Learning human-understandable models for the health assessment of Li-ion batteries via Multi-Objective Genetic Programming

Echevarría, Yuviny; Blanco, C.; Sánchez, Luciano

doi:10.1016/j.engappai.2019.08.013

Cited by 14 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a serial port is used to transmit the data to the upper computer, and the upper computer uses the serial port to collect the action data of basketball players and perform classified calculations and analysis of actions. The data are passed to the upper computer to shape the athlete's body posture (Echevarría et al, 2019 ). Data initialization mainly completes Quaternion initialization, acceleration initialization, and magnetic field intensity initialization.…”

Section: Research Model and The Methodologymentioning

confidence: 99%

Artificial Intelligence Technology in Basketball Training Action Recognition

Liang

Xu²,

Kuang³

2022

Front. Neurorobot.

View full text Add to dashboard Cite

The primary research purpose lies in studying the intelligent detection of movements in basketball training through artificial intelligence (AI) technology. Primarily, the theory of somatosensory gesture recognition is analyzed, which lays a theoretical foundation for research. Then, the collected signal is denoised and normalized to ensure that the obtained signal data will not be distorted. Finally, the four algorithms, decision tree (DT), naive Bayes (NB), support vector machine (SVM), and artificial neural network (ANN), are used to detect the data of athletes' different limb movements and recall. The accuracy of the data is compared and analyzed. Experiments show that the back propagation (BP) ANN algorithm has the best action recognition effect among the four algorithms. In basketball training athletes' upper limb movement detection, the average accuracy rate is close to 93.3%, and the average recall is also immediate to 93.3%. In basketball training athletes' lower limb movement detection, the average accuracy rate is close to 99.4%, and the average recall is immediate to 99.4%. In the detection of movements of upper and lower limbs: the recognition method can efficiently recognize the basketball actions of catching, passing, dribbling, and shooting, the recognition rate is over 95%, and the average accuracy of the four training actions of catching, passing, dribbling, and shooting is close to 98.95%. The intelligent basketball training system studied will help basketball coaches grasp the skilled movements of athletes better to make more efficient training programs and help athletes improve their skill level.

show abstract

Section: Research Model and The Methodologymentioning

confidence: 99%

Artificial Intelligence Technology in Basketball Training Action Recognition

Liang

Xu²,

Kuang³

2022

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…Although it has good regression performance and has been well used in other areas, such as strategy optimization and feature selection, no similar work has been done to date in estimating the SOH of batteries. Reference [35] used multi-objective GP to synthesize humanunderstandable HI from sequences of voltages, currents and temperatures streamed via on-vehicle sensors. In paper [36], the GP was used to address the challenge of automatically discovering advanced features, which can well capture fault progression.…”

Section: Problem Statementmentioning

confidence: 99%

Novel Lithium-Ion Battery State-of-Health Estimation Method Using a Genetic Programming Model

et al. 2020

View full text Add to dashboard Cite

State-of-health (SOH) is a health index (HI) that directly reflects the performance degradation of lithium-ion batteries in engineering, but the SOH of Li-ion batteries is difficult to measure directly. In this paper, a novel data-driven method is proposed to estimate the SOH of Li-ion batteries accurately and explore the relationship-like mechanism. First, the features of the battery should be extracted from the performance data. Next, by using the evolution of genetic programming to reflect the change in SOH, a mathematical model describing the relationship between the features and the SOH is constructed based on the data. Additionally, it has strong randomness in the formula model, which can cover most of the structural space of SOH and features. An illustrative example is presented to evaluate the SOH of the two batches of Li-ion batteries from the NASA database using the proposed method. One batch of batteries was used for testing and comparison, and another was chosen to verify the test results. Through experimental comparison and verification, it is demonstrated that the proposed method is rather useful and accurate.INDEX TERMS Genetic programming, Li-ion battery, state-of-health (SOH), prognostic and health management.

show abstract

“…It only considers the capacity sequence and does not consider other factors besides capacity (such as voltage, current, and temperature), so the accuracy of the actual online estimation of lithium-ion batteries will be affected. The second category is the most researched method that considers health features (HFs) in current data-driven methods [15]. The research and improvement of this kind of method mainly focus on how to extract features with high correlation and how to improve the prediction accuracy and efficiency of the model.…”

Section: Introductionmentioning

confidence: 99%

A Lightweight Neural Network Model For Battery State Of Health

Zhou

2022

Preprint

View full text Add to dashboard Cite

Accurate estimation of the state of health (SOH) of lithium-ion batteries is the key to ensure the safe use of lithium-ion batteries. In practice, the application of traditional health features is hindered by incomplete charge and discharge. When the battery is stably charged, the voltage and temperature of the battery under different health states show similar spatial degradation trends. Therefore, the degradation trend of voltage and temperature is directly taken as the health characteristic sequence through the dynamic time warping barycenter averaging (DBA) clustering. In addition, a new model attention depthwise temporal convolutional network (AD-TCN) considering health characteristics is proposed for SOH estimation. Depthwise separable convolution operation is used to extend temporal convolutional network (TCN) to a model suitable for multivariate prediction. Depthwise convolution is used as feature extractor, and pointwise convolution recombines all features for regression prediction. In addition, the convolutional block attention module is used in the channel dimension and spatial dimension to selectively enhance or suppress the details. Experiments on NASA data sets show that this method has strong reliability and high prediction accuracy.

show abstract

Learning human-understandable models for the health assessment of Li-ion batteries via Multi-Objective Genetic Programming

Cited by 14 publications

References 52 publications

Artificial Intelligence Technology in Basketball Training Action Recognition

Artificial Intelligence Technology in Basketball Training Action Recognition

Novel Lithium-Ion Battery State-of-Health Estimation Method Using a Genetic Programming Model

A Lightweight Neural Network Model For Battery State Of Health

Contact Info

Product

Resources

About