An improved neural network model for battery smarter state-of-charge estimation of energy-transportation system
The safety and reliability of battery storage systems are critical to the mass roll-out of electrified transportation and new energy generation. To achieve safe management and optimal control of batteries, the state of charge (SOC) is one of the important parameters. The machine-learning based SOC e...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-04-01
|
| Series: | Green Energy and Intelligent Transportation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2773153723000038 |
| _version_ | 1797837697628241920 |
|---|---|
| author | Bingzhe Fu Wei Wang Yihuan Li Qiao Peng |
| author_facet | Bingzhe Fu Wei Wang Yihuan Li Qiao Peng |
| author_sort | Bingzhe Fu |
| collection | DOAJ |
| description | The safety and reliability of battery storage systems are critical to the mass roll-out of electrified transportation and new energy generation. To achieve safe management and optimal control of batteries, the state of charge (SOC) is one of the important parameters. The machine-learning based SOC estimation methods of lithium-ion batteries have attracted substantial interests in recent years. However, a common problem with these models is that their estimation performances are not always stable, which makes them difficult to use in practical applications. To address this problem, an optimized radial basis function neural network (RBF-NN) that combines the concepts of Golden Section Method (GSM) and Sparrow Search Algorithm (SSA) is proposed in this paper. Specifically, GSM is used to determine the optimum number of neurons in hidden layer of the RBF-NN model, and its parameters such as radial base center, connection weights and so on are optimized by SSA, which greatly improve the performance of RBF-NN in SOC estimation. In the experiments, data collected from different working conditions are used to demonstrate the accuracy and generalization ability of the proposed model, and the results of the experiment indicate that the maximum error of the proposed model is less than 2%. |
| first_indexed | 2024-04-09T15:28:54Z |
| format | Article |
| id | doaj.art-47e3305878304c72a5e4587b3c27e5c4 |
| institution | Directory Open Access Journal |
| issn | 2773-1537 |
| language | English |
| last_indexed | 2024-04-09T15:28:54Z |
| publishDate | 2023-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Green Energy and Intelligent Transportation |
| spelling | doaj.art-47e3305878304c72a5e4587b3c27e5c42023-04-28T08:57:40ZengElsevierGreen Energy and Intelligent Transportation2773-15372023-04-0122100067An improved neural network model for battery smarter state-of-charge estimation of energy-transportation systemBingzhe Fu0Wei Wang1Yihuan Li2Qiao Peng3School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, ChinaSchool of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, ChinaSchool of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, China; Corresponding author.Group of Information Technology, Analytics & Operations, Queen's University Belfast, Belfast, BT9 5EE, UK; Corresponding author.The safety and reliability of battery storage systems are critical to the mass roll-out of electrified transportation and new energy generation. To achieve safe management and optimal control of batteries, the state of charge (SOC) is one of the important parameters. The machine-learning based SOC estimation methods of lithium-ion batteries have attracted substantial interests in recent years. However, a common problem with these models is that their estimation performances are not always stable, which makes them difficult to use in practical applications. To address this problem, an optimized radial basis function neural network (RBF-NN) that combines the concepts of Golden Section Method (GSM) and Sparrow Search Algorithm (SSA) is proposed in this paper. Specifically, GSM is used to determine the optimum number of neurons in hidden layer of the RBF-NN model, and its parameters such as radial base center, connection weights and so on are optimized by SSA, which greatly improve the performance of RBF-NN in SOC estimation. In the experiments, data collected from different working conditions are used to demonstrate the accuracy and generalization ability of the proposed model, and the results of the experiment indicate that the maximum error of the proposed model is less than 2%.http://www.sciencedirect.com/science/article/pii/S2773153723000038Battery managementSOC estimationData scienceNeural networkGolden section methodSparrow search algorithm |
| spellingShingle | Bingzhe Fu Wei Wang Yihuan Li Qiao Peng An improved neural network model for battery smarter state-of-charge estimation of energy-transportation system Green Energy and Intelligent Transportation Battery management SOC estimation Data science Neural network Golden section method Sparrow search algorithm |
| title | An improved neural network model for battery smarter state-of-charge estimation of energy-transportation system |
| title_full | An improved neural network model for battery smarter state-of-charge estimation of energy-transportation system |
| title_fullStr | An improved neural network model for battery smarter state-of-charge estimation of energy-transportation system |
| title_full_unstemmed | An improved neural network model for battery smarter state-of-charge estimation of energy-transportation system |
| title_short | An improved neural network model for battery smarter state-of-charge estimation of energy-transportation system |
| title_sort | improved neural network model for battery smarter state of charge estimation of energy transportation system |
| topic | Battery management SOC estimation Data science Neural network Golden section method Sparrow search algorithm |
| url | http://www.sciencedirect.com/science/article/pii/S2773153723000038 |
| work_keys_str_mv | AT bingzhefu animprovedneuralnetworkmodelforbatterysmarterstateofchargeestimationofenergytransportationsystem AT weiwang animprovedneuralnetworkmodelforbatterysmarterstateofchargeestimationofenergytransportationsystem AT yihuanli animprovedneuralnetworkmodelforbatterysmarterstateofchargeestimationofenergytransportationsystem AT qiaopeng animprovedneuralnetworkmodelforbatterysmarterstateofchargeestimationofenergytransportationsystem AT bingzhefu improvedneuralnetworkmodelforbatterysmarterstateofchargeestimationofenergytransportationsystem AT weiwang improvedneuralnetworkmodelforbatterysmarterstateofchargeestimationofenergytransportationsystem AT yihuanli improvedneuralnetworkmodelforbatterysmarterstateofchargeestimationofenergytransportationsystem AT qiaopeng improvedneuralnetworkmodelforbatterysmarterstateofchargeestimationofenergytransportationsystem |