<![CDATA[Temperature control in freezers is crucial to maintaining product quality and safety, particularly in the food and pharmaceutical industries. Uncontrolled temperature fluctuations can lead to product damage, increased waste, and reduced quality. Machine learning technology offers an effective solution for predicting and controlling temperature, enabling more accurate monitoring and rapid responses to changing conditions. This study aims to develop a machine learning model using the TensorFlow framework to predict freezer temperatures. Temperature data were collected from sensors installed inside the freezer and used to train and test several machine learning architectures, including Long Short-Term Memory (LSTM) and 1D Convolutional (Conv1D) networks. Model development leveraged TensorFlow's advanced features, enabling efficient model creation, training, and testing. The results show that the Conv1D model with a data composition of 90% training, 5% validation, and 5% testing achieved the best predictions, with a test RMSE of 0.02085°C and a test MAPE of 0.33522%. This predictive model has the potential to be used as an early warning system to prevent product damage. This research is expected to significantly contribute to the development of more efficient temperature monitoring and control systems in freezers, with potential applications across industries such as food and pharmaceuticals. The findings also reinforce the substantial potential of machine learning in environmental prediction and monitoring.]]>
Copyrights © 2024
