A Cell Screening Algorithm Integrating Genetic and Numerical Differentiation

The consistency of the cell has a significant impact on battery capacity,endurance,overall performance,safety,and service life extension.However,it is challenging to identify cells with high consistency and no loss of battery energy.This paper presents a cell screening algorithm that integrates genetic and numerical differentiation techniques.Initially,a mathematical model for battery consistency is established,and a multi-step charging strategy is proposed to satisfy the demands of fast charging technology.Subsequently,the genetic algorithm simulates biological evolution to efficiently search for superior cell combinations within a short time while evaluating capacity,voltage consistency,and charge/discharge efficiency.Finally,through experimental validation and comparative analysis with similar algorithms,our proposed method demonstrates notable advantages in terms of both search efficiency and performance.

Cell Consistency Evaluation Method Based on Multiple Unsupervised Learning Algorithms

Unsupervised learning algorithms can effectively solve sample imbalance.To address battery consistency anomalies in new energy vehicles,we adopt a variety of unsupervised learning algorithms to evaluate and predict the battery consistency of three vehicles using charging fragment data from actual operating conditions.We extract battery-related features,such as the mean of maximum difference,standard deviation,and entropy of batteries and then apply principal component analysis to reduce the dimensionality and record the amount of preserved information.We then build models through a collection of unsupervised learning algorithms for the anomaly detection of cell consistency faults.We also determine whether unsupervised and supervised learning algorithms can address the battery consistency problem and document the parameter tuning process.In addition,we compare the prediction effectiveness of charging and discharging features modeled individually and in combination,determine the choice of charging and discharging features to be modeled in combination,and visualize the multidimensional data for fault detection.Experimental results show that the unsupervised learning algorithm is effective in visualizing and predicting vehicle core conformance faults,and can accurately predict faults in real time.The“distance+boxplot”algorithm shows the best performance with a prediction accuracy of 80%,a recall rate of 100%,and an F1 of 0.89.The proposed approach can be applied to monitor battery consistency faults in real time and reduce the possibility of disasters arising from consistency faults.

State of health estimation for lithium-ion batteries in real-world electric vehicles

The state of health(SOH) plays a significant role in the mileage and safety of an electric vehicle(EV). In recent years, many methods based on data-driven analysis and laboratory measurements have been developed for SOH estimation. However, most of these proposed methods cannot be applied to real-world EVs. Here, we present a method for SOH estimation based on realworld EV data. A battery-aging evaluation health index(HI) with a strong correlation to the SOH is retrieved from battery-aging data and then modified with thermal factors to depict the former SOH. Afterward, a local weighted linear-regression algorithm is used to qualitatively characterize the declining trend of the HI, which eliminates the local HI fluctuation caused by data noise.Subsequently, a series of features-of-interest(FOIs) is extracted according to the battery consistency, cell-voltage extrema, and cumulative mileage, and validated using the grey relational analysis. Finally, a battery-degradation model is built using the extreme gradient-boosting algorithm with the selected FOIs. The experimental results from real-world data indicate that the proposed method has high estimation accuracy and generalization, and the maximum error is around 2% for batteries in realworld EVs.