Longyun Kang

The State of Health (SOH) prediction is crucial for battery management systems (BMS). For industrial deployment, the SOH prediction models are required to possess three essential capabilities: the generalization ability across chemical systems to minimize training and deployment costs; rapid adaptation to new battery types with limited historical data; probabilistic prediction to quantify uncertainties arising from manufacturing tolerances, operational variations, and other factors, to support risk-based decision-making. However, existing SOH probabilistic prediction methods fall short of meeting all these requirements. Therefore, this paper proposed a Meta-Adaptive Neural Processes (MNPs) for cross-chemistry SOH probability prediction. By innovatively introduce a meta-adaptive mechanism into NPs, the MNPs enable effective knowledge transfer across different battery chemistries, which significantly reduces historical data requirements for new chemistry batteries, and achieved unified probabilistic prediction across multiple battery types using a single MNPs model. Besides, 7 industrial-friendly features are also carefully designed as model inputs. Experimental results indicate that the MNPs proposed in this paper exhibit excellent prediction accuracy (RMSE is 0.24%) and show excellent robustness against incomplete input data.

Accurate estimation of the state of health (SOH) of lithium-ion batteries confronts two critical challenges: the extreme scarcity of labeled data in large-scale operational datasets and the mismatch between existing methods (relying on full charging–discharging conditions) and shallow charging–discharging conditions prevalent in real-world scenarios. To address these challenges, this study proposes a self-supervised learning framework for SOH estimation. The framework employs a dual-time-scale collaborative pre-training approach via masked voltage sequence reconstruction and interval capacity prediction tasks, enabling automatic extraction of cross-time-scale aging features from unlabeled data. Innovatively, it integrates domain knowledge into the attention mechanism and incorporates time-varying factors into positional encoding, significantly enhancing the capability to extract battery aging features. The proposed method is validated on two datasets. For the standard dataset, using only 10% labeled data, it achieves an average RMSE of 0.491% for NCA battery estimation and 0.804% for transfer estimation between NCA and NCM. For the shallow-cycle dataset, it achieves an average RMSE of 1.300% with only 2% labeled data. By synergistically leveraging massive unlabeled data and extremely sparse labeled samples (2–10% labeling rate), this framework reduces the labeling burden for battery health monitoring by 90–98%, offering an industrial-grade solution with near-zero labeling dependency.

To address the issue of excessive grid-connected power fluctuations in wind farms, this paper proposes a capacity optimization method for a hybrid energy storage system (HESS) based on wind power two-stage decomposition. First, considering the susceptibility of traditional k-means results to initial cluster center positions, the k-means++ algorithm was used to cluster the annual wind power, with the optimal number of clusters determined by silhouette coefficient and Davies–Bouldin Index. The overall characteristics of each cluster and the cumulative fluctuations were considered to determine typical daily data. Subsequently, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) was used to decompose the original wind power data for typical days, yielding both the grid-connected power and the HESS power. To leverage the advantages of power-type and energy-type storage while avoiding mode aliasing, the improved pelican optimization algorithm—variational mode decomposition (IPOA-VMD) was applied to decompose the HESS power, enabling accurate distribution of power for different storage types. Finally, a capacity optimization model for a HESS composed of lithium batteries and supercapacitors was developed. Case studies showed that the two-stage decomposition strategy proposed in this paper could effectively reduce grid-connected power fluctuations, better utilize the advantages of different energy storage types, and reduce HESS costs.

Inductor-based equalizers are characterized by high in power, but current inductor-based equalizers rarely consider the cost of the isolated power supplies for driving switches and the design of free-wheeling networks for inductor current. To tackle these issues, two inductor-based voltage equalizers are proposed in this paper. On the one hand, combining diodes and MOSFETs to form a switch array can achieve the common source electrode shared by MOSFETs on the same sides, reducing the required number of isolated power supplies and the circuit cost. On the other hand, free-wheeling networks with lower inductor current descent during the dead time are provided in the proposed equalizers, thus the equalization speed and efficiency can be improved compared with the current inductor-based methods. Topological structures, operation principles and mathematical modeling analysis are illustrated in detail first. Then circuit parameters are selected based on the simulation results. Comparisons between the proposed and the existing methods over the equalization performance, cost and size are also conducted. Finally, experiment platforms are established. The results verify the feasibility and high-performance of the proposed equalizers.

The open-circuit voltage (OCV) curve has a significant influence on the accuracy of the state of charge (SOC) estimation based on equivalent circuit models (ECMs). However, OCV curves are tested through offline experiments and are hard to be very accurate because they constantly change with the test method’s ambient temperature and aging status. Recently, researchers have attempted to improve the accuracy of OCV curves by increasing the volume of sample data or updating/reconstructing the curve combined with practical operation data. Still, prior offline tests are essential, and experimental errors inevitably exist. Consequently, a SOC estimation method without any offline OCV tests might be an efficient route to improve the accuracy of SOC. According to this idea, this paper presents a novel method for SOC estimation, which is based on online OCV curve construction. Meanwhile, a stepwise multi-timescale parameter identification algorithm is designed to improve the interpretability and precision of the estimated ECM parameters. The results demonstrate that the maximum SOC estimation error is only 0.05% at 25 °C, indicating good robustness under various ambient temperatures and operational conditions.

Accurate state of health (SOH) estimation is critical to the operation, maintenance, and replacement of lithium-ion batteries (LIBs), which have penetrated almost every aspect of our life. This paper introduces a new approach to accurately estimate the SOH for rechargeable lithium-ion batteries based on the corresponding charging process and long short-term memory recurrent neural network (LSTM-RNN). In order to learn the mapping function without employing battery models and filtering techniques, the LSTM-RNN is initially fed into the health indicators (HIs) extracted from the charging process and trained to encode the dependencies of the related data sequence. Subsequently, the trained LSTM-RNN can properly estimate online SOHs of LIBs using extracted HIs. We experiment on two public datasets for model construction, validation, and comparison. Conclusively, the trained LSTM-RNN achieves an overall root mean square error (RMSE) lower than 1% on the cases with the same discharging current rate and an RMSE of 1.1198% above 80% SOH on another testing case that underwent a different discharging current rate.

Hybrid energy storage systems (HESS) composed of a battery and ultracapacitor (UC) provide a feasible solution to the economy of electric vehicles (EVs). To fully exploit the potential of HESSs, a power distribution strategy that can split power between the battery and UC in HESSs plays an important role. Therefore, a novel power distribution strategy and its online application are proposed in this paper. First, a new and simple power distribution model of HESSs is proposed, and the model parameters are optimized offline through particle swarm optimization (PSO). Then, a driving condition recognizer based on a neural network is introduced, and the online application of the strategy is realized by combining offline global optimization and online recognition. Compared with the traditional rule-based strategy, the strategy proposed reduces the average fluctuation of the battery current by 52.53% and the average amplitude of the battery current by 11.51%. Meanwhile, it can be seen from the results that the strategy proposed is very close to the offline PSO-based strategy proposed and exhibits good performance under all driving cycles.

This paper proposes an effective model predictive current control (E-MPCC) method for grid-connected quasi-Z-source T-Type inverter(QZSTI), which has a purpose of neutral voltage balance and eliminates the weight factor. The inductance current and capacitance voltage are controlled simultaneously using an enhanced sliding mode control technique to prevent the weight component in the cost function. Additionally, a sector selection approach that is accurate and efficient is suggested, avoiding the need for numerous calculations to perform each optimization individually. Results from simulations and experiments support the efficacy and supremacy of this approach.

Bidirectional DC/DC converters are widely adopted in new energy power generation systems. Because of the low conversion efficiency and non-isolation for conventional, bidirectional DC/DC converters in the photovoltaic energy storage complementary system, this paper proposes a bidirectional isolation LLC converter topology, with compensating inductance for the energy storage system; it has excellent characteristics, such as wide input voltage range and soft switching in full-load range. First, an AC equivalent model based on the fundamental wave equivalent method is established to derive the voltage gain. Meanwhile, a small signal model is also built to design a reasonably closed-looped controller. Finally, the improved bidirectional LLC resonant converter is applied to the photovoltaic energy storage complementary system. The correctness and feasibility for the bidirectional LLC converter topology under the proposed charging and discharging control strategy of the DC bus are verified by simulation and experimental results.