BatteryLife: A Comprehensive Dataset and Benchmark for Battery Life Prediction

2025-02-26

AI Summary

Battery lifetime prediction (BLP) has long been hindered by three fundamental bottlenecks: limited data scale, low diversity, and inconsistent benchmarks—existing datasets predominantly comprise small-capacity lithium-ion batteries from controlled lab environments, covering narrow electrochemical chemistries, temperature ranges, and charge/discharge protocols, with no standardized cross-scenario evaluation. To address this, we introduce the first large-scale, highly diverse BLP benchmark, integrating data from 16 sources, spanning 8 form factors, 80 chemistries—including zinc-ion, sodium-ion, and industrial-scale lithium-ion cells—12 temperatures, and 646 distinct operational conditions. We further propose CyclePatch, a plug-and-play temporal modeling framework that significantly enhances generalization across chemistries and aging conditions. Evaluated on 18 state-of-the-art models, CyclePatch achieves new SOTA performance; critically, our benchmark enables the first systematic assessment of general-purpose time-series models in BLP, establishing a robust, reproducible evaluation paradigm.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Computer Vision: Large Vision Models
• Natural Language Processing: (Large) Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Battery Life Prediction (BLP), which relies on time series data produced by battery degradation tests, is crucial for battery utilization, optimization, and production. Despite impressive advancements, this research area faces three key challenges. Firstly, the limited size of existing datasets impedes insights into modern battery life data. Secondly, most datasets are restricted to small-capacity lithium-ion batteries tested under a narrow range of diversity in labs, raising concerns about the generalizability of findings. Thirdly, inconsistent and limited benchmarks across studies obscure the effectiveness of baselines and leave it unclear if models popular in other time series fields are effective for BLP. To address these challenges, we propose BatteryLife, a comprehensive dataset and benchmark for BLP. BatteryLife integrates 16 datasets, offering a 2.4 times sample size compared to the previous largest dataset, and provides the most diverse battery life resource with batteries from 8 formats, 80 chemical systems, 12 operating temperatures, and 646 charge/discharge protocols, including both laboratory and industrial tests. Notably, BatteryLife is the first to release battery life datasets of zinc-ion batteries, sodium-ion batteries, and industry-tested large-capacity lithium-ion batteries. With the comprehensive dataset, we revisit the effectiveness of baselines popular in this and other time series fields. Furthermore, we propose CyclePatch, a plug-in technique that can be employed in a series of neural networks. Extensive benchmarking of 18 methods reveals that models popular in other time series fields can be unsuitable for BLP, and CyclePatch consistently improves model performance establishing state-of-the-art benchmarks. Moreover, BatteryLife evaluates model performance across aging conditions and domains. BatteryLife is available at https://github.com/Ruifeng-Tan/BatteryLife.

Problem

• Limited dataset size hinders battery life insights.
• Generalizability issues due to narrow test conditions.
• Inconsistent benchmarks obscure model effectiveness.

Innovation

• Comprehensive dataset integration
• CyclePatch plugin technique
• Diverse battery life benchmarking