F-BBT: An Industrial Risk Detection Model Based on Feature Fusion

With the continuous improvement of modern indus-trial production capabilities, risk detection of industrial products has become more and more important. Industrial risk detection helps improve product quality and corporate competitiveness, and promote sustainable development. The development of detection technologies and systems is crucial to modern industrial production. However, as the types and scale of industrial products increase, the singularity of industrial product data increases geometrically. Traditional risk assessment methods are difficult to meet the needs of modern industrial safety supervision. In order to solve the above problems of product safety detection system. This paper proposes a deep learning industrial product risk assessment model: F-BBT Net. This model can more effectively predict and monitor potential safety issues,and then integrating and interacting features extracted from different existing models. Experimental results show that F-BBT Net has higher accuracy and reliability in risk identification, and the prediction accuracy is 75.82% higher than that of traditional methods. The model code and experimental code of the paper can be obtained from the website https://github.com/liuvvvvv1/F-BBT-model/tree/master.