A fast recognition method for assembly line workpieces based on an improved SSD model is proposed to address the problems of low detection accuracy and lack of real-time performance when existing target detection models face small-scale targets and stacked targets. Based on the SSD network, the optimized Inception_Resnet _V2 structure is used to improve its feature extraction layer and enhance the extraction capability of the network for small-scale targets. The repulsion loss (Reploss) is used to optimize the loss function of the SSD network to solve the problem of stacked workpieces. The issue of difficult detection is improved. The robustness of the algorithm is enhanced. The experimental results show that the improved SSD target detection method improves the detection accuracy by 9.69% over the traditional SSD map. The detection speed meets the real-time requirements, which is a better balance of detection real time and accuracy requirements. The algorithm can recognize small-scale and stacked targets with higher category confidence, better algorithm robustness, and better recognition performance compared to the same type of target detection algorithms.

In this paper, an in-depth analysis of automated production line faults based on fuzzy algorithms is carried out and based on an in-depth investigation of the mechanism of equipment faults, research work on equipment state prediction and production line fault diagnosis is carried out, and the corresponding algorithm model workflow is given, which has some practical application value for improving the accuracy of production line fault prediction. The algorithm with data mining association rules is proposed to extract the confidence parameters of the conditional state fuzzy net model, and an inverse conditional state fuzzy net is established based on the conditional state fuzzy net for fault diagnosis and reasoning, and a dynamic confidence level reasoning mechanism is also established for reverse reasoning based on the iterative algorithm of maximum algebra. To monitor the operating status of the production line more intuitively, a production line fault prediction and analysis system is developed based on the platform, which mainly includes a data management module, state monitoring module, state prediction module, fault diagnosis module, and maintenance advice module, which can more easily realize the monitoring of the production line equipment state and fault early warning prompting, making the system more practical value.