Optimising torque for three-disc afpmsm in electric vehicles using bp_ann and anfis algorithms
Trang: 1-15 Nguyen Van Hai, Vo Thanh HaTóm tắtDesigning an optimal torque distribution controller for the three-disc axial flux permanent magnet synchronous (three-disc AFPMSM) optimises performance while ensuring robustness, stability, and adaptability in a real-world condition. This is crucial for maximising the potential of AFPMSM, particularly in a modern application like an electric vehicle and a renewable energy. Thus, a controller compatible with more complex systems in the future is essential. This paper presents a system that combines torque control algorithms based on a back-propagation neural network (BP-ANN) and an Adaptive Neuro-Fuzzy Inference System (ANFIS). The BP-ANN uses a multi-layer structure where the input layer processes factors such as load torque, rotational speed, and stator current, hidden layers model complex nonlinear interactions, and the output layer predicts optimal torque for AFPMSM operation. Training involves minimising the error between predicted and actual torque through gradient descent and iterative adjustments of weights and biases. The ANFIS-based control enhances performance by integrating neural network learning with fuzzy logic to optimise torque output. By leveraging the strengths of both BP-ANN and ANFIS, the system offers a stable, efficient, and adaptable solution for three-disc AFPMSMs. The Matlab/Simulink simulations confirm its effectiveness, showing balanced torque distribution, reduced energy losses, improved drivetrain efficiency, and adaptability to sudden load or road changes, ensuring stability and enhanced dynamic response
A clip-based dual-stream method for text based vehicle search
Trang: 16-30 Quang Huy Can, Phuong Dung Nguyen, Thuy Binh Nguyen, Hong Quan Nguyen, Thien Linh Vo, Thi Lan LeTóm tắtA text-based vehicle search refers to a system where users can find vehicles or route information by entering text-based queries. The primary objective of text-based vehicle search is to identify the most relevant vehicle in a given dataset using a natural language description as a query. This approach leverages natural language processing (NLP) to understand and interpret description queries and provide relevant results. Despite significant progress, this task still faces several challenges due to the complexity and diversity of natural language, as well as inherent difficulties in the vision domain. Moreover, few studies have focused on tracked-vehicle retrieval, where vehicle tracklets are considered instead of single images. In this paper, we propose a novel framework for natural language-based tracked-vehicle retrieval based on CLIP model, one of the most effective models for image-text matching task. This framework leverages both appearance and motion information to enhance the matching accuracy of vehicle tracklet retrieval. Some experiments are conducted on the CityFlow-NL dataset, provided by the 6-th AI City Challenge, an annual competition. The results are comparable to state-of-the-art methods, achieving an MRR score of 46.63%, Rank@5 of 67.02%, and Rank@10 of 81.82%
Convolutional neural network for determining the flow field around an airfoil and blunt-based models
Trang: 31-41 Tran The HungTóm tắtThe convolutional neural network is widely applied in the classification of images and medicine. Some current networks are used in aerospace engineering and show a high potential in determining aerodynamic forces and flow fields. This article constructs a convolutional neural network for predicting pressure and velocity fields around a two-dimensional aircraft wing model (airfoil model). Training data is computed using the Reynolds-averaged method, and then extracted, focusing on the flow around the wing. Input data includes geometric parameters, and airfoil inlet velocity, and output data includes pressure field and flow velocity around the airfoil. The convolutional neural network is based on improving the U-Net network model, commonly used in medical applications. The results show that the convolutional neural network accurately predicts flow around the airfoil, with an average error below 3%. Therefore, this network can be used and further developed to predict flow around the wing. The network is then applied to predict the pressure and pressure fields around a blunt-based model with different aspect ratios. The main feature of the flow can be extracted from the network. Results related to pressure distribution, velocity, and method error are presented and discussed in the study. This study also suggests improving the network and applying it to pressure and velocity fields in aerospace engineering
Trang: 42-52 Nguyen Thi Bich Hang, Nguyen Van DungTóm tắtThe success of BRT systems in cities such as Curitiba (Brazil), Bogotá (Colombia), Jakarta (Indonesia), Guangzhou, Beijing, Kunming (China), and Seoul (South Korea) has inspired the widespread adoption of the BRT model. However, popularize BRT systems worldwide has not always yielded successful outcomes, as evidenced by the dismantling of BRT systems in New Delhi (India), Bangkok (Thailand), and Kuala Lumpur (Malaysia) due to operational inefficiencies. This highlights the necessity of customizing BRT systems to suit the unique conditions of each city. This paper presents an analysis of the urban context of Ho Chi Minh City, addressing factors such as population distribution, land use, travel behavior, and the current state of transport infrastructure, to propose a BRT model optimized for the city’s specific conditions. The proposed result is a small-capacity BRT system with dedicated lanes shared with regular buses and open stations serving each direction is the most appropriate solution for the city. These research findings can be applied in the design of future BRT routes in Ho Chi Minh City
Trang: 53-63 Dat Tuan VuTóm tắtThe bulk cement tanker trailer frame is the main load-bearing component, and it is manufactured by the welding method. Therefore, it is necessary to evaluate the fatigue strength of the trailer frame. In this study, the fatigue stress of this structure is determined by using the hot spot stress approach. First, a combined method of finite element (FE) analysis and multi-body dynamics (MBD) simulation is used to analyse the structural stress. Considering the factors of speed and road surface class in operating conditions in Vietnam, MBD simulation is used to determine the dynamic load acting on the trailer frame when the trailer is excited by an uneven road surface. The nodal stress in the time domain is determined by structural dynamic analysis of the trailer frame with this dynamic load. The linear extrapolation of stress at the reference points is then used to determine the structural hot spot stress of the critical locations. Finally, the selected fatigue curve that corresponds to the related fatigue class (FAT) is used to calculate the fatigue life. In the fatigue analysis model, the cumulative fatigue damage value is chosen taking into account the durability degradation due to the thermal influence of the welded structures
Trang: 64-79 Trung Thi Hoa Trang Nguyen, Thanh Toan Dao, Thanh Binh NgoTóm tắtResearch on integrating camera and LiDAR in self-driving car systems has important scientific significance in the context of developing 4.0 technology and applying artificial intelligence. The research contributes to improving the accuracy in recognizing and locating objects in complex environments. This is an important foundation for further research on optimizing response time and improving the safety of self-driving systems. This study proposes a real-time multi-sensor data fusion method, termed "Multi-Layer Fusion," for object detection and localization in autonomous vehicles. The fusion process leverages pixel-level and feature-level integration, ensuring seamless data synchronization and robust performance under adverse conditions. Experiments conducted on the CARLA simulator. The results show that the method significantly improves environmental perception and object localization, achieving a mean detection accuracy of 95% and a mean distance error of 0.54 meters across diverse conditions, with real-time performance at 30 FPS. These results demonstrate its robustness in both ideal and adverse scenarios
Macroscopic evaluation of road traffic safety using Qgis: A case study of Tuyen Quang province
Trang: 79-88 Vuong Xuan Can, Bui Duy Hien, Tran Trung HieuTóm tắtRoad traffic safety in Vietnam is one of the top social concerns due to the complicated situation of traffic accidents, requiring in-depth research to find appropriate solutions. Macroscopic evaluation of traffic safety is one of the effective ways to prevent and reduce road traffic accidents. The paper presents a new method based on an Equivalent Severity Score (ESS) to evaluate road traffic safety in an area using a geographic information system (GIS) tool, namely QGIS. The road traffic accident (RTA) data from 2021 to 2023 in Tuyen Quang province, Vietnam, was used to analyze and test this method. First, the RTA data was divided by the administrative units of Tuyen Quang, using several evaluation indicators, including the number of traffic accidents, fatalities, serious injuries, and slight injuries. Then, the ESS was determined based on these evaluation indicators to measure the seriousness of RTA across the administrative units. Finally, the ranking of road traffic safety of administrative units is presented by using QGIS software. From there, the traffic authorities can easily understand areas where RTA occurs more seriously and provide reasonable solutions. The results of the paper will help traffic authorities have more basis in making decisions related to solutions to solve traffic problems not only in Tuyen Quang province of Vietnam but also in other localities
Accelerated corrosion effects on steel pipe pile materials in simulated Nhatrang seawater, Vietnam
Trang: 89-101 Nguyen Thi Tuyet Trinh, Le Trung HieuTóm tắtSteel pipe piles are widely used in coastal infrastructure due to their high strength and durability. However, in tropical marine environments like Nha Trang, Vietnam, the high chloride content, temperature, and humidity significantly accelerate the corrosion process. Despite their extensive application, no published studies have specifically addressed the corrosion behavior of steel pipe piles in Vietnam's marine environment. This study investigated the accelerated corrosion effects on steel pipe pile materials in a simulated Nha Trang seawater environment, representing typical coastal conditions in Vietnam. Using an accelerated corrosion testing method, steel pipe pile material samples were exposed to controlled Nha Trang seawater conditions with varying salinity and environmental factors such as temperature and pH. The objective of this experiment was to analyze the corrosion rate and determine the corrosion mechanisms within a short period, simulating long-term effects typically seen in real seawater environments. The experiment revealed mass loss and pitting corrosion morphology on SKK490 samples, highlighting the degradation caused by high chloride content and other conditions in the Nha Trang simulated seawater environment. The results provide critical insights into the corrosion behavior specific to Nha Trang seawater environment of Vietnam, particularly regarding the reduction in cross-sectional area of the steel pile materials. These findings offer valuable guidance for coastal infrastructure projects, especially in the selection of appropriate materials and the development of effective corrosion prevention strategies for long-term use in seawater environments
A bond strength analysis of carboncor asphalt layer on road surfaces
Trang: 102-113 Nguyen Anh Tuan, Tran Danh Hoi, Ngo Ngoc Quy, Le Xuan QuyTóm tắtTransport infrastructure is a critical component of socio-economic development, particularly in rapidly urbanizing Vietnam, where increasing traffic congestion poses significant challenges. Road surface quality and durability are essential factors in ensuring the efficiency and longevity of the transportation system. Carboncor Asphalt (CA) material, with its superior resistance to cracking, water damage, and harsh weather conditions, is a promising solution for road surface construction in Vietnam. However, there is a limitation of research on the mechanical behavior of carboncor asphalt in the specific climatic and environmental conditions of the country. To address this knowledge gap, this study investigates the shear behavior of a carboncor asphalt layer interfaced with both asphalt concrete and cement concrete surface layers. A comprehensive range of laboratory tests is conducted to assess the bond strength between the carboncor asphalt layer and the overlying road surfaces. Results indicate a negative correlation between temperature and bond strength for the overlay carboncor asphalt layer on both asphalt and cement concrete substrates. Notably, bond strength demonstrated a significant increase over time. The findings in this study are expected to have significant implications for road construction and maintenance using CA overlay in Vietnam. By providing a scientific foundation for material selection, design, and construction of road surfaces tailored to local conditions, this study aims to enhance investment efficiency and reduce maintenance costs
Trang: 114-123 Nguyen Duy Tien, Hoang Viet Hai, Tran Duc Tam, Do Anh TuTóm tắtSilica fume as a partial replacement for cement in high-strength concrete has been the focus of numerous studies. However, the impact of substituting cement with silica fume in concrete mixtures on the mechanical and thermal properties of high-strength concrete remains insufficiently explored. Silica fume, characterized by its high pozzolanic activity and ultra-fine particles, is incorporated into concrete mixtures to enhance their mechanical properties and durability. The research examines the influence of varying silica fume content on the compressive strength and CTE of high-strength concrete. In the present study, concrete specimens with a water-cement ratio of 0.32 were prepared, with 5%, 10%, and 15% of the cement replaced by silica fume. Experimental results demonstrate that silica fume significantly improves compressive strength, particularly at early ages, starting from 7 days. However, the CTE of these mixtures is not significantly affected, with the average values varying slightly, ranging from 8.95 to 9.93 × 10⁻⁶/°C. This study contributes to further clarifying the role of silica fume in concrete mixtures and its effect on the CTE
