
1.5055 | 4.4055 | −0.1561 | −2.9739 | ||||
−2.2395 | 0.1014 | 0.9477 | 0.5772 | ||||
−4.0909 | 5.0135 | −0.0010 | 0.5644 | ||||
−0.9409 | −4.7907 | 1.1354 | 1.5813 | ||||
−3.0955 | −3.3766 | −0.2886 | 0.1238 | ||||
−9.3968 | 0.4713 | −0.8465 | −5.1520 | ||||
−18.7391 | 0.6081 | −0.8844 | −6.6339 | ||||
−3.9745 | 0.9659 | 0.2007 | −4.1959 | ||||
3.7267 | −1.6611 | −0.1511 | 3.7865 | ||||
0.1713 |
Dataset Partitions | MSE | R-sq |
---|---|---|
Training | 8.28 × | 0.9996 |
Validation | 8.30 × | 0.9996 |
Testing | 8.34 × | 0.9996 |
Overall | - | 0.9996 |
Weight | Value | Weight | Value | Weight | Value | Bias | Value |
---|---|---|---|---|---|---|---|
6.8392 | −0.0811 | −0.1686 | −5.2122 | ||||
1.5481 | 1.9788 | −0.0767 | −1.6627 | ||||
−2.7665 | 2.5017 | 0.0277 | 2.2216 | ||||
2.6111 | −0.0231 | −0.3693 | −0.6678 | ||||
1.1701 | 9.4484 | 0.0191 | 2.1594 | ||||
−2.6643 | −2.7645 | 0.0396 | −0.0218 | ||||
−23.6749 | 0.7517 | 0.1327 | −8.4033 | ||||
−1.0208 | 7.0473 | 0.0214 | 7.0193 | ||||
8.2776 | 8.9437 | −0.0232 | 6.5266 | ||||
3.856 | −0.076 | −-0.2172 | 2.0931 | ||||
−0.0677 |
Dataset Partitions | MSE | R-sq |
---|---|---|
Training | 7.4276 | 0.9996 |
Validation | 7.4900 | 0.9996 |
Testing | 7.4774 | 0.9996 |
Overall | - | 0.9996 |
Weight | Value | Weight | Value | Weight | Value | Bias | Value |
---|---|---|---|---|---|---|---|
15.2388 | 3.0079 | −0.0034 | −12.3583 | ||||
−0.6052 | 1.0072 | −0.0947 | 1.3888 | ||||
2.1241 | 4.8293 | −0.0131 | −3.1843 | ||||
0.7149 | −1.4651 | −6.1720 | 3.5928 | ||||
0.0627 | −0.935 | −1.7267 | 0.7731 | ||||
−7.2401 | −1.1123 | −0.0037 | 0.0887 | ||||
−24.7311 | −11.2042 | −0.0027 | −13.0898 | ||||
4.5421 | −0.9068 | 1.2184 | 2.7065 | ||||
4.5675 | −0.9336 | −1.1994 | 2.7071 | ||||
0.2263 | 1.8252 | −0.3606 | 2.2972 | ||||
7.0070 |
Dataset Partitions | MSE | R-sq |
---|---|---|
Training | 5.74 × | 0.9999 |
Validation | 5.76 × | 0.9999 |
Testing | 5.55 × | 0.9999 |
Overall | - | 0.9999 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Purohit, K.; Srivastava, S.; Nookala, V.; Joshi, V.; Shah, P.; Sekhar, R.; Panchal, S.; Fowler, M.; Fraser, R.; Tran, M.-K.; et al. Soft Sensors for State of Charge, State of Energy, and Power Loss in Formula Student Electric Vehicle. Appl. Syst. Innov. 2021, 4, 78. https://doi.org/10.3390/asi4040078
Purohit K, Srivastava S, Nookala V, Joshi V, Shah P, Sekhar R, Panchal S, Fowler M, Fraser R, Tran M-K, et al. Soft Sensors for State of Charge, State of Energy, and Power Loss in Formula Student Electric Vehicle. Applied System Innovation. 2021; 4(4):78. https://doi.org/10.3390/asi4040078
Chicago/Turabian StylePurohit, Kanishkavikram, Shivangi Srivastava, Varun Nookala, Vivek Joshi, Pritesh Shah, Ravi Sekhar, Satyam Panchal, Michael Fowler, Roydon Fraser, Manh-Kien Tran, and et al. 2021. "Soft Sensors for State of Charge, State of Energy, and Power Loss in Formula Student Electric Vehicle" Applied System Innovation 4, no. 4: 78. https://doi.org/10.3390/asi4040078