No abstract

No abstract

Ocean platforms that are under complex sea conditions and loads for long periods are prone to fatigue cracks. These cracks may lead to large deformations, even displacement, of the platform, and should be monitored to ensure engineering safety. Cracks are not easily detected in the micro stage and small levels of strain measurement are required to ensure high accuracy. Furthermore, cracks are prone to suddenly developing into large deformations, especially in structural connections in practical engineering. This study developed a novel adaptive range strain sensor for structural crack monitoring that can monitor the whole structural crack propagation process in ocean platforms. The strain sensor is used for micro deformation monitoring through its fiber Bragg grating (FBG) sensor with high sensitivity. The sensor can automatically adapt to crack fractures and provide warnings through an STM32 single-chip microcomputer (SCM) system when the structure suddenly cracks, causing large deformation. The experimental results demonstrate that the device has high precision in micro measurement with the ability to capture structural fractures. The field application shows the high strain sensitivity of the sensor in crack monitoring, which indicates that the adaptive range strain sensor is suitable for the structural crack monitoring of ocean platforms.

Floating Production Storage and Offloading (FPSO) is essential offshore equipment for developing offshore oil and gas. Due to the complex sea conditions, FPSOs will be subjected to long-term alternate loads under some circumstances. Thus, it is inevitable that small cracks occur in the upper part of the module pier. Those cracks may influence the structure’s safety evaluation. Therefore, this paper proposes a method for the FPSO module to support crack identification based on the PSPNet model. The main idea is to introduce an attention mechanism into the model with Mobilenetv2 as the backbone of the PSPNet, which can fuse multiple feature maps and increase context information. The detail feature loss caused by multiple convolutions and compressions in the original model was solved by applying the proposed method. Moreover, the attention mechanism is introduced to enhance the extraction of adequate information and suppress invalid information. The mPA value and MIoU value of the improved model increased by 2.4% and 1.8%, respectively, through verification on FPSO datasets.

No abstract