Batteries

Lithium-ion batteries (LIBs) can undergo thermal runaway (TR) under thermal abuse, and high-nickel LIBs face more severe safety challenges. Therefore, early warning of TR is crucial for the safe operation of LIBs. Overheating-induced TR experiments were conducted on 15 Ah NCM811 LIBs at different states of charge (SOCs, 10–100%), with synchronous monitoring of expansion force, temperature, voltage, and characteristic gases (CO, CO₂, HF, and H₂). Based on signals variations, five characteristic moments were defined, dividing TR into five stages: abnormal expansion-force increase (t_abn), cell venting (t_V), first gas detection (t_G), internal short circuit (t_ISC), and TR (t_TR). As SOC increased, deeper cathode delithiation and anode lithiation accelerated internal reactions, shifting all moments earlier. The expansion-force signal enabled the earliest anomaly identification, up to 1275 s before TR onset, while CO detection within 30 s after venting provided chemical confirmation. Voltage signals accurately indicated ISC, and temperature signals directly reflected the essence of TR. Consequently, a three-level early-warning strategy was proposed: Level 1 (dF/dt > 1 N/s), Level 2 (sequential force–gas confirmation), and Level 3 (“voltage + temperature” with duration constraints). The thresholds are SOC-independent, offering a reference for engineering deployment in high-nickel pouch LIBs.

Second-life lithium-ion banks in isolated microgrids combine heterogeneous, partially degraded cells with harsh tropical operation, yet conventional battery management reacts to voltage limits only once they are reached. This work proposes a degradation-aware battery management system in which the probabilistic state-of-health (SOH) estimate of each cell, obtained by Gaussian process regression, sets a proactive current-derating factor through an uncertainty-penalized effective SOH ($\mu -2\sigma$), so that estimation uncertainty becomes a control variable. The estimator was validated on four public datasets spanning four chemistry/format combinations, including six LG INR21700-M50T cells with a measured 50-month electric-vehicle-to-storage transition (out-of-fold RMSE 0.28% SOH; 0.69–2.29% on NASA, CALCE, and RWTH benchmarks). An independent 36-cell pack dataset confirms the premise: 14 cells fall below 3.0 V while the pack voltage still reads nominal. At the cycle level, the derating removes every envelope violation of unprotected operation while extracting 3.5% more energy than a safe per-cell cutoff. Over 1500 simulated days of an off-grid photovoltaic microgrid in the Colombian non-interconnected zones, with a bank built from the six measured second-life cells, the strategy preserves 6.5 SOH percentage points at zero loss of supply, rising to 11.8 pp at 35 °C and 13.9 pp for a pre-aged bank, where only the managed bank avoids end of life. The control law is algebraic (∼2 μs per evaluation), computationally compatible with low-cost embedded implementation.

Online battery remaining-useful-life (RUL) predictions can be optimistic when cycles from the same cell cross data splits, predictors use future observations, or right-censored records are labeled as failures. We present a leakage-resistant, censor-aware evaluation using a 209-cell pool from NASA, CALCE, HUST, and MATR. Of these, 86 cells formed the internal pool; 21 observed-endpoint MATR development cells froze the external model; 21 official MATR primary-test cells with a strict-80% state-of-health (SOH) endpoint provided the primary point evaluation; and 82 official MATR test cells (21 events and 61 censored) supported a survival sensitivity. Predictions are causal, cells are independent units, and censored cells receive no pseudo-endpoint. A benchmark-informed heuristic routes among ridge, LSBoost, and compact XGBoost using outer-training descriptors; it is a hypothesis, not a validated selector. Internal fold-macro RMSEs for NASA, CALCE, HUST repeated grouped, and HUST protocol-family holdout were 12.15, 38.91, 137.16, and 126.39 cycles. On the 21 primary-test cells, protocol-aware XGBoost achieved 26.98-cycle battery-macro RMSE and 92.92% coverage for nominal 90% intervals. Protocol-aware features reduced battery- macro RMSE by 13.36%; this improvement remains suggestive (p = 0.0868) rather than statistically conclusive. A matched audit showed XGBoost significantly outperformed ridge but not LSBoost or random forest. A HUST learning curve improved from 20 training cells to the full set, so the routing cutoff is not a sample-sufficiency threshold. At the strict-80% SOH endpoint, nonlinear XGBoost-AFT did not improve significantly over penalized linear AFT. This work introduces a leakage-resistant, censor-aware evaluation framework for capacity-only online lithium-ion battery remaining-useful-life (RUL) prediction, rather than proposing a novel standalone prediction model. Within this framework, existing base predictors including ridge regression, LSBoost, compact XGBoost, TCN, and GRU are reused as model backends. Protocol-aware metadata features serve as an optional add-on feature branch for ablation comparison and are not mandatory inputs for the core capacity-only framework. This study performs algorithm-oriented offline evaluation using ground-truth capacity/SOH readings from public cycling datasets, rather than testing on embedded BMS hardware. The prediction performance will deteriorate when fed with noisy SOH/capacity estimates output from real battery-management systems. The benchmark-informed routing scheme serves as a heuristic hypothesis, not a universally validated or preregistered model-selection criterion. The evidence supports rigorous cell-level evaluation and cautious, representation-aware model choice, while strict-endpoint sample size and early-life uncertainty remain unresolved. This study conducts algorithm-oriented offline evaluation using ground-truth capacity and state-of-health (SOH) readings from public battery-cycling datasets, rather than performing tests on embedded BMS hardware. Prediction performance will degrade when fed with noisy SOH/capacity estimates output by real-world battery-management systems.