Physics-Guided Masked Multi-Task Network for Edge-Friendly Battery Health Diagnostics from Sto-chastically Fragmented Charging Profiles
Summary
Proposes RoSIP-Batt, a physics-guided multi-task transformer for joint estimation of battery State of Health and Remaining Useful Life, achieving state-of-the-art accuracy on NASA, MIT-Stanford, and HUST datasets.
View Cached Full Text
Cached at: 07/22/26, 08:19 AM
# Physics-Guided Masked Multi-Task Network for Edge-Friendly Battery Health Diagnostics from Sto-chastically Fragmented Charging Profiles Source: [https://arxiv.org/abs/2607.18330](https://arxiv.org/abs/2607.18330) [View PDF](https://arxiv.org/pdf/2607.18330) > Abstract:The deployment of reliable lithium\-ion battery management systems is crucial for accelerating electrification, yet the joint prognosis of State of Health \(SOH\) and Remaining Useful Life \(RUL\) remains severely hindered by task heteroscedasticity\. Conventional multi\-task learning frameworks fail to balance the bounded, low\-variance noise of SOH estimation with the unbounded, nonlinearly expanding uncertainty of long\-term RUL predictions\. Here, we present the Rotary SOH\-Injected Prior Battery Transformer \(RoSIP\-Batt\), a unified co\-estimation framework that resolves these optimization conflicts\. By formulating joint prediction as a Bayesian multi\-task objective, RoSIP\-Batt introduces a homoscedastic uncertainty weighting mechanism to dynamically scale task\-specific gradients based on learned residual noise levels\. The architecture leverages decoupled dual classification tokens and a per\-dimension gated fusion mechanism, secured by a gradient\-detachment operator to prevent high\-variance RUL updates from corrupting the stable SOH representation space\. To capture electrochemical degradation patterns without relying on absolute cycle steps, Rotary Position Embedding \(RoPE\) is incorporated into a shared Transformer backbone to model translation\-invariant relative temporal profiles\. Crucially, the intermediate SOH estimate is directly injected into the RUL regression head as a physical degradation prior\. Evaluations across the NASA, MIT\-Stanford, and HUST datasets show that RoSIP\-Batt significantly outperforms state\-of\-the\-art baselines, reducing SOH estimation error to 1\.994% MAE on NASA and restricting RUL prediction error to 62\.85 cycles on Stanford\. These findings establish RoSIP\-Batt as a highly generalizable, computationally efficient solution suitable for real\-time embedded BMS deployment\. ## Submission history From: Chengyi Tu \[[view email](https://arxiv.org/show-email/9819aad2/2607.18330)\] **\[v1\]**Sun, 19 Jul 2026 08:20:12 UTC \(3,974 KB\)
Similar Articles
Dynamic Loss Balancing for Joint SOH and RUL Prediction of Lithium-Ion Batteries via a Rotary SOH-Injected Prior Battery Transformer
Proposes RoSIP-Batt, a Transformer-based model for joint State of Health and Remaining Useful Life prediction of lithium-ion batteries, using dynamic loss balancing and rotary position embeddings, achieving state-of-the-art results on multiple datasets.
Real-Time State-of-Health Estimation and Online Degradation Prognosis from Partial Battery Discharge Using Physics-Informed Neural Networks
The paper proposes a physics-informed deep learning approach for lithium-ion battery state-of-health estimation using incomplete discharge curves, achieving high accuracy and enabling real-time degradation trend prognosis.
BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting
The paper proposes BatteryMFormer, a multi-level Transformer for early battery degradation trajectory forecasting that integrates aging-condition-aware decoding, meta degradation pattern memory, and dual-view encoding to capture multi-level degradation structures and SOC-localized variations, consistently outperforming state-of-the-art baselines across four battery domains.
PiDDM: Physics-Informed Differentiable Degradation Modeling for Lithium-Ion Battery State-of-Health Prediction
This paper introduces PiDDM, a physics-informed differentiable degradation modeling framework that embeds battery degradation kinetics into neural network training to improve lithium-ion battery state-of-health prediction accuracy and physical consistency across diverse cycling protocols.
BattVAE-GP: Generative Modeling of Long-Horizon Battery Degradation with Uncertainty Quantification
This paper presents BattVAE-GP, a hybrid physics-probabilistic framework that combines a Variational Autoencoder with a sparse multitask Gaussian Process to generate and interpolate long-horizon battery degradation trajectories with uncertainty estimates, enabling efficient surrogate modeling for lithium-ion battery health prediction.