Maintenance Capability Research Articles

Fine-grained fault diagnosis of photovoltaic systems based on DMAD-GAN and IFD-FGIF

Abstract In the field of photovoltaic (PV) system monitoring, fault detection faces two critical challenges: data imbalance and fault diversity, as well as incomplete complex fault information. To tackle these issues, this paper proposes a dual-mechanism anomaly detection with generative adversarial network (DMAD-GAN) and an integrated fault diagnosis with fine-grained information fusion (IFD-FGIF). DMAD-GAN utilizes GAN to integrate dual mechanisms for anomaly detection in PV datasets, with coordinate-space attention enhancing the perception of subtle features and differences in PV panels. The anomaly scoring mechanism utilizes an improved loss function to compute anomaly scores, assessing the degree of anomaly for each sample. In the IFD-FGIF method, t-SNE is used to visualize features for fault pre-classification to determine the presence of new faults. A fine-grained information fusion module is designed, leveraging ResNet50 to extract features from fault key areas and original images. This module integrates fine-grained features, original features, and fine-grained attributes. Fault attributes and categories are determined using an attribute classifier and Euclidean distance. If a new fault is identified during pre-classification, the network undergoes transfer learning to recognize and adapt to the new fault. The experimental results demonstrate that the proposed method outperforms other networks, achieving an anomaly detection accuracy of 95.86%. The fault fine-grained recognition accuracy is 95.62%. The accuracy of fine-grained information fusion has improved by 4%, and unsupervised learning of new faults has been successfully achieved. The proposed method can enhance the intelligent operation and maintenance capability of PV power plants, reduce false alarm rates in fault detection, and minimize operational risks caused by potential faults, thus effectively shortening downtime and lowering maintenance costs.

Autonomous vehicle diagnostics and support: a framework for API-Driven microservices

The rapid evolution of autonomous vehicles (AVs) demands robust and scalable diagnostic and support systems to ensure seamless operations, safety, and performance. This paper presents a framework for API-driven microservices tailored to address the unique diagnostic and support requirements of AVs. Traditional monolithic systems are insufficient for managing the complex, real-time data generated by AVs, necessitating a shift toward microservices architecture. By leveraging API-driven microservices, the proposed framework ensures modularity, scalability, and real-time communication between various vehicle components and external support systems. The framework is designed to support continuous vehicle monitoring, predictive maintenance, fault detection, and real-time decision-making, all while minimizing latency. APIs play a critical role in enabling interaction between different microservices, allowing for seamless data exchange across diverse platforms. This interoperability facilitates integration with third-party services, such as cloud-based diagnostics, real-time traffic information, and software updates. Additionally, the microservices architecture ensures fault isolation, meaning that failures in one service do not compromise the entire system. The framework also emphasizes the importance of cybersecurity and data privacy. Given the sensitive nature of AV data, API security protocols such as OAuth2 and TLS encryption are incorporated to safeguard communication between microservices and external systems. Furthermore, the design is scalable, allowing for the integration of future AV technologies and third-party service enhancements without disrupting existing functionalities. In conclusion, API-driven microservices provide an efficient, flexible, and secure solution for autonomous vehicle diagnostics and support. This framework has the potential to improve AV reliability, reduce downtime, and enhance safety by enabling real-time, data-driven decision-making and proactive maintenance. Future work may explore the integration of machine learning algorithms to further optimize diagnostics and predictive maintenance capabilities.

AI-enhanced predictive maintenance systems for critical infrastructure: Cloud-native architectures approach

Critical infrastructure (CI), such as power grids, transportation systems, and telecommunications networks, is becoming increasingly complex, requiring sophisticated maintenance strategies and procedures to guarantee optimal performance and system durability. This paper examines the transformational potential of AI-driven predictive maintenance systems, highlighting their ability to prevent system failures, minimize downtime, and enhance resource efficiency. Integrating machine learning algorithms with real-time data analytics allows predictive maintenance frameworks to accurately foresee equipment failures, facilitating timely interventions that reduce the risk of catastrophic infrastructure breakdowns. This study primarily examines the development of cloud-native architectures, which include containers, microservices, and orchestration tools like Kubernetes, to facilitate the scalability, flexibility, and resilience required for contemporary CI maintenance systems. These designs facilitate the seamless integration of predictive maintenance solutions across geographically dispersed infrastructure, enabling effective administration of extensive datasets produced by Internet of Things (IoT) sensors, operational logs, and edge computing nodes. The document examines the essential function of intelligent data orchestration in facilitating the prompt gathering, processing, and analysis of operational data, which is vital for AI models to provide precise predictions. The amalgamation of AI-driven predictive maintenance with 5G and forthcoming 6G networks is poised to transform real-time system monitoring, diminishing latency and enhancing decision-making efficacy. Utilizing AI and cloud-native technologies substantially enhances system reliability, cost-effectiveness, and comprehensive infrastructure optimization. This article thoroughly analyses how AI, cloud-native platforms, and intelligent data orchestration may be utilized to tackle the changing maintenance issues of critical infrastructure by examining real-world case studies from sectors like power grids, telecommunications, and transportation. Integrating AI, cloud computing, and IoT in predictive maintenance improves system reliability and prepares critical infrastructure for future autonomous management and optimization developments. The study finishes by discussing new trends, such as the integration of digital twins and the synergies between AI and cloud-native solutions, which will enhance predictive maintenance capabilities.

Effect of ultrasound-assisted water-holding agent on the quality of frozen stored beef

Beef was soaked in an ultrasonic-assisted water-holding agent to increase its water-holding capacity without sacrificing its quality. Storage at -18 °C for 0, 7, 14, 21 and 28 days, the effects of the water-holding agent and ultrasound on the quality of the beef were discussed, along with the centrifugal loss rate, pH, texture, water distribution, and thiobarbituric acid reactive substances (TBARS) and other indexes. The centrifugal loss of the control group was found to be 14.33 %, while the chitosan treatment had the lowest centrifugal loss. The centrifugal losses of compound phosphate, soybean dietary fiber, and chitosan were found to be 10.77 %, 11.86 %, and 12.10 %, respectively, over the 28-days freezing time. Furthermore, there was less water migration and a lower free water P22 value in the chitosan and compound phosphate treatment groups, indicating improved water maintenance capabilities. The highest TBARS value in the control group was 1.17 mg/kg, and the lowest value of compound phosphate was 0.91 mg/kg, indicating that the compound phosphate had a good effect on lipid peroxidation. The findings of this study offer valuable insights into the water-holding properties of water-holding agents in frozen beef and serve as a guide for using these agents in the food industry.

Autonomous Vehicle Diagnostics and Support: A Framework for API-Driven Microservices

The rapid evolution of autonomous vehicles (AVs) demands robust and scalable diagnostic and support systems to ensure seamless operations, safety, and performance. This paper presents a framework for API-driven microservices tailored to address the unique diagnostic and support requirements of AVs. Traditional monolithic systems are insufficient for managing the complex, real-time data generated by AVs, necessitating a shift toward microservices architecture. By leveraging API-driven microservices, the proposed framework ensures modularity, scalability, and real-time communication between various vehicle components and external support systems. The framework is designed to support continuous vehicle monitoring, predictive maintenance, fault detection, and real-time decision-making, all while minimizing latency. APIs play a critical role in enabling interaction between different microservices, allowing for seamless data exchange across diverse platforms. This interoperability facilitates integration with third-party services, such as cloud-based diagnostics, real-time traffic information, and software updates. Additionally, the microservices architecture ensures fault isolation, meaning that failures in one service do not compromise the entire system. The framework also emphasizes the importance of cybersecurity and data privacy. Given the sensitive nature of AV data, API security protocols such as OAuth2 and TLS encryption are incorporated to safeguard communication between microservices and external systems. Furthermore, the design is scalable, allowing for the integration of future AV technologies and third-party service enhancements without disrupting existing functionalities. In conclusion, API-driven microservices provide an efficient, flexible, and secure solution for autonomous vehicle diagnostics and support. This framework has the potential to improve AV reliability, reduce downtime, and enhance safety by enabling real-time, data-driven decision-making and proactive maintenance. Future work may explore the integration of machine learning algorithms to further optimize diagnostics and predictive maintenance capabilities. Keywords: Autonomous Vehicles, Microservices, API-Driven Architecture, Diagnostics, Predictive Maintenance, Real-Time Data, Cybersecurity, Vehicle Support Systems, Modularity, Scalability.

Enhancing Information Exchange in Ship Maintenance through Digital Twins and IoT: A Comprehensive Framework

This article proposes a comprehensive framework for enhancing information exchange in ship maintenance through the integration of Digital Twins (DTs) and the Internet of Things (IoT). The maritime industry faces significant challenges in maintaining ships due to issues like data silos, delayed information flow, and insufficient real-time updates. By leveraging advanced technologies such as DTs and IoT, this framework aims to optimize maintenance processes, improve decision-making, and increase the operational efficiency of maritime vessels. Digital Twins create virtual replicas of physical assets, allowing for continuous monitoring, simulation, and prediction of ship conditions. Meanwhile, IoT devices enable real-time data collection and transmission from various ship components, facilitating a seamless flow of information. This integrated approach enhances predictive maintenance capabilities, reduces downtime, and improves resource allocation. The article will delve into the architecture of the proposed framework, implementation steps, and potential challenges, supported by case studies that demonstrate its practical application and benefits. By addressing these aspects, the framework aims to provide a robust solution for modernizing ship maintenance operations and ensuring the longevity and reliability of maritime assets.

Selection of Green Recycling Suppliers for Shared Electric Bikes: A Multi-Criteria Group Decision-Making Method Based on the Basic Uncertain Information Generalized Power Weighted Average Operator and Basic Uncertain Information-Based Best–Middle–Worst TOPSIS Model

This study introduces a novel multi-criteria group evaluation approach grounded in the theory of basic uncertain information (BUI) to facilitate the selection of green recycling suppliers for shared electric bikes. Firstly, a comprehensive index system of green recycling suppliers is established, encompassing recycling capacity, environmental sustainability, financial strength, maintenance capabilities, and policy support, to provide a solid foundation for the scientific selection process. Secondly, the basic uncertain information generalized power weighted average (BUIGPWA) operator is proposed to aggregate group evaluation information with BUI pairs, and some related properties are investigated. Furthermore, the basic uncertain information-based best–middle–worst TOPSIS (BUI-BMW-TOPSIS) model incorporating the best, middle, and worst reference points to enhance decision-making accuracy is proposed. Ultimately, by integrating the BUIGPWA operator for group information aggregation with the BUI-BMW-TOPSIS model to handle multi-criteria decision information, a novel multi-criteria group decision-making (MCGDM) method is constructed to evaluate green recycling suppliers for shared electric bikes. Case analyses and comparative analyses demonstrate that compared with the BUIWA operator, the BUIGPWA operator yields more reliable results because of its consideration of the degree of support among decision-makers. Furthermore, in contrast to the traditional TOPSIS method, the BUI-BMW-TOPSIS model incorporates the credibility of information provided by decision-makers, leading to more trustworthy outcomes. Notably, variations in attribute weights significantly impact the decision-making results. In summary, our methods excel in handling uncertain information and complex multi-criteria group decisions, boosting scientific rigor and reliability, and supporting optimization and sustainability of shared electric bike green recycling suppliers.

Research on risk management of ship maintenance projects based on multi agent swarm model simulation method

In recent years, the role of naval ship power has become increasingly prominent in regional conflicts and military operations worldwide, and the powerful capabilities demonstrated by naval forces have also been valued by countries around the world. While naval forces are frequently deployed to carry out various tasks, the intensity of equipment wear and tear on ships is also significantly increasing, posing a huge challenge to the maintenance and support capabilities of ship equipment. In the actual process of ship equipment maintenance, a series of risk factors such as cost, schedule, and quality will have a significant impact on the entire ship maintenance project, and even affect the success or failure of the entire project. This article first decomposes the project process of ship maintenance projects, further analyzes the various risk factors of ship maintenance projects based on the project decomposition situation, and then distinguishes the overall project, project process, and project risk factors to establish an intelligent agent group model for simulation analysis. Through the above simulation analysis, we will conduct in-depth research on the specific impact of project risks on ship maintenance projects, and analyze and verify the positive role and practical significance of project risk management in project risk control and project efficiency improvement. In the process of the above research content, methods and measures for risk management of ship maintenance projects are proposed, providing scientific and efficient risk management suggestions for such projects, improving the scientific management efficiency of ship maintenance projects, and contributing to the improvement of the quality and efficiency of project management.

Research on Maintenance Capability Standards for Drive Motor Systems of New Energy Vehicles

Developing industry recognized industry standards within the qualification framework is the benchmark for learning outcomes transformation. Based on the study of general competency standards, this article takes the maintenance competency requirements of new energy vehicle drive motor systems as a case study, and conducts a detailed analysis of the requirements for this module in vocational education undergraduate education for secondary and higher vocational schools. Finally, the vocational skill level standard for "electric vehicle high-voltage system evaluation and maintenance" is revised and preliminarily verified.

Operational excellence in total productive maintenance: statistical reliability as support for planned maintenance pillar

PurposeTotal productive maintenance consists of strategies and procedures that aim to guarantee the entire functioning of machines in a production process so that production is not interrupted and no loss of quality in the final product occurs. Planned maintenance is one of the eight pillars of total productive maintenance, a set of tools considered essential to ensure equipment reliability and availability, reduce unplanned stoppage and increase productivity. This study aims to analyze the influence of statistical reliability on the performance of such a pillar.Design/methodology/approachIn this study, we utilized a multi-method approach to rigorously examine the impact of statistical reliability on the planned maintenance pillar within total productive maintenance. Our methodology combined a detailed statistical analysis of maintenance data with advanced reliability modeling, specifically employing Weibull distribution to analyze failure patterns. Additionally, we integrated qualitative insights gathered through semi-structured interviews with the maintenance team, enhancing the depth of our analysis. The case study, conducted in a fertilizer granulation plant, focused on a critical failure in the granulator pillow block bearing, providing a comprehensive perspective on the practical application of statistical reliability within total productive maintenance; and not presupposing statistical reliability is the solution over more effective methods for the case.FindingsOur findings reveal that the integration of statistical reliability within the planned maintenance pillar significantly enhances predictive maintenance capabilities, leading to more accurate forecasts of equipment failure modes. The Weibull analysis of the granulator pillow block bearing indicated a mean time between failures of 191.3 days, providing support for optimizing maintenance schedules. Moreover, the qualitative insights from the maintenance team highlighted the operational benefits of our approach, such as improved resource allocation and the need for specialized training. These results demonstrate the practical impact of statistical reliability in preventing unplanned downtimes and informing strategic decisions in maintenance planning, thereby emphasizing the importance of your work in the field.Originality/valueIn terms of the originality and practicality of this study, we emphasize the significant findings that underscore the positive influence of using statistical reliability in conjunction with the planned maintenance pillar. This approach can be instrumental in designing and enhancing component preventive maintenance plans. Furthermore, it can effectively manage equipment failure modes and monitor their useful life, providing valuable insights for professionals in total productive maintenance.

Artificial intelligence for enhancing resilience

In an increasingly complex and unpredictable world, resilience-the ability to withstand and recover from adverse conditions is essential across various sectors. This research paper investigates the transformative potential of artificial intelligence (AI) in enhancing resilience across multiple domains. We explore how AI technology can be utilized to develop resilient infrastructure, providing advanced predictive maintenance and real-time monitoring capabilities that ensure robustness and longevity. The study examines the role of AI in improving disaster response, offering rapid data analysis and decision-making support to enhance emergency management outcomes. In climate change, AI-driven strategies are assessed for their effectiveness in fostering climate resilience, including predictive modeling of extreme weather events and optimizing resource allocation. The paper also discusses AI applications in healthcare resilience, such as enhancing diagnostics, patient care, and operational efficiency during crises. Business continuity and crisis management are examined, highlighting AI's capability to anticipate disruptions and maintain operational stability. The paper emphasizes the importance of strengthening cybersecurity resilience using AI to detect and mitigate threats proactively. AI's role in enhancing community and social resilience is analysed, particularly in supporting vulnerable populations and fostering social cohesion. Additionally, we explored AI-powered solutions for urban resilience, focusing on smart cities and sustainable development. The study also covers AI's contributions to environmental and ecological resilience, resilient supply chain management, and resilience in the hospitality and tourism industry. Finally, we investigated AI's potential in fostering psychological resilience, providing personalized mental health support and stress management tools. Through these diverse applications, the paper underscores AI's critical role in building a resilient future.

Machine Learning Algorithms for Predictive Maintenance in Wireless Sensor Networks

Predictive maintenance has emerged as a pivotal strategy in managing the operational efficiency of Wireless Sensor Networks (WSNs) across various industrial applications. This paper explores the integration of machine learning (ML) algorithms to enhance predictive maintenance capabilities within WSNs. By leveraging the vast amounts of data generated by sensor nodes, ML techniques can anticipate potential failures, optimize maintenance schedules, and reduce operational costs. We evaluate several ML algorithms, including Linear Regression, Decision Trees, Neural Networks, and Support Vector Machines, assessing their effectiveness in predicting maintenance needs. The study employs a comprehensive methodology encompassing data collection from real-world WSN deployments, feature selection, model training, and evaluation based on accuracy, precision, recall, and F1-score. Our findings indicate that Neural Networks and Support Vector Machines outperform other algorithms in terms of predictive accuracy and reliability. These results underscore the significant potential of ML-driven predictive maintenance in enhancing the longevity and performance of WSNs. The implications of this research suggest that adopting advanced ML techniques can lead to more resilient and efficient sensor networks, ultimately supporting the broader goals of Industry 4.0 and the Internet of Things (IoT).

Toward Proactive Maintenance: A Multi-Tiered Architecture for Industrial Equipment Health Monitoring and Remaining Useful Life Prediction

This research paper introduces a comprehensive proactive maintenance architecture designed for large-scale industrial machinery systems. The proposed architectural framework integrates supervised and unsupervised machine learning business processes in order to enhance maintenance capabilities. The primary objective of this architecture is to enhance operational efficiency and reduce the occurrence of problems in industrial equipment. The collection of data on the state of industrial machinery is conducted through the utilization of sensors that are attached to it. The recommended framework offers modules that might potentially implement capabilities such as immediate anomaly detection, pre-failure status prediction, and assessment of remaining usable life. We offer a prototype implementation to verify the appropriateness of the proposed framework for testing purposes. The prototype utilizes a simulation framework, Cooja, to model a sensor network. The concept entails the collection of status data from industrial machinery by each sensor. The prototype utilizes a machine learning library for data streams, the MOA framework, to design and implement a business process for anomaly detection using unsupervised machine learning, as well as a business process for early machine fault prediction using supervised machine learning. In addition, deep learning libraries are employed to construct a business process that predicts the remaining operational lifespan of industrial machinery that is anticipated to experience failure. Furthermore, we examined the efficacy of the prototype’s integrated business protocols in this investigation. The proposed framework aligns effectively with software architectures designed to offer maintenance functionalities for industrial machinery, as indicated by our research findings.

Integrating deep learning, MATLAB, and advanced CAD for predictive root cause analysis in PLC systems: A multi-tool approach to enhancing industrial automation and reliability

The integration of Deep Learning (DL), MATLAB, and Advanced Computer- Aided Design (CAD) in the root cause analysis of prognostic errors in Programmable Logic Controller (PLC) systems represents a significant advancement in industrial automation and reliability. This research explores the synergistic application of these technologies to diagnose, predict, and mitigate failures in PLC systems, which are critical for controlling automated processes in various industries. By employing DL algorithms, the study enhances predictive maintenance capabilities, allowing for early detection of anomalies and reducing downtime. MATLAB is utilized as the central platform for data processing, algorithm development, and simulation, providing a versatile environment for integrating DL models with real-time data from PLCs. Advanced CAD tools are employed to model and visualize the physical systems controlled by the PLCs, offering a comprehensive view that bridges the gap between digital analysis and physical implementation. The research methodology includes data collection from PLC systems, DL model training and validation, MATLAB-based simulations, and CAD modelling. The findings demonstrate improved accuracy in identifying the root causes of PLC prognostic errors, leading to more efficient maintenance strategies and enhanced system reliability. This paper concludes that the integration of DL, MATLAB, and CAD provides a powerful approach for advancing predictive maintenance in industrial settings, ultimately contributing to greater operational efficiency and cost savings.

Synchrophasing control of multiple propellers based on hardware in the loop experimental platform

A hardware in the loop experimental platform is established to evaluate the optimal noise reduction prediction and maintenance capability of multiple propellers under high-precision synchrophasing control. This platform incorporates an online propeller noise model and a digital turboprop engine model into a novel integrated measurement system. Firstly, an improved propeller signature theory using CFD simulation's sound pressure signals is proposed to predict the online propeller noise efficiently. It achieves acceptable noise prediction accuracy using a subset of synchrophase angles to predict noise for all synchrophase angles at all receivers. Secondly, a high-priority interrupt method is proposed for the novel integrated measurement system to guarantee precise measurement and ultimate high-precision synchrophasing control. Thirdly, a turboprop engine model based on a component level model and propeller performance maps' CFD data is also established. To enhance the simulation confidence of the system, we compare the dynamic synchrophasing control effects between systems with and without the integration of a turboprop engine mode. The experimental results demonstrate that the high-priority interrupt method effectively reduces the synchrophase angle(θ) error. These approaches reduce noise by 3.62dB at SPL, exhibit a noise variation within ±0.13dB/°, and effectively manage thrust fluctuation within 4.14%. These results indicate that the method meets the control accuracy and noise reduction requirements in a twin-engined turboprop aircraft.

Machine Learning Framework for Real-Time Pipeline Anomaly Detection and Maintenance Needs Forecast Using Random Forest and Prophet Model

This paper introduces an Intelligent Model for Real-Time Pipeline Monitoring and Maintenance Prediction to enhance infrastructure integrity and operational efficiency in Nigeria's oil and gas sector. Given the country's economic dependence on oil and gas revenue, efficient pipeline transportation is crucial. However, pipelines face challenges such as corrosion, mechanical failures, vandalism, and theft, leading to economic losses and environmental risks. Current monitoring systems are mainly reactive, lacking timely anomaly detection and predictive maintenance capabilities. To tackle these challenges, the study utilized sophisticated machine learning methods by combining the Random Forest classifier for real-time anomaly detection with the Prophet model for predictive maintenance forecasting. Datasets from Kaggle were used. The Random Forest classifier demonstrated robust performance with an accuracy of 93.48%, precision of 93.75%, recall of 96.77%, and an F1-score of 95.24%. The Prophet model provided accurate hourly forecasts of operational parameters, aiding proactive maintenance scheduling. Despite some errors encountered (RMSE: 21.48 and MAE: 18.17), the Mean Absolute Percentage Error (MAPE) of 14.87% indicates relatively minor discrepancies compared to actual values. In conclusion, the Intelligent Model shows significant advancements in pipeline monitoring and maintenance prediction by leveraging machine learning for early anomaly detection and timely maintenance interventions. This proactive approach aims to reduce downtime, prevent environmental damage, and optimize operational efficiency in Nigeria's oil and gas infrastructure. Future research could focus on enhancing system scalability across diverse terrains, employing advanced deep learning techniques such as Transformer Networks and Autoencoders for improved prediction accuracy, and exploring cybersecurity measures like blockchain integration to ensure data integrity and protect critical infrastructure from cyber threats.

Case Study of Solar Integration in HVAC Systems: Efficiency and Sustainability Outcomes

This study looks into the environmental advantages, economic feasibility, and technical viability of using solar energy to charge HVAC (Heating, Ventilation, and Air Conditioning) batteries. It also covers issues like the unpredictable nature of solar energy and the requirement for energy-storage technology. This study adds to the ongoing efforts to develop a more resilient and sustainable energy infrastructure by encouraging the incorporation of renewable energy sources into HVAC systems. PV (Photovoltaic) panels collect solar energy, a charge controller manages energy effectively, and a battery storage unit is adapted to meet HVAC needs make up the system. The purpose of solar energy integration into HVAC systems is to decrease dependency on the traditional grid, reduce environmental effects, and improve overall energy efficiency. Intelligent charge control algorithms, real-time monitoring, and predictive maintenance capabilities are some of the solar-powered charging system's key characteristics. These characteristics ensure that the HVAC system runs smoothly and leave as little of an environmental impact as possible while optimizing energy utilization. The system's scalability and adaptability to a wide range of customer needs enable it to serve HVAC applications in both residential and commercial settings.

Study of Urban Unmanned Aerial Vehicle Separation in Free Flight Based on Track Prediction

In recent years, the application prospect of urban logistics unmanned aerial vehicles has attracted extensive attention. The high-density operation of UAVs requires autonomous separation maintenance capability. To achieve autonomous separation maintenance, it is necessary to conduct autonomous track prediction and formulate the required separation accordingly. Based on the target level of safety requirements for UAV operation, aiming at the autonomous separation maintenance ability of UAVs and considering the accuracy of track prediction, a method to calculate the required separation between UAVs is proposed. This study consists of two parts. Firstly, based on historical data, the position prediction error of the flight track is investigated. Using a machine learning model, a two-stage track prediction method, which involves classification followed by prediction, is proposed for urban logistics UAV track data. Subsequently, based on the track prediction error distribution, by designing a gas model and a position error probability model, a separation-formulating model for urban logistics UAVs in free flight is proposed in which UAV maneuverability is considered. By applying this model, the required separation is formulated for UAVs. When the required separation is set to 48.5 m, the overall collision risk meets the TLS requirements. The research provides a feasible method for establishing autonomous separation for urban logistics UAVs.

Low-Power Wireless Sensor Module for Machine Learning-Based Continuous Monitoring of Nuclear Power Plants.

This paper introduces the novel design and implementation of a low-power wireless monitoring system designed for nuclear power plants, aiming to enhance safety and operational efficiency. By utilizing advanced signal-processing techniques and energy-efficient technologies, the system supports real-time, continuous monitoring without the need for frequent battery replacements. This addresses the high costs and risks associated with traditional wired monitoring methods. The system focuses on acoustic and ultrasonic analysis, capturing sound using microphones and processing these signals through heterodyne frequency conversion for effective signal management, accommodating low-power consumption through down-conversion. Integrated with edge computing, the system processes data locally at the sensor level, optimizing response times to anomalies and reducing network load. Practical implementation shows significant reductions in maintenance overheads and environmental impact, thereby enhancing the reliability and safety of nuclear power plant operations. The study also sets the groundwork for future integration of sophisticated machine learning algorithms to advance predictive maintenance capabilities in nuclear energy management.

Revolutionizing Business: The Role of AI in Driving Industry 4.0

The urgency of this research lies in understanding the critical role of Artificial Intelligence (AI) in the rapidly evolving landscape of Industry 4.0. As businesses strive to remain competitive, AI's integration into industrial processes has become essential. The primary aim of this study is to examine how AI drives innovation and efficiency within Industry 4.0. Using a literature review methodology, this research synthesizes findings from existing studies to provide a comprehensive overview of AI's impact on various business sectors, including manufacturing, logistics, and supply chain management. The results reveal that AI significantly enhances operational efficiency, predictive maintenance, and decision-making capabilities. Moreover, the study identifies key challenges in AI implementation, such as data privacy and the need for skilled workforce, while also highlighting the vast opportunities for future advancements. This research underscores the importance of AI in achieving higher levels of customization, quality, and competitiveness, paving the way for sustainable business growth in the digital era