KMITL Expo 2026 LogoKMITL 66th Anniversary Logo

Cooling suit with two-phase flow heat-exchange system

Cooling suit with two-phase flow heat-exchange system

Abstract

Cooling suit with two-phase flow heat-exchange system is a state-of-the-art heat sink, designed for thermal dissipation in fire fighter, racing driver and worker who needs to wear Personal Protective Equipment (PPE). The liquid cooling system with gas injection can enhance heat transfer performance and continuously maintain the temperature at 18-20 degree Celsius.

Objective

นักดับเพลิง นักแข่งรถ บุคคลที่ต้องสวมใส่ชุด PPE ในการทำงาน เป็นอาชีพที่มีความเสี่ยงที่จะเสียชีวิตจากโรคลมแดด (heat stroke) ดังนั้นจึงมีแนวคิดในการใช้องค์ความรู้ทางวิศวกรรมเครื่องกลมาออกแบบและสร้างนวัตกรรมใหม่ สำหรับกลุ่มบุคคลที่มีความเสี่ยงจากโรคลมแดด

Other Innovations

“THE VEIL” Community Mall and Agricultural Hub

คณะสถาปัตยกรรม ศิลปะและการออกแบบ

“THE VEIL” Community Mall and Agricultural Hub

A mixed-used complex consisting of commercial spaces, agricultural informative center, workshop, vertical farming and home office.

Read more
Muly mur

คณะอุตสาหกรรมอาหาร

Muly mur

A new jelly snack alternative for health-conscious individuals—delicious, convenient, and gut-friendly. Rich in probiotics and prebiotics, packed with antioxidants, and essential vitamins. Suitable for health enthusiasts and lactose-intolerant individuals. Free from artificial colors and flavors

Read more
Revolutionizing pill identification by using deep convolutional neural network based on widely-used essential household remedy drugs

คณะแพทยศาสตร์

Revolutionizing pill identification by using deep convolutional neural network based on widely-used essential household remedy drugs

This study explores the application of deep convolutional neural networks (CNNs) for accurate pill identification, addressing the limitations of traditional human-based methods. Using a dataset of 1,250 images across 10 household remedy drugs, various CNN architectures, including YOLO models, were tested under different conditions. Results showed that natural lighting was optimal for imprinted pills, while a lightbox improved detection for plain pills. The YOLOv5-tiny model demonstrated the best detection accuracy, and efficientNet_b0 achieved the highest classification performance. While the model showed strong results, its generalization is limited by sample size and drug variability. Nonetheless, this approach holds promise for enhancing medication safety and reducing errors in outpatient care.

Read more