Abstract
State-of-health (SOH) estimation is crucial for ensuring efficient, reliable and safe operation of power battery in electric vehicle (EV) application. However, due to the complicated physicochemical reactions happened in battery cells, it is extremely difficult to accurately estimate SOH, especially in real-world EV application scenarios. Traditional SOH estimation methods, including both model-based and data-driven ones, are deterministic, which cannot capture the stochastic property of battery aging process aroused from the inherent inconsistency during battery production. In this paper, Bayesian network (BN), which is a probabilistic graphical modeling method for indeterministic process, is used to battery degradation modeling. Its structure is derived from existing knowledge about battery aging mechanism. Two-year operational data and capacity calibration results of 16 electric taxies are collected for model training and validation. Specifically, a systematic data filling procedure is proposed to predict the missing values of variables necessary for SOH estimation. Markov Chain Monte Carlo method is adopted to generate the samples from parameterized BN for SOH estimation. Results show that the estimation result is very close to the calibrated SOH with mean absolute error below 4%. The proposed method is promising to be applied online for SOH estimation in real-world EV application.
Highlights
In the face of severe energy crisis and environmental problems, governments all over the world are actively promoting the development of electric vehicles (EVs) to reduce carbon emissions and reduce fossil energy consumption [1], [2]
For the model part, existing findings about battery aging mechanism are used to construct the Bayesian network (BN) structure and proper distribution type is selected for all variables and parameters
To cope with the inevitable data missing problem caused by unexpected situations like unreliable wire connection, a systematic data filling procedure, which applies one-stage Markov chain to fill vehicle-related data and adopts radius basis function neural network (RBF-NN) to fill battery-related data, is put forward
Summary
In the face of severe energy crisis and environmental problems, governments all over the world are actively promoting the development of electric vehicles (EVs) to reduce carbon emissions and reduce fossil energy consumption [1], [2]. The measured data items that are necessary for the following battery SOH estimation include vehicle acceleration a, vehicle velocity v, battery current I , battery voltage V , battery SOC, and temperature T. Once the velocity predictor is obtained, it can be used to generate the missing velocity on the step according to current existing velocity value based on Monte Carlo method [31] and this process can be continued until all continuous missing data are filled. With nodes and their relationships (directed edges) and CPD, BN can express the joint probability distribution of all nodes (variables) in the network: P(v1, v2, . After establishing the BN structure, proper distribution type for each variable is selected based on the analysis of their unique characteristics
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
