In the production of heat exchangers using additive manufacturing, maintaining consistent quality is a significant challenge due to irregular energy transformations during the manufacturing process. These irregularities can result in faulty products, leading to issues such as reduced efficiency and reliability of the heat exchangers. Traditional quality control methods are often inadequate for real-time detection and correction of such faults. This paper focuses on analyzing the occurrence of faulty products caused by irregular energy transformations in heat exchangers. A deep learning network, specifically ResNet-101, is employed to address this issue. The network is trained with characteristic features of the product and instantaneous variations in the heat exchanger to accurately identify faulty patterns resulting from degradation in the heat exchanger’s performance. By leveraging the deep learning network, which comprehensively understands both the product and heat exchanger features, the system can detect and classify faulty products in real time. This enables immediate corrective actions, such as pushing defective products into a recycling process, thereby maintaining high-quality standards in continuous production.
Read full abstract