Analysing and Optimizing the Refrigeration System Using Machine Learning Algorithm

Abstract

The Cold chain/Refrigeration plays an important role for preserving vaccines as per the vaccine storage and guidelines prescribed by World Health Organizations and it is better than most of other preservation methods. The primary goal of adopting phase change material is to increase performance, cooling duration, capacity for storage, and to sustain the steady cooling effect for a longer length of time during power outages. In experimental set up it is decoded to use Inorganic and Eutectic phase change materials which is encapsulated in plastic containers inside the vaccine storage. The project will involve collecting data from sensors installed in cabinet and using machine learning algorithms to analyse the data and generate insights. The results of the project can be used to inform best practices for vaccine storage and contribute to the development of more efficient and effective cabinet management systems. This project explores the use of machine learning techniques to optimize the storage of vaccines in cabinet. Proper storage is critical to maintain vaccine efficacy, and therefore it is important to ensure that the temperature and humidity are kept within specific ranges. Machine learning models can be trained to predict the temperature and humidity levels in the cold rooms and to detect anomalies that may indicate a potential problem. This can help improve the monitoring and maintenance of the cabinet and reduce the risk of vaccine spoilage. Machine Learning algorithms like Regression and Classification are used on web-app because they provide us with continuous as well as discrete value as an output. Libraries like pandas, Numpy, sklearn, matplotlib are used to predict along with visualization because of which it will be possible to forecast the actual aspects like temperature and humidity. User Interface has also been developed which acquires input from any user and displays the data according to user’s inputs. The project will involve collecting data from sensors installed in cabinet and using machine learning algorithms to analyse the data and generate insights. The results of the project can be used to inform best practices for vaccine storage and contribute to the development of more efficient and effective cabinet management systems.