A Lightweight Transfer Learning-Based State-of-Health Monitoring with Application to Lithium-ion Batteries in Unmanned Air Vehicles

2025-12-09

AI Summary

Addressing the challenge of online State-of-Health (SOH) estimation for lithium-ion batteries in resource-constrained mobile platforms (e.g., UAVs), where conventional transfer learning incurs excessive computational overhead and fails to meet stringent low-power and real-time requirements, this paper proposes a lightweight semi-supervised constructive incremental transfer learning method. The approach introduces a novel collaborative optimization framework integrating structural risk minimization, transfer mismatch suppression, and manifold consistency constraints—enabling efficient cross-operational-condition knowledge transfer under extremely limited labeled data. The resulting model achieves significant reductions in parameter count and inference energy consumption, facilitating embedded deployment. Evaluated on a real-world UAV battery dataset, it reduces RMSE by 58.2% on average—and up to 87.7%—compared to state-of-the-art methods including SS-TCA and MMD-LSTM-DA, thereby achieving an optimal trade-off among high accuracy, low complexity, and strong generalization capability.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Accurate and rapid state-of-health (SOH) monitoring plays an important role in indicating energy information for lithium-ion battery-powered portable mobile devices. To confront their variable working conditions, transfer learning (TL) emerges as a promising technique for leveraging knowledge from data-rich source working conditions, significantly reducing the training data required for SOH monitoring from target working conditions. However, traditional TL-based SOH monitoring is infeasible when applied in portable mobile devices since substantial computational resources are consumed during the TL stage and unexpectedly reduce the working endurance. To address these challenges, this paper proposes a lightweight TL-based SOH monitoring approach with constructive incremental transfer learning (CITL). First, taking advantage of the unlabeled data in the target domain, a semi-supervised TL mechanism is proposed to minimize the monitoring residual in a constructive way, through iteratively adding network nodes in the CITL. Second, the cross-domain learning ability of node parameters for CITL is comprehensively guaranteed through structural risk minimization, transfer mismatching minimization, and manifold consistency maximization. Moreover, the convergence analysis of the CITL is given, theoretically guaranteeing the efficacy of TL performance and network compactness. Finally, the proposed approach is verified through extensive experiments with a realistic unmanned air vehicles (UAV) battery dataset collected from dozens of flight missions. Specifically, the CITL outperforms SS-TCA, MMD-LSTM-DA, DDAN, BO-CNN-TL, and AS$^3$LSTM, in SOH estimation by 83.73%, 61.15%, 28.24%, 87.70%, and 57.34%, respectively, as evaluated using the index root mean square error.

Problem

• Lightweight transfer learning for battery health monitoring
• Reduces computational load in portable mobile devices
• Enhances accuracy under variable working conditions

Innovation

• Lightweight transfer learning for SOH monitoring
• Semi-supervised mechanism using unlabeled target data
• Structural risk and manifold consistency for cross-domain learning