Search Results (27)

CT scanners are essential tools in modern medical imaging. Sudden failures of their X-ray tubes can lead to equipment downtime, affecting healthcare services and patient diagnosis. However, existing prediction methods based on a single model struggle to adapt to the multi-stage variation characteristics of tube lifespan and have limited modeling capabilities for temporal features. To address these issues, this paper proposes an intelligent prediction architecture for CT tubes’ remaining useful life based on a dual-branch neural network. This architecture consists of two specialized branches: a residual self-attention BiLSTM (RSA-BiLSTM) and a multi-layer dilation temporal convolutional network (D-TCN). The RSA-BiLSTM branch extracts multi-scale features and also enhances the long-term dependency modeling capability for temporal data. The D-TCN branch captures multi-scale temporal features through multi-layer dilated convolutions, effectively handling non-linear changes in the degradation phase. Furthermore, a dynamic phase detector is applied to integrate the prediction results from both branches. In terms of optimization strategy, a dynamically weighted triplet mixed loss function is designed to adjust the weight ratios of different prediction tasks, effectively solving the problems of sample imbalance and uneven prediction accuracy. Experimental results using leave-one-out cross-validation (LOOCV) on six different CT tube datasets show that the proposed method achieved significant advantages over five comparison models, with an average MSE of 2.92, MAE of 0.46, and R² of 0.77. The LOOCV strategy ensures robust evaluation by testing each tube dataset independently while training on the remaining five, providing reliable generalization assessment across different CT equipment. Ablation experiments further confirmed that the collaborative design of multiple components is significant for improving the accuracy of X-ray tubes remaining life prediction. Full article

Background: Refractory ventricular fibrillation (RVF) is a life-threatening condition characterized by the persistence of ventricular fibrillation despite multiple defibrillation attempts. It represents a critical challenge in out-of-hospital cardiac arrest management, with poor survival outcomes and limited guidance from current resuscitation guidelines. In recent years, alternative defibrillation strategies (ADSs), including dual sequential external defibrillation (DSED) and vector change defibrillation (VCD), have emerged as potential interventions to improve defibrillation success and patient outcomes. However, their clinical utility remains debated due to heterogeneous evidence and limited high-quality data. Methods: This narrative review explores the current landscape of ADSs in patients with RVF. MEDLINE, Google Scholar, the World Health Organization, LitCovid NLM, EMBASE, CINAHL Plus, and the Cochrane Library were examined from their inception to April 2025. Results: The available literature is dominated by retrospective studies and case series, with only one randomized controlled trial (DOSE-VF). This trial demonstrated improved survival to hospital discharge with ADSs compared to standard defibrillation. DSED was associated with higher rates of return of spontaneous circulation and favorable neurological outcomes. However, subsequent meta-analyses have produced inconsistent results, largely due to the heterogeneity of the included studies. The absence of sex-, gender-, and ethnicity-specific analyses further limits the generalizability of the findings. In addition, practical barriers, such as equipment availability, pose significant challenges to implementation. Conclusions: ADSs represent a promising yet still-evolving approach to the management of RVF, with DSED showing the most consistent signal of benefit. Further high-quality research is required to enhance generalizability and generate more definitive, high-level evidence. Full article

The accurate real-time estimation of the remaining useful life (RUL) of lithium-polymer (LiPo) batteries is a critical enabler for ensuring the safety, reliability, and operational efficiency of unmanned aerial vehicles (UAVs). Nevertheless, achieving such prognostics on resource-constrained embedded platforms remains a considerable technical challenge. This study proposes an end-to-end TinyML-based framework that integrates embedded sensor data fusion with an optimized feedforward neural network (FFNN) model for efficient RUL estimation under strict hardware limitations. The system collects voltage, discharge time, and capacity measurements through a lightweight data fusion pipeline and leverages the Edge Impulse platform with the EON™Compiler for model optimization. The trained model is deployed on a dual-core ARM Cortex-M0+ Raspberry Pi RP2040 microcontroller, communicating wirelessly with a LabVIEW-based visualization system for real-time monitoring. Experimental validation on an 80-gram UAV equipped with a 1100 mAh LiPo battery demonstrates a mean absolute error (MAE) of 3.46 cycles and a root mean squared error (RMSE) of 3.75 cycles. Model testing results show an overall accuracy of $98.82\%$, with a mean squared error (MSE) of 55.68, a mean absolute error (MAE) of 5.38, and a variance score of 0.99, indicating strong regression precision and robustness. Furthermore, the quantized (int8) version of the model achieves an inference latency of 2 ms, with memory utilization of only 1.2 KB RAM and 11 KB flash, confirming its suitability for real-time deployment on resource-constrained embedded devices. Overall, the proposed framework effectively demonstrates the feasibility of combining embedded sensor data fusion and TinyML to enable accurate, low-latency, and resource-efficient real-time RUL estimation for UAV battery health management. Full article

This study aims to mitigate slope-collapse hazards that threaten life and property at the Lujiawan resettlement site in Wanbi Town, Dayao County, Yunnan Province, within the Guanyinyan hydropower reservoir. It integrates centimeter-level point-cloud data collected by a DJI Matrice 350 RTK equipped with a Zenmuse L2 airborne LiDAR (Light Detection And Ranging) sensor with detailed structural-joint survey data. First, qualitative structural interpretation is conducted with stereographic projection. Next, safety factors are quantified using the limit-equilibrium method, establishing a dual qualitative–quantitative diagnostic framework. This framework delineates six hazardous rock zones (WY1–WY6), dominated by toppling and free-fall failure modes, and evaluates their stability under combined rainfall infiltration, seismic loading, and ambient conditions. Subsequently, six-degree-of-freedom Monte Carlo simulations incorporating realistic three-dimensional terrain and block geometry are performed in RAMMS::ROCKFALL (Rapid Mass Movements Simulation—Rockfall). The resulting spatial patterns of rockfall velocity, kinetic energy, and rebound height elucidate their evolution coupled with slope height, surface morphology, and block shape. Results show peak velocities ranging from 20 to 42 m s⁻¹ and maximum kinetic energies between 0.16 and 1.4 MJ. Most rockfall trajectories terminate within 0–80 m of the cliff base. All six identified hazardous rock masses pose varying levels of threat to residential structures at the slope foot, highlighting substantial spatial variability in hazard distribution. Drawing on the preceding diagnostic results and dynamic simulations, we recommend a three-tier “zonal defense with in situ energy dissipation” scheme: (i) install 500–2000 kJ flexible barriers along the crest and upper slope to rapidly attenuate rockfall energy; (ii) place guiding or deflection structures at mid-slope to steer blocks and dissipate momentum; and (iii) deploy high-capacity flexible nets combined with a catchment basin at the slope foot to intercept residual blocks. This staged arrangement maximizes energy attenuation and overall risk reduction. This study shows that integrating high-resolution 3D point clouds with rigid-body contact dynamics overcomes the spatial discontinuities of conventional surveys. The approach substantially improves the accuracy and efficiency of hazardous rock stability assessments and rockfall trajectory predictions, offering a quantifiable, reproducible mitigation framework for long slopes, large rock volumes, and densely fractured cliff faces. Full article

Under the “dual-carbon” strategy, accurately quantifying carbon emissions in water conservancy projects is crucial to promoting low-carbon construction. However, existing life cycle assessment (LCA) methods for carbon emissions during the mechanical construction stage often fail to reflect actual processes and are limited by high costs and lengthy data collection, potentially leading to inaccurate estimates. To address these challenges, this paper proposes a carbon emission evaluation method for the mechanical construction stage, based on carbon footprint theory and discrete event simulation (DES). This method quantifies equipment operation time and energy consumption during the drilling and blasting processes, enabling a detailed and dynamic emission analysis. Using the Fumin Pumped Storage Power Station Tunnel Project as a case study, a comparative analysis is conducted to examine the carbon emission characteristics of drilling and blasting operations under different surrounding rock conditions based on DES. The validity of the proposed model is confirmed by comparing its results with monitoring data and LCA results. The results show a clear upward trend in carbon emission intensity as surrounding rock conditions deteriorate, with emission intensity rising from 8405.82 kgCO₂e/m for Class II to 16,189.30 kgCO₂e/m for Class V in the headrace tunnel. The total carbon emissions of the water conveyance tunnels reach 40,019.64 tCO₂e, with an average intensity of 13,565.98 kgCO₂e/m. This study presents a refined and validated framework for assessing the carbon emissions of pumped storage tunnels. It addresses key limitations of traditional LCA methods in the mechanical construction stage and provides a practical tool to support the green transition of hydraulic infrastructure. Full article

Accurate prediction of the remaining useful life (RUL) of rolling bearings was crucial for ensuring the safe operation of machinery and reducing maintenance losses. However, due to the high nonlinearity and complexity of mechanical systems, traditional methods failed to meet the requirements of medium- and long-term prediction tasks. To address this issue, this paper proposed a recurrent neural network with a dual attention model. By employing path weight selection methods, Discrete Fourier transform, and selection mechanisms, the prediction accuracy and generalization ability in complex time series analysis were significantly improved. Evaluation results based on mean absolute error (MAE) and root mean square error (RMSE) indicated that the dual attention mechanism effectively focused on key features, optimized feature extraction, and improved prediction performance. An end-to-end RUL prediction model was established based on the MS-DAN network, and the effectiveness of the method was validated using the IEEE PHM 2012 Data Challenge dataset, providing more accurate decision support for equipment maintenance engineers. Full article

The fracturing pump serves as a critical piece of equipment in enhancing oil and gas recovery rates. However, under the coupled action of high-pressure fluid pulsation circulation in the pump body and the vibration of fracturing equipment, the bolts connecting the fracturing pump and fracturing manifold flange are prone to fatigue failure. In this paper, a three-dimensional finite-element model of the threaded bolt connection structure at the fracturing pump outlet end with a fine thread structure was established, and the measured vibrational displacement of the fracturing pump under different driven modes was used as the load to obtain the internal stress state of the full-thread bolt and the double-headed bolt used in the fracturing operation site. Based on the stress state, the fatigue life of the two types of bolts under various loading conditions was then simulated using the Brown—Miller fatigue damage criterion. The results indicate that for bolts of the same structural type, the maximum stress and stress variation amplitude increase in the sequence of the diesel-driven, single-motor-driven, and dual-motor-driven methods. Additionally, under the same load, the stress of the full-thread bolt is lower than that of double-headed bolt. The fatigue life analysis results show that under the vibrational load of diesel drive, the full-thread bolt can obtain a longer fatigue life of approximately 2042.89 h. However, under the load of dual-motor-driven method, the fatigue life of double-headed bolt is the lowest, only 717.46 h. A comparison with the fatigue life of bolts in actual engineering projects indicates that the predicted fatigue life of the bolts is consistent with the actual service life, which can provide effective guidance for the inspection and maintenance of fracturing pump equipment. Full article

The construction industry faces significant challenges including a critical skill shortage and an aging workforce, threatening the industry’s productivity, resilience, and knowledge retention. To address this issue, it becomes critical to attract, hire, and retain younger generations, particularly Generation Z (Gen Z), who are projected to become a dominant workforce by 2030. To this end, this study explores the employer preferences of Gen Z students joining the USA construction industry, providing valuable insights into their priorities and expectations. The study evaluates 27 employer of choice (EOC) factors to identify key criteria influencing Gen Z’s choice of employers. Analyses were conducted across various demographic and experiential categories, including gender, racial/ethnic backgrounds, first-generation status, those with loans, family influence, prior industry experience, intimidation by macho culture, and shifts in perspectives due to the COVID-19 pandemic. The findings reveal that Gen Z prioritizes respect, work–life balance, and job security, and values flexibility in work schedules and hybrid work environments. The findings were also used to propose eight recommendations for employers to become EOCs. Insights from this research serve a dual purpose by offering a foundation for further academic exploration and equipping industry practitioners with the data needed to tailor their recruitment and retention strategies to Gen Z. Full article

This paper aims to address the challenges of significant data distribution differences and extreme data imbalances in the remaining useful life prediction modeling of rotating components of complex intelligent equipment under various working conditions. Grounded in deep learning modeling, it considers the multi-dimensional extraction method for degraded data features in the data feature extraction stage, proposes a network structure with multiple attention data extraction channels, and explores the extraction method for valuable data segments in the channel and time series dimensions. This paper also proposes a domain feature fusion network based on feature migration and examines methods that leverage abundant labeled data from the source domain to assist in target domain learning. Finally, in combination with a long short-term memory neural network (LSTM), this paper constructs an intelligent model to estimate the remaining lifespan of rotating components. Experiments demonstrate that, when integrating the foundational deep convolution network with the domain feature fusion network, the comprehensive loss error for life prediction on the target domain test set can be reduced by up to 6.63%. Furthermore, when adding the dual attention feature extraction network, the maximum reduction in the comprehensive loss error is 3.22%. This model can effectively enhance the precision of life prediction in various operating conditions; thus, it provides a certain theoretical basis and technical support for the operation and maintenance management of complex intelligent equipment. It has certain practical value and application prospects in the remaining life prediction of rotating components under multiple working conditions. Full article

Remaining useful life (RUL) prediction plays a fundamental role in the prognostics and health management of mechanical equipment. Consequently, extensive research has been devoted to estimating the RUL of mechanical equipment. Owing to the development of modern advanced sensor technologies, a significant amount of monitoring data is recorded. Traditional methods, such as machine-learning-based methods and statistical-data-driven methods, are ineffective in matching when faced with big data thus leading to poor predictions. As a result, deep-learning-based methods are extensively utilized due to their efficient capability to excavate deep features and realize accurate predictions. However, most deep-learning-based methods only provide point estimations and ignore the prediction uncertainty. To address this limitation, this paper proposes a parallel prognostic network to sufficiently excavate the degradation features from multiple dimensions for more accurate RUL prediction. In addition, accurate calculation of model evidence is extremely difficult when dealing with big data so the Monte Carlo dropout is employed to infer the model weights under low computational cost and high scalability to obtain a probabilistic RUL prediction. Finally, the C-MAPSS aero-engine dataset is employed to validate the proposed dual-channel framework. The experimental results illustrate its superior prediction performance compared to other deep learning methods and the ability to quantify prediction uncertainty. Full article

In fields such as manufacturing and aerospace, remaining useful life (RUL) prediction estimates the failure time of high-value assets like industrial equipment and aircraft engines by analyzing time series data collected from various sensors, enabling more effective predictive maintenance. However, significant temporal diversity and operational complexity during equipment operation make it difficult for traditional single-scale, single-dimensional feature extraction methods to effectively capture complex temporal dependencies and multi-dimensional feature interactions. To address this issue, we propose a Dual-Path Interaction Network, integrating the Multiscale Temporal-Feature Convolution Fusion Module (MTF-CFM) and the Dynamic Weight Adaptation Module (DWAM). This approach adaptively extracts information across different temporal and feature scales, enabling effective interaction of multi-dimensional information. Using the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset for comprehensive performance evaluation, our method achieved RMSE values of 0.0969, 0.1316, 0.086, and 0.1148; MAPE values of 9.72%, 14.51%, 8.04%, and 11.27%; and Score results of 59.93, 209.39, 67.56, and 215.35 across four different data categories. Furthermore, the MTF-CFM module demonstrated an average improvement of 7.12%, 10.62%, and 7.21% in RMSE, MAPE, and Score across multiple baseline models. These results validate the effectiveness and potential of the proposed model in improving the accuracy and robustness of RUL prediction. Full article

The power transformer is one of the most crucial pieces of high-voltage equipment in the power system, and its stable operation is crucial to the reliability of power transmission. Partial discharge (PD) is a key factor leading to the degradation and failure of the insulation performance of power transformers. Therefore, online monitoring of partial discharge can not only obtain real-time information on the operating status of the equipment but also effectively predict the remaining service life of the transformer. Meanwhile, accurate localization of partial discharge sources can assist maintenance personnel in developing more precise and efficient maintenance plans, ensuring the stable operation of the power system. Dual partial discharge sources in transformer oil represent a more complex fault type, and piezoelectric transducers installed outside the transformer oil tank often fail to accurately capture such discharge waveforms. Additionally, the sensitivity of the built-in F-P sensors can decrease when installed deep within the oil tank due to the influence of oil pressure on its sensing diaphragm, resulting in an inability to accurately detect dual partial discharge sources in transformer oil. To address the impact of oil pressure on sensor sensitivity and achieve the detection of dual partial discharge sources under high-voltage conditions in transformers, this paper proposes an optical fiber ultrasonic sensor with a pressure-balancing structure. This sensor can adapt to changes in oil pressure environments inside transformers, has strong electromagnetic interference resistance, and can be installed deep within the oil tank to detect dual partial discharge sources. In this study, a dual PD detection system based on this sensor array is developed, employing a cross-positioning algorithm to achieve detection and localization of dual partial discharge sources in transformer oil. When applied to a 35 kV single-phase transformer for dual partial discharge source detection in different regions, the sensor array exhibits good sensitivity under high oil pressure conditions, enabling the detection and localization of dual partial discharge sources in oil and winding interturn without obstruction. For fault regions with obstructions, such as within the oil channel of the transformer winding, the sensor exhibits the capability to detect the discharge waveform stemming from dual partial discharge sources. Overall, the sensor demonstrates good sensitivity and directional clarity, providing effective detection of dual PD sources generated inside transformers. Full article

Metal-ceramic composite coatings are produced on the surface of equipment components by laser cladding, improving the abrasive wear resistance of components and extending their service life. However, defects such as brittleness and cracks limit the wide application of metal-ceramic clad coatings in the field of construction machinery. In the present study, a dual-element (Ti/Nb) alloying method is innovatively adopted to regulate the microstructure and mechanical properties of tungsten carbide (WC)-reinforced clad coatings. Experimental results show that with the introduction of Ti/Nb, novel reinforcements are in-situ synthesized in the cladding coatings with two different kinds of morphologies: one is a core-shell carbide with the core of pure TiC and a shell of (Ti,Nb,W)C multiple carbide; the other is a (Ti,Nb,W)C multiple carbide. With 8 wt.% Ti/Nb addition, the newly formed multiple carbides with the appropriate content are well-dispersed and distributed in the clad coating, which effectively transfers load, inhibits the initiation and expansion of micro-cracks, and resists the wear damage of hard abrasive particles, solving the technical problems of the simultaneous improvement of toughness and abrasive wear resistance of metal-ceramic laser cladding coatings. Full article

Those with visual impairments, including complete blindness or partial sight loss, constitute a significant global population. According to estimates by the World Health Organization (WHO), there are at least 2.2 billion people worldwide who have near or distance vision disorders. Addressing their needs is crucial. Introducing a smart cane tailored for the blind can greatly improve their daily lives. This paper introduces a significant technical innovation, presenting a smart cane equipped with dual ultrasonic sensors for obstacle detection, catering to the visually impaired. The primary focus is on developing a versatile device capable of operating in diverse conditions, ensuring efficient obstacle alerts. The strategic placement of ultrasonic sensors facilitates the emission and measurement of high-frequency sound waves, calculating obstacle distances and assessing potential threats to the user. Addressing various obstacle types, two ultrasonic sensors handle overhead and ground-level barriers, ensuring precise warnings. With a detection range spanning 2 to 400 cm, the device provides timely information for user reaction. Dual alert methods, including vibrations and audio signals, offer flexibility to users, controlled through intuitive switches. Additionally, a Bluetooth-connected mobile app enhances functionality, activating audio alerts if the cane is misplaced or too distant. Cost-effective implementation enhances accessibility, supporting a broader user base. This innovative smart cane not only represents a technical achievement but also significantly improves the quality of life for visually impaired individuals, emphasizing the social impact of technology. The research underscores the importance of technological research in addressing societal challenges and highlights the need for solutions that positively impact vulnerable communities, shaping future directions in research and technological development. Full article

In order to ensure that dual-axis rotational inertial navigation systems (RINSs) maintain a high level of accuracy over the long term, there is a demand for periodic calibration during their service life. Traditional calibration methods for inertial measurement units (IMUs) involve removing the IMU from the equipment, which is a laborious and time-consuming process. Reinstalling the IMU after calibration may introduce new installation errors. This paper focuses on dual-axis rotational inertial navigation systems and presents a system-level self-calibration method based on invariant errors, enabling high-precision automated calibration without the need for equipment disassembly. First, navigation parameter errors in the inertial frame are expressed as invariant errors. This allows the corresponding error models to estimate initial attitude even more rapidly and accurately in cases of extreme misalignment, eliminating the need for coarse alignment. Next, by utilizing the output of a gimbal mechanism, angular velocity constraint equations are established, and the backtracking navigation is introduced to reuse sensor data, thereby reducing the calibration time. Finally, a rotation scheme for the IMU is designed to ensure that all errors are observable. The observability of the system is analyzed based on a piecewise constant system method and singular value decomposition (SVD) observability analysis. The simulation and experimental results demonstrate that this method can effectively estimate IMU errors and installation errors related to the rotation axis within 12 min, and the estimated error is less than 4%. After using this method to compensate for the calibration error, the velocity and position accuracies of a RINS are significantly improved. Full article