Journal of Electronic Research and Application

Research on Bearing Fault Diagnosis Method based on Deep Learning

Ting Zheng — 2025-02-14

Bearing is an indispensable key component in mechanical equipment, and its working state is directly related to the stability and safety of the whole equipment. In recent years, with the rapid development of artificial intelligence technology, especially the breakthrough of deep learning technology, it provides a new idea for bearing fault diagnosis. Deep learning can automatically learn features from a large amount of data, has a strong nonlinear modeling ability, and can effectively solve the problems existing in traditional methods. Aiming at the key problems in bearing fault diagnosis, this paper studies the fault diagnosis method based on deep learning, which not only provides a new solution for bearing fault diagnosis but also provides a reference for the application of deep learning in other mechanical fault diagnosis fields.

Improved YOLOv8-based Marine Life Detection Algorithm

Qiang Li — 2025-02-12

Aiming at the problems of insufficient feature extraction ability for small targets, complex image background, and low detection accuracy in marine life detection, this paper proposes a marine life detection algorithm SGW-YOLOv8 based on the improvement of YOLOv8. First, the Adaptive Fine-Grained Channel Attention (FCA) module is fused with the backbone layer of the YOLOv8 network to improve the feature extraction ability of the model. This paper uses the YOLOv8 network backbone layer to improve the feature extraction capability of the model. Second, the Efficient Multi-Scale Attention (C2f_EMA) module is replaced with the C2f module in the Neck layer of the network to improve the detection performance of the model for small underwater targets. Finally, the loss function is optimized to Weighted Intersection over Union (WIoU) to replace the original loss function, so that the model is better adapted to the target detection task in the complex ocean background. The improved algorithm has been experimented with on the Underwater Robot Picking Contest (URPC) dataset, and the results show that the improved algorithm achieves a detection accuracy of 84.5, which is 2.3% higher than that before the improvement, and at the same time, it can accurately detect the small-target marine organisms and adapts to the task of detecting marine organisms in various complex environments.

Nonconvex Constrained Consensus of Discrete-Time Heterogeneous Multi-Agent Systems with Arbitrarily Switching Topologies

Honghao Wu — 2025-02-17

This paper mainly focuses on the velocity-constrained consensus problem of discrete-time heterogeneous multi-agent systems with nonconvex constraints and arbitrarily switching topologies, where each agent has first-order or second-order dynamics. To solve this problem, a distributed algorithm is proposed based on a contraction operator. By employing the properties of the stochastic matrix, it is shown that all agents’ position states could converge to a common point and second-order agents’ velocity states could remain in corresponding nonconvex constraint sets and converge to zero as long as the joint communication topology has one directed spanning tree. Finally, the numerical simulation results are provided to verify the effectiveness of the proposed algorithms.

Analysis of the Impact of Legal Digital Currencies on Bank Big Data Practices

Zhengkun Xiu — 2025-02-12

This paper analyzes the advantages of legal digital currencies and explores their impact on bank big data practices. By combining bank big data collection and processing, it clarifies that legal digital currencies can enhance the efficiency of bank data processing, enrich data types, and strengthen data analysis and application capabilities. In response to future development needs, it is necessary to strengthen data collection management, enhance data processing capabilities, innovate big data application models, and provide references for bank big data practices, promoting the transformation and upgrading of the banking industry in the context of legal digital currencies.

Building a Diabetes Prediction System Based on Machine Learning Algorithms

Shubo Liang — 2025-02-12

This paper explores the possibility of using machine learning algorithms to predict type 2 diabetes. We selected two commonly used classification models: random forest and logistic regression, modeled patients’ clinical and lifestyle data, and compared their prediction performance. We found that the random forest model achieved the highest accuracy, demonstrated excellent classification results on the test set, and better distinguished between diabetic and non-diabetic patients by the confusion matrix and other evaluation metrics. The support vector machine and logistic regression perform slightly less well but achieve a high level of accuracy. The experimental results validate the effectiveness of the three machine learning algorithms, especially random forest, in the diabetes prediction task and provide useful practical experience for the intelligent prevention and control of chronic diseases. This study promotes the innovation of the diabetes prediction and management model, which is expected to alleviate the pressure on medical resources, reduce the burden of social health care, and improve the prognosis and quality of life of patients. In the future, we can consider expanding the data scale, exploring other machine learning algorithms, and integrating multimodal data to further realize the potential of artificial intelligence (AI) in the field of diabetes.

Audit Recommendations for Final Accounts of Photovoltaic Power Generation Projects

Jigang Jia — 2025-02-12

With the continuous adjustment of the energy structure, photovoltaic (PV) power generation projects are increasing, playing a crucial role in promoting the application of clean energy. However, the current audit of completed final accounts for photovoltaic power generation projects faces many challenges, such as incomplete institutional processes, scattered archive management materials, inadequate digital intelligence systems, and insufficient analysis of final account amounts. Based on this, this article aims to deeply analyze these issues and propose targeted audit suggestions to standardize the construction and audit work of photovoltaic power generation projects and promote the sustainable and healthy development of the photovoltaic power generation business.

Safety Production Management During the Construction and Operation Phases of Thermal Power Enterprises

Xu Liu — 2025-02-12

In the energy industry landscape, thermal power generation stands as a critical energy supply method, and the safety of its construction and operation is paramount. Currently, all stages of the life cycle of construction projects have garnered widespread attention. Among these, the infrastructure construction and operation phases of thermal power generation enterprises pose numerous issues worthy of in-depth study in terms of safety production management. This article starts by examining safety production management during these two phases, analyzing characteristics such as management models, legal bases, and responsible entities. It explores the reasons behind these characteristics and elaborates on key management priorities, providing a comprehensive and insightful reference for safety production management in thermal power generation enterprises.

Research on the Application of Computer Science and Technology in the Context of Big Data

Meng Zhang — 2025-02-17

Computer science and technology play an important role in people’s lives and work, especially in the era of big data. The application of computer science and technology is conducive to improving people’s production and living standards and provides a strong impetus for China’s social and economic development. Therefore, this paper analyzes the application of computer science and technology in the context of big data and puts forward new trends and requirements for its future development, aiming to provide some references for the computer science and technology industry.

Optimal Power Control for Energy Harvesting in Green Cognitive Radio Networks

Qiliang Gong — 2025-02-12

The integration of cognitive radio and energy has enhanced the utilization efficiency of the spectrum and promoted the application of green energy. To begin with, this paper presents the architecture of green energy-efficient communication and network models. It incorporates the distributed network model and the heterogeneous two-tier network model into the green cognitive radio power control and channel allocation model. The primary focus of this research lies in energy conservation at the physical layer. To mitigate the interference with primary users and address the peak constraint in secondary user power allocation, the article analyzes the system model of the cognitive radio network and subsequently elaborates on the dynamic throughput maximization allocation algorithm. Eventually, through experimental analysis and verification, the distinctiveness and comprehensiveness of the optimal power control for this subject are illustrated.

Comparative Study of the Hexagonal Structure of the SiC JBS Source Region

Yili Xu — 2025-02-14

Silicon carbide (SiC) junction barrier Schottky (JBS) diode has been widely used in power electronic systems due to its excellent physical characteristics and electrical performance, and the structural design of its source area has a particularly significant impact on the performance. This study provides a comparative analysis of the SiC JBS diode performance of different hexagonal structures, aiming to provide theoretical support and practical guidance for the optimization of JBS diode performance. Through theoretical derivation, experimental verification and data processing, the paper deeply analyzes the influence of hexagonal structure on JBS diode current distribution and breakdown voltage, and proposes a targeted optimization strategy.

Analysis of Power Marketing Strategies for Market-Oriented Thermal Power Enterprises

Weiyu Wang — 2025-02-12

For thermal power enterprises, the traditional business model of scale expansion and a single product line restricts the development of electricity marketing. Therefore, to achieve the transformation and upgrading of their electricity marketing, this study starts from the current situation of the electricity market and introduces in detail the market-oriented electricity marketing strategies of thermal power enterprises from four aspects: product strategy, price strategy, channel strategy, and promotion strategy. The analysis finds that a market-oriented electricity marketing strategy is not only an inevitable choice for thermal power enterprises to respond to current challenges but also an essential path for them to move toward high-quality development. Through continuous innovation and upgrading, thermal power enterprises will maintain a leading position in fierce market competition, achieve sustainable development, and make greater contributions to the prosperity and development of the energy industry.

The Road of “Coal to Gas” in the Transformation of Energy Structure — Current Status and Strategic Suggestions for Foshan City’s Policy Implementation

Wanyi Chen — 2025-02-12

Under the guidance of national policies, the “coal to gas” project has become one of the important measures to promote the transformation of energy structure in China. Foshan, an important industrial town in Guangdong province, the implementation of the “coal to gas” policy has demonstrated significance for the optimization of the national energy structure. Through the analysis of the change in Foshan’s energy consumption structure and the implementation of the policy, this paper found that there were some challenges in the policy implementation process, such as high economic cost, lagging infrastructure, low social acceptance, and lack of technical personnel. To address this, suggestions are put forward, including increasing financial subsidies, improving laws and regulations, promoting technological innovation, and encouraging social inclusion policies. These recommendations aim to provide guidance and reference for the remaining “coal to gas” projects and the development of clean energy.

Performance Control and Application of ZnO-Based P-N Junction Piezoelectric Devices

Xudong Shen — 2025-02-14

Zinc oxide (ZnO), as a broadband gap semiconductor material, exhibits unique physical and chemical properties that make it highly suitable for optoelectronics, piezoelectric devices, and gas-sensitive sensors, showing significant potential for various applications. This paper focuses on the regulation and application of ZnO-based p-n junctions and piezoelectric devices. It discusses in detail the preparation of ZnO materials, the construction of p-n junctions, the optimization of piezoelectric device performance, and its application in various fields. By employing different preparation methods and strategies, high-quality ZnO thin films can be grown, and effective control of p-type conductivity achieved. This study provides both a theoretical foundation and technical support for controlling the performance of ZnO-based piezoelectric devices, as well as paving new pathways for the broader application of ZnO materials.

Fantasy Transportation: New Rail-Powered Flying Coach

Shuangyue Zhao — 2025-02-12

To address the challenges of long commuting times, traffic congestion, high energy consumption, and emissions in inter-city travel, a new type of flying coach has been developed. This innovation aims to significantly shorten inter-city commuting times, enhance travel efficiency, and simultaneously reduce energy consumption and emissions. The flying coach integrates rail power supply technology, an intelligent operating system, and advanced new materials, comprising a catenary power supply guide rod and various sensor components. Based on analysis of traditional aircraft design principles, the research team simulated the design of the rail-powered flying coach using software such as AutoCAD and SolidWorks for three-dimensional modeling. The analysis results indicate that, compared to traditional aircraft and rail trains, the design of the new flying coach reduces its overall weight while maintaining carrying capacity, thereby improving commuting efficiency and environmental performance. This development lays a solid foundation for creating a greener, more efficient, and convenient inter-city transportation network.

Development of Virtual Simulation System Based on Motion Control Card and Unity Platform

Shuangquan Wen — 2025-02-12

Digital twin can simulate and monitor the state and behavior of physical entities in the real world, helping enterprises to better understand and manage real-world physical systems, improve production efficiency, reduce costs, and improve safety and reliability. In this paper, we use GTS motion control card and Unity engine to build a digital twin system, and control a virtual industrial automation handling platform including two screw servo axes and multiple sensors through the physical GTS motion control card. The control card program controls the motion of the virtual model through transmission control protocol (TCP) communication, and the virtual model system feeds back the signal to the control card program to achieve the virtual and real synchronous digital twin effect. The digital twin system uses Unity engine to create a highly realistic virtual environment, and can run on multi-platform terminals.

Overview of Automatic Spraying Technology for Building Exterior Walls

Jianheng Chen — 2025-02-12

The spraying robot for building exterior walls is an innovative technology in the field of modern construction. This paper discusses its design structure, application cases, technical benefits, and industrial impacts. Research shows that this type of robot improves the efficiency and quality of exterior wall construction. Its intelligent design enhances operation accuracy and safety, reduces costs and risks, and strengthens application ability in complex environments, showing broad application prospects and symbolizing the development trend of intelligence and automation in the industry. In the future, it is necessary to strengthen its intelligence and adaptive ability further, explore multi-function design, promote automation technology, and ensure construction safety and economic benefits.

Exploration and Practice of School-Enterprise Cooperative Education Model for Computer Majors

Youfang Li — 2025-02-12

With the deepening of vocational education reform, the teaching work of computer majors in higher vocational colleges should be further optimized. Teachers should actively introduce new educational concepts and education methods, to better arouse students’ interest, strengthen their understanding and application of the knowledge, and improve the education effect. School-enterprise collaboration, as a popular education concept at present, can greatly enrich the teaching content of computer majors, broaden the path of education, and greatly promote the more comprehensive development of students. Given this, this paper will carry out an analysis of school-enterprise collaborative education for computer majors, and put forward some strategies for other colleagues’ reference.

Intelligent Irrigation System for Agricultural Greenhouse Adaptive to Crop Growth Law

Haicheng Wan — 2025-02-12

Greenhouse planting is a key method for increasing the yield of agricultural products in China. The Academy of Agricultural Sciences has conducted extensive research on the water requirements of greenhouse crops during various growth stages. Studies indicate that crops in the germination stage, seedling stage, and other stages of their growth cycle have different water needs. Proper irrigation can significantly enhance both crop quality and yield. To apply the Academy of Agricultural Sciences’ expertise on irrigation during different growth stages to practical farming, and to avoid improper irrigation at specific stages that could reduce crop production and quality, our team has designed an intelligent irrigation system for agricultural greenhouses. This system adapts to the growth patterns of crops by establishing an irrigation model based on characteristic images of each growth stage and irrigation data provided by the Academy. Using image recognition technology, the system accurately identifies the growth stage of crops. It then employs a pre-set irrigation curve and data from humidity sensors to execute precise irrigation through a closed-loop Proportion-Integral-Differential (PID) control system. This ensures optimal water management, leading to improved crop quality and yield.

Design of Intelligent Garbage Handling Trolley Based on Single Chip Microcomputer

Yaxuan Ning — 2025-02-12

This paper introduces an intelligent garbage-handling trolley model based on an STM32 single chip microcomputer as the control core. The device is driven by four independent motors to achieve automatic tracking, automatic obstacle avoidance, and fixed-point docking. Using external execution structure to realize the car without the use of a mechanical arm, complete garbage collection, storage, and uninstall function. On this basis, the type of garbage is marked by color, and the color recognition sensor is applied to realize the type recognition after garbage collection and put into the corresponding unloading point, to realize its intelligent classification function. It can automatically complete the established task autonomously.

Analysis of Supplier Demand Factors Based on QFD in Mass Customization Environment

Yunlong Zhang — 2025-02-12

Supplier selection in a mass customization environment is a systematic engineering, and Quality Function Deployment (QFD) based on customer demand is a systematic product development method. This paper studies the adaptability of the QFD method and supplier selection process in a mass customization environment and puts forward a supplier selection framework based on the QFD idea. Furthermore, both the objective environment of demand factor analysis and the thinking of the customer representatives participating in the analysis have great uncertainty and fuzziness. Therefore, a demand factor analysis method for supplier selection in the mass customization environment based on language phrases of different granularity is proposed. The proposed method allows the customer representatives participating in the selection to use their preferred language phrase set to represent the importance of demand factors. Finally, the effectiveness and feasibility of the proposed method are verified by an example of a vehicle manufacturer.

Issues and Countermeasures in Energy Measurement Management of Thermal Power Enterprises

Kunyang Li — 2025-02-12

To promote energy conservation, emission reduction, and sustainable development in thermal power enterprises, this study conducted a detailed analysis of the problems existing in measurement management in these enterprises and explored targeted solutions. The analysis found that, faced with increasingly stringent environmental protection requirements and urgent needs to improve energy efficiency, thermal power enterprises must address the current issues in energy measurement management. They should actively respond to the national call for energy conservation and emission reduction, continuously optimize energy measurement management processes, improve energy utilization efficiency, reduce unnecessary energy consumption and emissions, and lay a solid foundation for the green transformation and sustainable development of the industry.

Preliminary Study on Irradiation Device of Fission Molybdenum-Technetium Production Based on China Advanced Research Reactor

Shi Shi — 2025-02-12

As a multipurpose research reactor, fission molybdenum-technetium irradiation production is one of the wide applications of China Advanced Research Reactor CARR. The goal of this study is to achieve “online loading and unloading” of the target during fission molybdenum-99 (99Mo) to technetium-99m (99mTc) irradiation production without affecting the normal reactor operation and other irradiation channels, which will make CARR more efficient in performing irradiation tasks. This paper introduces the design principles, requirements and concept structural design of the irradiation device of fission 99Mo-99mTc.

Simulated Calculation and Measured Analysis on the Spot with the 750 kV Transformer Switch-In with Load

Licheng Zhang — 2025-02-12

Through an example of a main transformer switch-in with load during the reverse transmission of a 750 kV power plan, the paper introduces the basic principle of transformer switch-in with load. EMTPE program that is used to establish a calculation model, at the same time mainly considers the excitation characteristics of the transformer, the transient model of the circuit breaker, and the model of high voltage transformer, and calculated the inrush current with transformer switch-in with load in this plan. During system debugging in the plan, the two sets of main transformers passed the closing and opening test, and the data of inrush current in the test are recorded and analyzed. The simulation calculation and measured data show that the results are consistent. The simulation calculation also shows that it is not recommended to perform on-load closing of the transformer except for special circumstances, because of the influence of hysteresis characteristic when the transformer was switched in with load or the terminal voltage of the transformer resumed normal level from a low one after an external near-end fault was cleared, which various transformer differential protection using the characteristics of inrush to implement block scheme may mal-operate.

Vertical Power Generation Technology of Heterojunction Solar Cell

Longhai Wu — 2025-02-12

In this study, the power generation difference between the east-west and the north-south orientation of the vertically installed heterojunction solar cell (HJT) modules was deeply discussed. East-west oriented HJT module has 30% higher power generation, especially in desert photovoltaic (PV) with a bimodal distribution. While the south-north one has a single peak, the same as normal PV modules. Vertical power generation technology of HJT also has less land occupation, which is of great significance for optimizing the design of photovoltaic systems.

Development of Intelligent Manufacturing Teaching and Training Platform Based on Digital Twin

Zizheng Zhao — 2025-02-12

With the advancement and maturation of digital technology, immersive experiences, virtual interactive systems, and real physical environments are combined to create an independent “digital twin” world. In the field of intelligent manufacturing, there is a growing need to explore and develop a new platform for practical teaching based on digital twins, in line with the intelligent, networked, and digital transformation of education. By analyzing the design elements of this platform, building various digital twin prototypes and environments, and developing a teaching and training platform for intelligent manufacturing based on digital twins, significant improvements can be achieved in efficiency. Therefore, this paper discusses the development of an intelligent manufacturing teaching and training platform based on digital twins, aiming to enrich both the form and content of intelligent manufacturing training.

Study on the Hydraulic Performance and Efficiency of a Siphon Sediment Discharge Device with Bottom Hole Opening through Simulation Experiments

Henglong Hui — 2025-02-12

In this study, the hydraulic behavior and sand transport efficiency of the siphon automatic sand discharge device were studied by software simulation tests. By simulating the actual situation, this study analyzed how factors such as the difference in water level, sediment concentration, and pipeline layout affected the sediment discharge effect. The results show that the sediment discharge device can effectively discharge sediment under diverse operating conditions and show adaptability to different environmental conditions, which indicates that it is suitable for various types of reservoir environments.

Research on the Interactive Design of Smart Home Interface for the Elderly Based on QFD and HCI

Kun Wang — 2025-02-13

In an aging society, the interface design of smart home products is crucial to the quality of life of the elderly. This paper combines Quality Function Deployment (QFD) and Human-Computer Interaction (HCI) theories, taking smart washing machines as an example, to explore new paths for the interface design of smart home products for the elderly. An interdisciplinary approach is adopted to construct a design process centered on elderly users, introduce the Kano model to classify requirements, realize the mapping and sorting of requirements to design parameters, and adopt the PUGH model for comprehensive evaluation. This study provides practical and theoretical support for the interface design of smart home products for the elderly.

High-Power Laser Technology and Industrial Development Research

Can Guo — 2025-02-13

High-power laser technology is widely used in manufacturing processing, medical diagnosis, and treatment, and is one of the important fields of strategic high-tech competition in China at the moment. In the context of industrial upgrading, high-power laser technology plays an important role in leading the development of the manufacturing industry and industrial intelligence. Based on this, this paper carries out research on high-power laser technology and industry, summarizes the basic principle and classification of high-power laser technology, analyzes the current status of high-power laser technology industry, points out the opportunities and challenges faced by the industry development, puts forward suggestions to promote the development of high-power laser technology industry, and to provide an effective reference for the application and development of high-power laser technology.

Differential Privacy-Enabled TextCNN for MOOCs Fake Review Detection

Caiyun Chen — 2025-02-13

The rapid development and widespread adoption of massive open online courses (MOOCs) have indeed had a significant impact on China’s education curriculum. However, the problem of fake reviews and ratings on the platform has seriously affected the authenticity of course evaluations and user trust, requiring effective anomaly detection techniques for screening. The textual characteristics of MOOCs reviews, such as varying lengths and diverse emotional tendencies, have brought complexity to text analysis. Traditional rule-based analysis methods are often inadequate in dealing with such unstructured data. We propose a Differential Privacy-Enabled Text Convolutional Neural Network (DP-TextCNN) framework, aiming to achieve high-precision identification of outliers in MOOCs course reviews and ratings while protecting user privacy. This framework leverages the advantages of Convolutional Neural Networks (CNN) in text feature extraction and combines differential privacy techniques. It balances data privacy protection with model performance by introducing controlled random noise during the data preprocessing stage. By embedding differential privacy into the model training process, we ensure the privacy security of the framework when handling sensitive data, while maintaining a high recognition accuracy. Experimental results indicate that the DP-TextCNN framework achieves an exceptional accuracy of over 95% in identifying fake reviews on the dataset, this outcome not only verifies the applicability of differential privacy techniques in TextCNN but also underscores its potential in handling sensitive educational data. Additionally, we analyze the specific impact of differential privacy parameters on framework performance, offering theoretical support and empirical analysis to strike an optimal balance between privacy protection and framework efficiency.

U-Net-Based Medical Image Segmentation: A Comprehensive Analysis and Performance Review

Aliyu Abdulfatah — 2025-02-13

Medical image segmentation has become a cornerstone for many healthcare applications, allowing for the automated extraction of critical information from images such as Computed Tomography (CT) scans, Magnetic Resonance Imaging (MRIs), and X-rays. The introduction of U-Net in 2015 has significantly advanced segmentation capabilities, especially for small datasets commonly found in medical imaging. Since then, various modifications to the original U-Net architecture have been proposed to enhance segmentation accuracy and tackle challenges like class imbalance, data scarcity, and multi-modal image processing. This paper provides a detailed review and comparison of several U-Net-based architectures, focusing on their effectiveness in medical image segmentation tasks. We evaluate performance metrics such as Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) across different U-Net variants including HmsU-Net, CrossU-Net, mResU-Net, and others. Our results indicate that architectural enhancements such as transformers, attention mechanisms, and residual connections improve segmentation performance across diverse medical imaging applications, including tumor detection, organ segmentation, and lesion identification. The study also identifies current challenges in the field, including data variability, limited dataset sizes, and issues with class imbalance. Based on these findings, the paper suggests potential future directions for improving the robustness and clinical applicability of U-Net-based models in medical image segmentation.

Design of Universal Platform Architecture for Complex Discrete Storage System

Yangyang Zhang — 2025-02-14

The flexible satellite batch production line is a complex discrete production system with multiple cross-disciplinary fields and mixed serial parallel tasks. As the source of the satellite batch production line process, the warehousing system has urgent needs such as uncertain production scale and rapid iteration and optimization of business processes. Therefore, the requirements and architecture of complex discrete warehousing systems such as flexible satellite batch production lines are studied. The physical system of intelligent equipment is abstracted as a digital model to form the underlying module, and a digital fusion framework of “business domain + middleware platform + intelligent equipment information model” is constructed. The granularity of microservice splitting is calculated based on the dynamic correlation relationship between user access instances and database table structures. The general warehousing functions of the platform are divided to achieve module customization, addition, and configuration. An open discrete warehousing system based on microservices is designed. Software architecture and design develop complex discrete warehousing systems based on the SpringCloud framework. This architecture achieves the decoupling of business logic and physical hardware, enhances the maintainability and scalability of the system, and greatly improves the system’s adaptability to different complex discrete warehousing business scenarios.

Design for Improving the Architectural Capabilities of Complex Network Intensive and Scalable Early Warning Release System

Ruiliang Ma — 2025-02-13

In order to solve the problems of high coupling and poor scalability of the traditional monomer early warning release system architecture, multi-level deployment in a complex network environment will lead to high investment in software and hardware and cannot achieve intensive multi-level deployment. This paper realizes the goal of system scalability by introducing micro service architecture and technology stack and realizes the goal of resource intensification by introducing the idea of a data forwarding agent. The designed architecture scheme has been practically applied in the “Jiangxi emergency early warning information release system software platform (phase I) project” (hereinafter referred to as “provincial emergency”), which meets the needs of flexible deployment of multi-level applications across meteorological wide area network (Wan), business private network of other commissions, offices, and bureaus, government extranet, Internet and other complex networks, and fully verifies the scientificity and rationality of the scheme. It has achieved the goal of intensive and scalable construction of provincial emergencies under the complex network environment, greatly improved the early warning capacity and communication capacity of emergencies and comprehensive disasters, provided a reliable guarantee for disaster prevention and reduction, and provided a reference for the construction of current and future early warning release system and capacity improvement project.

A Multi-Scale Attention-Based Pedestrian Detection Method for Roadways Using the YOLOv5 Framework

Ruihan Wang — 2025-02-13

Due to multi-scale variations and occlusion problems, accurate traffic road pedestrian detection faces great challenges. This paper proposes an improved pedestrian detection method called Multi Scales Attention-YOLOv5x (MSA-YOLOv5x) based on the YOLOv5x framework. Firstly, by replacing the first convolutional operation of the backbone network with the Focus module, this method expands the number of image input channels to enhance feature expressiveness. Secondly, we construct C3_CBAM module instead of the original C3 module for better feature fusion. In this way, the learning process could achieve more multi-scale features and occluded pedestrian target features through channel attention and spatial attention. Additionally, a new feature pyramid detection layer and a new detection channel are embedded in the feature fusion part for enhancing multi-scale pedestrian detection accuracy. Compared with the baseline methods, experimental results on a public dataset demonstrate that the proposed method achieves optimal detection accuracy for traffic road pedestrian detection.

Path Planning for Thermal Power Plant Fan Inspection Robot Based on Improved A* Algorithm

Wei Zhang — 2025-02-17

To improve the efficiency and accuracy of path planning for fan inspection tasks in thermal power plants, this paper proposes an intelligent inspection robot path planning scheme based on an improved A* algorithm. The inspection robot utilizes multiple sensors to monitor key parameters of the fans, such as vibration, noise, and bearing temperature, and upload the data to the monitoring center. The robot’s inspection path employs the improved A* algorithm, incorporating obstacle penalty terms, path reconstruction, and smoothing optimization techniques, thereby achieving optimal path planning for the inspection robot in complex environments. Simulation results demonstrate that the improved A* algorithm significantly outperforms the traditional A* algorithm in terms of total path distance, smoothness, and detour rate, effectively improving the execution efficiency of inspection tasks.

Research on Innovation and Application of Integrated Media Content Generation Based on Artificial Intelligence

Xiu Wang — 2025-02-14

As an emerging form of media, integrated media not only enriches the expression and dissemination of information, but integrates various forms, both online and offline, to enable resource flow and cross-platform communication. With the development and application of information technology and 5G technology, the information needs of the broad audience have undergone a shift from a single media format to more diversified and personalized integrated media content. The rapid development of Artificial Intelligence (AI) technology has provided strong support for the generation and innovation of integrated media content. Through automation, multimodal content generation, immersive experience, and other ways, the application of artificial intelligence technology can not only improve the efficiency of content creation and enrich creative expression forms, but also provide users with more diversified and personalized information.

Study on Bionic Fabrication and Morphology of the Two Wings of the Tiger Papilio

Fuming He — 2025-02-17

Based on research into bionic butterflies for environmental detection and ecological management, a scheme was proposed to develop and manufacture a bionic aircraft with two wings inspired by specific butterfly species. A flapping-wing aircraft with a simple structure was designed, and its two-wing design was optimized. The research focused on several key areas: the design and optimization of the wings, the development of the transmission mechanism, hardware design and fabrication, and 3D printing for component manufacturing. This resulted in the bionic replication of the wing shape and structure of the Tiger Papilio butterfly. The final bionic butterfly features a wingspan of 29.5 cm and a total weight of 13.8 g. This project integrates mechatronic principles and provides a valuable reference for advancements in the field of bionic butterflies. Future research could explore the aerodynamic characteristics of wings and innovative design approaches in greater depth.

Research on Bed Call System Based on AT89C52

Hong Wang — 2025-02-13

How to realize intelligent and fast bed calls has been a key concern of hospitals. The traditional wired bed call system is not only costly but also less efficient. In this paper, research on bed call systems based on AT89C52 microcontroller is carried out. The nurse-side host (AT89C52) and the bedside slave (AT89C52) communicate over long distances using wireless communication technology. The system transmits signals, including Liquid Crystal Display (LCD), voice announcements, and beeping alarms, to indicate the bed number requiring assistance. This allows the nurse to respond promptly. The system supports real-time updates, where calls and processing occur independently, ensuring efficiency. It is not only cost-effective but also enables a rapid and intelligent call-and-response process.

Research on the Theory and Practice of Hydrogen Fuel Cell

Yan Liu — 2025-02-13

Hydrogen energy is a renewable and clean resource, that can promote the transformation of energy use terminals to green and low carbon, alleviate the current problems of energy shortage, respond to China’s “double carbon” strategy, and further implement the energy-saving and emission reduction targets. The hydrogen fuel cell is an efficient and environmentally friendly distributed power generation device, with the advantages of high energy density, zero-emission, fast charging speed, etc., and has been widely used in the fields of new energy vehicles, electric power equipment, and portable equipment. This paper analyzes the principle and advantages of hydrogen fuel cells, analyzes the key technology system of hydrogen fuel cells and the application of artificial intelligence in hydrogen fuel cells, proposes to strengthen the research on hydrogen production technology, accelerates the technical research and transformation application of key materials and core components, formulate industrial planning scientifically and actively promote hydrogen fuel cell, and promote the transformation of scientific and technological achievements, to promote the development of the hydrogen fuel cell industry.

Research on Emotion Classification Supported by Multimodal Adversarial Autoencoder

Jing Yu — 2025-02-13

In this paper, the sentiment classification method of multimodal adversarial autoencoder is studied. This paper includes the introduction of the multimodal adversarial autoencoder emotion classification method and the experiment of the emotion classification method based on the encoder. The experimental analysis shows that the encoder has higher precision than other encoders in emotion classification. It is hoped that this analysis can provide some reference for the emotion classification under the current intelligent algorithm mode.

The Integration of Modern Computer Information Technology and Artificial Intelligence

Caihua Kong — 2025-02-14

With the advent of the information age, people’s production and life are more closely connected with the Internet. Internet technology not only improves the production efficiency, but also provides great convenience for people’s life. At present, people’s requirements for computer information technology are gradually increasing. When we look directly at the information transmission and storage capacity, computer information technology cannot meet the market demand. Due to rapid development, the integration of artificial intelligence (AI) can enable the development of computer information technology. In this paper, computer information technology and artificial intelligence integration act as a starting point, and the integration of the development of the two is analyzed for reference.

Research on the Application of Small UAVs in Maritime Search and Rescue Activities

Xiuku Dan — 2025-02-14

In recent years, with the increasing frequency of global Marine activities, the occurrence probability of Marine accidents and emergencies has also increased. As a new technical means, small unmanned aerial vehicles (UAVs) have shown great application potential in Marine search and rescue activities. In Marine search and rescue activities, small UAVs can quickly arrive at the scene of the accident and carry out efficient information collection and monitoring under its simple and flexible operation. Compared with traditional search and rescue methods, small UAVs can cover a wider area, provide more detailed and accurate on-site information, provide strong support for search and rescue decision-making, and thus improve the quality and efficiency of maritime rescue. In this regard, this paper first describes the application advantages of small UAVs in Marine search and rescue activities and then puts forward effective application paths, to provide some references for relevant researchers.

Design of a Small Bionic Butterfly Machine Under the Background of Innovation and Fusion

Yaxuan Wang — 2025-02-14

With the advancement of modern technology and the continuous development of science, research into flapping wing aircraft is becoming increasingly sophisticated. Addressing issues such as the large wingspan and heavy mass of existing bionic butterfly aircraft, this paper proposes the design of a lightweight lithium battery power supply, a chip integrated into a small circuit board, and a reference to the natural characteristics of butterfly wings. The wings are simulated using 0.125 mm polyethylene terephthalate (PET) film to replicate their movement. The driving structure employs a double motor and a four-bar mechanism to achieve natural and smooth wing vibrations. The control system features a lightweight motor, battery, and a high-performance low-power microcontroller for precise control. Using 3D printing technology, a lightweight design is realized, successfully simulating the structure and movement characteristics of a specific butterfly, demonstrating the principles of mechatronics. Furthermore, the design process incorporates multidisciplinary knowledge, and a workshop combining competitive discipline events with innovation and entrepreneurship has been established. This initiative fosters the deep integration of innovation and entrepreneurship education with professional training, effectively cultivating application-oriented technical talents.

Exploration on the Construction of Intelligent Big Data Platform of Ningxia Solar Photovoltaic Industry based on NB-IoT

Huijun Wang — 2025-02-14

As China’s first new energy comprehensive demonstration zone, Ningxia’s solar photovoltaic (PV) industry has developed rapidly, but it still faces shortcomings in terms of intelligence and digitalization. This study focuses on the application and construction of an intelligent big data platform based on Narrowband Internet of Things (NB-IoT) technology within Ningxia’s solar PV industry. It explores the application trends of digital technology in the energy sector, particularly in the PV industry under the backdrop of energy reform, analyzes the technological development status of the smart energy field both domestically and internationally, and details the research methods and design components of the platform (including the photovoltaic base data platform, outdoor mobile application, remote data system, and back-office management system). The study discusses the opportunities and challenges Ningxia’s PV industry faces and proposes a construction pathway. It provides a theoretical foundation and technical support for the digital transformation of Ningxia’s PV industry, facilitating industrial upgrading and sustainable development. Although the current research is limited to the proposed design scheme, it establishes a basis for future empirical research and platform development.

Study on Flue Gas Denitrification Performance and Mechanism Based on Carbon Source of Agricultural Waste

Shufeng Li — 2025-02-14

Currently, as environmental pollution becomes increasingly severe, flue gas denitrification has emerged as a significant area of research. With the advancement of modern industry and the improvement of living standards, air pollution has gained growing attention. Sulfur dioxide and nitrogen oxides (NO_x) have become major contributors to air pollution, posing serious harm to the environment. Consequently, flue gas desulfurization and denitrification technologies have become key research focuses in industrial development. This paper explores the selection of agricultural waste carbon sources and their pretreatment methods. It provides an in-depth analysis of the significance of agricultural waste carbon sources in flue gas denitrification, focusing on their performance and mechanisms. The study also discusses the role of agricultural waste carbon sources in flue gas denitrification, aiming to offer new research perspectives for relevant stakeholders.

Agricultural IoT Security Risk Assessment Method Based on Random Forest

Xinzhe Liu — 2025-02-14

The agricultural Internet of Things (IoT) system is a critical component of modern smart agriculture, and its security risk assessment methods have garnered increasing attention from the industry. Current agricultural IoT security risk assessment methods primarily rely on expert judgment, introducing subjective factors that reduce the credibility of the assessment results. To address this issue, this study constructed a dataset for agricultural IoT security risk assessment based on real-world security reports. A PCARF algorithm, built on random forest principles, was proposed, incorporating ensemble learning strategies to enhance prediction accuracy. Compared to the second-best model, the proposed model demonstrated a 2.7% increase in accuracy, a 3.4% improvement in recall rate, a 3.1% rise in Area Under the Curve ( AUC), and a 7.9% boost in Matthews Correlation Coefficient (MCC). Extensive comparative experiments showed that the proposed model outperforms others in prediction accuracy and robustness.

Research and Application of EMUs Braking System Control Logic Based on MBSE

Wen-yu Wang — 2025-02-18

As Model-Based Systems Engineering (MBSE) was applied to the Electric Multiple Unit (EMU) braking system control logic, a preliminary exploration was conducted for bullet train braking system control logic research using an MBSE practice framework. The framework mainly includes the requirement analysis phase, functional analysis phase, and design phase. Systems Modeling Language (SysML) was used as the modeling language, and Cameo Systems Modeler (CSM) was employed as the modeling tool. By integrating the EMU braking system control logic and utilizing a top-down design approach, the implementation of MBSE in the bullet train braking system was analyzed and studied. The results show that, according to the MBSE practice framework, a unified description of the requirement analysis, functional analysis, and design synthesis of the EMU braking system control logic can be achieved. Additionally, the correlation and traceability between models can be established.

Challenges and Solutions in the Practice of “From Coal to Gas” Transformation in the Foshan Ceramic Industry

Jiayi Liu — 2025-02-18

This paper focuses on the practice of building ceramics industry in Foshan City in the clean energy transition from coal to gas, and discusses the challenges and solutions in the transition process. As an important base of China’s building ceramics industry, Foshan City’s energy transformation is of great importance to regional energy security and environmental protection. This paper summarizes the practical background and effect of Foshan’s energy transformation and points out the challenges in the process of natural gas supply stability, technological renewal, and market competition. By comparing the experience of coal to gas at home and abroad, the paper summarizes the enlightenment of policy promotion, technological innovation, and upstream and downstream cooperation in the industrial chain. Based on this, the paper puts forward policy suggestions on strengthening policy support and supervision, promoting technological innovation, and research and development. Finally, it emphasizes the importance of promoting energy transformation to Foshan’s sustainable development and puts forward practical solutions.

The Evolution of Traffic Lights: A Comprehensive Analysis of Traffic Management Systems in Shanghai

Zhichen Eden Guo — 2025-02-18

This paper comprehensively analyzes the evolution of traffic light systems in Shanghai, highlighting the technological advancements and their impact on traffic management and safety. Starting from the historical context of the first traffic light in London in 1868 to the modern automated systems, the study explores the complexity and adaptability of traffic lights in Shanghai. Through field surveys and interviews with traffic engineers, the paper debunks common misconceptions about traffic light operation, revealing a sophisticated network that responds to real-time traffic dynamics using software like the Sydney Coordinated Adaptive Traffic System (SCATS) 6. The study also discusses the importance of pedestrian safety, suggesting future enhancements such as Global Positioning System (GPS) based emergency systems and accommodations for color-blind individuals. The paper further delves into the potential of Artificial Intelligence (AI) and Vehicle-to-Infrastructure (V21) technology in revolutionizing traffic light systems, emphasizing their role in improving traffic flow and safety. The findings underscore Shanghai’s progressive approach to traffic management, showcasing the city’s commitment to optimizing traffic control solutions for the benefit of both vehicles and pedestrians.