Key Takeaways & Executive Findings
- •• • The improved TrAdaBoost.R2 algorithm achieves an RMSE of 0.009 in SOH estimation, a 59% reduction compared to classical TrAdaBoost (0.022) and a 50% reduction versus Transfer Stacking (0.018). This precision is critical for grid-scale battery management systems where SOH errors below 1% directly impact dispatch decisions and warranty compliance. • • Feature extraction relies on IC curve values at fixed voltage points, with Pearson correlation analysis determining the optimal voltage difference ΔU. This segmentation approach enables SOH estimation from partial charging data (SOC 20%–80%), eliminating the need for full charge-discharge cycles that are impractical in operational storage plants. • • The integration of DTW-derived similarity into the TrAdaBoost.R2 weight update mechanism accelerates convergence and reduces computational overhead. This is industrially significant for real-time battery monitoring, where latency above 100 ms can degrade control loop performance. • • Validation on NASA B0005 and XJTU Batch-1 datasets confirms the method's generalizability across different cell chemistries and aging trajectories. The RMSE of 0.009 translates to a 0.9% SOH estimation error, which is within the 2% tolerance required for second-life battery grading and repurposing.
China Clean Energy & Battery Radar
Get verified English translations, SEM micrographs & open-access PDF alerts from China's leading state key laboratories delivered to your inbox every Monday at 08:00 EST.
Abstract
Conventional state-of-health (SOH) estimation algorithms for lithium-ion batteries fail to extract requisite features when cells operate under random partial charge-discharge cycling, a condition prevalent in grid-scale energy storage. This study proposes an estimation framework predicated on segmenting the initial charging voltage. Capacity increment (IC) curves are analyzed to extract features corresponding to the initial charge voltage point. Random forest and a composite index determine the optimal feature set and cardinality, which subsequently define the segmentation intervals for the initial charging voltage. Within each interval, interval-specific features are employed for SOH estimation. To address the data scarcity that impedes model training for operational batteries, a transfer learning strategy is implemented. A sample-based transfer method, TrAdaBoost.R2, improved by dynamic time warping (DTW), estimates battery state. DTW computes similarity between source and target domain features, and this similarity is integrated into the weight update mechanism of TrAdaBoost.R2, enhancing convergence and computational speed while preserving accuracy. Validation against NASA and XJTU datasets demonstrates the method's efficacy. In simulation experiment 2, the improved TrAdaBoost.R2 achieves a root mean square error (RMSE) of 0.009, outperforming classical TrAdaBoost (0.022), Transfer Stacking (0.018), and Two-stage TrAdaBoost (0.021). The proposed approach offers a robust solution for SOH estimation under partial charging conditions with limited target-domain data.
1. Introduction
Lithium-ion battery state-of-health (SOH) estimation is a cornerstone of reliable energy storage operation. Mainstream approaches bifurcate into electrochemical model-based methods, which demand precise internal parameters and falter under parameter drift, and data-driven methods, which learn degradation patterns from operational data but confront two critical bottlenecks: (1) energy storage batteries typically operate within partial charge-discharge windows (SOC 20%–80%), rendering global data features inaccessible; and (2) manufacturing variations and fluctuating operating conditions degrade algorithm generalizability. Existing partial-data methods, such as voltage-interval capacity change or adaptive smoothing combined with CEEMDAN, still require preset global voltage segmentation rules, limiting their adaptability.
This study introduces an adaptive feature segmentation framework anchored to the initial charging voltage. By dynamically partitioning voltage intervals to match local data characteristics, the method circumvents dependence on complete charge-discharge curves. To address data scarcity in deployed batteries—where dynamic loads, ambient temperature fluctuations, and batch differences couple to impede modeling—a transfer learning strategy is employed. Source-domain datasets train the model, which is then calibrated with limited target-domain samples. Dynamic time warping (DTW) resolves temporal misalignment in degradation trajectories, and its similarity metric is embedded into the weight update of the TrAdaBoost.R2 algorithm, enhancing both convergence speed and estimation accuracy.
Loading authentic research manuscript (Pages 1–5)...
WANG Shiyu, QU Xiaoli, DU Yan, SU Jianhui, TAO Xiao, LI Jinzhong, XIE Yuguang (2026). State-of-Health Estimation for Lithium-Ion Batteries Based on Initial Voltage Segmentation and Transfer Learning. Acta Energiae Solaris Sinica. https://doi.org/10.19912/j.0254-0096.tynxb.202608_9664
Research & Educational Purpose Only: The translations, structured abstracts, analytical annotations, and data reports provided by SinoGreenTechare intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoGreenTech claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is the primary failure mechanism that limits conventional SOH estimation under partial charging conditions?
Conventional data-driven methods rely on global features extracted from full charge-discharge cycles. Under partial charging (SOC 20%–80%), these features are absent, leading to feature extraction failure. The proposed method addresses this by segmenting the initial charging voltage and extracting IC curve values at fixed voltage points, which are available even in partial cycles. This yields a 0.009 RMSE, compared to 0.022 for classical TrAdaBoost, demonstrating a 59% error reduction.
How does the DTW-enhanced TrAdaBoost.R2 improve convergence and computational efficiency?
DTW computes the similarity between source and target domain feature sequences, accounting for temporal misalignment in degradation trajectories. This similarity is integrated into the weight update of TrAdaBoost.R2, prioritizing source samples that align with target domain characteristics. The result is faster convergence and reduced iteration count, with RMSE dropping to 0.009 versus 0.021 for Two-stage TrAdaBoost, while maintaining computational tractability for real-time deployment.
What are the scalability bottlenecks when deploying this method across heterogeneous battery fleets?
Scalability hinges on the availability of representative source-domain datasets and the computational cost of DTW for large feature sequences. The method requires initial training on a source domain with sufficient degradation data, followed by calibration with a small target-domain sample. For fleet-level deployment, the DTW computation can be parallelized, but memory usage scales with sequence length. The 0.009 RMSE achieved on NASA and XJTU datasets suggests robustness, but cross-chemistry validation (e.g., LFP vs. NMC) remains necessary to confirm generalizability.
What is the industrial impact of achieving a 0.009 RMSE in SOH estimation for grid-scale storage?
A 0.009 RMSE corresponds to a 0.9% SOH estimation error, which is within the 2% tolerance required for second-life battery grading and repurposing. This precision enables accurate state-of-charge (SOC) and state-of-power (SOP) co-estimation, directly affecting dispatch decisions, warranty compliance, and safety margins. In grid-scale storage, a 1% SOH error can translate to megawatt-hour-level misestimation of available capacity, impacting revenue and reliability.
How does the feature selection process balance estimation accuracy and computational cost?
The method uses a composite index C to balance RMSE and feature count. Pearson correlation analysis determines the optimal voltage difference ΔU for IC curve extraction. Too large a ΔU compresses the local charging data range, while too small a ΔU degrades filtering effectiveness. The random forest algorithm identifies the optimal feature set and cardinality, ensuring that each feature is contained within the partial charging segment. This yields a compact feature set that achieves 0.009 RMSE without excessive computational overhead.
Related Chinese Research & Cross-Citations
Wind Turbine Gearbox Fault Diagnosis Method Based on Improved CNN-XGBoost Fusion Model Under Gramian Angular Difference Field
Gearbox failures account for 20–30% of total wind turbine faults and incur maintenance costs equivalent to 10–15% of overall turbine value. Conventional vibration diagnostic pipelines—complementary ensemble empirical mode decomposition with singular value energy spectrum, time-varying filtering empirical mode decomposition, and Teager energy spectrum analysis—remain bounded below 90% accuracy and depend on expert-driven feature engineering that is sensitive to non-stationary operating conditions and noise. This study proposes an intelligent diagnostic architecture that converts one-dimensional gearbox vibration signals into two-dimensional images via Gramian angular difference field (GADF) transformation, preserving intrinsic temporal correlation and time-frequency structure while exploiting matrix sparsity to suppress interference. An improved convolutional neural network (CNN) extracts multi-dimensional features: a convolutional block attention module (CBAM) is embedded in the convolutional layers to weight critical channels and focus on fault-sensitive spatial regions, and a modified βc-ACONC activation function replaces ReLU to mitigate neuron necrosis and enable selective activation. The extracted composite features are then fed into an XGBoost network whose hyperparameters are optimized by an improved sparrow search algorithm (ISSA). Validation on a laboratory wind turbine gearbox dataset yields diagnostic accuracy exceeding 99%, demonstrating robust fault identification capability under complex operating conditions.
Joint Forecasting of Wind and Photovoltaic Power Considering Complementarity
The inherent spatiotemporal complementarity between wind and solar resources offers a theoretical basis for improving renewable power forecasting accuracy. This study proposes a joint wind-photovoltaic (PV) power forecasting strategy that explicitly exploits this complementarity. A bidirectional long short-term memory (BiLSTM) neural network serves as the baseline forecasting model, and a novel sorting and comparative optimization (SCO) algorithm is developed to optimize the model's hyperparameters. The SCO algorithm ranks individuals in ascending order and compares adjacent fitness values to escape local optima, a known deficiency in conventional metaheuristics such as genetic algorithms and particle swarm optimization. For wind farms and PV plants exhibiting significant complementarity, the joint forecasting strategy first aggregates their power outputs, normalizes the combined signal, and then feeds it into the optimized BiLSTM model. Experimental results demonstrate that the proposed SCO-BiLSTM model reduces the eMAPE by 10.313% compared with PSO-BiLSTM. Furthermore, joint forecasting under SCO-BiLSTM lowers the eRMSE by 27.443% relative to standalone PV power forecasting. The study also establishes that forecasting accuracy improves with stronger wind-solar complementarity but degrades as the forecasting horizon extends. These findings confirm that exploiting complementarity in joint forecasting substantially enhances predictive performance for renewable energy integration.
Ultra-Short-Term Wind Power Forecasting Based on Fluctuation Continuation Scenario Identification
Existing ultra-short-term wind power forecasting methods exhibit limited performance due to insufficient extraction of fluctuation information and inadequate analysis of evolution patterns. This paper proposes an ultra-short-term wind power forecasting method based on fluctuation continuation scenario identification. First, the coupling mechanism of wind power fluctuations under multiple turbulence processes is investigated, and historical wind power dynamics are decoupled into a combination of nonlinear and linear fluctuation components. A fluctuation continuation concept is introduced, and the future continuation scale of wind power fluctuations is derived from nonlinear and linear decoupling parameters, thereby classifying fluctuation continuation scenarios. A sparse neural network (SNN) oriented to high-dimensional sparse features is constructed to identify historical fluctuation continuation scenarios, and ultra-short-term power forecasting is conducted separately for each scenario. Validation using measured wind speed and power data from three wind farms shows that, compared with baseline models, the proposed model improves root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) by at least 1.46%, 2.44%, and 14.67%, respectively, demonstrating superior accuracy and stability. The method addresses the limitations of signal decomposition techniques that lack physical interpretability and are sensitive to hyperparameters, and overcomes the high-dimensional sparsity challenges faced by traditional scenario identification models.
Multi-Classifier Open Adversarial Network for Rolling Bearing Fault Diagnosis in Wind Turbine Generator Systems
Rolling bearings in wind turbine generator systems operate under variable speed and load conditions that induce significant data distribution shifts between training and field data, while unknown fault modes absent from the source domain are frequently misclassified as known classes. This study proposes a multi-classifier open adversarial network (MCOAN) for open-set fault diagnosis. Within an adversarial domain adaptation framework, a K-way classifier and an additional K+1-way one-vs-all classifier independently estimate target-sample similarity to the source domain. These similarity scores drive a dynamic weighting mechanism that adaptively reweights target samples during open-set adversarial training and supplies per-sample dynamic thresholds for known/unknown discrimination, thereby promoting cross-domain alignment of shared-class features while suppressing negative transfer from unknown samples. A non-adversarial domain classifier is introduced to stabilize dynamic weight estimation. Validation on two datasets demonstrates high-precision shared-class distribution alignment and unknown-class recognition with favorable robustness. The method removes reliance on empirically preset thresholds that plague conventional open-set back-propagation approaches, where a fixed threshold of 0.5 in the binary cross-entropy adversarial loss provides no per-sample adaptivity. By coupling K-way and K+1-way similarity estimates, MCOAN achieves simultaneous known-class alignment and unknown-class separation without prior knowledge of the unknown-class cardinality, addressing a persistent bottleneck in wind turbine drivetrain condition monitoring where unanticipated bearing failure modes emerge under field conditions.
Unsupervised Automated Identification Method for Abnormal States of Wind Turbine Gearboxes
Addressing the scarcity of labeled data for training classification models in wind turbine planetary gearbox anomaly identification, this study proposes an unsupervised automated detection method. Log Mel-band energy features are extracted from raw vibration signals and fed into an unsupervised anomaly recognition model centered on a U-net autoencoder. A health-state threshold is established based on reconstruction error between model input and output, enabling anomaly identification. The method is validated using factory gearbox test data and operational data from a wind farm in Yangtouya, Shanxi. For factory gearboxes, dual validation is performed using a spectrum amplitude modulation-based signal processing method. Results demonstrate that the proposed method achieves 93.34% recognition accuracy on both factory and wind farm test sets, confirming its capability to automatically and correctly separate abnormal wind turbine gearboxes. The approach eliminates reliance on labeled fault data, offering a scalable solution for full-lifecycle health monitoring, from factory acceptance testing to in-service early anomaly detection, adaptable across different operating conditions and turbine models.
Improved Adaptive Super-Twisting Sliding Mode Control for Permanent Magnet Synchronous Motors
Adaptive super-twisting sliding mode control (ASTSMC) for permanent magnet synchronous motors (PMSM) suffers from prolonged convergence and insufficient disturbance rejection under complex operating conditions. This paper proposes an improved ASTSMC incorporating a fixed-time disturbance observer (FTDO). A power term is introduced into the adaptive super-twisting controller to accelerate convergence far from the origin, while the discontinuous sign function is replaced by a continuous h(s) function to mitigate chattering. The FTDO ensures disturbance estimation converges within a fixed time independent of initial states, overcoming the limitations of traditional and finite-time observers. The estimated disturbance is fed forward to the sliding mode controller for compensation, enhancing robustness. The FTDO design is based on an auxiliary state variable z and its derivative, with error dynamics analyzed via Lyapunov stability. Comparative simulations against conventional disturbance observers and sliding mode controllers validate the proposed strategy. The results demonstrate shorter convergence time, improved dynamic performance, and superior disturbance rejection, making the approach suitable for high-performance servo systems. The method addresses the critical need for robust, fast-response control in electric vehicles, rail transit, and aerospace applications where PMSM drives face significant uncertainties and external disturbances.