Dynamic Weighing Signal Denoising Approach Based on Convolutional Denoising Autoencoders: A Novel Rapid Weight Determination for Egg Sorting Machines

Abstract

With the increasing scale of industrial egg production, rapid and precise weight classification has become a technical necessity. While dynamic weighing systems are employed to maintain high production speeds, load cell signals in these systems are significantly corrupted by mechanical vibrations and environmental noise, compromising measurement accuracy. This study proposes a Convolutional Denoising Autoencoder (CDAE)-based approach to effectively filter these dynamic weighing signals and ensure accurate classification. The performance of the proposed method was evaluated and compared against traditional filtering techniques, specifically Discrete Wavelet Transform (DWT) and Moving Average Filter (MAF). The results demonstrate that the CDAE-based model provides superior noise reduction, enabling faster and more stable weight determination compared to conventional methods. By addressing the limitations of traditional filters in high-speed environments, this study offers a robust artificial intelligence-based solution to the precision dynamic weighing challenges encountered in the food industry.