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
คณะวิทยาศาสตร์
In this paper, Vanadium dioxide (VO2) thin-film devices with two different use cases have been redesigned to introduce an asymmetrical resonant cavity structure. The structure is designed with the goal of enhancing the optical performance of the central VO2 layer and has an anti-reflection property in the cold state. The advantages and limitations of such a design are discussed.
คณะเทคโนโลยีสารสนเทศ
This research presents a deep learning method for generating automatic captions from the segmentation of car part damage. It analyzes car images using a Unified Framework to accurately and quickly identify and describe the damage. The development is based on the research "GRiT: A Generative Region-to-text Transformer for Object Understanding," which has been adapted for car image analysis. The improvement aims to make the model generate precise descriptions for different areas of the car, from damaged parts to identifying various components. The researchers focuses on developing deep learning techniques for automatic caption generation and damage segmentation in car damage analysis. The aim is to enable precise identification and description of damages on vehicles, there by increasing speed and reducing the work load of experts in damage assessment. Traditionally, damage assessment relies solely on expert evaluations, which are costly and time-consuming. To address this issue, we propose utilizing data generation for training, automatic caption creation, and damage segmentation using an integrated framework. The researchers created a new dataset from CarDD, which is specifically designed for cardamage detection. This dataset includes labeled damages on vehicles, and the researchers have used it to feed into models for segmenting car parts and accurately labeling each part and damage category. Preliminary results from the model demonstrate its capability in automatic caption generation and damage segmentation for car damage analysis to be satisfactory. With these results, the model serves as an essential foundation for future development. This advancement aims not only to enhance performance in damage segmentation and caption generation but also to improve the model’s adaptability to a diversity of damages occurring on various surfaces and parts of vehicles. This will allow the system to be applied more broadly to different vehicle types and conditions of damage inthe future
วิทยาลัยนวัตกรรมการผลิตขั้นสูง
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.