The current residential solar panels lack an adequate monitoring system, which hinders their optimal utilization. This research aims to design an Internet of Things (IoT) monitoring system and employ machine learning techniques to predict the current and voltage generated by solar panels. Experimental studies have revealed a correlation between dust accumulation and the current output of solar panels. The proposed system facilitates the prediction of the optimal time for cleaning solar panels.
ประเทศไทยนั้นเป็นประเทศในเขตร้อนที่เหมาะสมต่อการติดตั้งโซลาร์เซลล์เป็นอย่างมาก แต่เนื่องด้วยปริมาณฝุ่นเพิ่มขึ้นในทุกๆ ปี ซึ่งปริมาณฝุ่นนี้มีผลกระทบต่อแผงโซลาร์เซลล์ จึงมีแนวคิดในการพัฒนาระบบติดตามดูแลแผงสำหรับครัวเรือน ที่โดยส่วนใหญ่ไม่ได้มีการดูแลอย่างเหมาะสม
คณะเทคโนโลยีการเกษตร
During this cooperative education program at the Bang Bo District Agricultural Office, Samut Prakan Province, a study was conducted on the costs and returns of rice cultivation using chemical inputs compared to using biopesticides in combination with chemical inputs among farmers in Bang Phli Noi Subdistrict, Bang Bo District, Samut Prakan Province.The objectives of this study were: To examine the costs and returns of rice cultivation using chemical inputs compared to using biopesticides in combination with chemical inputs among farmers in Bang Phli Noi Subdistrict, Bang Bo District, Samut Prakan Province. To explore the challenges of using biopesticides in rice cultivation among farmers in Bang Phli Noi Subdistrict, Bang Bo District, Samut Prakan Province. The study found that in the 2024/25 growing season, the total production cost for rice cultivation using biopesticides in combination with chemical inputs was 5,099.50 THB per rai, consisting of variable costs of 4,432.50 THB per rai and fixed costs of 667.00 THB per rai. Meanwhile, the total production cost for rice cultivation using only chemical inputs was 5,129.00 THB per rai, consisting of variable costs of 4,390.00 THB per rai and fixed costs of 739.00 THB per rai. The cost difference between the two methods was 114.50 THB per rai. Regarding the returns on rice cultivation in the 2024/25 growing season, the field using biopesticides in combination with chemical inputs yielded 1,000.00 kilograms per rai, with an average selling price of 8,500.00 THB per rai. Farmers earned a total revenue of 8,585.00 THB per rai and a profit of 3,485.50 THB per rai. On the other hand, the field using only chemical inputs yielded 1,000.00 kilograms per rai, with an average selling price of 8,500.00 THB per rai. Farmers earned a total revenue of 8,500.00 THB per rai and a profit of 3,371.00 THB per rai. The total income difference between the two cultivation methods was 114.50 THB per rai. In terms of challenges related to the procurement of biopesticides, it was found that biopesticides are difficult to obtain, with limited or no availability in certain areas. Additionally, relevant agencies do not provide continuous support for biopesticides, making this the most significant issue. Regarding the use of biopesticides, the most critical challenge is that once fresh biopesticides are mixed, they must be used immediately and cannot be stored, as their effectiveness deteriorates over time.
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 app encourages users to clean by turning it into a fun game. Users can choose cleaning tasks, track dust levels, and earn reward points, making the cleaning process more engaging and enjoyable.