Chengdong Li

To accurately assess the demand response (DR) potential of residential users, this paper proposes a comprehensive framework integrating Gramian Angular Field (GAF)-based load representation, CAE-based deep embedded clustering, and trend-value dual-layer evaluation. First, normalized daily load profiles are transformed into two-dimensional Gramian Angular Summation Field (GASF) images to characterize temporal load patterns. To accommodate the two-dimensional image input, the conventional autoencoder (AE) in the Improved Deep Embedded Clustering (IDEC) framework is replaced with a convolutional autoencoder (CAE) for feature extraction and reconstruction, while retaining the joint optimization of clustering and reconstruction objectives. Ablation experiments are conducted to evaluate the contributions of the load representation and feature extraction architecture to clustering performance. Furthermore, a trend-value dual-layer evaluation framework is developed to quantify DR potential from complementary perspectives of load-shape consistency and load-magnitude deviation. Case studies based on actual residential load profiles demonstrate that the proposed framework achieves an average clustering purity of 0.97, outperforming the autoencoder-based K-means clustering (AE+K-means) and long short-term memory combined with weighted gene co-expression network analysis (LSTM-WGCNA) methods by 22.2% and 19.8%, respectively. The evaluation results distinguish the peak-shaving and valley-filling capabilities of different residential user types. In load aggregator (LA) dispatch simulations, the proposed strategy increases total revenue by 22.4%, yielding an additional profit of CNY 2,116.74. These findings demonstrate the potential of the proposed framework for refined residential DR assessment and hierarchical resource scheduling.

Pressure and flow measurements collected by IoT-enabled sensor networks provide essential data for condition monitoring of urban water distribution networks (WDN), where the accurate detection of disturbances caused by weak leakage is crucial for reducing water loss and preventing secondary disasters. Nevertheless, weak leakage signals in WDN are difficult to detect, because they can be easily submerged by the strong periodic fluctuations in daily water usage. To exploit both the spatio-temporal characteristics of WDN and to enhance leakage detection performance, this paper proposes a hybrid leakage detection strategy based on the physics-informed time-series reconstruction and spatio-temporal feature fusion. First, a periodic-pattern-driven time-series reconstructor (PPTSR) is designed, in which the local abrupt changes caused by weak leakages can be significantly amplified by aligning with the intra-day periodic pattern as physical prior knowledge. Then, the Hazen-Williams fluid dynamic impedance formula is incorporated as physical information into the attention mechanism, where the graph structure is adopted as the mask module. Additionally, an improved spatio-temporal graph transformer (ISTGT) is developed to extract and fuse spatio-temporal features of pipe networks. Finally, experiments are conducted on publicly available pipe data, and the proposed method is compared with six popular models. The experimental results indicate that the proposed method significantly outperforms the existing popular spatial and temporal baseline models in terms of overall classification performance, achieving a macro F1-score of 98.28%. Notably, for the highly challenging weak leakage cases, the model can achieve an ROC-AUC of 0.998, striking an optimal balance between false negatives and false positives.

Accurately predicting the energy consumption of chillers is crucial for improving the energy efficiency of heating, ventilation, and air-conditioning (HVAC) systems and achieving building energy conservation. However, existing models have limited generalization capabilities under variable operating conditions and sparse data, while conventional physics-informed neural networks (PINNs) face challenges in adaptively adjusting physical weights and avoiding deep network convergence issues. To address these issues, this study proposes a condition-aware adaptive physics-informed residual network (CAA-PIResNet) for modeling chiller energy consumption. First, a one-dimensional residual network (ResNet) is employed as the backbone to extract complex nonlinear features, mitigating the vanishing gradient problem. Second, the Stoecker semi-empirical model is embedded as a physical constraint within the loss function to restrict the search space and ensure physical consistency. Furthermore, a condition-aware adaptive mechanism based on a fuzzy neural network (FNN) is designed to dynamically adjust data and physical loss weights according to the chiller's actual operating characteristics. Finally, experiments are conducted to evaluate the model's prediction accuracy, noise robustness, and generalization ability under sparse data. Experimental results demonstrate that CAA-PIResNet is significantly better than popular benchmark models. Under sparse conditions with only 10% of the training data, the model remains stable, reducing prediction errors by over 12.05%. This proves that the proposed model achieves better accuracy, robustness, and generalization due to the embedded physical constraints and condition-aware adaptive mechanism.

In practical applications, tower cranes often operate in outdoor environments and are subject to a variety of disturbances. Additionally, the control performance is significantly affected by uncertain dynamics, such as frictional forces and payload mass. To address these challenges, this paper presents a novel adaptive fuzzy control mechanism for nonlinear 5-degree of freedom (5-DOF) tower cranes with variable cable length. The proposed fuzzy adaptive mechanism leverages fuzzy logic to compensate for dynamic uncertainties and external disturbances thereby enhancing the overall robustness of the controlled system. Moreover, to ensure safe operation and avoid collisions, auxiliary constraint terms are introduced to restrict the actuated state variables within predefined bounds throughout the transportation process. In particular, an adaptive law is developed to accurately estimate the payload mass， which is critical for precise cable positioning. To the best of our knowledge, this work proposes a novel adaptive fuzzy closed-loop control framework for 5-DOF tower crane systems with varying cable lengths. The framework systematically integrates online payload mass estimation, state variable constraints, and fuzzy adaptive compensation to improve system stability and robustness. Based on the Lyapunov technique and Barbalat’s lemma, the system stability is theoretically analyzed and proven. Finally, the effectiveness of the proposed controller is validated by hardware experiments.

Photovoltaic (PV) power systems can provide clean, carbon-free energy and have become an important pathway for achieving carbon neutrality goals. Accurate prediction of PV power output is crucial for the rational scheduling and allocation of solar power resources. To further enhance the prediction accuracy at some local regions, especially around the peak or bottom points, this paper proposes a novel fusion fuzzy model for PV power forecasting. This model begins with the development of a distributed function-weighted fuzzy method (DFWFM), which effectively simplifies the structure of traditional fuzzy systems and significantly reduces the number of fuzzy rules. And an iterative regularized least squares method is developed for tuning the parameters of the DFWFM. Furthermore, a data-driven multi-scale fusion model (DMFM) is proposed to alleviate local prediction errors by training additional local models with data from high-error regions. The construction processes for such a multi-scale fusion model are also provided. Finally, detailed experiments are conducted, comparing the DFWFM-DMFM with five other prediction models. Experimental and comparative results demonstrate that this strategy substantially enhances the prediction accuracy in specific local areas, thereby improving the overall performance of the forecasting model.

Tower cranes are crucial equipment for construction due to their high load-bearing capacity and efficiency in large-scale material handling. In practical applications, it is essential to ensure that payloads (end-effectors) are transported to desired positions efficiently and safely. However, tower cranes with underactuated structure often operate in complex environments and are subject to external disturbances such as payload weight and wind, such that it is difficult to guarantee the control performance. To address these issues, a nonlinear end-effector tracking controller with almost disturbance decoupling is designed for five-DOF underactuated tower cranes. First, a nonlinear coupling variable is defined based on the position of an end-effector by incorporating both actuated and unactuated states, such that the relationship between the payload position and actuated/unactuated states can be mapped directly. Besides, the almost disturbance decoupling strategy is employed to deal with uncertain external disturbances, which achieves excellent anti-swing for five-DOF tower cranes. Finally, the superiority of the developed method is verified compared with the existing almost disturbance decoupling and nonlinear block backstepping controllers through hardware experiments on an actual laboratory tower crane.

In Al–Fe alloys, the mechanical properties are determined by the morphology of iron-rich phases. In this work, AA8176(Al-1Fe)-nY (n = 0, 0.3, 0.5, 0.7, and 0.9 wt.%) alloys were prepared by the cast method. The effects of yttrium (Y) addition on the microstructure and mechanical properties of AA8176 alloy were studied using various techniques including optical microscopy (OM), scanning electron microscopy (SEM), transmission electron microscopy (TEM), X-ray diffraction (XRD), cooling curve analysis and tensile tests. The results revealed that the optimal refinement effect was achieved when the amount of Y content was 0.5 wt.%. When the Y content increased from 0 to 0.5 wt.%, the coarse needle-like Al₁₃Fe₄ phases were gradually transformed into short rod-like morphology and some fine Al₁₀Fe₂Y phases were formed around the Al₁₃Fe₄ phases. The average length of iron-rich phases was decreased from 10.01 μm to 2.65 μm. Additionally, as the Y content increased from 0 to 0.5 wt.%, the secondary dendrite arm spacing (SDAS) of AA8176 alloy was reduced from 31.33 μm to 20.24 μm. Furthermore, the mechanical properties of the AA8176 alloy were improved due to the modified microstructure. With the addition of 0.5 wt.% Y, the ultimate tensile strength, yield strength, elongation, and Vickers hardness were improved to 96.86 MPa, 57.21 MPa, 23.1%, and 30.55 HV, respectively, compared to 84.47 MPa, 50.71 MPa, 18.6%, and 27.28 HV for the unmodified AA8176 alloy. It is proposed that the growth of α-Al dendrite and Al₁₃Fe₄ phases were effectively inhibited by segregation of Y atoms around α-Al dendrite and Al₁₃Fe₄ phases during solidification. And the Al₁₀Fe₂Y phases were formed by these Y atoms with Al and Fe elements. However, the formation of coarse Al₁₀Fe₂Y phases was promoted by excessive Y content, resulting in a substantial degradation in mechanical properties.

In Al–Fe alloys, the mechanical performance is determined by the morphology of iron-rich phases. In this work, AA8176(Al-1Fe)- nY (n = 0, 0.3, 0.5, 0.7, and 0.9 wt.%) alloys were prepared by the cast method. To systematically analyze the influence of Y on microstructure evolution and tensile behavior, a multi-scale characterization approach was employed, combining metallography, electron microscopy, X-ray diffraction, cooling curve analysis, and tensile tests. The results revealed that the optimal refinement effect was achieved when the amount of Y content was 0.5 wt.%. The micro-structure of the alloy was significantly modified by Y addition. The coarse needle-like Al13Fe4 phases were gradually transformed into short rod-like and particle morphology. And the average length was decreased from 10.01 μm to 2.65 μm. Meanwhile, some small size Al10Fe2Y phases were formed around the Al13Fe4 phases. Additionally, the secondary dendrite arm spacing (SDAS) of A8176 alloy was reduced from 31.33 μm to 20.24 μm. Furthermore, the mechanical properties of the AA8176 alloy were improved due to the modified microstructure. The tensile strength of the alloy was increased from 84.47 MPa to 96.86 MPa, and the elongation was increased from 18.6 % to 23.1 %. It is proposed that the growth of α-Al dendrite and Al13Fe4 phases were effectively inhibited by segregation of Y atoms around α-Al dendrite and Al13Fe4 phases during solidification. And the Al10Fe2Y phases were formed by these Y atoms with Al and Fe elements. However, the formation of coarse Al10Fe2Y phases was promoted by excessive Y content, which resulting in a substantial degradation in mechanical properties.