System and method for detecting heat treatment state of high-steel-grade thick-wall pipe fitting based on deep learning

Abstract

The invention provides a system and a method for detecting a heat treatment state of a high-steel-grade thick-wall pipe fitting based on deep learning. The method comprises the following steps: 1, acquiring metallographic structure images of the inner surface and the outer surface of a to-be-detected area of the high-steel-grade thick-wall pipe fitting; 2, establishing a data set, and dividing the data set into a training set and a test set; 3, constructing a convolutional neural network, and training the constructed convolutional neural network to obtain a trained convolutional neural network; predicting the trained convolutional neural network, and classifying prediction results to obtain a classification result graph; 4, predicting the to-be-detected high-steel-grade thick-wall pipe fitting subjected to heat treatment, judging a prediction result, and further judging whether the to-be-detected high-steel-grade thick-wall pipe fitting subjected to heat treatment is qualified or not; the aim of economically, efficiently, objectively and accurately inspecting the heat treatment state of the high-steel-grade rear wall pipe fitting is achieved.

Description

technical field [0001] The invention belongs to the field of heat treatment and metallographic microscopic analysis, and relates to a system and method for detecting the heat treatment state of high-grade thick-walled pipe fittings based on deep learning. Background technique [0002] In order to achieve efficient transportation and reduce pipeline construction costs, more and more long-distance oil and gas pipelines use high-pressure transmission, large-diameter, high-grade steel and thick-walled pipes. During the construction of national key projects such as West-East Gas Transmission, Central Asia, China-Myanmar, and China-Russia oil and gas pipelines, a large number of X70 and X80 thick-walled pipe fittings (tees, elbows, etc.) are required. At present, the main production process of X70 and X80 thick-walled pipe fittings at home and abroad is: hot forming, that is, heat treatment of quenching + tempering. Among them, the heat treatment state of the pipe fittings determ...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a method for detecting the heat treatment state of high-grade thick-walled pipe fittings based on deep learning, which solves the problems of time-consuming, labor-intensive, high inspection cost and expense, and the need for equipment when detecting the heat-treatment state of high-grade steel-grade thick-walled pipe fittings in the prior art. Professional test technicians, and the shortcomings of unobjective and comprehensive test results

Images