Engineering

Abstract: As a third-generation semiconductor material, indium phosphide (InP) exhibits complex anisotropic etching characteristics, showing significantly varying etching morphologies under different temperature, concentration, and surfactant conditions. This complexity poses challenges in controlling the etching evolution process and predicting its three-dimensional structures. To address the simulation of InP etching structures and surface morphology, this study first establishes an atomic model of the InP etching system and analyzes how different atomic structures influence crystal plane etching rates. Subsequently, based on the microscopic activation energy theory, we propose an atomic removal determination function (InP-RPF) for InP etching substrates, numerically elucidating the relationship between macroscopic crystal plane etching rates and microscopic atomic removal probabilities. Furthermore, we develop an evolutionary Monte Carlo etching system model (InP-EMC), employing evolutionary algorithms to continuously optimize the energy parameters in the InP-RPF function, thereby adjusting the removal probabilities of various atomic types on the substrate and validating the simulated etching rates. Experimental comparisons demonstrate that the InP-EMC model accurately constrains atomic removal probabilities using limited crystal plane etching rate data, achieving simulation accuracy exceeding 90% for full-crystal-plane etching rates, mask etching structures, and surface morphology characteristics.

Abstract: Diffusers in diffuser-augmented wind turbines (DAWTs) require high-camber airfoils operating at low Reynolds numbers (Re) and its laminar separation bubbles significantly complicate aerodynamic predictions. This study provides an experimental and numerical data for a custom-designed airfoil tested at Re = 68k–159k and angles of attack α = 0°–17.5°. Lift, drag, and pressure coefficient (C_p) distributions were measured experimentally. The XFOIL, the fully turbulent 3D k-ω SST, and the γ-Re_θ transition RANS models were validated against the experimental data using multiple quantitative metrics. The γ-Re_θ model demonstrated superior performance, achieving lift Maximum Absolute Percent Error of 1.6–3.4%, near-zero bias, and coefficient of determination > 0.99. It accurately captured the laminar separation bubble pressure plateau at mid-chord, with mean gross-averaged C_p percent errors of 8.1% and 2.1% for upper and lower surfaces, respectively. In contrast, the k-ω SST model overpredicted lift by up to +9.8% at Re = 68k and underpredicted drag by up to 66%. XFOIL showed poor reliability in transitional flow regimes. Sensitivity analyses confirmed the robustness of the γ-Re_θ model across the tested Re and α ranges. The generated experimental dataset, combined with the validated transition-sensitive RANS approach, provides a strong foundation for low-Re airfoil and DAWT diffuser design. Future work should extend experimental measurement below Re = 5x10⁴ and above 2x10⁵, including post-stall conditions and system level designing.

Abstract: The recycling of polyethylene terephthalate (PET) is gaining increasing importance, as it enables the conversion of plastic waste into valuable raw materials and contributes to a circular economy. Recent research has primarily focused on optimizing the depolymerization step of PET glycolysis, while downstream processes often overlooking the at least equally critical downstream steps in recovering the monomer bis(2-hydroxyethyl) terephthalate (BHET). The implementation of a water‑free PET glycolysis process eliminates challenges related to internal solvent and homogeneous catalyst recycling that commonly occur in conventional processes. This study therefore focuses on BHET crystallization and filtration as key downstream unit operations. Two nucleation strategies, gassing and seeding, were investigated and compared with experiments without a nucleation strategy. The aim was to achieve reproducible process control during crystallization and to obtain crystals with good filterability, which is essential for efficient washing and high product purity. Experiments without a nucleation strategy showed poor reproducibility. In contrast, gassing and seeding improved crystallization control, particularly regarding nucleation temperature and relative crystallization yield. However, these strategies also resulted in significantly prolonged filtration times due to differences in filter cake properties. The anisotropic crystals exhibited a broad particle size distribution with a high fraction of fine particles, leading to small and heterogeneous pores in the filter cake. Limited crystal growth was identified as the main cause of the unfavorable filtration behavior.

Abstract: This study examines pedestrian perceptions of streetscapes in Isfahan’s cultural heritage site by integrating deep learning–based image segmentation with urban morphological analysis. Using a U-Net model applied to First-Person Pedestrian View (FPPV) images, five perceptual indices (imageability, enclosure, human scale, greenness, and walking index) were quantified to assess their influence on pedestrian experience. Street width was explicitly incorporated as a morphological variable to examine its relationship with perceptual qualities using spearman correlation analysis and visual trend analysis using Pearson correlation. The results reveal consistent relationships between visual composition and perceptual outcomes, particularly strong associations between imageability, enclosure, and vegetation structure, as well as trade-offs between enclosure and sky visibility. In contrast, variables such as human scale and walking index show weak or negligible associations with street width, suggesting that pedestrian presence and activity patterns in heritage contexts are more strongly influenced by landscape elements, water features, and spatial continuity than by dimensional factors alone. Findings highlight how urban renewal strategies, such as streetscape enhancement and cultural preservation, shape pedestrian movement and spatial perception. Segmentation-based analysis achieved an accuracy of 83% in classifying dominant streetscape elements, offering a robust alternative to traditional survey-based methods. This study contributes a data-driven framework for assessing pedestrian streetscapes, emphasizing morphological continuity, human-scale design, and green infrastructure as critical determinants of walkability. It also identifies key challenges, including fragmented spatial morphology and inconsistent urban furniture placement, which affect pedestrian comfort and use of space. These findings support evidence-based policy and design strategies for optimizing historic urban streetscapes, with implications for balancing heritage conservation and modern pedestrian needs. Future research may refine perceptual metrics and extend the approach across diverse urban contexts.

Abstract: The Sultanate of Oman enjoys plenty of solar energy and wind energy; both have been exploited successfully in the country. However, geothermal energy has not been exploited yet in Oman. This natural heat source deserves more studies to assess its technical potential and economic feasibility compared to other electricity generation technologies in Oman. The current study fills this gap by presenting a techno-economic assessment (TEA) of a small 30-MW geothermal power plant in Oman, operating on a binary (two-fluid) cycle, with a drilling depth of 2 km. The analysis was performed using the renowned software tool SAM (System Advisor Model) of the United States National Renewable Energy Laboratory (NREL). The current results suggest a levelized cost of energy (LCOE) of 8.68 cents/kWh (0.0868 US$/kWh) or 33.4 baisa/kWh (0.0334 OMR/kWh). When compared with electricity tariff or solar photovoltaic (PV) power purchase agreement (PPA) rates in Oman, it was found that geothermal-based electricity is too expensive. Furthermore, the estimated geothermal LCOE is more than three times the LCOE value of self-owned photovoltaic (PV) power systems in Oman, which is around 10 baisa/kWh (0.010 OMR/kWh). The estimated first-year electricity generation for the geothermal power plant model is 261.268 GWh/year, leading to a specific electricity generation of 8,709 kWh/kW/year. This is about five times the specific power generation from PV power plants. The study is augmented by sensitivity analyses and regression models to help understand the impact of multiple input parameters. The study provides novel results regarding decision-making for geothermal power investment in Oman.

Abstract: The rapid adoption of Wide Band Gap (WBG) and Ultra-Wide Band Gap (UWBG) semiconductor technologies, most notably Silicon Carbide (SiC) and Gallium Nitride (GaN), is reshaping wafer-level electrical testing beyond conventional silicon-based probing infrastructures.[1,2] Modern SiC devices require blocking voltage verification in the 650 V–3.3 kV range, extending beyond 6.5 kV, while GaN HEMTs operate with voltage slew rates exceeding 50–150 V/ns and current slew rates above 1–5 kA/µs. Un-der these conditions, probe cards evolve from passive interconnects into multi-physics systems coupling electrical, thermal, and mechanical domains.[3,4] Vertical MEMS probe card architectures enable high contact density, per-contact currents of 2–10 A (aggregated >1–3 kA), and loop inductance in the single-digit nanohenry range. This work analyzes probe-to-wafer contact physics, including constriction resistance (10–50mΩ) and wear under high current (>10⁵ A/cm²) and high-frequency conditions.[4] Electro-thermal limitations are discussed with focus on insulation integrity, partial discharge, di/dt-induced overshoot, and localized heating (>100–200 °C).[5,6,7] Emerging high-voltage solutions include ceramic insulation, controlled atmospheres, and on-board sensing. Wafer-level testing combines full-wafer screening with burn-in-like stress methodologies, where body diode characterization enables early defect detection in SiC devices. These results highlight the critical role of probe cards in WBG manufacturability and test reliability

Abstract: The aircraft is often difficult to be stably evaluated due to energy fluctuations in the final approach phase. The traditional single-parameter threshold monitoring method is difficult to capture the complex coupling relationship between dynamic energy and potential energy, and the adaptability is insufficient under variable meteorological disturbances. Therefore, this study proposes a new multi-dimensional prediction and evaluation method, which integrates energy management theory and deep learning technology, aiming to improve the early recognition ability of unstable approach under complex meteorological conditions and optimize the energy regulation ability. Firstly, a new stability evaluation framework is constructed from the perspective of energy. Two core evaluation parameters of ' energy altitude ' and ' balance energy ' are proposed. This method breaks the traditional way of monitoring speed and altitude parameters in isolation. In this paper, a dynamic safety boundary function is designed based on the principle of flight mechanics and civil aviation specifications. The function uses an altitude attenuation mechanism to make the boundary shrink smoothly with the decrease of flight altitude. At the same time, the sliding window statistics and balanced energy triggering mechanism are introduced, which significantly enhances the adaptability of the boundary to various disturbances and effectively overcomes the lag problem of static boundary response. By establishing a multi-dimensional parameter system with energy altitude and balance energy as the core, this study reveals the mechanism of dynamic energy potential energy coupling on approach stability. The hybrid dynamic boundary function realizes the collaborative optimization of physical constraints and data-driven. The research results provide a new theoretical paradigm for solving the evaluation of unstable approach under complex weather, and have important theoretical value and engineering application prospects for ensuring flight safety.

Abstract: Background/Objectives: Wearable technology is increasingly used to provide biofeedback in physical rehabilitation; however, there is no consensus on which biofeedback parameter is most clinically useful, as most studies evaluate only one arbitrarily selected parameter. This study presents a wearable multimodal biofeedback system integrating multiple parameters selected based on prior literature and evaluates its feasibility and explores potential changes in motor performance in rehabilitation context through a longitudinal post-stroke case study. Methods: The system integrates inertial and electromyographic sensors to monitor centre of mass (CoM-B), joint angle (ANG-B), and muscle activity (EMG-B), delivering real-time sensory cues (through augmented-reality glasses and an elastic vibrotactile band) based on the monitored parameters. Feasibility was assessed in a post-stroke participant (male, 32 years, 29 months post-stroke, left hemiparesis, Fugl–Meyer Lower Extremity Score = 27) across 15 sessions involving stand-to-sit, split-stance weight shifting, and walking tasks. Each task was practiced with all three biofeedback parameters, with five sessions per parameter. Results: The motor performance varied across biofeedback parameters and tasks. CoM-B was associated with favourable trends in motor performance during stand-to-sit, showing improvements in medio-lateral displacement (0.03/session); ANG-B during walking, increasing ankle dorsiflexion (1 deg/session); and EMG-B during weight shifting, increasing tibialis activation (5 µV/session). Conclusions: The findings highlight task-dependent variability in the ability of biofeedback to elicit favourable motor performance, suggesting that the choice of biofeedback parameters may need to be adapted to task demands. The system demonstrated high usability and feasibility, supporting its potential for post-stroke rehabilitation. Further studies are needed in larger populations.

Abstract: Simultaneous electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) provide complementary views of brain activity, capturing neural dynamics across temporal and spatial scales. Integrating these modalities offers a powerful approach for studying brain function, yet remains fundamentally challenging due to differences in measurement mechanisms, temporal resolution, and neurovascular coupling. At its core, EEG–fMRI fusion can be viewed as an inverse problem: the goal is to recover latent neural processes that are only partially observed through electrophysiological and hemodynamic signals. Here, we review data-driven fusion methods developed between 2000 and 2025, focusing on approaches that aim to identify shared neural representations across modalities. We organize the existing methods according to the fusion strategy (symmetric vs. asymmetric), the methodological objective (factorization vs. translation), and the modeling assumptions (linear vs. non-linear), and discuss commonly-used evaluation metrics and visualization strategies. We further examine evaluation strategies, highlighting the lack of a universal validation standard and the challenges of interpreting latent multimodal components. Across neurological, psychiatric, and cognitive applications, EEG-fMRI fusion has revealed distributed network dynamics that are not accessible through unimodal analyses. However, key challenges remain, including temporal misalignment, noise-induced coupling, and model-dependent interpretation. We discuss emerging directions such as nonlinear modeling, flexible coupling frameworks, and large-scale group-level fusion, which may enable more robust and interpretable multimodal integration. Together, this review reframes EEG-fMRI fusion as a problem of latent neural inference and outlines a path toward more principled, scalable, and biologically grounded approaches for understanding brain function and dysfunction.

Abstract: After leakage from buried hydrogen-blended natural gas pipelines, gas may seep through soil into enclosed spaces and form buoyancy-driven non-uniform combustible clouds. The effect of ignition delay on such clouds remains insufficiently understood, especially regarding the relationship between visible flame behavior and local thermal response. In this study, 44 soil-seepage combustion experiments were conducted in a 1.5 m × 1.5 m × 1.5 m enclosure. Methane and hydrogen concentrations at three heights, flame evolution, and transient temperatures were measured using gas sensors, high-speed imaging, and thermocouples. The ignition delay ranged from 27 s to 5429 s, with hydrogen blending ratios of 10–30 vol% and ignition positions at the floor, middle, and ceiling. The results show that longer ignition delays generally weakened visible flame luminosity and propagation extent. However, the peak temperature measured at the central thermocouple did not decrease accordingly. For the long-delay subset with td > 307 s, the central peak temperature increased with ignition delay, with R² = 0.74. Concentration measurements indicate that preferential hydrogen migration and slower methane redistribution continuously reconfigured the local flammability state before ignition. These findings suggest that, in enclosed soil-seepage HBNG scenarios, prolonged ignition delay may weaken visible flames but does not necessarily reduce local thermal exposure.

Abstract: As key lifting equipment in construction engineering, tower cranes (TCs) play a critical role in prefabricated buildings (PBs). However, current construction scheduling relies primarily on manual observation by operators and assistants and their experience to perform repetitive tasks, resulting in inefficiency, tediousness, and safety hazards. To enhance lean construction and management efficiency in PBs, this study proposes a scheduling model that comprehensively considers the initial hook position and the specific locations of prefabricated component (PC) supply and demand points. The model is then solved using particle swarm optimization (PSO). Optimization results clearly show that the operational times of two TCs are reduced by 23.94% and 12.16%, respectively, while their daily operating costs decrease by ¥207.29 and ¥293.96. Moreover, the overall construction cost of the PBs is lowered by 8.0%. These findings clearly demonstrate the effectiveness of the proposed model in significantly improving construction efficiency and promoting lean management in PBs.

Abstract: Imidacloprid (IMI), the commonly used neonicotinoid pesticide, has emerged as a persistent aquatic contaminant due to its high solubility and stability, posing risks to non-target organisms and ecosystem health. In this study, a MnZnFe₂O₄/SrWO₄ ferrite–tungstate nanocomposite was synthesized via a hydrothermal process and its ability to photocatalytically degrade IMI under UV light was assessed. SEM, XRD and FT-IR were used to characterize the composite to confirm its structural and morphological features. Photocatalytic performance was systematically investigated by examining the effects of operational factors, including initial pollutant concentration, catalyst dosage, pH, and irradiation time. The MnZnFe₂O₄/SrWO₄ nanocomposite exhibited significantly enhanced activity, achieving up to 87% degradation of IMI within 30 minutes at pH 9, outperforming individual components (SrWO₄: 37%; MnZnFe₂O₄: 75%) under identical conditions. The degradation kinetics followed a pseudo-first-order model consistent with the Langmuir–Hinshelwood mechanism. Effective interfacial charge transfer between the ferrite and tungstate phases, which promotes electron-hole recombination and increases the production of reactive species, is responsible for the enhanced performance. Furthermore, the composite demonstrated good stability and reusability across several cycles, indicating its practical applicability. Overall, the results demonstrate the potential of MnZnFe₂O₄/SrWO₄ nanocomposites as efficient and sustainable photocatalysts for removing imidacloprid and similar organic contaminants from aqueous systems.

Abstract: The growing demand for sustainable and economically efficient road maintenance solutions has driven the development of materials that reduce the use of natural aggregates and promote waste valorization. In this context, this study evaluates the use of reclaimed asphalt pavement (RAP) and Panasqueira mine waste, in the form of greywacke aggregates, as partial or total substitutes for granite aggregates in cold asphalt mixtures intended for rapid pothole repair. Reference mixtures and recycled mixtures were produced with controlled proportions of RAP and greywacke, using cationic bituminous emulsion and hydrated lime, as well as an additional mixture composed only of RAP with a fluxing cold binder. Three commercial mixtures, identified as CCM1, CCM2, and CCM3, were also evaluated. Performance was analyzed through Cantabro particle loss, Marshall stability and flow, indirect tensile stiffness modulus, and water sensitivity (ITSR). The results show that greywacke provides a robust granular skeleton, while RAP content and binder type influence stiffness, cohesion, and moisture resistance. Overall, the combination of RAP and greywacke proved to be technically viable and, in several cases, superior to the commercial mixtures studied.

Abstract: The fractional flow function in the Buckley--Leverett equation is conventionally assumed to be S-shaped. Rastegaev recently established a sufficient condition for this property based on monotonicity of \(m''/m'\), and showed that strict convexity of the phase mobilities alone is not sufficient. This note demonstrates that Rastegaev's criterion is not necessary, by exhibiting an explicit one-parameter polynomial family of strictly convex mobility functions, \[ m_\alpha(s)=s^2(1+\alpha s^4)=s^2+\alpha s^6,\qquad \alpha\ge 0, \] for which the symmetric fractional flow function \[ f_\alpha(s)=\frac{m_\alpha(s)}{m_\alpha(s)+m_\alpha(1-s)} \] retains its S-shape for every \(\alpha\ge 0\): \(f_\alpha''>0\) on \((0,1/2)\), \(f_\alpha''(1/2)=0\), and \(f_\alpha''<0\) on \((1/2,1)\). The mobility lies outside Rastegaev's class once \(\alpha>(5-2\sqrt 5)/15\approx 0.0352\). The proof reduces the sign of \(f_\alpha''\) to four explicit polynomial inequalities on \([0,1/4]\), certified by the convex-hull property of Bernstein coefficients. The same Bernstein certificate applies, without modification, to \(m_\alpha(s)=s^2(1+\alpha s^q)\) for every integer \(q\in\{2,3,4,5,6\}\); at \(q=7\) the certificate just fails.

Abstract: This paper originally introduces a weak magnetic measurement system characterized by a large-scale uniform magnetic field and a low magnetic limit of detection (LOD). The system employs a four-ring coil assembly housed within a multi-layer magnetic shielding cavity, generating a uniform magnetic field region of 120 mm while achieving a minimum LOD of less than 10 pT. The performance of the weak magnetic measurement system is appropriately validated through the use of a bulk magnetic-electric (ME) sensor. The experimental results confirm the system's dual functionalities in both magnetic sensor calibration and the measurement of weak magnetic parameters. Notably, this methodology is readily applicable to various forms of weak magnetic measurement.

Abstract: Digital agriculture employs a wide range of sensing, actuation, and analytics technologies to optimize productivity, sustainability, and decision-making in farming operations. However, rural and remote regions face persistent barriers, including limited network coverage and insufficient support for both low- and high-throughput applications, which hinder the deployment of conventional and broadband-intensive Internet of Things solutions. A central challenge is the lack of adequate field-level network infrastructure, with connectivity often unavailable or unreliable. This article presents a comprehensive survey of Broadband-based IoT as a solution for supporting both low- and high-data-rate digital agriculture applications, including UAVs, computer vision, and extended reality, even in settings without continuous internet connectivity. It examines how technologies such as 5G/6G, dynamic spectrum access, non-terrestrial networks, and edge computing can help address connectivity and infrastructure gaps in underserved agricultural areas. Furthermore, we introduce and analyze the concept of Evolved-Variety Technologies, which combines modified state-of-the-art modules with next-generation networks to create flexible, modular, and scalable system designs adaptable to diverse topographical and operational conditions. Beyond technical evaluations, the article examines economic feasibility, environmental sustainability, and policy implications, emphasizing the need for coordinated roles among governments, telecom providers, and agribusiness stakeholders. Our findings advocate for hybrid telecom architectures that integrate terrestrial and non-terrestrial components, leveraging emerging technologies to reduce the rural–urban digital divide and enable scalable, data-driven agriculture in underserved regions.

Abstract: In extremely shallow water environments, the limited water depth is comparable to the maximum bubble radius. The pulsation of an underwater explosion bubble is strongly constrained by both the free surface and the rigid seabed, exhibiting complex nonlinear coupling effects, which are of great significance for the safety assessment and protection design of nearshore engineering. To address this issue, an axisymmetric two-dimensional numerical model based on the Eulerian finite element method (EFEM) with operator splitting technique and the Volume of fluid (VOF) interface-capturing approach is established. Under the assumptions of inviscid and incompressible flow, a systematic numerical investigation is carried out to examine the effects of the water depth parameter λ, position parameter γ)and buoyancy parameter δ on the bubble dynamics and the evolution of free surface structures. The results show that the maximum bubble radius, pulsation period and jet characteristics are all significantly regulated by the above three parameters. Moreover, under multi-period bubble pulsation, different parameter conditions lead to diverse evolution characteristics of free surface structures including the water spike, wrinkles and water skirt. The findings reveal the governing mechanisms of key dimensionless parameters on the nonlinear bubble-multi-boundary coupling dynamics in extremely shallow water explosions, providing an important numerical basis and theoretical reference for the theoretical analysis and safety design of related shallow water explosion engineering problems.

Abstract: Plastics pyrolysis is increasingly pursued as a pathway for producing circular hydrocarbon feedstocks for petrochemical integration. However, non-integrated reactor configurations often exhibit limited heat-transfer control, significant char handling requirements, and variable product distributions. This work presents a system-level interpretation of the MLM-R™ process, an integrated pyrolysis–combustion loop in which a circulating solid heat carrier enables continuous thermal supply through internal oxidation of carbonaceous residues. Material Flow Analysis (MFA) was applied to reconcile mass, elemental carbon, and chemical energy distributions across the defined process boundary. For the representative case study (1,000 kg polyolefin basis), ~81% of feed carbon and ~83% of feed chemical energy (HHV basis) were recovered in the condensed liquid product, while ~7% of feed carbon was internally combusted to sustain autothermal operation. Simulated distillation analysis indicates that removal of a ~15 wt% C34+ heavy fraction enables compliance with refinery-relevant boiling range targets (≥95% below 480°C). The combined MFA and physicochemical interpretation supports the role of integrated solids circulation and heat-transfer control as primary drivers of product selectivity and process scalability in circular feedstock production.

Abstract: Sample return missions are the most difficult tasks we ask robotic spacecraft to undertake in exploring our solar system, but we do so because of the high value returned samples have for the planetary science community. Thus far, we have only acquired samples from: the Moon, three asteroids, a comet’s tail, and the solar wind at the Earth-Sun Lagrange Points. The National Academy’s most recent decadal survey of planetary science in NASA — Origins, Worlds, Life (OWL) — emphasized the value of samples returned to Earth for analysis and called for NASA to prioritize samples returned from Mars, the Moon’ South Pole, a Jupiter-family comet, and Ceres. Currently available rockets and propulsion technology impose severe, and possibly insurmountable, limits to where we can send robot explorers and return samples within a reasonable timescale. Now, the advent of large new rockets offers the potential for very high C3 Earth escape trajectories. Parallel developments in Nuclear Propulsion yield much higher ISP than chemical propulsion and can operate far away from the Sun. Our novel trajectory and mission architecture analysis shows that, combining these technologies, sample return from all across the solar system starts to become feasible within the career lifetime of a planetary scientist.

Abstract: Multimodal sensors can collect multiple signals and have great potential in robotics and other technical fields. However, such sensors often encounter challenges of signal crosstalk and insufficient real-time performance, particularly in the detection of pressure and temperature, which significantly affect measurement accuracy. To address this issue, a multimodal PCSC sensor was developed. This sensor reduces signal crosstalk by separating force and temperature signals. It uses the pressure-resistance variation of carbon quantum dots (CQDs) to detect force and the thermochromic properties of spiropyran (SP) to detect temperature. When pressure and temperature act on the sensor simultaneously, the resistance increases with pressure and stabilizes when the pressure becomes constant. The response time is 0.4 s. As the temperature rises, the resistance decreases, and the color becomes deeper. Both resistance and color stabilize within 7.5 s. To improve temperature sensing accuracy, a lightweight ResNet-Transformer network (LRTNet) was proposed. This algorithm combines ResNet’s ability to extract features and Transformer’s ability to model sequences. It efficiently fuses color and resistance signals for temperature detection. Tests on a robotic manipulator for dual recognition of temperature and force showed that LRTNet achieved a runtime of 152.08 ms and a temperature sensing accuracy of 95%. LRTNet improved overall performance by at least 11% compared to traditional algorithms. The sensor and algorithm improved the performance and reliability of multimodal sensors.