An efficient robotic-assisted bolt-ball joint looseness monitoring approach using CBAM-enhanced lightweight ResNet

Abstract Bolt-ball joints are widely used in space structures, and their looseness may lead to major safety accidents. The current bolt monitoring methods based on deep learning usually have high computational complexity, and it is difficult to guarantee its computational efficiency under practical scenario. To mitigate this problem, here in this paper, an efficient robotic-assisted bolt-ball joint looseness monitoring approach using convolutional block attention module (CBAM)-enhanced lightweight ResNet is proposed. Firstly, the robotic-assisted tapping method is applied to bolt-ball joints to generate audio signals, which are constructed into time-frequency maps by continuous wavelet transform. Secondly, the original ResNet is improved as a lightweight network, which successfully reduces model complexity, and employs time-frequency maps as input. Then, CBAM is introduced to capture global information and focus on the critical feature. Thus, the efficiency of feature extraction is significantly improved. Finally, by the overall optimized structure, a CBAM-enhanced lightweight ResNet model is established to monitor the bolt-ball joints looseness state accurately. Experimental results demonstrate the high efficiency while maintaining very lightweight structure of the proposed method, verifying the effectiveness and superiority of the robot-assisted approach using CBAM-enhanced lightweight ResNet over other methods.