Journal of Military Science and Technology

Fault detection in wind turbine based on machine learning

Dr Minh Nguyen Quoc — 2024-04-22

Renewable energy in general and wind energy in particular are receiving increasing attention with the goal of reducing greenhouse gas emissions and producing clean energy. In recent years, wind farms and plants have significantly increased, driving wind energy to become an immensely potential energy source. However, due to the unpredictable nature of wind energy, ensuring the safe operation of wind turbine systems, minimizing downtime due to malfunctions plays a crucial role in optimizing production costs and enhancing the system's reliability. In this study, the authors propose using machine learning models to detect issues occurring in wind turbine systems. Operational parameters measured from SCADA are used as input data for the machine learning models. The results indicate that machine learning models can detect issues in the wind turbine system with an accuracy of over 99%, with model training taking only tens of milliseconds.

Application of multi-agent deep reinforcement learning method to solve the dynamic weapon target assignment problem

Xuân Trường Nguyễn — 2024-04-22

This paper presents the Multi-Agent Deep Reinforcement Learning method to solve the dynamic weapon target assignment (DTWA) in the air defense command and control system. The weapon model is built based on predicting the optimal trajectory of air targets and the status of objects on the ground, as well as the optimal plan to coordinate the activities of weapons in the system. The weapon model is built on the OpenAI Gym library, describes the rules of the dynamic air defense combat environment and uses deep reinforcement learning algorithms (Deep Q-Leanring) to optimize the policy. Experimental simulation results with different air defense scenarios demonstrate that, after being trained, the deep reinforcement learning model of the air defense weapon has the ability to automatically analyze, perceive situations, and coordinate with other air defense weapons in the system, build a dynamic resistance interaction plan and select the optimal plan taking into account practical constraints so that the overall loss function has a minimum value for the entire combat process. Therefore, the reinforcement learning model has the ability to be applied to develop software modules to support decision-making in the air defense command and control system.

Application of neural networks in diagnosing engine faults based on vibration signals

Nguyễn Đức Thành — 2024-04-22

This paper investigates and applies artificial intelligence (AI) to improve the monitoring and diagnosis process of electrical engine faults based on vibration signals. The research aims to build a model to collect sample data from engines and utilize three different AI networks in this study, including YOLO (You Only Look Once), Resnet (Residual neural network), and SVM (Support Vector Machine). By applying these models to independently identify faults using the common input signal of vibration, particularly focusing on bearing-related faults in engine systems, the paper concentrates on exploring various faults. The experimental results presented in the paper demonstrate the accuracy of using these networks in diagnosing engine faults and provide important insights into the accuracy and practical applicability of AI networks in the field of industrial equipment maintenance and management.

Advanced algorithm for improving the quality of filtering and tracking multiple marine targets for command and control

Xung Ha Vo — 2024-04-22

In this article, an advanced algorithm for improving the quality of filtering and tracking multiple marine targets for command and control based on analysing high-resolution radar images is proposed. The proposed method includes two stages. The first stage of the proposed method is used for estimating target characteristics such as: center coordinates, reflected energy, movement direction and window tracking size. These charateristics are used as inputs for the second stages. The effectiveness of the algorithm is evaluated by simulation of filtering tracking two targets moving close together using MATLAB tool. The simulation results are compared with other methods such as GNN and JPDA. The results show that the proposed algorithm limits the limitations of the GNN and JPDA methods that confuse or lose the trajectory of the above algorithms.

Pitch angle control based on uncertainty observation for hydraulic motor system in wind turbine

Thước Nghiêm Xuân — 2024-04-22

This article presents a model of a servo hydraulic motor driving a wind turbine blade under the influence of total uncertainty including model error, wind load moment and moment caused by friction, thereby Apply uncertainty controllers and monitors to increase accuracy and stability in the process of controlling the pitch angle of the propeller. A control structure combining a disturbance observer and a Dynamic Surface Sliding Controller (DSC) has been proposed, in which the observer is designed to deal with the harmful effects that the uncertain disturbance component causes to the system. wind turbine system, the accuracy of the control system is significantly improved thanks to the appearance of the observer. The proposed control structure ensures stability for the entire wind turbine system through verification using Lyapunov stability theory. Numerical simulations were performed comparing the proposed controller with Backstepping controllers (BSP) and dynamic surface sliding controls, clearly showing a clear improvement in control quality.

Technical assessment of the influence of rooftop solar power system on power loss of the ray-shaped urban distribution grid in Vietnam

Vu Hoang Giang — 2024-04-22

The penetration of solar power into the distribution grid in general has fundamentally changed the nature of the load from only power consumption to both consumption and power generation into the grid. Because of that, the flow of current in the grid also changes, there are cases where the curent runs backwards from the load to the transformer. This paper introduces the results of research to assess the influence of rooftop solar power (PV) on the power loss of urban distribution grids in Vietnam. First, the typical structure of the distribution grid is selected to simulate the conditions of penetration and locations of PV on each phase along the length of the line. The solar radiation intensity and the typical load profile of the urban distribution grid are also taken into account to observe changes of power loss in the grid. The research results show that under the influence of PV, the power loss has a great change according to the penetration level and the variation of the load.

Research to optimize fiber manufacturing and 3D printing for CF/PA6 materials

Thế Dũng Đinh — 2024-04-22

Research and manufacturing of 3D printing fibers using polyamide 6 (PA6) polyamide and short carbon fibers are conducted, and these fibers are utilized for printing samples. The study involves the utilization of BASF's 6 polyamide and Toray's (Japan) carbon fiber with a length of less than 300μm to produce 3D printed fibers. The mechanical properties of various fiber processing conditions are assessed by measuring tensile strength and bending strength. The tensile strength of 3D printing fibers is determined by analyzing printing samples, which allows for the evaluation of mechanical properties under various printing settings. The optimal conditions for achieving the highest strength in CF/PA6 3D printing fibers are a melting temperature of 270 ^oC, a screw speed of 50 rpm, and a pull speed of 5 cm/s. The optimal conditions for 3D printing in survey settings involve achieving the maximum pull resistance by using infill density of 50%, concentric pattern, wall thickness of 2 layers, and a layer height of 0.1 mm.

Research on the ability of 2,4-Dichlorophenoxyacetic and 2,4,5-Trichlorophenoxyacetic degradation by oxidation catalyst at hight temperature

Nguyễn Thị Thùy Dương — 2024-04-22

Research on the ability to decompose 2,4-D and 2,4,5-T by catalytic oxidation at high temperatures. Currently, soil contaminated with 2,4-D and 2,4,5-T is still an urgent problem that requires appropriate treatment plans. The heating method combined with high pressure is of great interest. This article presents the results of research on treating soil contaminated with 2,4-D and 2,4,5-T in soil under different conditions of temperature, time and amount of catalyst. Determination of 2,4-D and 2,4,5-T residues in soil before and after treatment by liquid chromatography (HPLC). The article has researched and proposed a technological process with the most optimal temperature, time, and catalyst factors to achieve near-absolute efficiency for treatment.

Optimization of the synthesis parameters and analysis of characteristics of 1,1-diamino-2,2-dinitroethylene

Hóa Nguyễn — 2024-04-22

2,2-Dinitroethene-1,1-diamine (FOX-7) is a low-sensitive explosive suitable for various energy-material applications. It can be synthesized based on the nitration and hydrolysis of heterocyclic precursors derived from 2-methylimidazole-4,5-dione (MID) or 2-methylpyrimidine-4,6-diol (MPD). However, more information about its optimal synthesis parameters during production from MPD as a starting material is needed. In this study, Taguchi's experimental design method was used to improve the yield of FOX-7. Verification of the results shows that the optimal synthesis parameters are as follows: the molar ratio of HNO₃/MPD is 8, the reaction time is 180 minutes, and the reaction temperature is 15°C; the maximum yield of FOX-7 can reach 79.14%. Furthermore, the synthesized FOX-7 was identified and characterized by nuclear magnetic resonance (NMR) spectroscopy analysis, Fourier transforms infrared spectroscopy (FTIR), Raman spectroscopy analysis, and powder X-ray diffraction (PXRD).

Improving the durability of polyester geotextiles with fluoropolymer/bitum organic coatings in application of coast protecting construction

Phuong Chien Tran — 2024-04-22

This study aims to manufacture and test protective coatings for polyester geotextiles (DKT) to enhance fabric durability and application in building soft embankments to reduce waves to protect the sea. The coating was made from Fluoropolymer/bitumen/cashew oil polymer matrix, UV resistant additives and some other additives. The manufactured coating satisfied the requirements for adhesion, increased mechanical properties and environmental durability for polyester DKT fabric. Mechanical properties were determined by measuring tensile strength. The physico-chemical properties of the coating were tested through TGA/DSC and FTIR analysis methods. Environmental durability was determined by the QUV test method of 2000 hours with a cycle of 4 hours of UV irradiation and 4 hours of mist spraying. Research had established the optimal coating formulation. Test results also showed that the coating helps polyester ĐKT fabric increase physical and mechanical properties by 27% and environmental durability by 30%.

Research on the material composition and performance of Li-Si/FeS2 thermal batteries

Tri Thien Vu — 2024-04-22

Thermal batteries are disposable storage batteries that use electrolytes that are molten inorganic salts in the temperature range of 400 ÷ 550 ^oC. Along with the development of science and technology, thermal batteries are constantly being researched to improve technical features, such as reducing activation time and mass, while increasing capacity, energy density, working duration, storage time, and ability to withstand harsh working conditions. In this article, we present the results of a study on the chemical composition of Li-Si/FeS₂ thermal batteries and the performance of a single cell as well as a full battery. The analysis shows that the thermal battery utilizes pellet pressing technique. The anode is made of FeS₂, the cathode is made of Li-Si alloy, the electrolyte is a mixture of LiCl and KCl, and the pyrolysis agent is Fe:KClO4. A single cell's voltage is 1,8 V, and a full thermal battery's voltage is 22 V at a 1,5 A discharge current.

Evaluation of changes in decorative properties and service life for acrylic paints in the climatic conditions in Northern Vietnam

Dr Dinh Trung Do — 2024-04-22

Northern Vietnam is characterized by four distinct seasons (spring, summer, autumn, and winter), with winters typically dry and summers ranging from hot to mild. Materials (typically protective coatings for steel structures) used in this climate zone are also subject to extremely complex influences and are quickly destroyed. Therefore, the service life and decorative properties of coatings are always of concern to users and paint manufacturers. This work presents results of service life prediction, changes in gloss, and color of acrylic paint by accelerated tests. Stages of the accelerated test were simulated according to rural tropical conditions at Hoa Lac station (Yen Binh commune, Thach That district, Hanoi city, Vietnam). The service life of acrylic paints is determined according to Russian State standard GOST 9.401-2018, gloss is determined according to Vietnamese standard TCVN 2101:2016, and the color change is determined according to TCVN 9882:2013. Results of the accelerated test have shown that the corrosion time of acrylic paints reaches Ri 3 (according to TCVN 12005-3:2017 assessment), the service life of acrylic paint AR-752 is 3.35 years, and paint Tar 5366 is 3.60 years.

Research on synthesis of imidazole-based ionic liquids as metal corrosion inhibitors

Bang Ha Quoc — 2024-04-22

Ionic liquids (ILs) have gained significant attention in recent years as potential corrosion inhibitors to various applications. Traditional corrosion inhibitors, such as organic compounds and inorganic salts, have limitations in terms of toxicity, volatility, and environmental impact. However, ionic liquids offer a promising alternative. Ionic liquids are salts that exist in a liquid state at or below 100 degrees Celsius. They typically comprise an organic cation and an inorganic or organic anion. The unique combination of a liquid state and ionic nature gives them several advantageous properties, such as high thermal stability, low vapor pressure, and tunable physicochemical properties. Additionally, the charged nature of the ionic liquid allows for electrochemical interactions with the metal surface, further enhancing corrosion inhibition. In this paper, imidazole-based ionic liquids were synthesized by alkylation of imidazole derivatives using 1-bromohexadecane. The anti-corrosion properties of the material were evaluated using the weight method and potentiodynamic polarization method. Results showed that the synthesized ILs are good corrosion inhibitor for CT3 steel.

Research on formulating ingredients and evaluating the conversion process of 2-chloroethyl phenylsulfide of green decontamination based on tungsten

Thanh Bình Vũ — 2024-04-22

This paper presents the results of research on formulating ingredients and evaluating the detoxification efficiency of 2-chloroethyl phenylsulfide (2-CEPS is a simulant of the military poison yperit) of green decontamination based on tungsten. Each main component of green decontamination was investigated and their roles in the detoxification process were determined, including catalyst (K₂WO₄), oxidant (H₂O₂) and buffer (C₆H₅K₃O₇ và K₂CO₃). From the research results, a detergent formula has been proposed that has a 2-CEPS conversion efficiency of over 99% after 15 minutes (TĐX-2). At the same time, a number of products were identified, thereby suggesting the mechanism of 2-CEPS conversion process within 30 minutes of the reaction.

ISO 4037 narrow spectrum X-ray reference field: Simulation and measurement

Ngoc-Thiem LE — 2024-04-22

The paper presents the characteristics of the ISO-4037 narrow spectrum X-ray reference fields in 02 different manners: simulation using the SpekPy and measurement using a calibrated ionization chamber. The physical (air Kerma rate) and radiation (X-ray fluence-spectrum-averaged energy, the first and the second half value layers, as well as the beam homogeneity coefficient) quantities were simulated using the SpekPy web-based simulation toolkit. In addition, air Kerma rates were measured by the ionization chamber. The characteristics of the ISO-4037 narrow spectrum X-ray reference fields were determined for various X-ray beam qualities (i.e., N-40, 60, 80, 100, 120, and 150) at 250 cm from the X-ray focal spot. The air Kerma rate tendency was deduced by comparing simulation and measurement data. The combined standard uncertainty of measured air Kerma rate was investigated and presented.

Research, calculation, and simulation to investigate the influence of machine setting errors on the performance of thermal imaging systems

Đình Phước Dương — 2024-04-22

This article studies the effects of Single Point Diamond Turning (SPDT) setting errors on machined surface errors and offers solutions to evaluate the effects of these errors on the optical system by simulating aspherical/diffraction surfaces after machining and the entire optical system in Zemax optical design software. The results show that the main types of errors, such as off-axis and tool tilt, will reduce the MTF function and change the focal length of the optical system, especially off-axis errors.

A hybrid terrain data compression method in unity for deployment on resource-limited devices

Luu Van Sang — 2024-04-22

With geographic information systems in general and simulation systems in particular, terrain data takes up most of the hard drive space and is often deployed on data servers. The higher the resolution of the terrain data, the more detailed it is, the larger the space occupied on the hard drive. If terrain data needs to be deployed offline on resource-limited devices such as minicomputers, it will face many difficulties due to hard drive space limitations. Terrain data compression is a solution that reduces terrain capacity to overcome that problem. This article presents an efficient hybrid approach based on Brotli and LZ4 compression algorithms to compress terrain data for deployment on resource-limited devices. Experimental results show that the proposed method significantly reduces the volume of terrain data compared to using each component algorithm independently while still ensuring quality.

A method of drawing double arrow symbols with automation support for 2D digital map applications

Mac Van Vien — 2024-04-22

This paper addresses the challenges of translating pivotal military symbols like double arrows onto 2D digital maps, particularly when automation is essential. It proposes a comprehensive method integrating data structure, user workflow, and algorithms to generate tactically aligned, balanced, and visually appealing double arrows for military 2D digital maps. Experimental validation affirms its efficacy in meeting tactical requisites and aesthetic standards. Additionally, it outlines avenues for future research to further enhance and broaden the applicability of this method. In essence, this study presents a robust solution for the automated generation of double arrows on 2D digital military maps, marking a significant step in advancing automated symbolization for military planning.

Predict software project completion time and cost using XGBoost

Thế Anh Lê — 2024-04-22

Nowadays, with the rapid development of information technology, managing costs and time to complete software projects has become an urgent issue. To be able to manage software projects, the need to predict costs and completion times is extremely important. Traditional methods often use EVM earned value management to predict project costs and completion times. However, this method often does not achieve very high accuracy when the data has a lot of noise. In recent years, machine learning methods have emerged as a useful solution for leveraging past data to predict future values. In this study, we propose to use the XGBoost machine learning model to predict project costs and completion time. Experimental results show that XGBoost has the potential to solve this problem.

Application of deep learning in computer vision for the target detection-tracking system on shoulder-training flight vehicles

Công Đặng — 2024-04-22

The paper presents an application of a deep learning model in computer vision for the target detection and tracking system on shoulder-training flight vehicles. The purpose of the research is to use the digital camera system as a simulated detection and tracking system similar to the features of the seeker of shoulder-launched flight vehicles, as a basis for building shoulder-training flight vehicles. To detect and track moving targets outdoors, 3D target detection ability must meet accuracy requirements; however, when traditional image processing algorithms are applied, they are not effective. To solve this problem, the article focuses on researching and applying the YOLO deep learning model to the digital camera tracking system. Using the YOLO version 8 model, the authors tested data collection, image processing and model training as well as considered the target detection and tracking ability of a digital camera system. At the same time, a newly designed shoulder-training flight vehicle - 72 millimeters with a digital camera tracking system was tested outdoors. As a result, detecting and tracking the target by the digital camera system similar to the shoulder-launched flight vehicle - 72 millimeters in a specifically limited range condition is obtained.

Investigation of dynamic and vibrational parameters of anti-tank missile launchers using the "dynamic-reaction" launch principle

Bùi Đình Tân — 2024-04-22

Anti-tank missiles are launched according to the "dynamic-reaction" principle, creating a high velocity for the missile in a short period of time, minimizing the recoil of the launch system. Because the launch phase takes place in a very short time (size 0.02 s), the processes take place quickly, easily unbalanced, causing danger to the equipment and the gunner to shoot. The article proceeds to build a mathematical model describing the processes taking place in the launch phase, determining the dynamic parameters of the projectile and the launch system. This is the theoretical basis used for the design and manufacture of the launch system according to this principle. The application calculates the typical anti-tank missile prototype system.

Research on design and manufacturing technology of integrated circuit for calibration signal circuit board in 9П516 launching structure

Trịnh Anh Văn — 2024-04-22

This article presents technology for manufacturing hybrid integrated circuits using thick film technology and ceramic materials with passive elements: resistors, capacitors, inductors, conductive paths, and contacts manufactured on the surface. The surface of the insulated base plates uses thick film technology, and the active elements (transistors, diodes, etc.) are installed on the base plate through solder paste technology. Application of hybrid chip technology on the calibration circuit board in the launch mechanism of the air defense complex.