Intelligent manufacturing product quality inspection is an integral part of intelligent manufacturing, which is of great significance to improving product quality and production efficiency, ensuring equipment safety, and protecting the environment. However, traditional product quality inspection has problems like low efficiency, poor accuracy, and weak adaptability, which are challenging to meet the development needs of intelligent manufacturing. To this end, this paper proposes an intelligent manufacturing product quality inspection method based on the convolutional neural network model of EfficientNet. First, according to the model structure and compound scaling method of EfficientNet, a network model suitable for product quality inspection is designed. And its training and inference process are introduced. Second, to improve the generalization ability and robustness of the model, data preprocessing and augmentation, as well as model training and optimization strategies, are adopted. Then, according to the performance evaluation and comparative analysis of EfficientNet on image classification, its applicability and advantages in intelligent manufacturing product quality inspection are expounded. Finally, an intelligent manufacturing product quality inspection system based on EfficientNet is built, and the effectiveness of the method proposed in this paper is proved through simulation and experimental verification.