The primary methods for oil and gas pipeline defect identification currently rely on acoustic and magnetic techniques, with visual solutions remaining scarce. However, recent artificial intelligence (AI) advancements suggest promising avenues for real-time visual defect detection. This research explores the capabilities of AI for real-time detection and aims to refine and optimize this methodology. We achieve this by implementing widely utilized deep learning neural networks, such as YOLO and DETR, for training and processing on-site video images. Our model demonstrates a recognition accuracy exceeding 87% through subsequent application testing, indicating significant potential for real-world implementation in oil and gas pipeline defect detection.
Quantifying internal crack detection signals in steel pipelines requires a high level of expertise from researchers. The traditional signal features cannot fully characterize the actual signals. This paper uses steel plate specimens to simulate steel pipelines for crack detection signal quantification research. Firstly, a differential eddy current test platform based on incremental permeability extraction is built, and the self-developed eddy current detection technology is used to detect the crack defects and form a quantitative database of crack defects; then, end-to-end crack detection signal quantification models DRSN1d and DRSN2d are established; finally, noise is added to the database to compare the traditional model with DRSN2d. The results show that the constructed deep learning model achieves an average crack depth inversion accuracy of ±0.018mm and an average crack width inversion accuracy of ±0.015mm, which meets the industrial requirements. The deep learning quantization model outperforms the traditional machine learning model on high-noise data, and the features formed from the end-to-end model training are also better than the traditional features.
The porous silicon nitride ceramics were prepared by carbothermic reduction-pressureless sintering with SiO2 and α-Si3N4 in nitrogen. By changing the relative content of α-Si3N4, SiO2 and C powder in the raw material, the porosity controlled porous silicon nitride that consists mostly of the β-Si3N4 grains was formed. The porous laminated silicon nitride ceramics composite with three layers were fabricated by this technique. The influence of the α-Si3N4 content for the intermediate layer on the properties of the porous laminated silicon nitride ceramics composite was researched. When the linear shrinkage of the intermediate layer and superficial layer was very different, although it was a weak interfacial bonding, but the interfacial residual stress was very beneficial to the mechanical properties of the porous laminated silicon nitride. When the linear shrinkage and porosity of the intermediate layer and superficial layer were similar, it caused the conversion of weak interfacial bonding into the strong interfacial bonding. The three-layer porous laminated silicon nitride ceramics composite exhibited outstanding mechanical properties.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.