One of the focal points in industrial product defect detection lies in the utilization of deep learning-based object detection algorithms. With the continuous introduction of these algorithms and their refined models, notable achievements have been attained. However, challenges persist in industrial settings, such as substantial variations in defect scales, the delicate balance between accuracy and speed, and the detection of small objects. Various methods have been proposed to address these challenges and propel the advancement of defect detection. To comprehensively review the latest developments in deep learning-based industrial product defect detection algorithms and foster further progress, this paper encompasses typical datasets and evaluation metrics used in industrial product defect detection, traces the development history of supervised one-stage and two-stage object detection algorithm-based and unsupervised algorithm-based industrial defect detection methods, discusses major challenges, and outlines future directions. It highlights the potential for further improving the accuracy, speed, and reliability of defect detection systems in industrial applications.

A lumped model of the arterial system has been used in constructing a hybrid mock loop due to its real-time response. However, the parameters of the model are always from a general case and not adapted to a specific patient. In this study, we focused on on-line parameter identification of the lumped model of the arterial system that could be used for a specific patient. A five-element lumped arterial model is adopted in this study, in which the five parameters are to be determined. The aortic flow rate and the venous pressure are chosen as the inputs of the model, and aortic pressure as the output. An iterative optimization based on the established state space equations of the five-element model is used to seek the best parameter values by minimizing the difference between the model prediction and the previously obtained aortic pressure. The method is validated using simulated data from a complete numerical cardiovascular model. Results show that the method can track the dynamic variation of the parameters very well. Finally, a sensitivity analysis of the model parameters is conducted to interpret the effect of parameter changes. The good performance of the identification demonstrates the potential application of this method to customize a hybrid mock loop for a specific patient or clinically monitor the arterial vessel characteristics in real time.

Aiming at the abnormality detection of industrial insert molding processes, a lightweight but effective deep network is developed based on X-ray images in this study. The captured digital radiography (DR) images are firstly fast guide filtered, and then a multi-task detection dataset is constructed using an overlap slice in order to improve the detection of tiny targets. The proposed network is extended from the one-stage target detection method of yolov5 to be applicable to DR defect detection. We adopt the embedded Ghost module to replace the standard convolution to further lighten the model for industrial implementation, and use the transformer module for spatial multi-headed attentional feature extraction to perform improvement on the network for the DR image defect detection. The performance of the proposed method is evaluated by consistent experiments with peer networks, including the classical two-stage method and the newest yolo series. Our method achieves a mAP of 93.6%, which exceeds the second best by 3%, with robustness sufficient to cope with luminance variations and blurred noise, and is more lightweight. We further conducted ablation experiments based on the proposed method to validate the 32% model size reduction owing to the Ghost module and the detection performance enhancing effect of other key modules. Finally, the usability of the proposed method is discussed, including an analysis of the common causes of the missed shots and suggestions for modification. Our proposed method contributes a good reference solution for the inspection of the insert molding process.

Inspired by shallow-water sloshing in a moving tank, a novel type of vibration-based piezoelectric energy harvesting device composed of a piezoelectric bimorph beam and an extension tank is proposed in this paper. The structure and working principle of the proposed device are provided. Then, the effects of different heights of water filling in the tank on the performances of the harvester are studied and analyzed. Experiments are set up to investigate the actual device performance by changing the base excitation frequency and load resistance for different water heights. The results show that by modulating the water height, the resonant frequency and bandwidth can be adjusted, which can enhance the energy harvesting performance of the device at different ambient vibration frequencies. This study provides some clues to improve the performance of the vibration-based energy harvesting devices.