Research on the Application of Target Detection and Recognition Technology Based on Deep Learning in Industrial Automation

With the rapid development of industrial automation technology, target detection and recognition technology is playing an increasingly important role in modern manufacturing industry. This paper deeply discusses the application of target detection and recognition technology based on deep learning in industrial automation. Aiming at the task of target detection and recognition in industrial automation, this paper designs an innovative deep learning model-"industrial automation object detection network” (IAODN). The model is based on convolutional neural network (CNN) architecture, combined with feature pyramid network (FPN) and multi-scale feature fusion strategy to adapt to the changeable target size in industrial automation scenes. The model uses the pre-trained ResNet-50 as the backbone network and combines with FPN to construct a multi-scale feature map, and further improves the detection performance of the model for multi-scale targets through a multi-scale feature fusion module. The experimental results show that the IAODN model has excellent performance on public data sets (COCO and PASCAL VOC) and practical application data, especially in identifying small targets and multi-scale targets. By introducing deep learning technology, the production efficiency and safety in industrial automation scenarios have been significantly improved. In specific application scenarios such as production line monitoring, the IAODN model can monitor the status of parts on the production line in real time, find and identify defective parts in time, thus improving product quality and reducing the cost of manual inspection.