State of charge prediction of supercapacitors via combination of Kalman filtering and backpropagation neural network

Wang, Houlian; Zhou, Gongbo

doi:10.1049/iet-epa.2017.0242

Cited by 33 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ultrakapacitors sangat cocok untuk digunakan dalam kondisi aplikasi yang ekstrim karena suhunya yang lebih luas dan siklus masa pakai yang lama dalam siklus pelepasan muatan (Pavkovic, dkk, 2014). Akhirnya, ultrakapacitors dapat diisi dan dikosongkan secara mendalam, sehingga risiko pengisian berlebih dan pemakaian berlebih pada ultrakapacitor lebih kecil daripada perangkat penyimpanan energi lainnya (Houlian & Gongbo, 2018).…”

Section: Pendahuluanunclassified

Estimasi State of Charge (SoC) Ultrakapasitor menggunakan Extended Kalman Filter Berbasis Ladder Equivalent Circuit Model

Afandi

WINDARKO²,

SUMANTRI³

et al. 2022

ELKOMIKA

View full text Add to dashboard Cite

ABSTRAKPenggunaan perangkat penyimpan energi semakin lama semakin meningkat pada peralatan berdaya kecil maupun besar. Baterai selama ini menjadi pilihan utama sebagai penyimpan energi. Namun akhir-akhir ini ultrakapasitor menjadi pilihan alternatif karena lifetime lebih panjang dan respon daya sesaat yang jauh lebih besar dari baterai. Pada manuskrip ini dibahas tentang estimasi nilai State of Charge (SoC) pada ultrakapasitor. Estimasi dilakukan berdasarkan rangkaian ekivalen ladder. Extended Kalman Filter adalah metode estimasi yang handal terhadap sistem dinamis dan tidak memerlukan banyak memori. Estimasi menggunakan metode Extended Kalman filter yang ditanamkan pada sistem embedded untuk mengantisipasi kondisi non-linier pada ultrakapasitor. Ultrakapasitor diuji dengan kondisi charging dan discharging. Hasil pengujian menunjukkan, kinerja metode dibandingkan antara data simulasi dan percobaan dengan perbedaan hasil sebesar 6%.Kata kunci: State of Charge, Metode Extended Kalman Filter, Ultrakapasitor ABSTRACTThe use of energy storage devices is increasing in both small and large power equipment. Batteries have been the main choice for energy storage. However, recently ultracapacitors have become an alternative choice because of a longer lifetime and a much larger instantaneous power response than batteries. This manuscript discusses the estimation of the State of Charge (SoC) value on the ultracapacitor. Estimates are made based on a ladder equivalent circuit. Extended Kalman Filter is a reliable estimation method for dynamic systems and does not require a lot of memory. The estimation uses the Extended Kalman filter method implemented in embedded system to anticipate non-linear conditions on the ultracapacitor. Ultracapacitors were tested under charging and discharging conditions. The test results show that the performance of the method is compared between simulation and experimental data with a difference of 6% in results.Keywords: State of Charge, Metode Extended Kalman Filter, Ultrakapasitor

show abstract

Section: Pendahuluanunclassified

Estimasi State of Charge (SoC) Ultrakapasitor menggunakan Extended Kalman Filter Berbasis Ladder Equivalent Circuit Model

Afandi

WINDARKO²,

SUMANTRI³

et al. 2022

ELKOMIKA

View full text Add to dashboard Cite

show abstract

“…Backpropagation (BP) NN is firstly proposed by Rumelhard and McClelland in 1986 ( Rumelhart et al., 1986 ). It can be regarded as a typical multilayer feedforward NN, and its topology mainly includes an input layer, a few hidden layers, and an output layer ( Houlian and Gongbo, 2018 ). The error back propagation algorithm is mostly widely accepted in guided learning algorithms.…”

Section: Machine-learning-based Soh Predictionmentioning

confidence: 99%

State of health prediction of lithium-ion batteries based on machine learning: Advances and perspectives

Shu

Shen

et al. 2021

iScience

View full text Add to dashboard Cite

Summary Accurate state of health (SOH) prediction is significant to guarantee operation safety and avoid latent failures of lithium-ion batteries. With the development of communication and artificial intelligence technologies, a body of researches have been performed toward precise and reliable SOH prediction method based on machine learning (ML) techniques. In this paper, the conception of SOH is defined, and the state-of-the-art prediction methods are classified based on their primary implementation procedure. As an essential step in ML-based SOH algorithms, the health feature extraction methods reported in the literature are comprehensively surveyed. Next, an exhausted comparison is conducted to elaborate the development of ML-based SOH prediction techniques. Not only their advantages and disadvantages of the application in SOH prediction are reviewed but also their accuracy and execution process are fully discussed. Finally, pivotal challenges and corresponding research directions are provided for more reliable and high-fidelity SOH prediction.

show abstract

“…The high accuracy of model requires massive complicated parameter computations and excessive design cost. Other than the model-based SOC estimation, the artificial neural networks (ANNs) are well suited for non-linear systems while applying to SOC estimation [17][18][19]. The battery characteristics such as current, voltage, and temperature are independent variables.…”

Section: Introductionmentioning

confidence: 99%

Novel estimation solution on lithium‐ion battery state of charge with current‐free detection algorithm

Wang

Fan

Chen

et al. 2019

IET Circuits, Devices & Systems

View full text Add to dashboard Cite

Lithium-ion battery as an efficient, sustainable, and clean energy for electric vehicles (EVs) and smart devices becomes more popular with the worldwide demand for reduction of greenhouse gas emission. In all kinds of applications, an accurate real-time estimation for state of charge (SOC) of battery is necessary. Some conventional methods usually need to sample both battery currents and voltages. This article presents a novel SOC estimation algorithm without current detection. This algorithm just acquires the port voltages of cell to calculate the open-circuit voltage (OCV) which is related to SOC. By extracting a large number of battery voltages based on a step response, some important parameters that can track battery working process are determined. In order to verify the algorithm feasibility and accuracy, it has been tested on a commercial common field-programmable gate array (FPGA) in different application conditions. The algorithm accuracy is mainly limited by model accuracy and sampling sensor accuracy. The maximum error between ideal SOC and calculated SOC by this algorithm is within 4%, and the mean error is about 0.99%. So, this high-feasibility, accredited accuracy, easy integration, and low-cost solution has bright potential in smarter future.

show abstract

State of charge prediction of supercapacitors via combination of Kalman filtering and backpropagation neural network

Cited by 33 publications

References 27 publications

Estimasi State of Charge (SoC) Ultrakapasitor menggunakan Extended Kalman Filter Berbasis Ladder Equivalent Circuit Model

Estimasi State of Charge (SoC) Ultrakapasitor menggunakan Extended Kalman Filter Berbasis Ladder Equivalent Circuit Model

State of health prediction of lithium-ion batteries based on machine learning: Advances and perspectives

Novel estimation solution on lithium‐ion battery state of charge with current‐free detection algorithm

Contact Info

Product

Resources

About