AI Paper Atlas

Research map / Large language models / AI and society

Battery Fault: A Comprehensive Dataset and Benchmark for Battery Fault Diagnosis

Qingdi Liu, Yan Fu, Lishuo LIU, Yanke LIN, Jin Xin, Jianfeng Zhang, Cheng Hao Liu, Lujia Pan, Dongxu Guo, Yuejiu Zheng, Qiang Li

ICLR 2026 · Large language models › AI and society · approach: Benchmarking and reproducibility practice

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use CNN instead of RFclassification · CH-BatteryGen single-file LFP dischargeF1-score: 0.6860 -> 0.9206Improved
use CNN instead of SVMclassification · CH-BatteryGen single-file NCM chargeF1-score: 0.8033 -> 0.8823Improved
use CNN instead of LSTMclassification · CH-BatteryGen single-vehicle LFP chargeF1-score: 0.7685 -> 0.8899Improved
use CNN instead of LSTMclassification · CH-BatteryGen single-vehicle NCM dischargeF1-score: 0.7460 -> 0.8580Improved
use LSTM instead of CNNclassification · CH-BatteryGen single-vehicle NCM chargeF1-score: 0.8313 -> 0.8897Improved
use deep learning (LSTM) instead of RFgrading · CH-BatteryGen single-file LFP chargeF1-score: 0.5976 -> 0.7289Improved
use CNN instead of LSTMgrading · CH-BatteryGen single-file LFP chargeF1-score: 0.7289 -> 0.8031Improved
use CNN instead of LSTMgrading · CH-BatteryGen single-vehicle LFP chargeF1-score: 0.7273 -> 0.8813Improved
switch from charging to discharginggrading CNN · CH-BatteryGen single-vehicle LFPF1-score: 0.8813 -> 0.7823Hurt
switch from charging to dischargingSVM classification · CH-BatteryGen single-file LFPF1-score: 0.7077 -> 0.6222Hurt
switch from classification to gradingCNN · CH-BatteryGen single-file LFP dischargeF1-score: 0.9206 -> 0.7442Hurt
use vehicle-level split instead of single-fileCNN · CH-BatteryGen NCM dischargeF1-score: 0.8732 -> 0.8580Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy