The capture of a target spacecraft by a chaser is an on-orbit docking operation that requires an accurate, reliable, and robust object recognition algorithm. Vision-based guided spacecraft relative motion during close-proximity maneuvers has been consecutively applied using dynamic modeling as a spacecraft on-orbit service system. This research constructs a vision-based pose estimation model that performs image processing via a deep convolutional neural network. The pose estimation model was constructed by repurposing a modified pretrained GoogLeNet model with the available Unreal Engine 4 rendered dataset of the Soyuz spacecraft. In the implementation, the convolutional neural network learns from the data samples to create correlations between the images and the spacecraft’s six degrees-of-freedom parameters. The experiment has compared an exponential-based loss function and a weighted Euclidean-based loss function. Using the weighted Euclidean-based loss function, the implemented pose estimation model achieved moderately high performance with a position accuracy of 92.53 percent and an error of 1.2 m. The in-attitude prediction accuracy can reach 87.93 percent, and the errors in the three Euler angles do not exceed 7.6 degrees. This research can contribute to spacecraft detection and tracking problems. Although the finished vision-based model is specific to the environment of synthetic dataset, the model could be trained further to address actual docking operations in the future.
In one, docking is defined as “when one incoming spacecraft rendezvous with another spacecraft and flies a controlled collision trajectory in such a manner to align and mesh the interface mechanisms”, and defined docking as an on-orbital service to connect two free-flying man-made space objects. The service should be supported by an accurate, reliable, and robust positioning and orientation (pose) estimation system. Therefore, pose estimation is an essential process in an on-orbit spacecraft docking operation. The position estimation can be obtained by the most well-known cooperative measurement, a Global Positioning System (GPS), while the spacecraft attitude can be measured by an installed Inertial Measurement Unit (IMU). However, these methods are not applicable to non-cooperative targets. Many studies and missions have been performed by focusing on mutually cooperative satellites. However, the demand for non-cooperative satellites may increase in the future. Therefore, determining the attitude of non-cooperative spacecrafts is a challenging technological research problem that can improve spacecraft docking operations. One traditional method, which is based on spacecraft control principles, is to estimate the position and attitude of a spacecraft using the equations of motion, which are a function of time. However, the prediction using a spacecraft equation of motion needs support from the sensor fusion to achieve the highest accuracy of the state estimation algorithm. For non-cooperative spacecraft, a vision-based pose estimator is currently developing for space application with a faster and more powerful computational resource.
คณะวิศวกรรมศาสตร์
This cooperative education project aims to enhance the efficiency of Hydrogen Manufacturing Unit 2 (HMU-2) and Pressure Swing Adsorption 3 (PSA-3) by using AVEVA Pro/II process modeling and a Machine Learning model for process simulation. The study found that the AVEVA Pro/II model predicted outcomes with deviations ranging from 0–35%, including a hydrogen flow rate deviation from the PSA unit of 12%, exceeding the company’s acceptable limit of 10%. To address this, a Machine Learning model based on the Random Forest algorithm was developed with hyperparameter tuning. The Machine Learning model demonstrated high accuracy, achieving Mean Squared Errors (MSE) of 8.48 and 0.18 for process and laboratory data, respectively, and R-squared values of 0.98 and 0.88 for the same datasets. It outperformed the AVEVA Pro/II model in predicting all variables and reduced the hydrogen flow rate deviation to 4.75% and 1.35% for production rates of 180 and 220 tons per day, respectively. Optimization using the model provided recommendations for process adjustments, increasing hydrogen production by 7.8 tons per day and generating an additional annual profit of 850,966.23 Baht.
คณะเทคโนโลยีการเกษตร
Soil is home to a diverse array of living organisms that interact within a complex food web, facilitating energy and nutrient cycling essential for sustaining life above ground. Among these organisms, soil microbes play a crucial role in supporting plant growth. Beneficial microorganisms enhance nutrient availability, improve soil structure by increasing porosity, and strengthen plant resistance to diseases. Conversely, harmful microorganisms, such as plant pathogens, can hinder plant growth and reduce crop yields when present in high concentrations. Neutral microorganisms, which naturally inhabit the soil, contribute to the soil ecosystem without directly impacting plants. A single teaspoon of soil contains over a billion microorganisms, yet only about 1% of them can be cultured in laboratory conditions. This highlights soil as one of the richest reservoirs of microbial diversity on Earth.
คณะอุตสาหกรรมอาหาร
The Ginbanirose project aims to develop herbal extracts for alleviating menstrual pain using key ingredients: roselle, banana inflorescence, and ginger. These ingredients contain bioactive compounds with anti-inflammatory, antioxidant, and pain-relieving properties. The extracts are enhanced through liposome encapsulation technology, which improves absorption and stability. The production process involves herbal extraction, freeze-drying, and liposome formulation using lecithin and stabilizers. Experimental results demonstrate high phenolic content and antioxidant activity via the DPPH method. Ginbanirose addresses women’s quality of life concerns while offering significant business opportunities in the rapidly growing herbal market, particularly in the Asia-Pacific region.