Looseness extent recognition of hydraulic pipeline clamps based on multi-scale feature fusion CNN model

The clamp, as a fixed connection element of hydraulic pipeline system, its condition affects sustainability, reliability and safety of the whole system. Therefore, it is essential to identify level of loosed clamp caused by wear and tear. This paper proposes a clamp looseness extent recognition method based on multi-scale feature fusion convolutional neural network (MFF-CNN). The 2-D input constructed by small sample data of 7 distributed FBG sensors is useful for integration of temporal-spatial feature of clamp looseness. Furthermore, multi-scale fused features in MFF-CNN are more effective to overcome problem of small sample data caused by transient nature of mechanical faults and improves efficiency of CNN model training. The proposed model provides better performance on clamp looseness extent recognition compared to 1DCNN, 2DCNN and MSCNN. The average recognition accuracy reaches up to 96.3%.