Since organic rice storage silos were faced with an insect problem, an owner solved this problem using the expert system (ES) in the controlled atmosphere process (CAP) under the required standard, fumigating insects with an N2, reducing O2 concentration to less than 2% for 21 days. This article presents the computational fluid dynamics (CFD) assisted ES successfully solved this problem. First, CFD was employed to determine the gas flow pattern, O2 concentration, proper operating conditions, and a correction factor (K) of silos. As expected, CFD results were consistent with the experimental results and theory, assuring the CFD’s credibility. Significantly, CFD results revealed that the ES controlled N2 distribution throughout the silos and effectively reduced O2 concentration to meet the requirement. Next, the ES was developed based on the inference engine assisted by CFD results and the sweep-through purging principle, and it was implemented in the CAP. Last, the experiments evaluated CAP’s efficacy in controlling O2 concentration and insect extermination in the actual silos. The experimental results and owner’s feedback confirmed the excellent efficacy of ES implementation; therefore, the CAP is effective and practical. The novel aspect of this research is a CFD methodology to create the inference engine and the ES.
การเก็บรักษาข้าวใน ไซโลเก็บข้าวอินทรีย์ เป็นแนวทางสำคัญในการรักษาคุณภาพข้าวและลดการสูญเสียหลังการเก็บเกี่ยว อย่างไรก็ตาม ปัญหาการปนเปื้อนของแมลงศัตรูข้าว เป็นอุปสรรคสำคัญที่ส่งผลกระทบต่อคุณภาพและความปลอดภัยของข้าว โดยทั่วไป การกำจัดแมลงในไซโลมักใช้สารรมยาเคมี เช่น ฟอสฟีน (PH₃) หรือ เมทิลโบรไมด์ (CH₃Br) ซึ่งอาจก่อให้เกิดสารตกค้าง ส่งผลต่อสุขภาพผู้บริโภค และสร้างผลกระทบต่อสิ่งแวดล้อม
วิทยาลัยอุตสาหกรรมการบินนานาชาติ
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.
คณะสถาปัตยกรรม ศิลปะและการออกแบบ
This conceptual model, inspired by the Rose Window in Gothic architecture, embodies intricate geometric patterns that reflect divine harmony and balance. Its symmetrical structure and the interplay of light passing through stained glass create a sense of movement, enhancing the sacred and mystical atmosphere. The composition evokes a celestial presence, like a window to heaven.
คณะวิศวกรรมศาสตร์
This project aims to develop a conceptual prototype of a weapon aiming system that simulates an anti-aircraft gun. Utilizing an optical camera, the system detects moving objects and calculates their trajectories in real time. The results are then used to control a motorized laser pointer with two degrees of freedom (DoF) of rotation, enabling it to aim at the predicted position of the target. Our system is built on the Raspberry Pi platform, employing machine vision software. The object motion tracking functionality was developed using the OpenCV library, based on color detection algorithms. Experimental results indicate that the system successfully detects the movement of a tennis ball at a rate of 30 frames per second (fps). The current phase involves designing and integratively testing the mechanical system for precise laser pointer position control. This project exemplifies the integration of knowledge in electronics (computer programming) and mechanical engineering (motor control).