Advancing Open Science

Surrogate models are widely used in science and engineering to approximate other methods that are usually computationally expensive. Here, artificial neural networks (ANNs) are employed as surrogate regression models to approximate the finite element method in the problem of structural analysis of steel frames. The focus is on a multi-objective neural architecture search (NAS) that minimizes the training time and maximizes the surrogate accuracy. To this end, several configurations of the non-dominated sorting genetic algorithm (NSGA-II) are tested versus random search. The robustness of the methodology is demonstrated by the statistical significance of the hypervolume indicator. Non-dominated solutions (consisting of the set of best designs in terms of accuracy for each training time or in terms of training time for each accuracy) reveal the importance of multi-objective hyperparameter tuning in the performance of ANNs as regression surrogates. Non-evident optimal values were attained for the number of hidden layers, the number of nodes per layer, the batch size, and alpha parameter of the Leaky ReLU transfer function. These results are useful for comparing with state-of-the-art ANN regression surrogates recently attained in the recent structural engineering literature. This approach facilitates the selection of models that achieve the optimal balance between training speed and predictive accuracy, according to the specific requirements of the application.

In spoke-type permanent magnet synchronous motors (PMSMs), an asymmetric rib structure has been investigated as a method to reduce cogging torque. However, such rotor asymmetry tends to an increase in the axial force, which limits its applicability in precision and low-vibration systems. To overcome this limitation, this study proposes a new motor design method that introduces a skew factor as an additional design variable. The skew factor, defined as the ratio of the skewed region to the total stack length, enables simultaneous control of cogging torque and axial force by adjusting the degree of asymmetry along the rotor stack. Using parametric modeling and finite element analysis (FEA), the combined effects of the asymmetric rib and skew factor were investigated, and an optimized motor structure achieving balanced cogging torque and axial force characteristics was derived. The proposed design approach provides an effective method for simultaneously considering cogging torque and axial force in spoke-type PMSMs.

The energy that powers electric vehicles comes directly from their high-performance batteries, serving as the heart of their operation. They convert stored chemical energy into mechanical energy to propel vehicles. One of the most vital parts of an electric vehicle is a battery pack. Superior advantages such as higher energy density, longer life cycles, and the fast-charging ability of lithium-ion batteries set them apart from the others. However, battery performance and longevity exhibit a high degree of temperature sensitivity. In other words, operating batteries below and above the specified temperature range values causes problems such as decreased lifespan, safety issues, and performance losses. In electric vehicles, varying power demands during driving cause different current levels to be drawn from the battery packs. This leads to fluctuations in battery temperatures due to chemical reactions occurring. Besides that, regional and seasonal temperature variations also affect the operating temperatures of batteries. Therefore, maintaining the batteries within the specified temperature range, typically between 25 and 40 °C, is only achievable with an adequate battery thermal management system. This review intends to guide researchers working on designing more efficient thermal management systems by providing refined information about previous efforts in this field. The designs found in the literature have been illustrated with simplified figures. Cooling inlet and outlet locations are indicated in blue and red, enabling easier comparison and better understanding of different cooling designs. Air-cooling studies in the literature show that a well-designed system can keep the T_max and ΔT values of LiB cells ~305 K and 2.8 K during 3C discharge at a T_ambient of about 298.15 K. When liquid cooling systems are examined, a 50% glycol–water mixture can maintain pouch cells at nearly 30.3 °C with a ΔT of 2.78 °C under similar 3C and 25 °C conditions. Overall, the results demonstrate that well-designed BTMS configurations including optimized airflow or coolant–flow arrangements are capable of keeping LiBs safely within their optimal thermal operating conditions.

The increasing variety in last-mile delivery demands requires diverse vehicle-drone collaboration models to meet various scenarios. Meanwhile, growing environmental concerns demand that we optimize not just delivery efficiency but also sustainability. This study thus proposes a unified multi-mode framework for collaborative multi-vehicle, multi-drone delivery networks to enable fair model comparisons. We introduce a hybrid metaheuristic algorithm combining NSGA-II and VND using specialized encoding and neighborhood structures to handle complex constraints, thereby comprehensively enhancing both efficiency and sustainability. Experiments on nine benchmark instances across three models reveal a nonlinear trade-off between efficiency and sustainability, with our migratory-relay model consistently outperforming others in terms of the Pareto front across multiple comparisons. Sensitivity analysis shows diminishing returns from adding more drones; while the first drone can cut emissions by up to 23.1%, additional drones bring progressively smaller reductions. These findings provide a strong framework and practical insights for designing sustainable urban logistics systems.

Shale gas reservoirs are currently a focus in exploration and development in China. However, they exhibit pronounced vertical heterogeneity, are influenced by numerous geological and engineering parameters, and present significant challenges for “sweet spot” identification. Traditional sweet spot identification methods mainly rely on geologists’ experience and judgment regarding individual influencing parameters, which inevitably introduces subjectivity and uncertainty. The rapid development of artificial intelligence technology offers an opportunity to address this issue. This study adopts a geology–engineering integration approach and, based on data integration and a multi-algorithm prediction ensemble model with deep learning, proposes a predictive model built on actual data from the Nanchuan Block of the Sichuan Basin. The model integrates the Tetrahedral Topology Optimization (TBO) algorithm, Extreme Gradient Boosting (XGBoost), and Geological Attribute Feature Mapping (GAFM), aiming to improve the accuracy of shale gas reservoir sweet spot identification more effectively. The results show that sweet spots are jointly influenced by geological, rock-mechanical, and hydraulic fracturing parameters. The primary reservoir property factors controlling post-fracture productivity include TOC, permeability, porosity, and gas saturation, while the main rock-mechanical controlling factors are Poisson’s ratio, Young’s modulus, brittleness index, and Bursting Pressure. Based on the analysis of these productivity-controlling factors, the proposed integrated AI learning model achieved a sweet spot identification accuracy of 88.5%, enabling precise identification of single-well sweet spot distribution.

Industrial workplaces, especially in vulnerable, hot, and arid developing countries, face major challenges in maintaining indoor comfort conditions due to the escalating problem of global temperature rise. This study investigates passive scenarios of adaptive retrofitting for a case study carpet and rug industrial plant in Cairo, Egypt to achieve indoor comfort conditions and energy efficiency. The research method included a Post Occupancy Evaluation (POE) for the operational phase of individual work units through measurements and simulations to investigate indoor thermal, visual, and acoustic comfort conditions as well as air quality concerns. Thus, the study presents a set of recommendations for building unit(s) and collectively for the entire facility by applying integrated application of building envelope enhancements; optimized opening design, thermal wall insulation and high-albedo (reflective) exterior coatings for wall and roof surfaces. Comparing the modified case to the base case scenario shows significant improvements. Thermal comfort achieved a 16% to 33% reduction in discomfort hours during peak summer, primarily through a 33% increase in air flow velocity and better humidity control. Visual comfort indicated improvements in daylight harvesting, with Daylighting Autonomy increasing by 47% to 64% in core areas, improving light uniformity and reducing glare potential by decreasing peak illuminance by approximately 25%. Thus, the combined envelope and system modifications resulted in a 60 to 80% reduction in monthly Energy Use Intensity (EUI). The effectiveness of the mitigation measures using acoustic insulation was demonstrated in reducing sound pollution transferring outdoors, but the high indoor sound levels require further near-source mitigation or specialized acoustic treatment for complete success. Eventually, the research method helps create a mechanism for measuring and controlling indoor comfort conditions, provide an internal baseline or benchmark to which future development can be compared against, and pinpoint areas of improvement. This can act as a pilot project for green solutions to mitigate the problem of climate change in industrial workplaces and pave the way for further collaboration with the industrial sector.

Importance: Patient with head and neck cancer of the oropharynx (HNC-OROP) undergo curative-intent definitive or post-operative radiation therapy. The systemic inflammation response index (SIRI) has independent prognostic capacity in HNC-OROP. We hypothesized that the use of SIRI may produce a parsimonious model of HNC-OROP outcomes. Objective: We aimed to investigate the prognostic utility of systemic inflammatory response index (SIRI) in oropharyngeal head and neck cancer patients who underwent radiation therapy. Design, Setting, and Participants: Random survival forest (RSF) machine learning was used to model survival in 568 oropharyngeal cancer patients in this retrospective cohort study. SIRI was calculated via pre-treatment bloodwork. Model validation was performed in an external cohort of 421 oropharyngeal cancer patients. Exposures: Exposure was curative-intent definitive or post-operative radiation therapy for head and neck cancer of the oropharynx (HNC-OROP). Results: This is a retrospective study with 568 and 421 patients in the Roswell Park and external Ohio State University cohorts. We evaluated full and reduced RSF models and a robust decision tree model. The C-index of the models was 0.758 (RSF full), 0.725 (RSF reduced), and 0.702 (decision tree). The incorporation of SIRI (with performance status and smoking history) into a machine learning model identified three risk-groups that significantly stratified overall survival (p < 0.0001). These findings were validated in the external validation cohort (p = 0.0019). Progression-free survival was also significantly different for the three groups in the validation cohort (p = 0.0025). Conclusions and Relevance: An integrated machine learning model using SIRI, performance status, and smoking history was successfully developed and externally validated in oropharyngeal head and neck cancer patients.

To investigate the mechanism of road collapse induced by structural defects in underground drainage/sewerage pipelines in water-rich sands, laboratory physical model tests were conducted to reproduce the macroscopic development of surface subsidence. A computational fluid dynamics-discrete element method (CFD-DEM) model was then established and validated against the tests to assess its reliability. Using the validated model, we examined the effects of defect size and groundwater level on the progression of groundwater-ingress-driven internal erosion and tracked the evolution of vertical stress and intergranular contacts around the pipe. Results show that internal erosion proceeds through three stages—initial erosion, slow settlement, and collapse—culminating in an inverted-cone collapse pit. After leakage onset, the vertical stress in the surrounding soil exhibits a short-lived surge followed by a decline on both sides above the pipe. The number of intergranular contacts decreases markedly; erosion propagates preferentially in the horizontal direction, where the reduction in contacts is most pronounced. Within the explored range, higher groundwater levels and larger defects accelerate surface settlement and yield deeper and wider collapse pits. Meanwhile, soil anisotropy strengthens with increasing groundwater level but peaks and then slightly relaxes as defect size grows. These qualitative findings improve understanding of the leakage-induced failure mechanism of buried pipelines and offer references for discussions on monitoring, early warning, and risk awareness of road collapses.