PaperlayerView exact revision on arXiv

Source-linked AI summary

Infrared Hotspot-Guided Early Warning of Lithium-Ion Battery Thermal Runaway Under Mechanical Abuse

Syed Sajid Ullah, Salman Khan, Muhammad Zunair Zamir

arXiv:2608.20383v1eess.SYcs.AI

TL;DR

Mechanical abuse can produce localized heating before conventional sensor signals become decisive, motivating earlier thermal-runaway warning. The paper uses a two-stage hotspot-guided model that distills thermal instability before multimodal prediction, achieving strong discrimination while retaining an interpretable intermediate signal.

Abstract

from arXiv · show

Mechanical abuse can trigger thermal runaway (TR) in lithium-ion batteries through localized heat generation before sensor signals become decisive. This paper proposes a two-stage early-warning approach that estimates localized thermal instability from infrared hotspot dynamics and then fuses this instability score with mechanical, electrical, thermal, and image-intensity features for a 20-frame warning horizon. Evaluation uses repeated experiment-wise three-fold validation, with out-of-fold Stage-I scores during Stage-II training to prevent stacked-model optimism. Hotspot dynamics alone achieve Stage-I ROC-AUC 0.945, and the two-stage classifier reaches Stage-II ROC-AUC 0.908, exceeding direct multimodal fusion while preserving an interpretable intermediate instability signal. Thermal gradient rise precedes voltage-based detection by 40 frames (4 seconds) on average, enabling earlier battery management system intervention. Lead-time analysis at a fixed 0.5 threshold yields a 14.8-frame mean lead time.

I. INTRODUCTION

Mechanical abuse can create localized heating that precedes decisive conventional sensor signals. The paper addresses this gap with a leakage-controlled two-stage framework that converts hotspot dynamics into an interpretable instability score before multimodal warning prediction.

  • Mechanical abuse can damage internal layers, cause short circuits, and initiate localized Joule heating that may evolve into thermal runaway.Source: §I · p. 1
  • Conventional voltage, temperature, force, and deformation thresholds may miss spatially localized thermal responses that precede runaway.Infrared imaging captures hotspot formation, growth, gradients, entropy, and centroid motion.Source: §I · p. 1
  • The proposed two-stage strategy estimates localized thermal instability from hotspot features, then fuses the score with mechanical, electrical, thermal, and global IR features.This separates thermal-instability detection from final warning prediction.Source: §I · p. 1
  • The architecture uses leakage control, structured diagnostics, and an interpretable intermediate score while improving operating-threshold performance over direct multimodal fusion.Source: §I · p. 1
  • ROC-AUC 0.945 is achieved by the compact hotspot-dynamics representation for Stage-I instability estimation.Source: §I · p. 1

II. RELATED WORK

Prior work provides practical sensor-based warning and spatial thermal information, but often does not separate localized instability estimation from final warning decisions. This paper combines hotspot scoring, experiment-wise leakage control, and structured reporting in a compact pipeline.

  • Mechanical abuse studies examine indentation, compression, nail penetration, and impact, where localized precursors complicate early diagnosis.Source: §II · p. 1
  • Sensor-based methods use voltage, temperature, force, strain, gas, pressure, or ultrasound, but scalar measurements can be delayed or spatially incomplete.Source: §II · p. 1
  • Thermal imaging captures hotspot formation, spatial gradients, and propagation, while multimodal studies combine images, sensor streams, and interpretable tools.Source: §II · p. 2
  • Prior directions do not always separate localized thermal-instability estimation from the final warning decision.The paper treats language-model-assisted safety reporting as structured classifier-output reporting rather than an independent predictor.Source: §II · p. 2
  • The pipeline combines hotspot-derived instability scoring, experiment-wise leakage control, and structured diagnostic reporting.Source: §II · p. 2
  • The dataset contains synchronized 10 Hz mechanical, electrical, scalar-thermal, and infrared records from cylindrical cells under indentation loading.Runaway-propagation frames are excluded from pre-runaway prediction, leaving 12,425 training rows from 194 experiments.Source: A. Experimental Setup and Dataset · p. 2
  • Inputs are organized by mechanical, electrical, scalar-thermal, image-intensity, and hotspot-dynamics roles, with Stage II predicting TR within the next 20 frames.Event-derived variables are excluded to prevent leakage.Source: A. Experimental Setup and Dataset · p. 2

B. Problem Formulation

The formulation first estimates a localized thermal-instability score from hotspot dynamics alone, then augments compact multimodal features with that score to predict near-term thermal runaway.

  • For each frame, the multimodal feature vector contains mechanical, electrical, scalar-thermal, image-intensity, and hotspot-dynamics features.Source: B. Problem Formulation · p. 2
  • Stage I estimates the localized thermal-instability state using hotspot-dynamics features only.Source: B. Problem Formulation · p. 2
  • The instability score ˆs_t is a probability in [0, 1] derived from the annotated thermal-instability label and observed thermal spatial patterns.Source: B. Problem Formulation · p. 2
  • Stage II augments compact sensor and image-intensity features with the instability score before estimating early-warning probability.Source: B. Problem Formulation · p. 2
  • The Stage-II target indicates whether thermal runaway occurs within the next 20 frames.Source: B. Problem Formulation · p. 2

C. Baseline Classifiers

The baseline classifiers organize inputs by physical modality and compare single-stage, hotspot-focused, image-based, and multimodal configurations.

  • Sensor-only uses mechanical, electrical, and scalar-thermal measurements.Source: C. Baseline Classifiers · p. 2
  • Image-all combines raw intensity statistics with hotspot-dynamics features.Source: C. Baseline Classifiers · p. 2
  • Hotspot-only uses area, centroid, gradient, entropy, growth-rate, and velocity features.Source: C. Baseline Classifiers · p. 2
  • Direct multimodal fuses all feature groups in one stage.Source: C. Baseline Classifiers · p. 2
  • The proposed two-stage configuration produces a Stage-I instability score before combining it with sensor features and four raw intensity statistics.Stage-I compares Sensor-only, Image-all, Hotspot-only, and Multimodal; Stage-II compares Sensor-only, Image-all, Direct multimodal, and the proposed design under grouped folds.Source: C. Baseline Classifiers · p. 2

D. Two-Stage Architecture

The architecture separates localized thermal-instability estimation from final warning prediction through an interpretable bottleneck and constrained diagnostic reporting.

  • Stage I receives hotspot dynamics only and outputs an instability probability.Source: D. Two-Stage Architecture · p. 3
  • Stage II fuses the out-of-fold instability score with sensor variables and four global image-intensity statistics instead of directly reusing hotspot descriptors.Source: D. Two-Stage Architecture · p. 3
  • The diagnostic layer reports structured evidence from the trained classifier without changing its prediction.Source: D. Two-Stage Architecture · p. 3
  • LightGBM is used for both stages to model nonlinear cross-modality interactions in low-dimensional tabular data with missing hotspot coordinates.The shared hyperparameters and grouped folds support fair comparison.Source: D. Two-Stage Architecture · p. 3

E. Evaluation Metrics

Evaluation uses repeated experiment-wise three-fold cross-validation and reports discrimination, precision-recall, threshold performance, and lead time under a fixed warning criterion.

IV. RESULTS AND DISCUSSION

Results examine modality contributions, thermal-signal timing, and threshold-based lead time across the two-stage early-warning framework.

Thermal evidence

Temporal warning

Stage-I contributions

B. Stage II: Early-Warning Prediction

Stage II combines the learned instability score with multimodal measurements for early-warning prediction. The two-stage classifier outperforms direct multimodal fusion on ROC-AUC and threshold-level metrics.

  • 0.908 ROC-AUC is achieved by the full two-stage classifier, versus 0.903 for direct multimodal fusion.The two-stage model also reaches F1 0.752 versus 0.738 and BAcc 0.836 versus 0.824.Source: B. Stage II: Early-Warning Prediction · p. 4
  • Mechanical variables are the strongest single physical modality at ROC-AUC 0.871, ahead of electrical, scalar-thermal, and thermal-image pathways.The corresponding single-modality ROC-AUC values are 0.706, 0.657, and 0.655, respectively.Source: B. Stage II: Early-Warning Prediction · p. 4
  • Thermal signals become abnormal before voltage reaches a critical reading in the multimodal trajectories.The figure marks stable, precursor, localized, and runaway stages, with a dashed line indicating TR onset.Source: Figure 4 · p. 5
  • Stage-II ROC and precision-recall curves compare the proposed classifier with alternative classifier configurations.AUC and AP values are displayed in the figure legend.Source: B. Stage II: Early-Warning Prediction · p. 5

C. Ablation Study and Diagnostic Reporting

Ablations show that the explicit instability score and compact global image context jointly support Stage-II performance. Diagnostic analyses identify hotspot-driven contributions, while threshold 0.5 provides near-optimal operating behavior within the evaluated dataset.

Ablation Study

  • 0.896 ROC-AUC results when raw intensity statistics are removed, compared with 0.905 without the Stage-I score and 0.908 for the complete model.The ablation identifies the combination of explicit instability scoring and global image context as strongest.Source: C. Ablation Study and Diagnostic… · p. 5

Diagnostic Reporting

  • Growth rate, thermal gradient, and area have positive SHAP contributions toward Stage-I instability detection.In Stage II, the injected instability score is dominant, followed by compact image-intensity and voltage-related cues.Source: C. Ablation Study and Diagnostic… · p. 5

Threshold Analysis

  • 14.8 frames is the mean lead time for 183 valid in-horizon warnings at threshold 0.5.Other detections occur beyond the 20-frame horizon; the best mean F1 at threshold 0.55 improves over 0.5 by less than 0.001.Source: C. Ablation Study and Diagnostic… · p. 5

Scope

Diagnostic Reporting

V. CONCLUSION

The paper presents a two-stage hotspot-aware framework for warning of mechanically induced lithium-ion battery thermal runaway. It distills hotspot dynamics into an interpretable instability score before multimodal fusion, with cross-setting validation identified as future work.

  • 0.945 Stage-I ROC-AUC and 0.908 Stage-II ROC-AUC support hotspot-aware instability estimation followed by compact multimodal fusion.Thermal signatures precede voltage collapse by up to 40 frames on average.Source: §V · p. 6
  • The instability score remains the dominant Stage-II driver according to SHAP analysis.Source: §V · p. 6
  • Future work should validate the model across additional abuse modes, cell chemistries, and pack-level propagation settings.Deployment-specific threshold calibration and end-to-end thermal-video alternatives are also identified for study.Source: §V · p. 6
Loading 2608.20383v1…