Hasil untuk "Automation"

M. Endsley, D. Kaber

L. Onnasch, C. Wickens, Huiyang Li et al.

LIU Donglin, ZHOU Xia, DAI Jianfeng, XIE Xiangpeng, TANG Yi, LI Juanshi

Integrated energy systems in buildings are an effective means to achieve low-carbon buildings. To further tap into their demand-side flexibility adjustable potential and carbon reduction potential, and reasonably allocate the interests of various entities in the building integrated energy system, a bi-level optimization scheduling strategy for building integrated energy system considering virtual energy storage in buildings under Stackelberg game framework is proposed. First, the thermal inertia of the cooling and heating system inside the building and the flexibility of the cooling and heating load are considered to leverage the virtual energy storage function of the building and improve system flexibility in the game model. Then, the genetic algorithm is used to solve the upper-level pricing model of energy operators, updating the purchase and sale electricity prices set by upper-level leaders, while the CPLEX solver is used to solve the lower-level problem, optimizing equipment output, demand response, and electricity trading plans. Finally, the proposed model is verified by case studies that it can effectively improve the economic performance and low-carbon characteristics of building integrated energy systems.

Ahmed Raza Amir, Syed Muhammad Atif

Workflow automation has become increasingly accessible through low-code platforms, enabling small organizations and individuals to improve operational efficiency without extensive software development expertise. This study evaluates the performance impact of workflow automation using n8n through a small-scale business case study. A representative lead-processing workflow was implemented to automatically store data, send email confirmations, and generate real-time notifications. Experimental benchmarking was conducted by comparing 20 manual executions with 25 automated executions under controlled conditions. The results demonstrate a significant reduction in the average execution time from 185.35 seconds (manual) to 1.23 seconds (automated), corresponding to an approximately 151 times reduction in execution time. Additionally, manual execution exhibited an error rate of 5%, while automated execution achieved zero observed errors. The findings highlight the effectiveness of low-code automation in improving efficiency, reliability, and operational consistency for small-scale workflows.

C. Gold, Moritz Körber, C. Hohenberger et al.

Highly automated vehicles (Level 3, [1]) are likely to enter the market within the next decade. By removing the driver from the driver-vehicle system, positive impacts, for instance on road-safety or fuel consumption, are expected. These predicted effects can only arise if automated vehicles are accepted by society. Trust as well as the attitude towards technology has been found to be a precursor in the acceptance formation process. Therefore, we conducted a driving simulator experiment within the interdisciplinary research group at the Munich Center of Technology in Society (MCTS) in order to investigate how the experience of automated driving will change trust in automation and the attitude of the driver towards automation. The sample consisted of 72 participants between 19 and 79 years (M = 44.97, SD = 22.16). Participants completed a questionnaire before and after the driving simulator experience to assess trust in automation, safety gain, intention to use and other constructs in order to analyze the change caused by the driving simulation experience. Besides participants’ ratings from the questionnaires, their gaze behavior was recorded in order to measure a change of trust by a change in scanning behavior. The participants drove highly automated on a three lane highway at a speed of 120 km/h. As critical situations are expected to have a significant impact on trust in automation, the participants experienced three take-over scenarios (system limits). Results indicate that the driving experience increased self-reported trust in automation and lead to a decrease in other measured constructs like safety gain. Older participants rated the vehicle automation more positively than younger drivers. Horizontal gaze behavior could not be confirmed as a metric for measuring trust in automation, although this measure behaved as expected and analogous to the self-reported level of trust.

Zhaoxuan Lu, Lyuchao Liao, Xingang Xie et al.

In recent years, climate change and marine pollution have significantly degraded coral reefs, highlighting the urgent need for automated coral detection to monitor marine ecosystems. However, underwater coral detection presents unique challenges, including low image contrast, complex coral structures, and dense coral growth, which limit the effectiveness of general object detection algorithms. To address these challenges, we propose SCoralDet, a soft coral detection model based on the YOLO architecture. First, we introduce a Multi-Path Fusion Block (MPFB) to capture coral features across multiple scales, enhancing the model’s robustness to uneven lighting and image blurring. We further improve inference efficiency by applying reparameterization. Second, we integrate lightweight components such as GSConv and VoV-GSCSP to reduce computational overhead without sacrificing performance. Additionally, we develop an Adaptive Power Transformation label assignment strategy, which dynamically adjusts anchor alignment metrics. By incorporating soft labels and soft central region loss, our model is guided to prioritize high-quality, well-aligned predictions. We evaluate SCoralDet on the Soft-Coral dataset, achieving an inference latency of 9.52 ms and an mAP50 of 81.9. This surpasses the performance of YOLOv5 (79.9), YOLOv6 (79.4), YOLOv8 (79.5), YOLOv9 (78.3), and YOLOv10 (79.5). These results demonstrate the effectiveness and practicality of SCoralDet in underwater coral detection tasks.

Lv Fuyong, Wang Jie, Du Tong et al.

In small and medium-sized permanent magnet synchronous wind turbines, the bridge rectifier + DC / DC converter topology has the advantages of simple structure. The DC / DC circuit has Boost and Buck topologies. Exploring the difference between the maximum power point tracking ( MPPT ) control performance of the two is the key to its optimal design. The measurement and control system is an important means of performance analysis. Through the overall scheme design of the system, the system parameters and indexes are confirmed. The four-leg DC / DC topology is analyzed, and the acquisition of system voltage, current, power and frequency is realized based on high-end current sampling and isolated sampling technology. The power drive and single chip microcomputer control circuit are designed. The software of MPPT climbing search method suitable for single chip microcomputer is discussed. The software design and implementation of the upper computer control system based on LabVIEW is given. The measurement and control system is built, and the MPPT and two topology measurement and control results are compared. The experimental results show that the measurement and control system has achieved the design goal.

Risheng Long, Qingyu Shang, Shaoni Sun et al.

Surface texturing has been proven to be an effective method for improving the lubrication characteristics and tribological behavior of tribo-pairs under various operating conditions. Inspired by the unique Swiss cheese-like leaves of Monstera riedrichsthalii, eight bionic texture patterns were introduced. The influence of vein features, such as costal vein angles (45° and 60°), vein symmetry (symmetric, asymmetric), and elliptical holes, on the tribological and vibration characteristics of rolling bearings was investigated under starved lubrication through a wear test rig and time‒frequency domain vibration signal analysis. The results show that the average coefficients of friction and wear losses of the Monstera riedrichsthalii bionic-textured groups are generally lower than those of the smooth reference. The amplitudes and parameters (i.e., peak value, root mean square (RMS), and crest factor) of the time-domain vibration signals of the textured groups are greater than those of the smooth group in the early stages, but the vibration parameters of most textured groups are lower than those of the smooth bearings in the later stages, especially those of the groups with elliptical holes. The amplitudes and power spectral density (PSD) curves of the frequency-domain vibration signals exhibit similar variations to those of the time-domain signals. Compared with the smooth reference, the Monstera riedrichsthalii bionic-textured group with a combination of 45° secondary-vein angle, asymmetry, and elliptic holes can provide excellent tribological and vibration performance. Its well-lubricating period, average coefficient of friction (CoF), and mass loss can be effectively prolonged or reduced by 37.4%, 7.3%, and 43.9%, respectively.

YU Yongtao, SUN Ao, LI Ang, ZHU Linlin

In industrial surface Quality Control (QC) scenarios, deep classification neural networks are widely used to classify product images for qualified judgment or quality grading. However, surface QC equipment equipped with deep classification neural networks must meet Attribute Reproducibility and Repeatability (AR&R) assessment requirements. Perturbations in product images, caused by assembly tolerance, equipment vibrations, and other factors, lead to variations in position, angle, brightness, and blurring. These perturbations result in inconsistent classification outputs, causing the surface QC equipment to fail the AR&R assessment, a problem referred to as the network output reproducibility issue. To address this issue, this study proposes a training method for classification neural networks based on Siamese networks. The Siamese primary network is trained using original samples for supervised learning to learn correct classification categories. The Siamese secondary network copies the weights of the primary network via exponential smoothing and generates feature embeddings of perturbed samples corresponding to the original ones. These embeddings are used for comparative learning training of the primary network, enabling it to output consistent classification probabilities for both original and perturbed sample inputs. During inference, only the primary network is retained for product defect classification. The results show that the classification accuracy reaches 99.346 2%, with a classification probability variance of 0.001 016. The described method effectively improves the output reproducibility of deep classification neural networks for industrial product image classification by reducing classification probability variance and enhancing accuracy.

Thywill Cephas Dzogbewu, Deon Johan de Beer

Direct laser powder bed fusion (LPBF) of ceramics has experienced tremendous advancement and it is about to be metamorphosed from the laboratory research phase to the industrial scale. Nonetheless, several challenges need to be overcome before progressing to the next phase of manufacturing crack-free, large-size, and multimaterial ceramic products via the direct LPBF process with high surface quality and homogeneous mechanical integrity. Surprising the current challenges required automation of the in-process activities to control the high viscous ceramic molten pool and its solidification mechanisms to mitigate the building up of thermal stress, and crack formation to ensure the production of crack-free, large-size ceramic parts with high surface quality. The automation of the process would ensure consistency, reliability, and reproducibility of direct printing of ceramic products, which would speed up the development of a validation framework for the certification of direct printed ceramic products. The post-processing activities of the indirect ceramic printing process might not be the ideal approach for producing dense crack-free ceramic products, since it could increase the cost of the product by 70 % without any significant improvement as compared to the direct LPBF ceramic manufacturing route.

Fengyuan Li

The current study examined the multifaceted effects of digital transformation on information disclosure and organisational efficiency in Chinese-listed companies. In this study technology adoption, digital strategy, process automation, transparency, and process innovation are used to understand the digital transformation to drive information disclosure towards organisational efficiency. A quantitative research design was utilised, employing a structured survey directed at senior executives, including directors, managers, chief information officers, and chief transformation officers. A nonprobability snowball sampling technique was employed to access a specialised population of experts. The research initially identified pertinent enterprises via the official information disclosure platform of the China Securities Regulatory Commission (CSRC). Five hundred questionnaires were disseminated through email and social media platforms from February 2023 to July 2023. Following the exclusion of incomplete and outlier responses, 300 completed questionnaires were analysed. The analysis was performed using a combination of PLS-SEM and artificial neural network (ANN) approaches. An ANN investigation was conducted to enhance the findings of PLS-SEM and improve predictive accuracy. The findings indicate a substantial positive correlation between digital transformation and increased information disclosure, along with enhanced organisational efficiency. Digital technologies enhance transparency and data-sharing systems, thereby improving decision-making processes. Moreover, research indicates that IT leadership within organisations is pivotal in facilitating successful digital transformation initiatives. These findings highlight the essential function of digital transformation in promoting corporate accountability and operational efficiency. Future research ought to investigate industry-specific impacts of digital transformation and incorporate longitudinal analyses to capture the evolving trends in digital adoption and corporate governance.

Martyna Zemlik, Beata Białobrzeska, Mateusz Stachowicz et al.

As a result of welding processes in boron-alloyed martensitic armor steels, unfavorable microstructural changes occur, leading to a significant reduction in the mechanical properties of both the weld metal and the base material. The dendritic structure of the weld metal and the partial tempering in the heat-affected zone contribute to the decreased durability of structural components, thereby deteriorating their performance. This issue is particularly important since such steels are widely used not only in the defense industry but also in the mining, construction, transportation, and metallurgical sectors, where they operate under conditions of intensive abrasive wear. For this reason, the authors attempted to improve the mechanical properties of welded joints of boron-alloyed martensitic armor steel (with a nominal hardness of 500 HBW) through post-weld heat treatment. The welded joint was evaluated based on metallographic examinations using light microscopy and scanning electron microscopy, as well as abrasive wear tests carried out on a T-07 tribotester. The conducted investigations demonstrated that, under loose abrasive conditions (using electrofused alumina), heat treatment increased the wear resistance of the joints by 55% compared to the as-welded condition. The obtained results were compared with selected grades of Hardox steel commonly used in industrial applications.

Netsawang Prud, Huangsorn Padipan, Nathan Komkrish et al.

This study addressed the production challenges in high-fiber cattle feed pelleting, where conventional die design and low steam temperature led to die wear, excessive fines, and low throughput. The effects of the pellet die type and steam conditioning temperature on pellet quality, energy consumption, and throughput were evaluated using a full factorial experiment at a commercial feed null. Two die types (standard and counterdrilled) and five steam temperatures (65—85 °C) were tested. Key parameters included the pellet durability index (PDI). dust content, motor current, production rate, and nutritional composition. Results showed that steam temperature significantly influenced pellet quality (p < 0.05). with optimal PDI (-97%) and minimal dust (-1.5%) achieved at 80—85 °C. The die type significantly affected the energy efficiency and output (p < 0.001); the counterdrilled die reduced the motor current by up to 18% and increased the throughput by -20%. No significant differences were found in the protein, fiber, or fat content (p > 0.05). indicating nutritional stability'. The combination of high-temperature steam conditioning and a counterdrilled die offers an effective strategy for enhancing the pellet quality and reducing the energy load. This approach is suitable for high-capacity cattle feed mills, aiming for a consistent performance and improved operational efficiency.

Oscar Girón-Vallejo, Bernardo Garcia-Nuñez, Isidoro Narbona-Arias et al.

Three-dimensional (3D) modeling and printing technologies are increasingly used in pediatric surgery, offering improved anatomical visualization, surgical planning, and personalized approaches to complex conditions. Compared to standard imaging, patient-specific 3D models—virtual or printed—provide a more intuitive spatial understanding of congenital anomalies, tumors, and vascular anomalies. This review compiles evidence from pediatric surgical fields including oncology, abdominal, and thoracic surgery, highlighting the clinical relevance of 3D applications. The technological workflow—from image segmentation to computer-aided design (CAD) modeling and multimaterial printing—is described, emphasizing accuracy, reproducibility, and integration into hospital systems. Several clinical cases are presented: neuroblastoma, cloacal malformation, conjoined twins, and two cases of congenital diaphragmatic hernia (one with congenital pulmonary airway malformation, CPAM). In each, 3D modeling enhanced anatomical clarity, increased surgeon confidence, and supported safer intraoperative decision-making. Models also improved communication with families and enabled effective multidisciplinary planning. Despite these advantages, challenges remain, such as production time, cost variability, and lack of standardization. Future directions include artificial intelligence-based automation, expanded use of virtual and mixed reality, and prospective validation studies in pediatric cohorts. Overall, 3D modeling represents a significant advance in pediatric precision surgery, with growing evidence supporting its safety, clinical utility, and educational value.

Hikaru Sasaki, Naoto Komeno, Takumi Hachimine et al.

While robotic automation has demonstrated remarkable performance, such as executing hundreds of experiments continuously over several days, designing synchronized motions between the robot and experimental jigs remains challenging, especially for flexible experimental automation. This challenge stems from the fact that even minor changes in experimental conditions often require extensive reprogramming of both robot motions and jig control commands. Previous systems lack the flexibility to accommodate frequent updates, limiting their practical utility in actual laboratories. To update robotic automation systems flexibly by chemists, we propose a concept that enables the automation of experiments by utilizing dual demonstrations of robot motions and jig operations by chemists. To verify this concept, we developed a chemical-experiment-automation system consisting of jigs to assist the robot in experiments, a motion-demonstration interface, a jig-control interface, and a mobile manipulator. We validate the concept through polymer-synthesis experiments, focusing on critical liquid-handling tasks such as pipetting and dilution. The experimental results indicate high reproducibility of the demonstrated motions and robust task-success rates. This comprehensive concept not only simplifies the robot programming process for chemists but also provides a flexible and efficient solution to accommodate a wide range of experimental conditions, providing a practical framework for intuitive and adaptable robotic laboratory automation. Our project page is available at: https://sasakihikaru.github.io/Chemical-Experiment-Automation-with-Dual-Demonstration/.

Shriyank Somvanshi, Anannya Ghosh Tusti, Mahmuda Sultana Mimi et al.

The increasing presence of automated vehicles (AVs) presents new challenges for crash classification and safety analysis. Accurately identifying the SAE automation level involved in each crash is essential to understanding crash dynamics and system accountability. However, existing approaches often overlook automation-specific factors and lack model sophistication to capture distinctions between different SAE levels. To address this gap, this study evaluates the performance of three advanced tabular deep learning models MambaAttention, TabPFN, and TabTransformer for classifying SAE automation levels using structured crash data from Texas (2024), covering 4,649 cases categorized as Assisted Driving (SAE Level 1), Partial Automation (SAE Level 2), and Advanced Automation (SAE Levels 3-5 combined). Following class balancing using SMOTEENN, the models were trained and evaluated on a unified dataset of 7,300 records. MambaAttention demonstrated the highest overall performance (F1-scores: 88% for SAE 1, 97% for SAE 2, and 99% for SAE 3-5), while TabPFN excelled in zero-shot inference with high robustness for rare crash categories. In contrast, TabTransformer underperformed, particularly in detecting Partial Automation crashes (F1-score: 55%), suggesting challenges in modeling shared human-system control dynamics. These results highlight the capability of deep learning models tailored for tabular data to enhance the accuracy and efficiency of automation-level classification. Integrating such models into crash analysis frameworks can support policy development, AV safety evaluation, and regulatory decisions, especially in distinguishing high-risk conditions for mid- and high-level automation technologies.

Anaïs Halin, Christel Devue, Marc Van Droogenbroeck

The increasing integration of automation in vehicles aims to enhance both safety and comfort, but it also introduces new risks, including driver disengagement, reduced situation awareness, and mode confusion. In this work, we propose the DEV framework, a closed-loop framework for risk-aware adaptive driving automation that captures the dynamic interplay between the driver, the environment, and the vehicle. The framework promotes to continuously adjusting the operational level of automation based on a risk management strategy. The real-time risk assessment supports smoother transitions and effective cooperation between the driver and the automation system. Furthermore, we introduce a nomenclature of indexes corresponding to each core component, namely driver involvement, environment complexity, and vehicle engagement, and discuss how their interaction influences driving risk. The DEV framework offers a comprehensive perspective to align multidisciplinary research efforts and guide the development of dynamic, risk-aware driving automation systems.

Mantas Mazeika, Alice Gatti, Cristina Menghini et al.

AIs have made rapid progress on research-oriented benchmarks of knowledge and reasoning, but it remains unclear how these gains translate into economic value and automation. To measure this, we introduce the Remote Labor Index (RLI), a broadly multi-sector benchmark comprising real-world, economically valuable projects designed to evaluate end-to-end agent performance in practical settings. AI agents perform near the floor on RLI, with the highest-performing agent achieving an automation rate of 2.5%. These results help ground discussions of AI automation in empirical evidence, setting a common basis for tracking AI impacts and enabling stakeholders to proactively navigate AI-driven labor automation.

Haoyuan Wu, Haisheng Zheng, Zhuolun He et al.

Recently, with the development of tool-calling capabilities in large language models (LLMs), these models have demonstrated significant potential for automating electronic design automation (EDA) flows by interacting with EDA tool APIs via EDA scripts. However, considering the limited understanding of EDA tools, LLMs face challenges in practical scenarios where diverse interfaces of EDA tools exist across different platforms. Additionally, EDA flow automation often involves intricate, long-chain tool-calling processes, increasing the likelihood of errors in intermediate steps. Any errors will lead to the instability and failure of EDA flow automation. To address these challenges, we introduce EDAid, a multi-agent collaboration system where multiple agents harboring divergent thoughts converge towards a common goal, ensuring reliable and successful EDA flow automation. Specifically, each agent is controlled by ChipLlama models, which are expert LLMs fine-tuned for EDA flow automation. Our experiments demonstrate the state-of-the-art (SOTA) performance of our ChipLlama models and validate the effectiveness of our EDAid in the automation of complex EDA flows, showcasing superior performance compared to single-agent systems.

Jia Li, Zhi Jin, Huangzhao Zhang et al.

Software development automation is a long-term goal in software engineering. With the development of artificial intelligence (AI), more and more researchers are exploring approaches to software automation. They view AI systems as tools or assistants in software development, still requiring significant human involvement. Another initiative is ``vibe coding'', where AI systems write and repeatedly revise most (or even all) of the code. We foresee these two development paths will converge towards the same destination: AI systems participate in throughout the software development lifecycle, expanding boundaries of full-stack software development. In this paper, we present a vision of an iterative end-to-end automated software development paradigm AutoSW. It operates in an analyze-plan-implement-deliver loop, where AI systems as human partners become first-class actors, translating human intentions expressed in natural language into executable software. We explore a lightweight prototype across the paradigm and initially execute various representative cases. The results indicate that AutoSW can successfully deliver executable software, providing a feasible direction for truly end-to-end automated software development.