scholarly journals Design and implementation of state-of-charge estimation based on back-propagation neural network for smart uninterruptible power system

2019 ◽  
Vol 15 (12) ◽  
pp. 155014771989452
Author(s):  
Shuo Li ◽  
Song Li ◽  
Haifeng Zhao ◽  
Yuan An
Keyword(s):  
Neural Network ◽  
Power System ◽  
Lithium Battery ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
The State ◽  
State Of Charge ◽  
Marquardt Algorithm ◽  
Uninterruptible Power ◽  
State Of Charge Estimation

In this article, a method for estimating the state of charge of lithium battery based on back-propagation neural network is proposed and implemented for uninterruptible power system. First, back-propagation neural network model is established with voltage, temperature, and charge–discharge current as input parameters, and state of charge of lithium battery as output parameter. Then, the back-propagation neural network is trained by Levenberg–Marquardt algorithm and gradient descent method; and the state of charge of batteries in uninterruptible power system is estimated by the trained back-propagation neural network. Finally, we build a state-of-charge estimation test platform and connect it to host computer by Ethernet. The performance of state-of-charge estimation based on back-propagation neural network is tested by connecting to uninterruptible power system and compared with the ampere-hour counting method and the actual test data. The results show that the state-of-charge estimation based on back-propagation neural network can achieve high accuracy in estimating state of charge of uninterruptible power system and can reduce the error accumulation caused in long-term operation.

scholarly journals ESTIMASI STATE OF CHARGE BATERAI LITHIUM POLYMER MENGGUNAKAN BACK PROPAGATION NEURAL NETWORK

2020 ◽  
Vol 12 (2) ◽  
pp. 140-149
Author(s):  
Mohammad Imron Dwi Prasetyo ◽  
Hasnira Hasnira ◽  
Novie Ayub Windarko ◽  
Anang Tjahjono
Keyword(s):  
Neural Network ◽  
Renewable Energy ◽  
Open Circuit Voltage ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Open Circuit ◽  
State Of Charge ◽  
Input Layer

Baterai merupakan salah satu komponen yang penting dalam konteks implementasi renewable energy. Jenis Baterai yang memiliki kepadatan dalam penyimpanan energy adalah lithium polymer. Parameter dalam baterai yang harus diperhatikan adalah estimasi State Of Charge (SOC). Pada umumnya estimasi SOC baterai menggunakan metode coloumb counting karena tingkat kesulitanya rendah. Namun terdapat kelemahan dari sisi ketergantungan terhadap utilitas sensor arus yang digunakan sebagai akumulasi dari integral arus yang masuk maupun arus yang keluar terhadap waktu. Dalam penelitian ini menyajikan Back Propagation Neural Network (BPNN) sebagai algoritma untuk estimasi SOC berdasarkan kurva karakteristik OCV – SOC. Kurva karakteristik OCV – SOC baterai didapatkan dari pengujian pulsa baterai. Tegangan, arus, dan waktu discharging baterai digunakan sebagai input layer BPNN pertama untuk estimasi Open Circuit Voltage (OCV). OCV akan dilearning sebagai input layer BPNN kedua untuk estimasi SOC baterai. Hasil dari simulasi estimasi SOC didapatkan galat rata-rata sebesar 0.479% terhadap SOC riil berdasarkan kurva karakteristik OCV – SOC.

A Review of Research on the State-of-Charge Estimation Methods for Electric Vehicle Battery

2019 ◽  
Vol 13 ◽  
Author(s):  
Mingyue Zhang ◽  
Xiaobin Fan ◽  
Jing Gan ◽  
Zeng Song ◽  
Bin Zhao
Keyword(s):  
Control Theory ◽  
Electric Vehicle ◽  
Estimation Method ◽  
Estimation Algorithm ◽  
The State ◽  
State Of Charge ◽  
Estimation Methods ◽  
Advantages And Disadvantages ◽  
Electric Vehicle Battery ◽  
State Of Charge Estimation

Background: Battery technology has been one of the bottlenecks in electric cars. Whether it is in theory or in practice, the research on battery management is extremely important, especially for battery state-of-charge estimation. In fact, the battery has a strong time change and non-linear properties, which are extremely complex systems. Therefore, accurate estimating the state of charge is a challenging thing. Objective: The study aims to report the latest progress in the studies of the state-of-charge estimation methods for electric vehicle battery. Methods: This paper reviews various representative patents and papers related to the state of charge estimation methods for electric vehicle battery. According to their theoretical and experimental characteristics, the estimation methods were classified into three groups: the traditional estimation algorithm based on the battery experiment, the estimation algorithm based on modern control theory and other estimation algorithm based on the innovative ideas, especially focusing on the algorithms based on control theory. Results: The advantages and disadvantages, current and future developments of the state-of-charge estimation methods are finally provided and discussed. Conclusion: Each kind of state of charge estimation method has its own characteristics, suitable for different occasions. At present, algorithms based on control theory, especially intelligent algorithms, are the focus of research in this field. The future development direction is to establish rich database, improve hardware technology, put up with more perfect battery model, and give full play to the advantages of each algorithm.

Sign in / Sign up

Export Citation Format

Share Document