The borescope damage detection is a key link to ensure the safe operation of equipment in the field of aero-engine operation and maintenance, which often faces the problem of balancing real-time performance and accuracy. To address this issue, this study proposes a training method of borescope damage detection model based on the fusion of knowledge distillation and reinforcement learning. First, this paper designs a simple and efficient ranking loss function, which prioritizes the damage features output by the teacher model and ensures that the student model can accurately capture key damage information during the learning process as well as effectively avoid the interference of secondary features on detection accuracy. Additionally, in order to further improve the model′s adaptability, a reinforcement learning mechanism is introduced to adaptively adjust the core parameters of knowledge distillation function and dynamically optimize the parameter configuration. This allows for the adaptation to different types of borescope damage without manual interventions. The optimization process does not require modifying the basic structure of object detection network, significantly reducing the deployment difficulty in the engineering applications. Furthermore the basic validation is performed on the Pascal VOC 2007 general object detection dataset in order to verify the effectiveness of the method, which eliminates the interference of dataset specificity on the experimental results and confirms the generality of the method. Finally, the comparative experiments are conducted using the YOLOv8-n lightweight object detection network on a real aero-engine borescope image dataset. The results show that, this training method improves the borescope damage detection accuracy of YOLOv8-n by 6.93% without increasing the number of model parameters or inference time. The experiment fully demonstrated its application value in the engineering practice, providing a reliable technical solution for the real-time and high-precision borescope inspection of aero-engines.