Search Results (547)

This study presents a breakthrough in sustainable injection molding by uniquely combining a backpropagation neural network (BPNN) with particle swarm optimization (PSO) to overcome traditional optimization challenges. The BPNN’s exceptional ability to learn complex nonlinear relationships between six key process parameters (including melt temperature and holding pressure) and product quality is amplified by PSO’s intelligent search capability, which efficiently navigates the high-dimensional parameter space. Together, this hybrid approach achieves what neither method could accomplish alone: the BPNN accurately models the intricate process-quality relationships, while PSO rapidly converges on optimal parameter sets that simultaneously meet strict quality targets (66–70 g weight, 3–5 mm thickness) and minimize energy consumption. The significance of this integration is demonstrated through three key outcomes: First, the BPNN-PSO combination reduced optimization time by 40% compared to traditional trial-and-error methods. Second, it achieved remarkable prediction accuracy (RMSE 0.8229 for thickness, 1.5123 for weight) that surpassed standalone BPNN implementations. Third, the method’s efficiency enabled SMEs to achieve CAE-level precision without expensive software, reducing setup costs by approximately 25%. Experimental validation confirmed that the optimized parameters decreased energy use by 28% and material waste by 35% while consistently producing parts within specifications. This research provides manufacturers with a practical, scalable solution that transforms injection molding from an experience-dependent craft to a data-driven science. The BPNN-PSO framework not only delivers superior technical results but does so in a way that is accessible to resource-constrained manufacturers, marking a significant step toward sustainable, intelligent production systems. For SMEs, this framework offers a practical pathway to achieve both economic and environmental sustainability, reducing reliance on resource-intensive CAE tools while cutting production costs by an estimated 22% through waste and energy savings. The study provides a replicable blueprint for implementing data-driven sustainability in injection molding operations without compromising product quality or operational efficiency. Full article

Nanoimprint lithography (NIL) has emerged as a promising sub-10 nm patterning at low cost; yet, robust process control remains difficult because of time-consuming physics-based simulators and labeled SEM data scarcity. We propose a data-efficient, two-stage deep-learning framework here that directly reconstructs post-imprint SEM images from binary design layouts and delivers calibrated pixel-by-pixel uncertainty simultaneously. First, a shallow U-Net is trained on conformalized quantile regression (CQR) to output 90% prediction intervals with statistically guaranteed coverage. Moreover, per-level errors on a small calibration dataset are designed to drive an outlier-weighted and encoder-frozen transfer fine-tuning phase that refines only the decoder, with its capacity explicitly focused on regions of spatial uncertainty. On independent test layouts, our proposed fine-tuned model significantly reduces the mean absolute error (MAE) from 0.0365 to 0.0255 and raises the coverage from 0.904 to 0.926, while cutting the labeled data and GPU time by 80% and 72%, respectively. The resultant uncertainty maps highlight spatial regions associated with error hotspots and support defect-aware optical proximity correction (OPC) with fewer guard-band iterations. Extending the current perspective beyond OPC, the innovatively model-agnostic and modular design of the pipeline here allows flexible integration into other critical stages of the semiconductor manufacturing workflow, such as imprinting, etching, and inspection. In these stages, such predictions are critical for achieving higher precision, efficiency, and overall process robustness in semiconductor manufacturing, which is the ultimate motivation of this study. Full article

The integration of Building Information Modeling (BIM) and Digital Twin (DT) technologies offers new opportunities for enhancing reinforcement design and on-site constructability. This study addresses a current gap in DT applications by introducing an intelligent framework that simultaneously automates rebar layout generation and reduces rebar cutting waste (RCW), two challenges often overlooked during the construction execution phase. The system employs heuristic algorithms to generate constructability-aware rebar configurations and leverages Industry Foundation Classes (IFC) schema-based data models for interoperability. The framework is implemented using Autodesk Revit and Dynamo for rebar modeling and layout generation, Microsoft Project for schedule integration, and Autodesk Navisworks for clash detection. Real-time scheduling synchronization is achieved through IFC schema-based BIM models linked to construction timelines, while embedded clash detection and constructability feedback loops allow for iterative refinement and improved installation feasibility. A case study on a high-rise commercial building demonstrates substantial material savings, improved constructability, and reduced layout time, validating the practical advantages of BIM–DT integration for RC construction. Full article

This study presents the design and development of a structurally optimized mobile robotic system with a machine learning-based energy-efficient path planning framework. Topology optimization (TO) and finite element analysis (FEA) were applied to reduce structural weight while maintaining mechanical integrity. The optimized components were manufactured using Fused Deposition Modeling (FDM) with ABS (Acrylonitrile Butadiene Styrene) material. A custom power analysis tool was developed to compare energy consumption between the optimized and initial designs. Real-world current consumption data were collected under various terrain conditions, including inclined surfaces, vibration-inducing obstacles, gravel, and direction-altering barriers. Based on this dataset, a path planning model was developed using machine learning algorithms, capable of simultaneously optimizing both energy efficiency and path length to reach a predefined target. Unlike prior works that focus separately on structural optimization or learning-based navigation, this study integrates both domains within a single real-world robotic platform. Performance evaluations demonstrated superior results compared to traditional planning methods, which typically optimize distance or energy independently and lack real-time consumption feedback. The proposed framework reduces total energy consumption by 5.8%, cuts prototyping time by 56%, and extends mission duration by ~20%, highlighting the benefits of jointly applying TO and ML for sustainable and energy-aware robotic design. This integrated approach addresses a critical gap in the literature by demonstrating that mechanical light-weighting and intelligent path planning can be co-optimized in a deployable robotic system using empirical energy data. Full article

There is a present need to develop alternative biotherapeutic drugs to mitigate the exacerbated inflammatory immune responses characteristic of sepsis. The potent endotoxin lipopolysaccharide (LPS), a major component of Gram-negative bacterial outer membrane, activates the immune system via Toll-like receptor 4 (TLR4), triggering macrophages and a persistent cascade of inflammatory mediators. Our previous studies have demonstrated that Fh15, a recombinant member of the Fasciola hepatica fatty acid binding protein family, can significantly increase the survival rate by suppressing many inflammatory mediators induced by LPS in a septic shock mouse model. Although Fh15 has been proposed as a TLR4 antagonist, the specific mechanisms underlying its immunomodulatory effect remained unclear. In the present study, we employed a quantitative proteomics approach using tandem mass tag (TMT) followed by LC-MS/MS analysis to identify and quantify differentially expressed proteins that participate in signaling pathways downstream TLR4 of macrophages, which can be dysregulated by Fh15. Data are available via ProteomeXchange with identifier PXD065520. Based on significant fold change (FC) cut-off of 1.5 and p-value ≤ 0.05 criteria, we focused our attention to 114 proteins that were upregulated by LPS and downregulated by Fh15. From these proteins, TNFα, IL-1α, Lck, NOS2, SOD2 and CD36 were selected for validation by Western blot on murine bone marrow-derived macrophages due to their relevant roles in the NF-κB, iNOS, oxidative stress, and phagosome signaling pathways, which are closely associated with sepsis pathogenesis. These results suggest that Fh15 exerts a broad spectrum of action by simultaneously targeting multiple downstream pathways activated by TLR4, thereby modulating various aspects of the inflammatory responses during sepsis. Full article

The construction sector presently consumes about 40% of global energy and generates 36% of CO₂ emissions, making facade retrofits a priority for decarbonising buildings. This review clarifies how ventilated facades (VFs), wall assemblies that interpose a ventilated air cavity between outer cladding and the insulated structure, address that challenge. First, the paper categorises VFs by structural configuration, ventilation strategy and functional control into four principal families: double-skin, rainscreen, hybrid/adaptive and active–passive systems, with further extensions such as BIPV, PCM and green-wall integrations that couple energy generation or storage with envelope performance. Heat-transfer analysis shows that the cavity interrupts conductive paths, promotes buoyancy- or wind-driven convection, and curtails radiative exchange. Key design parameters, including cavity depth, vent-area ratio, airflow velocity and surface emissivity, govern this balance, while hybrid ventilation offers the most excellent peak-load mitigation with modest energy input. A synthesis of simulation and field studies indicates that properly detailed VFs reduce envelope cooling loads by 20–55% across diverse climates and cut winter heating demand by 10–20% when vents are seasonally managed or coupled with heat-recovery devices. These thermal benefits translate into steadier interior surface temperatures, lower radiant asymmetry and fewer drafts, thereby expanding the hours occupants remain within comfort bands without mechanical conditioning. Climate-responsive guidance emerges in tropical and arid regions, favouring highly ventilated, low-absorptance cladding; temperate and continental zones gain from adaptive vents, movable insulation or PCM layers; multi-skin adaptive facades promise balanced year-round savings by re-configuring in real time. Overall, the review demonstrates that VFs constitute a versatile, passive-plus platform for low-carbon buildings, simultaneously enhancing energy efficiency, durability and indoor comfort. Future advances in smart controls, bio-based materials and integrated energy-recovery systems are poised to unlock further performance gains and accelerate the sector’s transition to net-zero. Emerging multifunctional materials such as phase-change composites, nanostructured coatings, and perovskite-integrated systems also show promise in enhancing facade adaptability and energy responsiveness. Full article

Plasma jet cutting is a non-conventional process commonly used in modern industry for processing metal sheets and preparing them for subsequent technological steps. In this context it is very important to achieve the best possible final-quality workpiece to minimize additional post-processing costs, and time. This is especially challenging by the plasma jet processing of aluminum and its alloys. In this paper, a comprehensive analysis regarding the machinability and optimal circular quality of aluminum alloy 5083 was performed. Process parameters whose effects were analyzed are the cutting speed, arc current and cutting height. The circular quality was considered through responses: the circular kerf width, circular bevel angle, and circularity error on the top and bottom sheet of the metal side. To design functional relations between the process inputs and quality performances, an artificial intelligence fuzzy logic technique supported by ANOVA was applied. In order to define the process conditions that result in optimal cut quality responses, the multi-objective optimization of hybrid grey relational analysis (GRA) and the fuzzy logic approach was presented. Corresponding surface plots were created to determine the Pareto front of optimal solutions that simultaneously optimize all circular quality objective functions. The optimization procedure was confirmed through a test in which the mean absolute percentage error represented as the validation metric. Full article

This article deals with drilling, the most common and simultaneously most important traditional machining operation, and which is significantly influenced by the properties of the machined material itself. To fully understand this process, both from a theoretical and practical perspective, it is essential to examine the influence of technological and tool-related factors on its various parameters. Based on the evaluation of experimentally obtained data using advanced statistical methods and machine learning decision trees, we present a detailed analysis of the effects of technological factors (f_n, v_c) and tool-related factors (D, ε_r, α₀, ω_r) on variations in torque (M_c) during drilling of two types of engineering steels: carbon steel (C45) and case-hardening steel (16MnCr5). The experimental verification was conducted using CTS20D cemented carbide tools coated with a Triple Cr SHM layer. The analysis revealed a significant influence of the material on torque variation, accounting for a share of 1.430%. The experimental verification confirmed the theoretical assumption that the nominal tool diameter (D) has a key effect (53.552%) on torque variation. The revolution feed (f_n) contributes 36.263%, while the tool’s point angle (ε_r) and helix angle (ω_r) influence torque by 1.189% and 0.310%, respectively. No significant effect of cutting speed (v_c) on torque variation was observed. However, subsequent machine learning analysis revealed the complexity of interdependencies between the input factors and the resulting torque. Full article

Nowadays, the development of the food industry and economic recovery have driven escalating consumer demands for high-quality, nutritious, and safe food products, and spectroscopic technologies are increasingly prominent as essential tools for food quality inspection. Concurrently, the rapid rise of artificial intelligence (AI) has created new opportunities for food quality detection. As a critical branch of AI, deep learning synergizes with spectroscopic technologies to enhance spectral data processing accuracy, enable real-time decision making, and address challenges from complex matrices and spectral noise. This review summarizes six cutting-edge nondestructive spectroscopic and imaging technologies, near-infrared/mid-infrared spectroscopy, Raman spectroscopy, fluorescence spectroscopy, hyperspectral imaging (spanning the UV, visible, and NIR regions, to simultaneously capture both spatial distribution and spectral signatures of sample constituents), terahertz spectroscopy, and nuclear magnetic resonance (NMR), along with their transformative applications. We systematically elucidate the fundamental principles and distinctive merits of each technological approach, with a particular focus on their deep learning-based integration with spectral fusion techniques and hybrid spectral-heterogeneous fusion methodologies. Our analysis reveals that the synergy between spectroscopic technologies and deep learning demonstrates unparalleled superiority in speed, precision, and non-invasiveness. Future research should prioritize three directions: multimodal integration of spectroscopic technologies, edge computing in portable devices, and AI-driven applications, ultimately establishing a high-precision and sustainable food quality inspection system spanning from production to consumption. Full article

The development of inter-well channeling pathways has become a major challenge restricting the effectiveness of the thermal recovery process for heavy oil reservoirs, which leads to non-uniform sweep and reduced oil recovery. This is especially true for the characteristics of the higher injection–production intensity in offshore operations, making the issue more prominent. In this study, a quick and widely applicable approach is proposed for channeling identification, utilizing the static reservoir parameters and injection–production performance. The results show that the cumulative injection–production pressure differential (CIPPD) over the cumulative water equivalent (CWE) exhibits a linear relationship when connectivity exists between the injection and production wells. Thereafter, the seepage resistance could be analyzed quantitatively by the slope of the linear relationship during the steam injection process. Simultaneously, a channeling identification chart could be obtained based on the data of injection–production performance, dividing the steam flooding process into three different stages, including the energy recharge zone, interference zone, and channeling zone. Then, the established channeling identification chart is applied to injection–production data from two typical wells in the Bohai oilfield. From the obtained channeling identification chart, it is shown that Well X1 exhibits no channeling, while Well X2 exhibited channeling in the late stage of the steam flooding process. These findings are validated against the field performance (i.e., the liquid rate, water cut, flowing temperature, and flowing pressure) to confirm the accuracy. The channeling identification approach in this paper provides a guide for operational adjustments to improve the effect of the thermal recovery process in the field. Full article

Fully mechanized mining involves high energy consumption, particularly during cutting and transportation. Scraper conveyors, crucial for coal transport, face energy efficiency challenges due to the lack of accurate dynamic coal flow models, which restricts precise energy estimation and optimization. This study constructs dynamic coal flow and scraper conveyor energy efficiency models to analyze the impact of multiple variables on energy consumption and lump coal rate. A dynamic coal flow model is developed through theoretical derivation and EDEM simulations, validated for parameter settings, boundary conditions, and numerical methods. The multi-objective optimization model for energy consumption is solved using the NSGA-II-ARSBX algorithm, yielding a 33.7% reduction in energy consumption, while the lump coal area is reduced by 27.7%, indicating a trade-off between energy efficiency and coal fragmentation. The analysis shows that increasing traction speed while decreasing scraper chain and drum speeds effectively lowers energy consumption. Conversely, simultaneously increasing both chain and drum speeds helps to maintain lump coal size. The final optimization scheme demonstrates this balance—achieving improved energy efficiency at the cost of increased coal fragmentation. Additional results reveal that decreasing traction speed while increasing chain and drum speeds results in higher energy consumption, while increasing traction speed and reducing chain/drum speeds minimizes energy use but may negatively affect lump coal integrity. Full article

Remaining useful life (RUL) prediction of cutting tools plays an important role in modern manufacturing because it provides the criterion used in decisions to replace worn cutting tools just in time so that machining deficiency and unnecessary costs will be restrained. However, the performance of existing deep learning algorithms is limited due to the smaller quantity and low quality of labeled training datasets, because it is costly and time-consuming to build such datasets. A large amount of unlabeled data in practical machining processes is underutilized. To solve this issue, an unlabeled-data-enhanced tool RUL prediction method is proposed to make full use of the abundant accessible unlabeled data. This paper proposes a novel and effective method for utilizing unlabeled data. This paper defines a custom criterion and loss function to train on unlabeled data, thereby utilizing the valuable information contained in these unlabeled data for tool RUL prediction. The physical rule that tool wear increases with the increasing number of cuts is employed to learn knowledge crucial for tool RUL prediction from unlabeled data. Model parameters trained on unlabeled data contain this knowledge. This paper then transfers the parameters through transfer learning to another model based on labeled data for tool RUL prediction, thus completing unlabeled data enhancement. Since multiple sensors are frequently used to simultaneously collect cutting data, this paper uses a graph neural network (GNN) for multi-sensor data fusion, extracting more useful information from the data to improve unlabeled data enhancement. Through multiple sets of comparative experiments and validation, the proposed method effectively enhances the accuracy and generalization capability of the RUL prediction model for cutting tools by utilizing unlabeled data. Full article

Heating, ventilation, and air-conditioning systems account for 40–60% of the energy consumed in commercial buildings, and much of this load originates from sub-optimal piping layouts in chiller-plant rooms. This study presents an automated routing framework that couples Building Information Modeling (BIM) with an enhanced A* search to produce collision-free, low-resistance pipelines while simultaneously guiding component selection. The algorithm embeds protective buffer zones around equipment, reserves maintenance corridors through an attention-based cost term, and prioritizes 135° elbows to cut local losses. Generated paths are exported as Industry Foundation Classes (IFC) objects for validation in a BIM digital twin, where hydraulic feedback drives iterative reselection of high-efficiency devices—including magnetic-bearing chillers, cartridge filters and tilted-disc valves—until global pressure drop and life-cycle cost are minimized. In a full-scale shopping-mall retrofit, the method significantly reduces pipeline resistance and operating costs, confirming its effectiveness and replicability for sustainable chiller-plant design. Full article

Population ageing is revealing acute mismatches between inherited village layouts and older residents’ everyday needs in China’s peri-urban fringe. This study combines space-syntax diagnostics with an exploratory factor analysis to create a building-oriented retrofit workflow. Using Liulin Village, Beijing, as a test bed, axial-line modelling pinpoints the low-integration alleys and mono-functional retail strips, while elder-user surveys distil four latent demand factors, led by personal convenience. Overlaying these two layers highlights the “high-demand/low-fit” segments for intervention. Prefabricated 3 m × 6 m health kiosks, sunrooms and rest pergolas—constructed from light-gauge steel frames and assembled with dry joints—are then inserted along a newly permeated corridor–core walking loop. The modules follow a 600 mm dimensional grid and can be installed or removed within a single working day, cutting the on-site labour by roughly one-third relative to that required for conventional masonry kiosks and enabling their future relocation or reuse. The workflow shows how small-scale, low-carbon building interventions can simultaneously improve accessibility, social interaction and functional diversity, providing a transferable template for ageing-responsive public-space retrofits in rapidly transforming village contexts. Full article

The accelerating global demand for sustainable and efficient energy storage has driven substantial interest in supercapacitor technology due to its superior power density, fast charge–discharge capability, and long cycle life. However, the low energy density of supercapacitors remains a key bottleneck, limiting their broader application. This review provides a comprehensive and focused overview of the latest breakthroughs in supercapacitor research, emphasizing strategies to overcome this limitation through advanced material engineering and device design. We explore cutting-edge developments in electrode materials, including carbon-based nanostructures, metal oxides, redox-active polymers, and emerging frameworks such as metal–organic frameworks (MOFs) and covalent organic frameworks (COFs). These materials offer high surface area, tunable porosity, and enhanced conductivity, which collectively improve the electrochemical performance. Additionally, recent advances in electrolyte systems—ranging from aqueous to ionic liquids and organic electrolytes—are critically assessed for their role in expanding the operating voltage window and enhancing device stability. The review also highlights innovations in device architectures, such as hybrid, asymmetric, and flexible supercapacitor configurations, that contribute to the simultaneous improvement of energy and power densities. We identify persistent challenges in scaling up nanomaterial synthesis, maintaining long-term operational stability, and integrating materials into practical energy systems. By synthesizing these state-of-the-art advancements, this review outlines a roadmap for next-generation supercapacitors and presents novel perspectives on the synergistic integration of materials, electrolytes, and device engineering. These insights aim to guide future research toward realizing high-energy, high-efficiency, and scalable supercapacitor systems suitable for applications in electric vehicles, renewable energy storage, and next-generation portable electronics. Full article