Volume 16 Issue 8
Published on September 2025The emergence of AI technology has brought about tremendous changes in human life. The traditional ways of working and living in the past have been further optimized by AI, evolving into more advanced forms of development. In terms of sustainable development, artificial intelligence technology has shown promising prospects, paving the way for increasingly long-term and viable progress in the future. This paper adopts a combined research approach, integrating literature review, case analysis, and qualitative research, to systematically explore the technological application paths and practical challenges of artificial intelligence in the field of sustainable development. While AI provides robust technical support for sustainable development, this paper argues that it is crucial to balance efficiency improvements with ethical risks through technical iterations, upgrading human skills, and optimizing policy frameworks. By doing so, we can achieve in-depth optimization of human-machine collaboration and promote long-term, sustainable development.
View pdf
This paper provides a comprehensive review of supercapacitors as an emerging energy storage device, highlighting the various issues and challenges they face. It discusses the progress in energy storage mechanisms, electrode materials, electrolytes, separator materials, and practical applications. The paper summarizes the advantages and disadvantages of electric double-layer capacitance, pseudocapacitance, and hybrid capacitance mechanisms. It evaluates the application prospects of carbon-based materials, metal oxides, and conductive polymers in electrode design; the optimization strategies for aqueous electrolytes, organic electrolytes, and ionic liquids; and the application requirements for biomass-based separators, synthetic polymer-based separators, and inorganic composite separators. In practical applications, supercapacitors demonstrate their function as high-energy storage devices and have shown promising integration in vehicular batteries and lithium-ion battery systems.
View pdf
In the context of rapid digital transformation, artificial intelligence (AI) and big data have become pivotal forces reshaping decision-making processes across industries such as healthcare, finance, retail, manufacturing, and transportation. This paper investigates the integration of AI and big data, aiming to explore their combined impact on organizational efficiency and predictive accuracy. The research adopts a comprehensive literature review methodology, analyzing scholarly articles, industry reports, and real-world applications to evaluate how these technologies are applied, the challenges they present, and future directions. Through this method, the study identifies key trends in the deployment of AI-powered analytics, including predictive modeling, personalized services, and automated operations. It also addresses critical issues such as ethical concerns, data security, and scalability. The findings suggest that while AI and big data significantly enhance operational performance, their responsible implementation requires robust frameworks for fairness, transparency, and privacy protection. This study concludes by emphasizing the need for collaborative efforts among governments, academia, and industry to ensure equitable access and sustainable technological advancement.
View pdf
With the nationwide promotion of Mandarin, regional dialects are gradually fading, especially among the elderly, who often face communication barriers due to limited proficiency in Mandarin. This negatively impacts their quality of life and social participation. This study aims to enable high-quality bidirectional translation between Cantonese and Mandarin, contributing to dialect preservation and the inheritance of intangible cultural heritage. Based on the Transformer architecture, we fine-tuned Meta’s multilingual translation model, NLLB-200, using a self-constructed Cantonese-Mandarin parallel corpus. Data sources include subtitles from short video platforms, local forums, and community interview transcripts, resulting in a high-quality corpus of 200,000 sentence pairs. Technically, we employed transfer learning and data augmentation strategies to enhance performance in low-resource environments, and evaluated the model using BLEU and chrF metrics. On the test set, the fine-tuned model achieved a 17.3% improvement in BLEU score, with translations showing natural fluency, indicating that NLLB-200 has strong dialect translation capabilities. Additionally, we explored deploying the system on mobile devices to develop a lightweight voice translation application for elderly users, enhancing usability and accessibility. This research not only validates the effectiveness of NLLB-200 in low-resource language translation tasks but also provides a reference path for the promotion and application of multi-dialect translation technologies. By combining technological innovation and social service, it significantly contributes to the protection and revitalization of dialects in the digital era.
View pdf
With the advancement of artificial intelligence (AI) technologies, object detection, data processing, and lidar navigation have become increasingly prevalent in autonomous driving, offering convenient transportation solutions. However, challenges such as low obstacle detection accuracy, high error rates, and frequent failures in emergency avoidance persist, necessitating further research into AI applications in autonomous driving. This paper explores the application scenarios of object detection, data processing, and navigation technologies in autonomous driving, compares the advantages and disadvantages of autonomous and human driving, and proposes a solution based on the fusion of data processing, visual navigation, and lidar navigation. The aim is to enhance the intelligence level of autonomous driving and provide theoretical support and practical references for the technology.
View pdf
Aiming at the problems of traditional path planning algorithms, such as high computational complexity, low search efficiency, and poor smoothness of planned paths due to non-compliance with kinematic constraints, this paper proposes a path planning method for plant protection Unmanned Aerial Vehicles (UAVs) based on the fusion of dynamic weight functions and Bézier curves. Firstly, the overall framework of the path planning algorithm is constructed based on the A* algorithm, and a weight function dynamically adjusted with the path is introduced to improve the heuristic function of the A* algorithm, which effectively reduces the number of search nodes and improves the overall search efficiency. Subsequently, the second-order Bézier curve is fused with the improved A* algorithm to reduce the number of turning points in the path planning process of the A* algorithm and improve the smoothness of the path. Finally, the effectiveness of the algorithm is verified based on Python and MATLAB platforms. The research results show that compared with the traditional A* algorithm, the improved A* algorithm fused with the dynamic weight function and Bézier curve can significantly improve the search efficiency and path smoothness; moreover, although the search efficiency of the search algorithm using dynamic weight coefficients is similar to that of the traditional algorithm, its path planning quality is significantly improved.
View pdf
Agriculture is a cornerstone of global food security, yet it faces significant challenges in the modern era, including labor shortages, environmental pressures, and the need for sustainable practices. Traditional farming methods are often labor-intensive and inefficient, leading to increased costs and reduced productivity. To address these challenges, the integration of advanced technologies into agricultural practices has become essential. Among these technologies, computer vision has emerged as a powerful tool, offering precise and automated solutions that can significantly enhance farming efficiency and sustainability. This paper presents a comprehensive review of computer vision technologies and their algorithmic applications in agricultural robotics, highlighting their transformative role in modernizing traditional farming practices. The study underscores computer vision as a pivotal driver for scalable, efficient, and sustainable agriculture, with future potential in resource optimization and food security. Proposals for future computer vision-enabled agricultural robots in the fields of picking and weeding, crop identification, path planning, pest detection, seed screening, etc.
View pdf
With advantages such as high power density, long cycle life, and environmental friendliness, flywheel energy storage systems hold great promise in applications like renewable energy integration and grid frequency regulation. As the core component for energy storage, the rotor’s stress distribution and evolution under high-speed rotation directly affect the system’s safety and reliability. This paper reviews the stress analysis of rotor materials and structures in flywheel energy storage systems, systematically summarizing current research progress. First, from the perspective of material constitutive properties, it compares the stress responses of conventional metals (e.g., steel and aluminum alloys) and high-performance composite materials (e.g., carbon fiber-reinforced polymers and metal matrix composites) under centrifugal loads, with a focus on the failure mechanisms of anisotropic materials, high-cycle fatigue stress, and thermo-mechanical coupled stress. Second, in terms of structural design, it explores the influence of topology optimization, thin-walled hollow structures, and stiffener configurations on stress concentration and distribution within the rotor, and elaborates on the complex evolution of stress fields under multi-physics coupling (centrifugal force, temperature, and electromagnetic fields). Furthermore, it summarizes the current applications of finite element simulation, experimental methods (strain gauges and digital image correlation), and multi-objective optimization in stress analysis. The study shows that although existing research has revealed the critical influence of material and structural parameters on stress, challenges remain in areas such as refined modeling of multi-field coupling, integrated material-structure optimization, and full lifecycle stress prediction. Future research should integrate the development of novel materials with intelligent design approaches to deepen the understanding of stress mechanisms and provide theoretical support for the lightweight and high-reliability design of flywheel energy storage rotors for engineering applications.
View pdf
This paper aims to study the spatial distribution pattern and influencing factors of land use carbon budget in 19 urban agglomerations in China based on the "dual carbon" goal, and provide a theoretical basis for land use optimization and "dual carbon" decision-making in the development process of China's urban agglomerations. Based on land use data from 19 urban agglomerations in China in 2022, this study calculates the carbon budget for these agglomerations. Spatial autocorrelation analysis and cluster analysis are employed to study the spatial variation pattern of the carbon budget. Furthermore, the influencing factors of the carbon budget are explored from economic, demographic, and energy consumption perspectives, and a regression model for the carbon budget based on key influencing factors is constructed. Research has found that: (1) In 2022, the spatial pattern of the carbon budget across the 19 urban agglomerations in China exhibited characteristics of "higher carbon emissions in the east and lower in the west, higher carbon sequestration in the south and lower in the north." Based on the carbon budget distance, these agglomerations can be roughly clustered into five categories. (2) According to the hot spot analysis of the carbon budget, hot spots for carbon emissions are concentrated around the Bohai Rim in northern China, while hot spots for carbon sequestration are concentrated in northeastern, southeastern, and southwestern regions. (3) Energy consumption, population size, and GDP are the primary factors influencing carbon emissions, while net primary productivity (NPP) of vegetation and precipitation are the main factors influencing carbon sequestration. In summary, the land use of urban agglomerations should be rationally planned, ecological protection should be emphasized, and the carbon sink capacity of urban agglomerations should be consolidated and improved. Formulate differentiated carbon emission reduction measures according to local conditions, focus on optimizing energy consumption and industrial structure, reasonably control the number of population, build urban green space, and give full play to the important role of vegetation in carbon absorption.
View pdf
Pointer-type instruments remain widely used in industrial environments due to their cost-efficiency and reliability. However, manual reading of such instruments is labor-intensive, error-prone, and unsuitable for real-time monitoring. This paper presents a lightweight and interpretable method for automatic pointer-type instrument recognition using classical image processing techniques provided by OpenCV. The proposed approach includes image preprocessing, circular dial detection via the Hough Circle Transform, scale calibration, pointer extraction using probabilistic Hough Line detection, and value computation through geometric analysis. Experimental results on standard analog gauge images demonstrate the method’s accuracy in identifying gauge boundaries, calibrating tick marks, and determining the pointer's angular position. The approach enables flexible value mapping and delivers reliable readings under standard lighting conditions. Compared to deep learning methods, this solution offers better computational efficiency and easier integration into resource-constrained systems. It is particularly suitable for industrial automation and retrofitting of legacy analog devices. Future work will focus on improving robustness under complex backgrounds and dynamic conditions.
View pdf