Hybrid Mechanism Research Articles

Interface characteristics and fracture mechanism of laser-arc hybrid welded Al-Ti dissimilar butt-joint through beam oscillation

Two laser oscillating patterns including circle and inscribed double-circle were adopted for the laser-arc hybrid welding of Al-Ti dissimilar butt-joint, and compared with the none-oscillating hybrid welding. The results showed that a two-layer intermetallic compounds (IMCs) including Al3Ti and Al2Ti was formed at the Al-Ti interface without laser oscillation, and the thickness (τ) of IMCs layer reached up to 5.56 μm. The IMCs layer was transferred to a single-layer Al2Ti with decreased the τ to 1.18 μm by the optimized inscribed double-circle oscillating hybrid welding. The optimized laser oscillation benefited to form local turbulences inside the molten pool, which optimized the composition of interface IMCs layer and effectively reduced its thickness. Due to the combined improvements, the ultimate tensile strength of Al-Ti dissimilar butt-joint was increased by 18% from 182.6 to 215 MPa. The corresponding tensile fracture of welded joint changed from the two-layer IMCs layer to the base metal. Because no orientation relationship between them along the Al3Ti/ Al2Ti was formed, the tensile crack preferentially propagated between the Al3Ti and Al2Ti IMCs at the interface, resulting in the poor tensile properties.

Solid/liquid hybrid lubrication behaviors of amorphous carbon film coupling with nonpolar and polar base oils

The amorphous carbon film (a-C) has aroused intensive interest in solid-oil hybrid lubrication design due to its low friction, high wear resistance, and good chemical inertness. However, the solid/liquid hybrid lubrication behaviors and mechanisms of a-C films when coupled with nonpolar and polar oils of similar viscosity are still insufficiently understood and ambiguous to date. In this study, we compared the lubrication properties of nonpolar paraffin oil and polar polyether oils with different molecular structures when combined with a-C film. The results demonstrated that the lubrication performance of polyether oils coupled with a-C film surpassed that of paraffin oil across various lubrication regimes. Notably, the stable superlubricity (friction coefficient<0.01) was achieved under mixed lubrication regime on the a-C film when coupled with polyethylene glycol (PEG) oil after a prolonged sliding duration. The tribo-induced formation of carbon quantum dots (CQDs) at the steel/a-C friction interface lubricated by PEG oils was firstly observed. The hydroxylation of the counter ball surface and the fabrication of CQDs might jointly contribute to the achievement of the robust superlubricity of the PEG oil/a-C film hybrid lubrication system.

A Biomimetic Nociceptor Based on a Vertical Multigate, Multichannel Neuromorphic Transistor.

Nociceptors, crucial sensory receptors within biological systems, are essential for survival in diverse and potentially hazardous environments. Efforts to replicate nociceptors through advanced electronic devices, such as memristors and neuromorphic transistors, have achieved limited success, capturing basic nociceptive functions while more advanced characteristics like various forms of central sensitization and analgesic effect remain out of reach. Here, we introduce a vertical multigate, multichannel electrolyte-gated transistor (Vm-EGT), designed to mimic nociceptors. Utilizing the hybrid mechanism combining electric-double-layer (EDL) with ion intercalation/deintercalation in EGTs, our approach successfully replicates peripheral sensitization and desensitization characteristics of nociceptors. The intricate multigate and multichannel design of the Vm-EGT enables the emulation of more advanced nociceptive functionalities, including central sensitization and analgesic effect. Furthermore, we demonstrate that by exploiting the inherent current-voltage relationship, the Vm-EGT can simulate these advanced nociceptive features and seamlessly transition between them. Integrating a Vm-EGT with a thermistor and a heating plate, we have developed an artificial thermal nociceptor that closely mirrors the sensory attributes of its biological counterpart. Our approach significantly advances the emulation of nociceptors, providing a basis for the development of sophisticated artificial sensory systems and intelligent robotics.

Facile nanofabrication and simultaneous color-and-Raman hybrid mechanism of economic SERS substrate with tunable structure color for high enhancement factor

The conventional SERS technique utilizing metal nanoparticles (MNPs) is a powerful optical sensing method, relying on the inelastic collision between incident light and the analyte. However, the development of traditional color-tunable MNP-SERS substrates remains limited to two separate components of the color supporter for generating structure color and followed by the MNPs coating to generate the localized surface plasmonic resonance for SERS sensing. Here, a novel color-tunable SERS substrate without MNPs based on the economic one-step anodic aluminum oxide (AAO) coated with nanoporous Pt films was proposed to generate the color-and-Raman hybrid effect for high enhancement factor. This novel SERS substrate employs an economic method, that is a facile and low-cost one-step anodization process to fabricate the AAO with tunable structure color, enabling adaptation to excitation of laser sources. The substrate with the lowest reflectance to laser light exhibits the highest enhancement factor due to the coupling between the laser and the substrate. The resultant SERS substrate demonstrates a high enhancement factor (EF) of 5.27x105 to methylene blue with a good uniformity of the relative standard deviation (RSD) of 6.35 %. In a practical application, one of preservative, benzoic acid, was detected with a low concentration of 1 ppm in the extraction solution of tapioca balls. This innovative approach promotes limitations associated with traditional color-tunable SERS substrates and offers a promising path for sensitive and versatile trace substance detection.

Design and analysis of a thick-panel origami-inspired soft crawling robot with multiple locomotion patterns

Abstract Due to the flexibility obtained through both materials and structures, soft robots have wide potential applications in complicated internal and external environments. This paper presents a new soft crawling robot with multiple locomotion patterns that integrate inchworm motion and various turning motions. First, the conceptual design of the proposed robot is presented by introducing thick-panel origami into the synthesis of a crawling robot, resulting in a Waterbomb-structure-inspired hybrid mechanism. Second, all locomotion patterns of the robot are precisely described and analyzed by screw theory in an algebraic manner, which include inchworm motion, restricted planar motion, quantitative turning motion, and marginal exploration motion. Then, the output motion parameter for each locomotion pattern is analytically modeled as a function of the robotic dimensional parameters, and the robot can thus be designed and controlled in a customized way for the expected output motion. Finally, the theoretical analysis and derivations are validated by simulation and physical prototype building, which lay the foundations for the design and manufacture of small-scale soft crawling robots with precise output motions in a complex planar environment.

A Hybrid Mechanism Metasurface Based on Absorption and Phase Cancellation for Ultra‐Wideband RCS Reduction

AbstractThis paper proposes a hybrid mechanism based on phase cancellation and absorption to design a metasurface with ultra‐wideband 10 dB radar cross‐section (RCS) reduction from 6 to 64.7 GHz (171%). At high frequencies of 15–64.7 GHz, 10 dB RCS reduction is achieved by a phase cancellation mechanism, which is realized by arranging a perfect electric conductor (PEC) to form an arrayed structure with varying heights. At low frequencies of 6–15 GHz, 10 dB RCS reduction is achieved by the absorption mechanism, which is realized by designing a rotationally symmetric dual‐pattern absorber. The coupled mode theory (CMT) is used to explain the absorption mechanism. Additionally, it is found that a 180° phase difference is obtained by two different patterns to enhance RCS reduction in the high‐frequency band of 28–35 GHz. Finally, the phase cancellation and absorption mechanisms are combined to achieve an ultra‐wideband 10 dB RCS reduction from 6 to 64.7 GHz, which is realized by integrating the absorber into the arrayed structure to form the ultra‐wideband RCS reduction metasurface. The designed metasurface has a compact size (subwavelength), and a thin profile with 0.105λL.

A Hybrid Mechanism and Data‐Driven Approach for Predicting Fatigue Life of MEMS Devices by Physics‐Informed Neural Networks

ABSTRACTOur research group has focused on the long‐term performance degradation of micro‐electro‐mechanical systems (MEMS) devices under mechanical, thermal, and electrical stresses. We previously used physics‐based models for performance prediction, but the diverse materials, structures, and environmental conditions of MEMS devices affect their long‐term stability. Traditional physics‐based models struggle to account for these factors, limiting practical application. To address this, we employ data‐driven methods to include more variables. This paper introduces a hybrid approach combining physical principles with data‐driven techniques, specifically physics‐informed neural networks (PINN), to model and analyze performance degradation in MEMS resonators. We compare this method with previous physics‐based and data‐driven approaches (support vector machine and random forest) under identical conditions. The hybrid method not only provides accurate predictions but also considers more operating conditions, enhancing practical application.

Mechanisms of Controllable Growth and Ohmic Contact of Two-Dimensional Molybdenum Disulfide: Insight from Atomistic Simulations.

ConspectusTwo-dimensional (2D) semiconducting transition metal dichalcogenides (TMDs), in particular molybdenum disulfide (MoS2), have recently attracted huge interest due to their proper bandgap, high mobility at 2D limit, and easy-to-integrate planar structure, which are very promising for extending Moore's law in postsilicon electronics technology. Great effort has been devoted toward such a goal since the demonstration of protype MoS2 devices with high room-temperature on/off current ratios, ultralow standby power consumption, and atomic level scaling capacity down to sub-1-nm technology node. However, there are still several key challenges that need to be addressed prior to the real application of MoS2-based electronics technology. The controllable growth of wafer-scale single-crystal MoS2 on industry-compatible insulating substrates is the prerequisite of application while the currently synthesized MoS2 films mostly are polycrystalline with limited sizes of single-crystal domains and may involve metal substrates. The precise layer-control is also very important for MoS2 growth since its electronic properties are layer-dependent, whereas the layer-by-layer growth of multilayer MoS2 dominated by the van der Waals (vdW) epitaxy leads to poor thickness uniformity and noncontinuously distributed domains. High density up to 1013 cm-2 of sulfur vacancies (SVs) in grown MoS2 can cause unfavorable carrier scatting and electronic properties variations and will inevitably disturb the device performance. The dangling-bond-free surface of MoS2 gives rise to an inherent vdW gap at metal-semiconductor (M-S) contact, which leads to high electrical resistance and poor current-delivery capability at the contact interface and thereby substantially limits the performances of MoS2 devices.In this Account, we briefly review recent experimental and theoretical attempts for addressing the aforementioned challenges and present our own insights from atomistic simulations. We theoretically revealed the vital role of substrate steps for guiding unidirectional nucleation of monolayer MoS2 and uniform nucleation and edge-aligned growth of bilayer MoS2 by advanced simulations. The established thermodynamic mechanisms have successfully directed the experimental works on the controllable growth of 2 in. single-crystal monolayer and centimeter-scale uniform bilayer MoS2. The postgrowth repair mechanism of SV defect in MoS2 via thiol chemistry treatment has been theoretically explored with the consideration of side reaction of surface functionalization to help experimentally reduce SV defect density by 75%. Beyond the atomic level understanding, theoretical simulations proposed the electronic states hybridization mechanism across the semimetal-MoS2 vdW interface, thereby guiding experimental effort for realizing Ohmic contact at the MoS2-Sb(0112) vdW interface with record-low contact resistance.These advances provide a sound basis with an atomic-level understanding for addressing the related issues. However, there are still notable gaps in terms of system size and time scale of dynamics between atomistic simulations and experimental observations for the studies of MoS2 growth and interfaces. The combination of multiscale simulations and artificial intelligence technology is expected to narrow these gaps and provide a more insightful understanding of the controllable growth and interfacial properties modulation of MoS2. We conclude the Account with the standing challenges and outlook on future research directions from the theoretical perspective.

Three-Dimensional Flexible SnO2@Hard Carbon@MoS2@Soft Carbon Fiber Film Anode toward Ultrafast and Stable Sodium Storage.

Developing flexible electrodes for the application in sodium-ion batteries (SIBs) has received great attention and has been still challenging due to their merits of additive-free, lightweight, and high energy density. In this work, a free-standing 3D flexible SIB anode with the composition of SnO2@hard carbon@MoS2@soft carbon is designed and successfully synthesized. This electrode combines the energy storage advantages and hybrid sodium storage mechanisms of each material, manifested in the enhanced flexibility, specific capacity, conductivity, rate, cycling performances, etc. Based on the synergistic effects, it exhibits much higher specific capacity than SnO2 carbon nanofibers, as well as more excellent cycling performance (250 mA h g-1 after 500 cycles at 1 A g-1) than MoS2 nanospheres (32 mA h g-1). In addition, relevant kinetic mechanisms are also expounded with the aid of theoretical calculation. This work provides a feasible and advantageous strategy for constructing high-performance and flexible energy storage electrodes based on hybrid mechanisms and synergistic effects.

Tribological performance and mechanism of the titanium fiber-SiC whisker hybrid reinforced aluminum matrix composites prepared by pressure infiltration

In this contribution, a Ti-6Al-4V fiber (Tif) and SiCw (SiCw) hybrid reinforced 5056 Al composites (Tif + SiCw/5056 Al) were fabricated, and the effects of SiC whisker contents on the microstructure, mechanical properties, and wear resistance were investigated. The mechanical properties and the hardness of the composites increased first and then decreased with the increase of SiCw contents. The optimal ratio of SiCw to titanium fibers is 3 wt%. The flexural strength of the optimal composites reached 533 MPa, and the fracture toughness reached 29.1 MPa • m1/2. Under a load of 40 N, compared with the Tif/5056 Al composites sample, the wear rate of the optimal composites sample decreased by 80.7%. The uniformly dispersed SiC whiskers promote the formation of a mechanical mixing layer (MML) on the friction surface; the wear mechanism mainly involves abrasive wear and adhesive wear.

Kinematic analysis of 3-RSR&4R hybrid mechanism

Kinematic analysis of 3-RSR&4R hybrid mechanism

Strategically Modulating Proton Activity and Electric Double Layer Adsorption for Innovative All-Vanadium Aqueous Mn2+/Proton Hybrid Batteries.

Aqueous Mn-ion batteries (MIBs) exhibit a promising development potential due to their cost-effectiveness, high safety, and potential for high energy density. However, the development of MIBs is hindered by the lack of electrode materials capable of storing Mn2+ ions due to acidic manganese salt electrolytes and large ion radius. Herein, the tunnel-type structure of monoclinic VO2 nanorods to effectively store Mn2+ ions via a reversible (de)insertion chemistry for the first time is reported. Utilizing exhaustive in situ/ex situ multi-scale characterization techniques and theoretical calculations, the co-insertion process of Mn2+/proton is revealed, elucidating the capacity decay mechanism wherein high proton activity leads to irreversible dissolution loss of vanadium species. Further, the Grotthuss transfer mechanism of protons is broken via a hydrogen bond reconstruction strategy while achieving the modulation of the electric double-layer structure, which effectively suppresses the electrode interface proton activity. Consequently, the VO2 demonstrates excellent electrochemical performance at both ambient temperatures and -20°C, especially maintaining a high capacity of 162mAhg-1 at 5Ag-1 after a record-breaking 20000 cycles. Notably, the all-vanadium symmetric pouch cells are successfully assembled for the first time based on the "rocking-chair" Mn2+/proton hybrid mechanism, demonstrating the practical application potential.

Exploration of Time-Fractional Cancer Tumor Models with Variable Cell Killing Rates via Hybrid Algorithm

Abstract Cancer is marked by abnormal cell growth that invades healthy tissues, potentially spreading throughout the body through the bloodstream or lymphatic system. It arises when body cells show irregularities in the genes that control cell growth. To treat and minimize the growth of these abnormal cells, different models have been proposed to predict and analyze cancer-tumor. The current study contains analysis of fractional cancer-tumor with different uncertain conditions. To include the uncertainties in the model, Pentagonal fuzzy numbers (PFNs) approach is utilized. A hybrid mechanism, combining homotopies with perturbation technique and a generalized integral transform, is proposed to efficiently handle fractional derivatives with fuzzified conditions. The validity of obtained solutions is checked by calculating residual errors. Graphical analysis assesses the impact of important parameters on the solution profiles, and confirms the reliability of the proposed methodology for complex fractional tumor models and other intricate physical phenomena.

Deformation mechanism and life prediction model of titanium alloy laser-arc hybrid welded joint during fatigue

The deformation mechanism and life prediction model of titanium alloy laser-arc hybrid welded joint during fatigue were studied. At the relatively small maximum cyclic stresses σmax (310 MPa to 350 MPa), the fatigue cracks initiated at the interface of lamellar α′ and needle-like α′ around the pore. At σmax=370MPa, the elongated lamellar α′ around the pore promoted fatigue crack propagation, leading to the formation of secondary cracks. At σmax=390MPa, the formation of two fatigue crack initiation locations and the occurrence of secondary cracks led to the maximum fatigue damage and the minimum fatigue life. In addition, the plastic deformation mainly occurred in β at σmax=310MPa, and it transformed into the phase interface of secondary α-β and granular β-α′ at σmax=350MPa. At σmax=390MPa, the main deformation forms were the cross-slip in β and the dislocations entanglement in α′. Finally, the fatigue life prediction model was established based on the equivalent cyclic stress, and the predicted fatigue life fell within a 3-fold error band.

Clinical decision support system using hierarchical fuzzy diagnosis model for migraine and tension-type headache based on International Classification of Headache Disorders, 3rd edition.

To determine whether the diagnostic ability of the newly designed hierarchical fuzzy diagnosis method is consistent with that of headache experts for probable migraine (PM) and probable tension-type headache (PTTH). Clinical decision support systems (CDSS) are computer systems designed to help doctors to make clinician decisions by information technology, and have proven to be effective in improving headache diagnosis by making medical knowledge readily available to users in some studies. However, one serious drawback is that the CDSS lacks the ability to deal with some fuzzy boundaries of the headache features utilized in diagnostic criteria, which might be caused by patients' recall bias and subjective bias. A hybrid mechanism of rule-based reasoning and hierarchical fuzzy diagnosis method based on International Classification of Headache Disorders, 3rd edition (ICHD-3) was designed and then validated by a retrospective study with 325 consecutive patients and a prospective study with 380 patients who were clinically diagnosed with migraine and TTH at the headache clinic of Chinese PLA General Hospital. The results of the diagnostic test in the retrospective study indicated that the fuzzy-based CDSS can be used in the diagnosis of migraine without aura (MO) (sensitivity 97.71%, specificity 100%), TTH (sensitivity 98.57%, specificity 100%), PM (sensitivity 91.25%, specificity 98.75%) and PTTH (sensitivity 90.91%, specificity 99.63%). While in the prospective study, the diagnostic performances were MO (sensitivity 91.62%, specificity 96.52%), TTH (sensitivity 92.17%, specificity 95.47%), PM (sensitivity 85.48%, specificity 98.11%) and PTTH (sensitivity 87.50%, specificity 98.60%). Cohen's kappa values for the consistency test were 0.984 ± 0.018 (MO), 0.991 ± 0.018 (TTH), 0.916 ± 0.051 (PM), 0.932 ± 0.059 (PTTH) in the retrospective study and 0.884 ± 0.047 (MO), 0.870 ± 0.055 (TTH), 0.853 ± 0.073 (PM), 0.827 ± 0.118 (PTTH) in the prospective study, which indicated good consistency with the fuzzy-based CDSS and the gold standard (p < 0.001). We developed a fuzzy-based CDSS performs much more similarly to expert diagnosis and performs better than the routine CDSS method in the diagnosis of migraine and TTH, and it could promote the application of artificial intelligence in the area of headache diagnosis.

Evaluation of Axial Compressive and Tensile Properties of PE/PVA Hybrid Fiber Reinforced Strain-Hardening Geopolymer Composites.

The strain-hardening geopolymer composite (SHGC) is a new type of fiber concrete with excellent ductility and environmental friendliness. However, the high cost of fibers greatly limits its widespread application. This paper proposes the use of untreated low-cost polyvinyl alcohol (PVA) fibers and polyethylene (PE) fibers to develop a low-cost, high-performance SHGC. Axial compression and axial tension tests were conducted on the SHGC with different PE fiber volume fractions (1%, 1.5%, and 2%) and different PVA fiber replacement ratios (0%, 25%, 50%, 75%, and 100%) to investigate the hybrid effects of fibers with different surface properties and to reveal the mechanism of fiber hybridization on the mechanical behavior of SHGCs. The results show that increasing the PE fiber volume fraction improves the compressive and tensile ductility of the SHGC while increasing the PVA fiber replacement rate impacts the strength indicators positively due to the good interface effect formed between its hydrophilic surface and the matrix. When the PVA fiber replacement ratio is 100%, the compressive strength (93.4 MPa) of the SHGC is the highest, with a 21.1% increase compared to the control group. However, the tensile strength shows a trend of first increasing and then decreasing with the increase in the PVA fiber replacement ratio, reaching the highest at a 25% replacement ratio, with a 12.5% increase compared to the control group. Furthermore, a comprehensive analysis of the economic and environmental performance of the SHGC indicates that a 25% PVA fiber replacement ratio results in the best overall economic benefits and relatively low actual costs, although the effect of fiber hybridization on carbon emission indicators is not significant. This paper provides new ideas and a theoretical basis for designing low-cost SHGCs.

Machine learning assisted mechanism modeling for gas phase electrohydrodynamic system

In this paper, a hybrid physics-data driven model for electrohydrodynamic gas system (EHDGS) was developed by combining artificial neural network (ANN) with mechanism modeling method. ANN was used to correlate the relationship between the variables (electrode distance, diameter of grounding cylinder, applied voltage, electric field gradient, etc.) in a needle-cylinder EHDGS and the initial space charge density. The results showed that the ANN model of nine neurons can well predict the initial space charge density. The coefficient of determination (R2) reaches 0.9874, and the mean absolute error is as low as 0.0067. Subsequently, a hybrid mechanism model where the initial space charge density was predicted from the ANN model was constructed to simulate the needle-cylinder EHDGS. The experiment with the needle-cylinder EHDGS was carried out. The simulation results were in good agreement with the experimental data, demonstrating the reliability of the proposed hybrid model. The electric field distribution, space charge distribution, and flow field distribution behavior of the EHDGS were then analyzed in detail. The effects of key parameters on the flow characteristics of EHDGS were systematically studied, showing that higher voltage and shorter distance give higher flow rate up to 2.5 m/s. The diameter of the cylinder also significantly influences the breakdown voltage. Three dimensionless groups were defined and their effects on spatial charge density distribution were investigated. This study provides both insights and an efficient tool for the design and optimization of EHDGS.

Research on the supporting mechanism of internal feedback hydrostatic hybrid bearing considering flow rate correction

The internal feedback hydrostatic bearing features a distinctive structural design, playing a pivotal role in high-precision machine tools. Its performance significantly influences the improvement of machining accuracy and stiffness. In this study, the working principle of the internal feedback closed hydrostatic bearing is described, the equivalent liquid resistance model of oil circuit considering internal flow effect is established, an analysis method for evaluating the support performance of the internal feedback hydrostatic bearing is proposed, flow rate correction methods are proposed, and the influence of load-carrying capacity and flow rate due to inlet pressure, oil film thickness, and the size of the restrictor is discussed. The accuracy of the method is verified by simulation, and insights for the future development of hydrostatic bearings are provided.

VSmTrans: A hybrid paradigm integrating self-attention and convolution for 3D medical image segmentation

PurposeVision Transformers recently achieved a competitive performance compared with CNNs due to their excellent capability of learning global representation. However, there are two major challenges when applying them to 3D image segmentation: i) Because of the large size of 3D medical images, comprehensive global information is hard to capture due to the enormous computational costs. ii) Insufficient local inductive bias in Transformers affects the ability to segment detailed features such as ambiguous and subtly defined boundaries. Hence, to apply the Vision Transformer mechanism in the medical image segmentation field, the above challenges need to be overcome adequately. MethodsWe propose a hybrid paradigm, called Variable-Shape Mixed Transformer (VSmTrans), that integrates self-attention and convolution and can enjoy the benefits of free learning of both complex relationships from the self-attention mechanism and the local prior knowledge from convolution. Specifically, we designed a Variable-Shape self-attention mechanism, which can rapidly expand the receptive field without extra computing cost and achieve a good trade-off between global awareness and local details. In addition, the parallel convolution paradigm introduces strong local inductive bias to facilitate the ability to excavate details. Meanwhile, a pair of learnable parameters can automatically adjust the importance of the above two paradigms. Extensive experiments were conducted on two public medical image datasets with different modalities: the AMOS CT dataset and the BraTS2021 MRI dataset. ResultsOur method achieves the best average Dice scores of 88.3 % and 89.7 % on these datasets, which are superior to the previous state-of-the-art Swin Transformer-based and CNN-based architectures. A series of ablation experiments were also conducted to verify the efficiency of the proposed hybrid mechanism and the components and explore the effectiveness of those key parameters in VSmTrans. ConclusionsThe proposed hybrid Transformer-based backbone network for 3D medical image segmentation can tightly integrate self-attention and convolution to exploit the advantages of these two paradigms. The experimental results demonstrate our method's superiority compared to other state-of-the-art methods. The hybrid paradigm seems to be most appropriate to the medical image segmentation field. The ablation experiments also demonstrate that the proposed hybrid mechanism can effectively balance large receptive fields with local inductive biases, resulting in highly accurate segmentation results, especially in capturing details. Our code is available at https://github.com/qingze-bai/VSmTrans.

A simple load model based on hybrid mechanism and data-driven approach for district heating in building complex

Accurate prediction of heating loads in district heating systems is essential for the implementation of demand-driven heating. This work presents a novel heating load prediction model that is particularly suitable for complex multi-user buildings. The input characteristics of the model are established through the heat transfer mechanism, considering factors such as the cumulative impact of outdoor temperature and user demand (indoor temperature). The specific form of the heating load function is determined using the MLR-PSO (Multiple Linear Regression-Particle Swarm Optimization) method. Only the indoor and outdoor temperatures need to be provided for the model to calculate future heating loads. Practical engineering tests demonstrated that the model achieved normalized mean bias errors of daily loads between 4.98 % and 5.54 % across different heating seasons, with a minimum annual relative deviation of 0.75 % for annual loads. Additionally, the model helps guide the operation of heating systems. For example, during the 2021–2022 heating season, setting the target indoor temperature at 18 °C reduced weekly energy consumption by 15.3 % compared to the previous season. This approach may be employed to construct a simple load model for existing heating systems to accurately predict both short-term and long-term loads, providing valuable insights into the management and control of heating systems.