Guozhong Huang

To enhance the energy efficiency and energy density of physical energy storage (PES) systems, this study introduces a novel hybrid advanced adiabatic compressed air and gravity energy storage (HAACAGES) system. This system integrates advanced adiabatic compressed air energy storage (AA-CAES) and gravity energy storage (GES) components, utilizing the mass of the compressed air (denoted by Δ m ) to make the HAACAGES system overwhelm the capabilities of individual systems. A numerical analysis model was established to validate the proposed system. Results demonstrate the HAACAGES system outperforms the individual systems in terms of both energy efficiency and density. Specifically, the energy efficiency is always higher than the sum of the individual systems at altitudes from 0 to 3 km. At 3 km altitude, the energy density reaches nearly 1.5 times that of conventional AA-CAES systems. At 1 km altitude, it exceeds 10 times that of conventional GES systems. Overall, the HAACAGES system shows clear potential as a promising solution for the next generation of large-scale PES systems.

Accurate prediction of electrical fire risk is important for early warning, but real-world monitoring data are often affected by sensor noise, transient anomalies, and non-Gaussian interference. This study proposes an HL-Transformer that incorporates an HL-Pooling layer based on the Hodges–Lehmann estimator into the Transformer feature aggregation process. The HL-Pooling layer replaces conventional mean- or max-based pooling by using the median of pairwise averages, aiming to suppress abnormal perturbations while preserving temporal information. Experiments were conducted on a real-world electrical fire monitoring dataset and the public ETTh1 dataset, with additional robustness tests under different outlier ratios and intensities. The results show that, within the same Transformer backbone, HL-Transformer reduced the MSE by 75.4% compared with the Max-Pooling variant and achieved an R² of 0.879 on the electrical fire risk prediction task. Under injected outliers, the HL-Pooling layer showed more stable error trends, and its transfer to TCN, CNN-LSTM, and 1D-CNN models further improved predictive performance. These findings indicate that HL-Pooling is a robust and portable alternative to conventional pooling for time-series forecasting in noisy monitoring environments.

Cables, which are critical for power and signal transmission in complex buildings and underground infrastructure, are exposed to elevated fire risks during operation, making reliable risk prediction essential for building fire safety. This study proposes a multivariate cable fire risk prediction model that integrates three deep temporal networks (RNN, LSTM, and GRU) through a Q-learning-based ensemble learning (QBEL). The model uses current, voltage, power, temperature, humidity, oxygen concentration, and system risk values acquired from an intelligent fire alarm system as inputs. Using a real-world dataset comprising 3060 seven-dimensional time steps collected from a tobacco logistics center, QBEL achieves a test-set MSE of 1.73, RMSE of 1.31, MAE of 0.84, and MAPE of 2.66%, improving the MAE and MAPE of the best single recurrent network by approximately 10–12%. Comparative experiments against conventional ensemble approaches based on XGBoost (Python package, version 3.0.0) boosting and stacking, as well as recent time-series forecasting models including DLinear, PatchTST, MoLE, and Fredformer, demonstrate that QBEL attains the lowest MAE and MAPE among all methods, while maintaining an MSE close to that of the best linear baseline and a moderate computational cost of approximately 5.5 × 10⁻³ GFLOPs and 45 MB of memory per inference. These results indicate that QBEL provides a favorable balance between prediction accuracy and computational efficiency, supporting its potential use in edge-oriented monitoring pipelines for timely cable fire risk warnings in building environments.

To reduce the safety risks caused by vehicle defects, this study aims to optimize recall strategies and improve recall efficiency by analyzing the dynamic game behaviors of the government, manufacturers, and consumers in the vehicle recall process. This study proposes a tripartite evolutionary game model to formulate the strategic behaviors and interactions between the government, manufacturers, and consumers. Given three different penalty types (i.e., no-, static, and dynamic mechanisms), a number of simulations are conducted to analyze the impact of government regulatory intensity, manufacturer voluntary recall decisions, and consumer participation on recall effectiveness. Through the numerical simulations, it is found that the government regulatory intensity significantly influences manufacturer recall proactivity. The dynamic penalty mechanism encourages manufacturers to recall defective vehicles proactively and increases consumer willingness to participate, thereby improving the overall recall process performance. Additionally, strict government regulation combined with dynamic reward and penalty mechanisms can reduce safety risks and enhance consumer trust in the government and manufacturers.

The fire risk of cables constantly changes over time and is affected by the materials and working conditions of cables. To address its internal timing property, it is essential to use a dynamic analysis method to assess cable fire risk. Meanwhile, data uncertainty resulting in the deviation of risk values must also be considered in the risk assessment. In this regard, this study proposes a hybrid cloud model (CM)-enabled Dynamic Bayesian network (DBN) method to estimate the cable fire risk under uncertainty. In particular, the CM is initially applied to determine the membership degrees of the assessment data relative to different states of the root nodes; then, these degrees are considered the prior probabilities of DBN, where the dynamic risk profiles are reasoned. Subsequently, the Birnbaum and Fussell–Vesely importance measures are constructed to identify the key nodes for risk prevention and control, respectively. Moreover, a case study of the Chongqing Tobacco Logistics Distribution Center is conducted, the computational results of which indicate the proposed method’s decision-making effectiveness. Finally, a comparison of the reasoning results between the proposed and traditional methods is performed, presenting strong evidence that demonstrates the reliability of the proposed method.

Large-scale epidemics impose significant burdens globally and cause an imbalance of medical supplies among different regions owing to the dissimilarly and unevenly distributed prevalence of the infection. Along with rebalancing the limited medical supplies to meet the demand and supply requirements, ensuring that the supplies are allocated to support the affected regions is also important. Hence, this study focuses on the collaborative medical supply rebalancing and allocating process to balance the demand and supply. The law of diminishing marginal utility is incorporated in this study to quantify the principle of fairness in rebalancing and allocating medical supplies. Accordingly, under uncertainty, a marginal-utility-oriented optimization model is proposed to formulate the rebalancing and allocation of collaborative medical supplies. Because the proposed model is nonlinear and computationally intractable, a linearization approach is adopted to obtain the global optimum that supports decision-making in response to epidemics. Furthermore, a real case study of the United States is implemented, where the sensitivity analysis of critical parameters is conducted on the coronavirus disease 2019. Computational results indicate that additional medical supplies, stock levels, and scenario constructions significantly influence the supply/demand point identification and outgoing/incoming shipments. Moreover, this study not only validates the effectiveness and feasibility of the method but also highlights the importance of incorporating the law of diminishing marginal utility into the collaborative medical supply rebalancing and allocating problem.

In the new-type clustered industrial park, the closer distance between enterprises leads to risk aggregation, and the layout of enterprises affects the safety and economy of the park. However, previous studies have often paid insufficient attention to safety, and few studies have considered park profits. To address this issue, a bi-level three-dimensional layout optimization model was proposed to minimize the overall association risk of the park and maximize the rental profit. In particular, this article explained the enterprise association risks and provided calculation formulas, considering multiple risk types. To solve the proposed nonlinear model, a specific variable conversion method was presented to reduce the problem scale. Subsequently, an improved genetic algorithm was developed and applied to obtain the layout results. Furthermore, a case study of an industrial park was conducted, and the computational results indicated the validity of the model and methods. Finally, two different scenarios were implemented, and critical parameters were tested to provide valuable management insights.

Cable overload is one of the most critical contributors to early cable fires. This study proposes a hybrid Bayesian network (BN)-based fire risk analysis model, to investigate the evolution of overload-induced early cable fire risks. In particular, the fire risk transmission paths caused by cable overload are reported, considering the critical factors that likely lead to fires. A BN with a specific structure was considered using the fire risk transmission paths. Later, given the risk index system, a hybrid fire risk assessment model caused by cable overload was developed based on the entropy weight method. Subsequently, the corresponding risk levels were evaluated based on the evolution of the fire risk, using numerical simulations. Finally, a case study was conducted to validate the proposed methods, and the results indicated that the proposed methods can effectively evaluate the state of the cable and explain the causes of fire risk, which can be used for early fire warnings.

The continuous-space single- and multi-facility location problem has attracted much attention in previous studies. This study focuses on determining the globally optimal facility locations for two- and higher-dimensional continuous-space facility location problems when the Manhattan distance is considered. Before we propose the exact method, we start with the continuous-space single-facility location problem and obtain the global minimizer for the problem using a statistical approach. Then, an exact method is developed to determine the globally optimal solution for the two- and higher-dimensional continuous-space facility location problem, which is different from the previous clustering algorithms. Based on the newly investigated properties of the minimizer, we extend it to multi-facility problems and transfer the continuous-space facility location problem to the discrete-space location problem. To illustrate the effectiveness and efficiency of the proposed method, several instances from a benchmark are provided to compare the performances of different methods, which illustrates the superiority of the proposed exact method in the decision-making of the continuous-space facility location problems.