The randomness, volatility, and intermittence of solar power generation make it difficult to achieve the desired accuracy of PV output-power prediction. Therefore, the time learning weight (TLW) proposed in this paper is used to improve the time correlation of the LSTM network. The Fusion Activation Function (FAF) is used to resolve gradient disappearance. Learning Factor Adaptation (LFA) and Momentum Resistance Weight Estimation (MRWE) are used to accelerate weight convergence and improve global search capabilities. Finally, this paper synthesizes the improvement and proposes the AHPA-LSTM model to stabilize the convergence domain. Using actual data verification, the δMAPE indicator of the improved model is only 2.85% on a sunny day, 5.92% on a cloudy day, 7.71% on a rainy day, and only 5.8% on average. Therefore, the AHPA-LSTM model under full climate and climatic conditions has a good predictive effect which is generally applicable to the prediction of ultra-short-term PV power generation.

In vision-based bearing defect detection, random shapes and multiscale defects can result in inaccurate feature extraction, and complex backgrounds can interfere with defect localization. Therefore, a novel bearing defect detection network (BDDN) is proposed in this article, aiming to improve the accuracy of bearing defect detection, which consists of deformable ResNet50 network (DRN) and double attention feature pyramid network (DA-FPN). In the DRN, it is found that using deformable convolution for stages 1–3 of ResNet50 is able to extract features that are closer to the actual defect regions through rich experiments. The DA-FPN is employed to reduce the interference of complex backgrounds for defect detection, which consists of a feature-enhanced attention module (FEAM) and a feature-communication attention module (FCAM). The FEAM obtains more refined high-level semantic information in channel feature extraction, while the FCAM efficiently fuses defect features across different levels. Experimental results demonstrate that the BDDN effectively detects bearing cover surface defects, achieving a mean average precision of 87.9%. In addition, it outperforms several defect detection models on the public Northeastern University dataset (NEU-DET) in terms of accuracy.

This paper proposes an effective method to estimate the state of health (SOH) of a lithium-ion battery based on the ohm internal resistance R₀. Unlike other estimation methods, this work considers the variation of R₀ with the state of charge (SOC). The improved unscented particle filter (IUPF) is presented to track and predict R₀. That is, an unscented Kalman filter (UKF) is used to generate an importance probability density function in the particle filter, and a method to select the fittest particle in the resampling stage is proposed. Based on the experimental data, a second-order resistance-capacitance equivalent circuit model is set up and the parameters are identified. To verify the accuracy of the proposed method, UKF and IUPF are compared in the prediction of R₀ at different SOC points under the same cycle and at the same SOC point of different cycles. The results show that IUPF has certain advantages, and the SOH estimation error is always less than 3% during the charge-discharge stage.

For a Battery Energy Storage System (BESS)-based autonomous DC microgrid, owing to the coupling complexity between multiple control objectives under a hierarchical control framework, coordination control for large-signal stabilization is well-acknowledged as a non-trivial problem. This paper aims to present a self-disciplined nonsmooth coordination control strategy to address the multi-objective task within one framework. Firstly, a nonsmooth composite regulation law is designed to mitigate the increasing constant power loads (CPLs) by employing a feedforward compensation. Secondly, a dynamic droop strategy aiming for dynamic power allocation for state-of-charging (SOC) balancing of BESS is built based on a nonsmooth dynamic average consensus protocol with low communication cost. Then by utilizing a dynamic power allocation strategy and a large-signal stabilizer for each energy storage unit (ESU), both SOC dynamic balancing and system level large-signal stability can be ensured. Moreover, a fast performance recovery ability can be promised by bringing into two convergence rate coordination factors. Simulation and comparative experimental studies have demonstrated the efficacy of the proposed control strategy.