Journal of Electronic Research and Application

Standardized Research on High-Voltage Safety of Drive Motor Systems

Bowen Yin, Hang Sun, Hui Rong — Thu, 15 May 2025 00:00:00 +0800

This paper focuses on the high-voltage safety of drive motor systems in new energy vehicles and conducts standardized research on functional safety design in the concept phase. In view of the lack of high-voltage hazard analysis for drive motor systems in existing standards, based on theories such as GB/T 34590 and ISO 26262, the safety levels are deeply analyzed. The HAZOP method is innovatively used, and 16 types of guidewords are combined to comprehensively analyze the system functions, identifying vehicle hazards such as high-voltage electric shock caused by functional abnormalities, including high-voltage interlock function failure and abnormal active discharge. Subsequently, safety goals such as preventing high-voltage electric shock are set, functional safety requirements such as accurately obtaining collision signals and timely discharging high-voltage electricity are formulated, and requirements for external signal sources and other technologies are clearly defined, constructing a complete high-voltage safety protection system. The research results provide important technical support and standardized references for the high-voltage safety functional design of drive motor systems in new energy vehicles, and are of great significance for improving the high-voltage safety level of the new energy vehicle industry, expecting to play a key role in subsequent product development and standard improvement.

Fault Diagnosis for Key Components of Metro Vehicles based on Wavelet Threshold Denoising and EEMD

Xichun Luo, Haoran Hu — Thu, 15 May 2025 00:00:00 +0800

With the increasing adoption of intelligent operation and maintenance technologies in urban rail transit, most maintenance systems have been equipped with fault diagnosis modules targeting key components of metro vehicles. However, the integration between engineering-level diagnostic algorithms and advanced academic research remains limited. Two major challenges hinder vibration-based fault diagnosis under real-world operating conditions: the complex noise and interference caused by wheel–rail coupling and the typically weak expression of fault features. Considering the widespread application of wavelet transform in noise reduction and the maturity of ensemble empirical mode decomposition (EEMD) in handling nonlinear and non-stationary signals without parameter tuning, this study proposes a diagnostic method that combines wavelet threshold denoising with EEMD. The method was applied to bearing vibration signals collected from an operational subway line. The diagnostic results were consistent with actual disassembly findings, demonstrating the effectiveness and practical value of the proposed approach.

Research on Cybersecurity Threats and Defenses in the Context of Financial Technology

Sishan Li, Wei Li — Thu, 29 May 2025 14:12:48 +0800

With the rapid development of information technology, the deep integration of the financial sector and the internet has become a key driving force for economic growth. However, while this trend brings convenience, it also poses significant cybersecurity challenges to the financial sector. This study comprehensively analyzes the current state, challenges, and protective measures of cybersecurity in the financial sector, aiming to provide important references for financial institutions in formulating cybersecurity strategies and enhancing risk management.

The Latest Research Progress of Attention Mechanism in Deep Learning

Xu Jiang, Xiaoling Bai, Lifeng Yin — Thu, 29 May 2025 00:00:00 +0800

With the development of artificial intelligence and deep learning, the attention mechanism has become a key technology for enhancing the performance of complex tasks. This paper reviews the evolution of attention mechanisms, including soft attention, hard attention, and recent innovations such as multi-head latent attention and cross-attention. It focuses on the latest research outcomes, such as lightning attention, the PADRe polynomial attention replacement algorithm, the context anchor attention module, and improvements in attention mechanisms for large models. These advancements improve the efficiency and accuracy of models, expanding the application potential of attention mechanisms in fields such as computer vision, natural language processing, and remote sensing object detection, aiming to provide readers with a comprehensive understanding and stimulate innovative thinking.

Application of Big Data Technology in User Behavior Analysis of E-commerce Platforms

Yanzhao Jia — Thu, 29 May 2025 00:00:00 +0800

With the rapid development of the Internet and e-commerce, e-commerce platforms have accumulated huge amounts of user behavior data. The emergence of big data technology provides a powerful means for in-depth analysis of these data and insight into user behavior patterns and preferences. This paper elaborates on the application of big data technology in the analysis of user behavior on e-commerce platforms, including the technical methods of data collection, storage, processing and analysis, as well as the specific applications in the construction of user profiles, precision marketing, personalized recommendation, user retention and churn analysis, etc., and discusses the challenges and countermeasures faced in the application. Through the study of actual cases, it demonstrates the remarkable effectiveness of big data technology in enhancing the competitiveness of e-commerce platforms and user experience.

Study on Smart Telematics Cache Optimization Strategy Based on Edge Computing

Yangbo Cheng — Thu, 29 May 2025 00:00:00 +0800

With the rapid development of intelligent transportation systems, vehicular networks (VANETs) have become an essential part of the intelligent transportation infrastructure. Due to the high dynamics of efficient vehicular network nodes and the low latency requirement of data interaction, the traditional cloud computing model makes it difficult to meet the real-time and performance criteria, and the storage optimization strategy based on edge computing can effectively improve the data access efficiency and system response. This paper explores optimizing the data caching mechanism of intelligent telematics using edge computing to reduce network latency, improve data availability, and enhance overall system performance.

Research on the Practical Strategy of 5G Mobile Communication Technology in Power Communication

Wanshen Peng — Thu, 29 May 2025 14:41:51 +0800

With the acceleration of the intelligent transformation of power systems, the requirements for communication technology are increasingly stringent. The application of 5G mobile communication technology in power communication is analyzed. In this study, 5G technology features, application principles, and practical strategies are discussed, and methods such as network slicing, customized deployment, edge computing collaborative application, communication equipment integration and upgrading, and multi-technology collaboration and complementation are proposed. It aims to effectively improve the efficiency, reliability, and security of power communication, solve the problem that traditional communication technology is difficult to meet the diversified needs of power business, and achieve the effect of optimizing the power communication network and supporting the intelligent development of the power system.

Enterprise Digital Planning and Architecture Based on the Industrial Internet Platform

Li Wang, Xiong Li, Juan Zhang, Ming Luo, Mengwei Liu — Thu, 29 May 2025 14:49:37 +0800

Under the current background of an information society, the digital transformation of enterprises has become a necessary means to enhance the competitiveness of enterprises. This article is based on the industrial Internet platform, the digital planning and architecture of enterprises research. First, we analyze the current challenges of digital transformation and the development opportunities brought by the industrial Internet. Then, we propose a digital planning method based on the industrial Internet platform, which takes the full connectivity of people, machine and things and intelligent decision making as the core, takes data collection, processing, analysis and application as the main line, and finally forms the top-level design of the digital transformation of enterprises. At the same time, we also built an industrial Internet platform architecture model, including the previous end perception layer, network transmission layer, platform service layer, and application innovation layer for four levels, to support enterprises in innovative applications and decision support under the industrial Internet environment. Research shows that this kind of enterprise digital planning and architecture based on an industrial Internet platform can effectively promote enterprises to achieve business model innovation, system innovation, and strengthen the flexibility and agility of enterprises to respond to market changes. The results of this research not only have important theoretical and practical significance for guiding enterprises to carry out digital planning and build an industrial Internet platform, but also provide useful reference for relevant policy formulation.

Research on Intelligent Design from the Perspective of Age-Friendly Design: Taking “Remembering” as an Example

Wenrui Xie, Dan Ni, Xinyi Liu, Xiaoxiu Cong — Thu, 29 May 2025 00:00:00 +0800

This study focuses on the elderly memo app “Remembering,” addressing memory decline and operational difficulties. It introduces a progressive interaction system with three core modules: Dynamic font adjustment, intelligent voice reminders, and family warning systems. Health monitoring and remote care functions are also integrated, creating a simple operation process. The research highlights four design dimensions for elderly-friendly products: Usability, security, emotionalization, and personalization. This innovation reduces the digital barrier and provides a model for smart elderly-friendly product development.

AI-Driven Implementation of Universal Control

Zhi Tang — Thu, 29 May 2025 15:01:25 +0800

Control serves the process technology. Therefore, the optimal implementers of process control should be process engineers rather than control engineers. While process engineers best understand the control requirements of the technology, the inherent complexity of control systems has rendered many process engineers incapable of accomplishing these control tasks ^[1]. The greatest truths are the simplest, from abacus to calculator, from DOS to Windows, each technological revolution has been driven by application-oriented simplification. Can integrated automation in process industries also achieve such extreme simplicity and rapid implementation? This is precisely what this paper aims to explore.

Research on Compliance Flight Test Technology of Integrated Modular Avionics (IMA) System

Bo Xu — Thu, 29 May 2025 15:05:16 +0800

Based on the analysis and research of the airworthiness objective of integrated modular avionics system (IMA), and the characteristics of IMA system’s comprehensive and complex cross-linking with other airborne systems, the extraction strategy of IMA system’s compliance flight test subjects and the selection method of IMA system’s compliance flight test parameters are proposed. The data analysis method based on the abnormal probability matrix of the IMA system is proposed for the first time, and the abnormal state information of the IMA system can be quickly identified. The compliance flight test of the IMA system is completed with limited flight test resources, which achieves the purpose of saving flight test sorties and improving flight test efficiency. This research has been successfully applied to the airworthiness certification flight test of a certain civil transport aircraft in China, and can provide technical support for the subsequent type flight test.

Fault Detection for Split Pins of Power Transmission Fittings in UAV Inspections via Automatic Image Cropping-based Super-Resolution Reconstruction and Enhanced YOLOv8

Shihao Cui, Zhengyu Hu, Fangcheng Qiu, Qinglong Wang — Thu, 29 May 2025 00:00:00 +0800

In modern industrial applications, ensuring the reliability of mechanical fittings is critical for maintaining operational safety and efficiency, particularly in power grid systems where split pins serve a pivotal role despite being susceptible to environmental degradation and failure. Existing UAV-based inspection systems are hampered by a low representation of split pin elements and complex backgrounds, leading to challenges in accurate fault detection and timely maintenance. To address this pressing issue, our study proposes an innovative fault detection method for split pins. The approach employs a three-step process: first, cropping operations are used to accurately isolate the fittings containing split pins; second, super-resolution reconstruction is applied to enhance image clarity and detail; and finally, an improved YOLOv8 network, augmented with inner-shape IoU and local window attention mechanisms, is utilized to refine local feature extraction and annotation accuracy. Experimental evaluations on a split pin defect dataset demonstrate robust performance, achieving an accuracy rate of 72.1% and a mean average precision (mAP) of 67.7%, thereby validating the method’s effectiveness under challenging conditions. The proposed approach contributes to the field by specifically targeting the challenges associated with split pin detection in UAV-based inspections, offering a practically applicable and reliably precise method.

Research on the Problem of Autonomous Collision Avoidance and Risk Avoidance of Ships

Qiang Tan — Thu, 29 May 2025 15:16:26 +0800

This paper deeply explores the autonomous collision avoidance algorithm for intelligent ships, aiming to enhance the intelligence level and safety of ship collision avoidance by integrating navigation experience. An autonomous collision avoidance algorithm based on navigation experience is designed, a collision avoidance experience database is constructed, a quantitative model is established, and specific algorithm steps are implemented. The algorithm is verified and analyzed through simulation tests. The results show that the algorithm can effectively achieve autonomous ship collision avoidance in different scenarios, providing new ideas and methods for the development of intelligent ship collision avoidance technology.

Design of Mechanical Automation Control System Based on Arti􀏐icial Intelligence

Zhen Sun — Thu, 29 May 2025 15:20:45 +0800

Aiming at the problems of poor adaptability and insufficient fault prediction of traditional mechanical automation control systems in complex working conditions, a mechanical automation control system based on artificial intelligence is designed. This design integrates expert control, fuzzy control, and neural network control technologies, and builds a hierarchical distributed architecture. Fault warning adopts threshold judgment and dynamic time warping pattern recognition technologies, and state monitoring realizes accurate analysis through multi-source data fusion and Kalman filtering algorithm. Practical applications show that this system can reduce the equipment failure rate by more than 30%. With the help of intelligent scheduling optimization, it can significantly improve production efficiency and reduce energy consumption, providing a reliable technical solution and practical path for the intelligent upgrade of the mechanical automation field.

Research on the Output Performance of a Solar-Cooled PV/T System

Yaolin Zhu, Hanning Zhu, Yongfeng Zhu — Thu, 29 May 2025 15:25:57 +0800

Owing to their high practicability, solar PV/T (photovoltaic/thermal) collectors have attracted considerable attention from researchers in both photovoltaic and solar-thermal fields worldwide. In this study, we designed and constructed a novel solar-cooled PV/T system. Through experimental methods, we conducted an in-depth investigation of its thermal and electrical output characteristics and developed mathematical models for both thermal performance and electrical performance. Finally, we validated the experimental data against simulations. The results demonstrate that the designed solar-cooled PV/T system exhibits excellent thermal and electrical output performance. The utilization rate of waste heat from the PV module’s back plate reached 18.59%, and the system’s electrical efficiency improved by 1.92% compared to a conventional PV/T system. This work provides theoretical and experimental guidance for the further optimization and improvement of the solar-cooled PV/T system.

Global Terminal Switching Sliding Mode Control of Robot Manipulators Based on Entire Fixed-Time Disturbance Observer

Fengning Zhang — Thu, 29 May 2025 00:00:00 +0800

This paper presents an entire fixed-time disturbance observer-based global terminal switching sliding mode control of robot manipulators, which has inner and external uncertainties. The entire fixed-time disturbance observer-based global terminal switching sliding mode control has the global finite-time reaching characteristic, the property that system convergence time can be prescribed, and the global robustness to uncertainties, with the entire fixed-time disturbance observer that accurately estimates uncertainties after a fixed time, despite the initial state. The joints of the control system can arrive at the prescribed joint angular position at the predefined joint angular speed at the prescribed time.

Research on Recommendation Algorithm Based on TrustSVD++ and XGBoost

Gongjin Chen, Yantao He, Yuting Kong — Thu, 29 May 2025 15:35:56 +0800

Aiming at the problem that the data in the user rating matrix is missing and the importance of implicit trust between users is ignored when using the TrustSVD model to fill it, this paper proposes a recommendation algorithm based on TrustSVD++ and XGBoost. Firstly, the explicit trust and implicit trust were introduced into the SVD++ model to construct the TrustSVD++ model. Secondly, considering that there is much data in the interaction matrix after filling, which may lead to a rather complex calculation process, the K-means algorithm is introduced to cluster and extract user and item features at the same time. Then, in order to improve the accuracy of rating prediction for target users, an XGBoost model is proposed to train user and item features, and finally, it is verified on the data sets MovieLens-1M and MovieLens-100k. Experiments show that compared with the SVD++ model and the recommendation algorithm without XGBoost model training, the proposed algorithm has the RMSE value reduced by 2.9% and the MAE value reduced by 3%.