AVIA - International Journal of Aviation Science and Engineering
Not a member yet
50 research outputs found
Sort by
Bird Detection System Design at The Airport Using Artificial Intelligence
Get PDFBird strike is a process of crashing between bird and airplane which occurs in flight phase. Based on data, there are 40 times bird strike occurs every day (FAA, 2019). There are lot of research that already conducted to decrease number of birds at the airport. But it is not given significant changes. Hence, it is needed a model that can detect bird at the airport so that we can decrease the number of birds. Study already conducted by comparing motion detection with object detection and filter which can be used to improve detection quality. Model already developed using YOLOv4 object detection with 71.89% mean average precision. It is expected that object detection can be developed to become a bird repellent system in the futur
Selection of the Use of Formwork in the Holiday Inn Bukit Randu Hotel Project Using the Fuzzy AHP Method
Get PDFAlong with the development of the construction world, formwork has also progressed from being assembled on site to being assembled first at the factory. In Indonesia, many types of formwork have been used, which each have their own advantages and disadvantages. In selecting the type of formwork used, many factors or criteria need to be considered. The purpose of this study is to determine the type of formwork that is relatively best for use in the Holiday Inn Bukit Randu Hotel Project by calculating the weight of the criteria, sub criteria, and also the alternatives used using the Fuzzy AHP Method. Based on the criteria and alternatives that have been compiled by the researcher, as well as the analysis carried out using the Fuzzy AHP method, it is known that metal (system) formwork is the relatively best formwork with the largest final weight of 43.6%, while semi-system formwork with a final weight of 24, 6% and conventional formwork by 31.8%. However, after being reviewed based on the cost aspect, the semi-system formwork is the relatively best formwork to be used in the Holiday Inn Bukit Randu Hotel Project
Circular Airport Concept Analysis for Indonesian Archipelago
Get PDFCircular Airport Concept, issued by Hessellink in 2014, divides the expert opinion, but the project is still running. The idea is how visible to engage this concept into Indonesian Archipelago. To build airport within limit area for several islands in Indonesia is a big challenge. Some pioneer routes which connecting remote areas with a small aircraft is still searching for some development. Another challenge is the environmental sustainability. This paper makes an analysis about application of the concept into Indonesian Archipelago, and how this concept might be a solution. The discussion will cover analysis of airport design, aircraft to operate, and area to be treated
Predictive Maintenance for Aircraft Engine Using Machine Learning: Trends and Challenges
Get PDFThis article aims to prove that Machine Learning (ML) methods are effective for Predictive Maintenance (PdM) and to obtain other developing methods that suitable applied on PdM, especially for aircraft engine, and potential method that can apply on future research, and also compared between articles in International and Indonesia institution. Maintenance factors are important to prognostic the states of a machine. PdM is one of the factor strategies based on realtime data to diagnosis a failure of the machine through forecasting remaining useful life (RUL), especially on aircraft machine where the safety is priority due to enormous cost and human life. ML is the technique that accurately prediction through the data. Applied ML on PdM is the huge contribution for saving cost and human life guarantee of safety. This work provides the literature survey for recent research which trends and challenges on PdM of aircraft engine using ML that compared the research from international and Indonesia from 2016 to 2021. Result of this work shows that ML method, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) are the best method to calculate PdM with more than 99% on rate accuracy, and low level of Indonesia institution research which focused on PdM on aircraft engine using M
Development of Flight Multifunctional Indicator Based on A320 and B737 NG Flight Indicator
Get PDFThe objectives of this research are: to know the concept of modeling and simulation the cockpit display based on disadvantages and differences between A320 and B737NG; to offer the development and new technology to design the development (new) flight instruments of the display based on Airbus A320 and Boeing B737 NG flight instrument technology. Methodologies that have been used in this research are literature review, interview/discussion/questionnaire, and descriptive analysis. Questionnaire towards the users/pilots who flies airplane A320 or B737 NG. For the questionnaire, the Likert-scale method is utilized to collect data and information. This research result’s in finding that: 1. the technology of flight instrument system between A320 and B737 NG visually displays similarity with several differences such as ergonomic side, ECAM technology, and VSD technology. 2. Based on works of literature review and response from the users/pilots, the author finds and proposes several technologies or requirements to apply in the new type model of PFD and Multi-function Display, they are including: PFD and MFD merged into one display only with some additional menu buttons; ECAM + engine warning display, ECAM + systems display, and digital instruction to solve the problem merged into one display only with some additional buttons; display design is using the fully digital display, computerized system, LCD technology, VSD, and EHSI technology, and layout display is using configuration “basic T”; standby flight instrument merged into one display only with some additional menu button
CFD Analysis on Aerodynamic Coefficients of Flying Saucer
Get PDFWith the growing of Unmanned Aerial Vehicle (UAV) usage, many new types of UAV are introduced. Flying Saucer is a new type of UAV which is not yet famous in the market. The aim of this study is to analysis the aerodynamic coefficients of a Flying Saucer. The research question arise is What the optimum angle of attack for Flying Saucer flight is. The study is conducted in Computational Fluid Dynamics (CFD) using COMSOL Multiphysics with Laminar Flow physics for several angles of attack. The analysis considers Lift and Drag coefficient in the form of and to angle of attack (α) plot, ratio of / to angle of attack (α) plot and drag polar plot. We conclude that a symmetric Flying Sauce has aerodynamic characteristic with the optimum operational angle of attack in the range of 8 to 16 deg. The and has a quadratic relationship with large 0 due to the geometric of Flying Saucer. It recommends that further study should explore in the area of zero and maximum angle of attack (α) and validation in wind tunnel experiment
Effect of Production Method on the Mechanical Properties of Resin - Fiber S-GLASS Composite for the Rocket Nose Cone Application
Get PDFComposite materials are increasingly developing in industrial advances both for everyday life or technological applications in industry. Composite material is a combination of two or more different components. Composite materials have certain physical and mechanical properties that are better than the properties of each of their constituent components. This research has been analyzed to determine the effect of the method of making fiber composites s-glass matrix resin 100 as material nose cone rocket rx-450 by using the method of hand lay up and vacuum infusion. Making a nose cone is carried out in several stages which are quite complicated, starting with preparation master mole for print beginning until polishing compound molding release on molding as finishing. The results obtained from this study are by using the method vacuum infusion lighter compared with material results method hand lay-up because on method vacuum infusion resin can be removed from the laminate. Whereas on method hand layup infiltration resin in fiber not enough perfect and administration of resin that cannot be controlled so that it can affect the mass from product composite
Systematic Comparison of Machine Learning Model Accuracy Value Between MobileNetV2 and XCeption Architecture in Waste Classification System
Get PDFGarbage generated every day can be a problem because some types of waste are difficult to decompose so they can pollute the environment. Waste that can potentially be recycled and has a selling value is inorganic waste, especially cardboard, metal, paper, glass, plastic, rubber and other waste such as product packaging. Various types of waste can be classified using machine learning models. The machine learning model used for classification of waste systems is a model with the Convolutional Neural Network (CNN) method. The selection of the CNN architecture takes into account the required accuracy and computational costs. This study aims to determine the best architecture, optimizer, and learning rate in the waste classification system. The model designed using the MobileNetV2 architecture with the SGD optimizer and a learning rate of 0.1 has an accuracy of 86.07% and the model designed using the Xception architecture with the Adam optimizer and a learning rate of 0.001 has an accuracy of 87.81%
Deep Learning Implementation on Aerial Flood Victim Detection System
Get PDFHydrometeorological hazard such as floods are considered as a regular natural disaster in Indonesia due to its frequent occurrence. To mitigate the risk, search and rescue operations need to be carried out immediately. The sheer magnitude of floods poses a major challenge for responders, and the emerging drone technology could help to alleviate the problem due to its deployment speed and coverage. Automation in drone technology has potential to improve its effectiveness. This paper explores the idea of human detection during floods using a computer vision approach. This approach utilizes a one stage detector model as detection speed is crucial in disaster management case. The dataset used for training consists of 200 labelled and negative images taken from drone point of view. This paper conducted 3 experiments to find out the difference in performance when the model was trained on flood and non-flood dataset, as well as the effect of image input size to the model’s performance. The first experiment was trained on non-flood dataset. The second experiment was trained on flood dataset, and the third experiment is the modified version of the second model. The results show that the model trained on flood dataset performed worse than non-flood counterparts with the non-flood mAP reached 90.80% while flood mAP reached 39.15%. In addition, the experiments also conclude that increasing the input size of image during training, will increase the detection performance of the model at the cost of FP
Analysis of Star Catalog Model Based on The Nearest Star Composition and Brightest Star as Guide Star
Get PDFStar sensor is the most advanced attitude determining instrument for spacecraft with very high accuracy, and it is independent of other attitude sensors. However, the star sensor's accuracy and processing time depend on selecting the algorithm, which starts from detecting the star pattern until the matching process with the star catalog. The star catalog consists of the right ascension and declination of stars' position and magnitude for 250.000 stars which need a large memory size. Therefore, modifying a new star catalog consisting of guide stars' position,magnitude, and nearest star composition can reduce the required memory and processing time without losing accuracy. T he nearest star catalog model in this paper used radial based featurewhere for each guide star candidate, the number of stars in each binary (bin) layer around the guide star will be calculated. This paper focuses on determining the best architecture for the nearest star catalog model, such as the number of bin layers and bin ranges, and the influence ofstar sensor field of view and guide star limitation with the model's accuracy. The proposed star catalog provides excellent performance in low-cost star sensors with a high and medium field of view