Method and system for detecting inner and outer surface defects of TA22 titanium alloy pipe

Abstract

The invention provides a TA22 titanium alloy pipe inner and outer surface defect detection method and system, and relates to the technical field of defect detection. Comprising the following steps: according to enhanced signal data, performing defect feature extraction on the enhanced signal data by adopting a convolutional neural network, and obtaining defect features according to extraction; introducing characteristic factors of the TA22 titanium alloy material to recheck and judge the defect characteristics to obtain a defect analysis result after recheck and judgment; and on the basis of a defect analysis result after re-checking and judging, predicting defect extension. According to the method, the characteristic factors of the TA22 titanium alloy material are introduced, and the step-by-step rechecking judgment process of the inner surface and the outer surface is combined, so that the precision of defect characteristic analysis is optimized; integrating the crack propagation factor and the stress intensity factor, and combining the propagation saturation factor to realize the propagation prediction for the defect; the detection efficiency is greatly improved through a targeted design, and a rapid closed loop of defects from detection to report generation is realized.

Description

Technical Field

[0001] The present application relates to the technical field of defect detection, and in particular to a method and system for detecting inner and outer surface defects of a TA22 titanium alloy pipe. Background Art

[0002] TA22 titanium alloy has been widely used in industrial fields with high performance requirements such as aerospace and chemical equipment due to its excellent strength-to-weight ratio, high corrosion resistance and good processing performance; However, due to the high activity and complex structural characteristics of titanium alloy materials, they are extremely susceptible to processing defects during production and use. Conventional processing defects include cracks, pores and inclusions; processing defects may cause a significant decrease in the mechanical properties of the material, thereby threatening the safety of equipment or structures.

[0003] At present, the detection method using ultrasonic detection has certain defects, as follows: The signal processing capability is limited. Conventional methods are susceptible to noise interference for defect signals on complex surfaces and inside materials, making it difficult to achieve high-precision defect identification. The defect feature extraction is not comprehensive, and there is a lack of in-depth analysis of the multimodal features of the defect signal, making it difficult to effectively distinguish the defect type and determine the specific parameters of the defect; There is a lack of review mechanism, and the test results mainly rely on the output of a single method. There is a lack of review mechanism for the determination results, and there is a lack of targeted review standards for specific materials. A single method cannot be adapted to the review and defect inspection of specific materials, and there is a risk of false detection or missed detection. Summary of the invention

[0004] The present application provides a method and system for detecting internal and external surface defects of TA22 titanium alloy pipes, aiming to solve the technical problem of limited signal processing capability in related technologies, avoid the problem of incomplete defect feature extraction, and solve subsequent problems caused by the lack of a review mechanism.

[0005] In order to achieve the above-mentioned purpose, in the present application, a method for detecting inner and outer surface defects of a TA22 titanium alloy pipe is provided, comprising the following steps: Arrange ultrasonic sensors to obtain signal data of the inner and outer surfaces of TA22 titanium alloy pipes according to the ultrasonic sensors; According to the signal data, an adaptive filtering algorithm is used to perform denoising; According to the denoised signal data, the time-frequency analysis algorithm is used to enhance it; According to the enhanced signal data, a convolutional neural network is used to extract defect features, and the defect features are obtained based on the extraction; The characteristic factors of TA22 titanium alloy material are introduced to review and determine the defect characteristics, and the defect analysis results after review and determination are obtained; Based on the defect analysis results after review and determination, the expansion of defects is predicted; Generate a test report based on the prediction results.

[0006] Preferably, an ultrasonic sensor is arranged, and signal data of the inner and outer surfaces of the TA22 titanium alloy pipe are obtained according to the ultrasonic sensor. The specific steps are as follows: Ultrasonic sensors are evenly arranged on the inner and outer surfaces of TA22 titanium alloy pipes to form full coverage of detection signal data; The transmitting end of the ultrasonic sensor adjusts the transmitting angle so that the ultrasonic signal forms a uniformly distributed sound wave field on the surface of the pipe; The sensors at the receiving end are arranged in a circular distribution manner, evenly arranged around the outer surface of the pipe to ensure the spatial coverage of signal collection; The receiving end sensor adjusts the receiving angle and sensitivity in real time to adapt to the local changes on the pipe surface. The adjustment formula is: ; In the formula, For the Adjust the receiving angle of each receiving end sensor. is the initial receiving angle, is the sensitivity parameter, which reflects the responsiveness of the receiving angle to surface changes. It is the local geometric variation of the pipe surface; the acquired signal data contains the morphological information of the pipe surface and the echo signal of the internal defects, and the signal data provides a data benchmark for subsequent steps.

[0007] Preferably, according to the signal data, an adaptive filtering algorithm is used to perform denoising processing on it, and the denoising formula is: ; In the formula, the adaptive filtering algorithm uses the minimum mean square error algorithm to dynamically update the filter coefficients and optimize the signal-to-noise ratio of the signal data; represents the signal data after denoising, is the adaptive weight of the filter, is the input signal data, is the order of the filter.

[0008] Preferably, according to the denoised signal data, a time-frequency analysis algorithm is used to enhance the signal data, and the enhancement formula is: ; In the formula, short-time Fourier transform is used to perform time-frequency decomposition on the denoised signal data, enhance the signal strength of the low-frequency part, and suppress high-frequency noise; represents the time-frequency representation after short-time Fourier transform, represents the signal data after denoising; represents the window function; Indicates frequency, Represents the center position of the discrete time window.

[0009] Preferably, based on the enhanced signal data, a convolutional neural network is used to extract defect features, and the defect features are obtained based on the extraction. The specific steps are as follows: Configure the convolutional neural network structure, segment the data set, train and optimize the configured convolutional neural network, obtain the optimized convolutional neural network, input the enhanced signal data into the optimized convolutional neural network, and use the convolutional neural network to extract features from the enhanced signal data. Based on the extraction, the defect features are obtained and visualized.

[0010] Preferably, an image recognition algorithm is used to review and determine the defect analysis result to obtain the defect analysis result after review and determination. The specific steps are as follows: The characteristic factors of TA22 titanium alloy material are introduced to review and determine the defect characteristics, and the defect analysis results after review and determination are obtained. The specific steps are as follows: According to the defect characteristics, the review and judgment are carried out, and the roughness correction factor is introduced to review the inner surface defect characteristics of TA22 titanium alloy pipes, specifically: ; In the formula, Indicates the comprehensive confidence of internal surface defect review, is the number of inner surface defect features, For the The matching value of the inner surface defect features, For the The weights of the internal surface defect features are assigned according to the importance of the features. is the roughness correction factor of the inner surface of TA22 titanium alloy, and its calculation formula is: ; In the formula, is the roughness correction factor of the inner surface of TA22 titanium alloy, Indicates the inner surface The roughness of the place; It is the maximum roughness threshold allowed for the inner surface.

[0011] For the internal surface defect feature review, the comprehensive confidence is calculated according to the formula ;when When , the inner surface detection result is determined to be consistent; otherwise, it is marked as a divergence point. The defect features marked as divergence points will be fed back to the convolutional neural network and used to adjust the model parameters; the calculation formula for the inner surface judgment threshold is: ; In the formula, is the threshold for inner surface determination, is the basic judgment threshold, which is 0.85; is the deviation value of the current maximum roughness of the inner surface, which is obtained by calculating the difference between the actual roughness value of the inner surface and the preset target value of the inner surface roughness of the TA22 titanium alloy pipe; The maximum roughness threshold allowed for the inner surface.

[0012] The fatigue factor was introduced to review the external surface defect characteristics of TA22 titanium alloy tubes, specifically: ; In the formula, Indicates the comprehensive confidence level of the external surface defect review; is the number of external surface defect features; For the The matching value of the external surface defect feature should be explained as follows: The value of is 0 or 1; is the weight of the th external surface defect feature, which is allocated according to the importance of the defect feature; is the outer surface fatigue factor, and its calculation formula is: ; In the formula, is the outer surface fatigue factor, is the yield strength of TA22 titanium alloy, For the Point stress distribution value; Indicates the comprehensive confidence level of the external surface defect review; Represents the number of external surface defect features.

[0013] For the review of external surface defect features, the comprehensive confidence is calculated according to the formula ;when When , the outer surface detection result is determined to be consistent; otherwise, it is marked as a divergence point. The defect features marked as divergence points will be fed back to the convolutional neural network and used to adjust the model parameters; the calculation formula for the outer surface judgment threshold is: ; In the formula, is the threshold for external surface determination, is the basic judgment threshold, which is consistent with the value of the basic judgment threshold of the inner surface; is the preset fatigue limit stress, is the maximum stress value currently measured, is the yield strength of TA22 titanium alloy.

[0014] Preferably, based on the defect analysis results after review and determination, the defect expansion is predicted, and the specific steps are as follows: According to the defect analysis results, the defect expansion path is predicted, specifically: ; In the formula, Indicates that the defect is at time spatial location, is the initial position of the defect, is the initial expansion speed of the defect, is the crack growth factor of TA22 titanium alloy, which is calculated by substituting the measured value; is the defect stress intensity factor, which is calculated from the fatigue properties of the material.

[0015] The prediction of the defect expansion size is as follows: ; In the formula, For the moment The defect size, is the initial defect size, is the material expansion rate constant, It is the expansion saturation factor, which is used to reflect the deceleration characteristics of defect expansion.

[0016] Preferably, a test report is generated according to the prediction results, and the specific steps are as follows: According to the defect prediction results, the defect information is extracted, including the specific location of the defect, the defect type, the defect size, the defect expansion path and the defect evolution trend. The defect information is integrated and a test report is generated. The test report includes: a three-dimensional model of the defect distribution, marking the specific location, defect size and defect type of the defect; a dynamic curve chart of the defect expansion trend; after the test report is generated, the test report is fed back to the operator, who then maintains the pipe.

[0017] The present application further provides a TA22 titanium alloy pipe internal and external surface defect detection system, comprising the following units: A data acquisition unit, used to arrange ultrasonic sensors and acquire signal data of the inner and outer surfaces of the TA22 titanium alloy pipe according to the ultrasonic sensors; A denoising processing unit, used for denoising the signal data by using an adaptive filtering algorithm; An enhancement processing unit, used to enhance the denoised signal data by using a time-frequency analysis algorithm; A defect extraction unit is used to extract defect features from the enhanced signal data using a convolutional neural network, and obtain defect analysis results based on the extraction; A review and determination unit is used to review and determine the defect analysis result by using an image recognition algorithm to obtain the defect analysis result after review and determination; The prediction unit predicts the evolution trend and expansion of defects based on the defect analysis results after review and judgment; The report generating unit is used to generate a detection report according to the prediction result.

[0018] The beneficial effects of this application are: 1. The characteristic factors of TA22 titanium alloy materials are introduced, combined with the step-by-step review and judgment process of the inner and outer surfaces, to optimize the accuracy of defect feature analysis; for defect expansion prediction, the crack extension factor and stress intensity factor are integrated, combined with the expansion saturation factor, to establish a dynamic expansion model that conforms to the characteristics of TA22 titanium alloy, which can not only accurately describe the acceleration stage of defect expansion, but also effectively predict its stabilization process; in addition, the present invention greatly improves the detection efficiency through targeted design, reduces the time cost of the review and prediction process, and realizes a fast closed loop from defect detection to report generation; it provides a solution for the inner and outer surface defect detection of TA22 titanium alloy pipes under complex working conditions; 2. The present invention adopts an adaptive filtering algorithm combined with a time-frequency analysis algorithm to perform multi-stage processing on ultrasonic signals, optimizes the signal-to-noise ratio by dynamically updating the filter coefficient, and uses short-time Fourier transform to enhance the low-frequency characteristics of the signal, effectively suppressing high-frequency noise interference, and providing a data basis for subsequent defect feature extraction; 3. Based on the convolutional neural network, the enhanced signal data is subjected to feature extraction, and the multi-layer convolution kernel is used to achieve accurate analysis of the defect location, type and size; compared with the conventional single feature extraction method, the present invention can simultaneously capture the time domain characteristics, frequency domain characteristics and geometric characteristics of the defect signal, significantly improving the comprehensiveness and accuracy of defect feature extraction. In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following is a detailed description of the preferred embodiments in conjunction with the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A flow chart of a method for detecting inner and outer surface defects of a TA22 titanium alloy tube provided in an embodiment of the present application.

[0021] Figure 2 This is an architectural diagram of a system for detecting internal and external surface defects of a TA22 titanium alloy tube provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0023] See also Figure 1 , Figure 1 A flow chart of a method for detecting inner and outer surface defects of a TA22 titanium alloy tube is provided for an embodiment of the present application.

[0024] In this embodiment, a method for detecting inner and outer surface defects of a TA22 titanium alloy tube includes step S10, step S20, step S30, step S40, step S50, step S60 and step S70.

[0025] Step S10: deploy ultrasonic sensors, and obtain signal data of the inner and outer surfaces of the TA22 titanium alloy pipe according to the ultrasonic sensors. The specific steps are as follows: Ultrasonic sensors are evenly distributed on the inner and outer surfaces of the TA22 titanium alloy pipe to achieve full coverage of detection signal data.

[0026] It should be noted that in order to ensure comprehensive and accurate detection, the density and position of the ultrasonic sensors need to be selected according to the geometric dimensions of the pipe and the detection requirements; the layout plan adopts an equidistant arrangement to ensure that the signal data fully covers the inner and outer surfaces of the pipe.

[0027] The transmitting end of the ultrasonic sensor adjusts the transmitting angle so that the ultrasonic signal data forms a uniformly distributed sound wave field on the surface of the pipe.

[0028] It should be noted that the uniformity of the acoustic wave field is pre-designed through simulation software, and the emission angle is controlled by a stepper motor with an adjustment range of 0° to 45° to cover the detection area of ​​complex curved surfaces. The sensor uses a pulse mode when emitting signal data, and the duration of the signal data is controlled at the microsecond level to ensure the time resolution of the detection.

[0029] The sensors at the receiving end are arranged in a circular distribution manner and evenly arranged around the outer surface of the pipe to ensure the spatial coverage of signal data collection.

[0030] It should be noted that the specific spacing of the annular distribution of the receiving-end sensors is optimized according to the pipe diameter and the ultrasonic propagation attenuation characteristics; for pipes with a diameter larger than that of conventional models, the spacing of the receiving-end sensors is set to 5mm to 20mm to ensure the integrity of the echo signal data.

[0031] The receiving end sensor adjusts the receiving angle and sensitivity in real time to adapt to the local changes on the pipe surface. The adjustment formula is: ; In the formula, For the Adjust the receiving angle of each receiving end sensor. is the initial receiving angle, is the sensitivity parameter, which reflects the responsiveness of the receiving angle to surface changes. It is the local geometric variation of the pipe surface; the acquired signal data contains the morphological information of the pipe surface and the echo signal of the internal defects, and the signal data provides a data benchmark for subsequent steps.

[0032] It should be noted that the receiving angle adjustment is achieved through stepper motor control, and the sensitivity adjustment is completed through amplifier gain control.

[0033] Step S20: Adopt an adaptive filtering algorithm to perform denoising on the signal data. The denoising formula is: ; In the formula, the adaptive filtering algorithm uses the minimum mean square error algorithm to dynamically update the filter coefficients and optimize the signal-to-noise ratio of the signal data; represents the signal data after denoising, is the adaptive weight of the filter, is the input signal data, is the order of the filter.

[0034] It should be noted that the adaptive filtering algorithm is based on the input signal data Dynamically adjust the filter weights , to achieve the separation of signal data and noise; the output of the filter It is the filtered signal data with a higher signal-to-noise ratio; the order of the filter It determines the coverage of the filter on the historical data in the signal data. The larger the order, the wider the response range of the filter, but the computational complexity also increases. The specific order is selected according to the characteristics of the actual detection signal data, and the value range is limited to 10 to 50. The adaptive filter dynamically updates the weights through the minimum mean square error algorithm. , to minimize the output signal data The error between the expected signal data and the expected signal data is reduced, thereby optimizing the signal-to-noise ratio; the denoised signal data not only retains the key features of the original signal data, but also suppresses the interference of environmental noise, providing stable quality input data for subsequent analysis steps.

[0035] Step S30: Based on the denoised signal data, a time-frequency analysis algorithm is used to enhance the signal data. The enhancement formula is: ; In the formula, short-time Fourier transform is used to perform time-frequency decomposition on the denoised signal data, enhance the signal strength of the low-frequency part, and suppress high-frequency noise; represents the time-frequency representation after short-time Fourier transform, represents the signal data after denoising; represents the window function; Indicates frequency, Represents the center position of the discrete time window.

[0036] It should be noted that short-time Fourier transform is a time-frequency analysis method that can simultaneously obtain the time domain and frequency domain characteristics of signal data by segmenting the signal data; the window function The introduction of ensures the stability of signal data within the local time window; the enhancement function of the time-frequency analysis algorithm is mainly reflected in the enhancement of the low-frequency part of the signal data and the suppression of high-frequency noise; The amplitude is dynamically adjusted, and the algorithm can highlight the signal data with low-frequency characteristics while filtering out high-frequency noise; the result of the short-time Fourier transform is expressed in the form of a time-frequency diagram, with time on the horizontal axis and frequency on the vertical axis, and the color or brightness of the image represents the intensity of the signal data; this result provides the basis for the input data of the subsequent convolutional neural network; the application of the time-frequency analysis algorithm needs to be combined with the characteristics of the ultrasonic signal data, and short-time Fourier transform is performed on each segment of signal data separately. The processed enhanced signal data is stored in digital form, and the sampling rate is set according to the characteristics of the signal data, and the lower limit of the sampling rate is set to 1GHz.

[0037] Step S40: According to the enhanced signal data, a convolutional neural network is used to extract defect features, and defect features are obtained according to the extraction. The specific steps are as follows: Configure the convolutional neural network structure, segment the data set, train and optimize the configured convolutional neural network, obtain the optimized convolutional neural network, input the enhanced signal data into the optimized convolutional neural network, and use the convolutional neural network to extract features from the enhanced signal data. Based on the extraction, the defect features are obtained and visualized.

[0038] It should be noted that the structural design of the convolutional neural network includes input layer, convolution layer, pooling layer, fully connected layer and output layer; the configuration is optimized according to the characteristics of the enhanced signal data; the convolution layer is used to extract local features of the signal data, the pooling layer reduces redundant data by dimensionality reduction, the fully connected layer maps the features into high-dimensional vectors, and the output layer is used to classify defect features.

[0039] It should be further explained that, in order to improve the training effect, the enhanced signal data is divided into training set, validation set and test set with a segmentation ratio of 8:1:1; the training set is used to train the convolutional neural network, the validation set is used to adjust the network parameters, and the test set is used to evaluate the network performance.

[0040] It should be further explained that the training process adopts the supervised learning method, uses the labeled defect feature data as labels, and updates the network weights through the back propagation algorithm. The optimization methods include: Learning rate adjustment: The initial learning rate is set to 0.001, which gradually decays with the increase of training rounds; Regularization processing: L2 regularization is introduced to avoid overfitting; Data enhancement: The training samples are expanded through translation and scaling operations of signal data to improve the generalization ability of the network.

[0041] It should be further explained that the optimized convolutional neural network receives the time-frequency features of the enhanced signal data and uses it as input data; the convolution layer extracts the local features of the input signal data through the convolution kernel, and the size, number and step size of each layer of the convolution kernel are designed according to the characteristics of the signal data; after feature extraction, the generated feature map contains the spatial distribution, type and signal strength of the defects.

[0042] It should be further explained that the visual mapping reduces the high-dimensional features into three-dimensional space and generates a 3D point cloud map; different types of defects are mapped to different colors or brightness to facilitate operators to intuitively understand the type and distribution of defects.

[0043] Step S50, introducing characteristic factors of TA22 titanium alloy material to review and determine the defect characteristics, and obtaining defect analysis results after review and determination, the specific steps are as follows: According to the defect characteristics, the review and judgment are carried out, and the roughness correction factor is introduced to review the inner surface defect characteristics of TA22 titanium alloy pipes, specifically: ; In the formula, Indicates the comprehensive confidence of internal surface defect review, is the number of inner surface defect features, For the The matching value of the inner surface defect features, For the The weight of the inner surface defect feature, is the roughness correction factor of the inner surface of TA22 titanium alloy, and its calculation formula is: ; In the formula, is the roughness correction factor of the inner surface of TA22 titanium alloy, Indicates the inner surface The roughness of the place; It is the maximum roughness threshold allowed for the inner surface.

[0044] It should be noted that The value range is 0 or 1, 0 means match, 1 means no match.

[0045] It should be noted that Calculated by the following formula: ; In the formula, For the The influencing factor of each defect characteristic is determined according to the influence of the defect on the mechanical properties of the pipe; is the roughness correction factor, which is used to reflect the importance of internal surface roughness to specific defect characteristics; is the total number of inner surface defect features, For the The weight of the internal surface defect feature.

[0046] It is further necessary to explain that The influence of different roughness on the fatigue performance of TA22 titanium alloy was determined by measuring, and the critical roughness value was determined according to the influence. The roughness safety factor was introduced according to the critical roughness value. The critical roughness value and the roughness safety factor were substituted into the calculation to obtain The specific value of .

[0047] ; In the formula, is the critical roughness value determined experimentally, is the safety factor, ranging from 0.1 to 0.2.

[0048] For the internal surface defect feature review, the comprehensive confidence is calculated according to the formula ,when When , the inner surface detection result is determined to be consistent; otherwise, it is marked as a divergence point. The defect features marked as divergence points will be fed back to the convolutional neural network and used to adjust the convolutional neural network weights; the calculation formula for the inner surface judgment threshold is: ; In the formula, is the threshold for inner surface determination, is the basic judgment threshold, which is 0.85; is the deviation value of the current maximum roughness of the inner surface; The maximum roughness threshold allowed for the inner surface.

[0049] It should be noted that It is calculated by comparing the actual roughness value of the inner surface with the preset target value. The specific formula is: ; In the formula, is the actual measured roughness value of the inner surface, The preset target value is determined based on the pipe design requirements, use environment and processing capability of TA22 titanium alloy, and is obtained based on the standard surface roughness range of the pipe combined with actual measurement. It is the deviation value of the current maximum roughness of the inner surface.

[0050] The fatigue factor was introduced to review the external surface defect characteristics of TA22 titanium alloy tubes, specifically: ; In the formula, Indicates the comprehensive confidence level of the external surface defect review; is the number of external surface defect features; For the The matching value of the external surface defect features, For the The weight of each external surface defect feature is allocated according to the importance of the defect feature; is the outer surface fatigue factor, and its calculation formula is: ; In the formula, is the outer surface fatigue factor, is the yield strength of TA22 titanium alloy, For the Point stress distribution value, Represents the comprehensive confidence of the external surface defect review, Represents the number of external surface defect features.

[0051] It should be noted that The value is 0 or 1, 0 means no match, and 1 means match.

[0052] It should be further explained that the distribution of the weight of the external surface defect feature is calculated based on the influence of the defect feature, and the calculation formula is: ; In the formula, For the The sensitivity factor of each defect feature is determined based on the effect of the defect location on the fatigue resistance of the outer surface. is the outer surface fatigue factor, is the feature weight of the external surface defects.

[0053] It should be noted that The value range is 0 or 1, 0 means match, 1 means no match.

[0054] It should be further noted that the yield strength is obtained by tensile testing according to the standard test procedure ASTME8 / E8M, and the specific steps are as follows: A1. Prepare specimens of standard size; A2. Use a tensile testing machine to apply load to the sample and record the relationship between stress and strain; A3. Take the 0.2% offset value in the stress-strain curve as the yield strength.

[0055] It should be further explained that the stress distribution value is calculated by the finite element method based on the stress field analysis, specifically: ; In the formula, is the applied load, is the effective cross-sectional area of ​​the defect location, is the stress distribution value.

[0056] For the review of external surface defect features, the comprehensive confidence is calculated according to the formula ;when When , the outer surface detection result is determined to be consistent; otherwise, it is marked as a divergence point. The defect features marked as divergence points will be fed back to the convolutional neural network and used to adjust the convolutional neural network weights; the calculation formula for the outer surface judgment threshold is: ; In the formula, is the threshold for external surface determination, is the basic judgment threshold, which is 0.85; is the preset fatigue limit stress, is the maximum stress value currently measured, is the yield strength of TA22 titanium alloy.

[0057] It should be noted that the fatigue limit stress is based on the actual fatigue test data of TA22 titanium alloy and is set in combination with the application environment: B1. Determine the fatigue strength of the material under different cycle numbers through fatigue test; B2. Introduce fatigue safety factor based on the use environment Perform the calculation: ; In the formula, is the experimentally determined fatigue strength, is the fatigue safety factor, is the fatigue limit stress.

[0058] Step S60: Based on the defect analysis results after review and determination, predict the expansion of the defect. The specific steps are as follows: According to the defect analysis results, the defect expansion path is predicted, specifically: ; In the formula, Indicates that the defect is at time spatial location, is the initial position of the defect, is the initial expansion speed of the defect, is the crack growth factor of TA22 titanium alloy; is the defect stress intensity factor.

[0059] It should be noted that the crack growth factor is based on fatigue crack growth test and is obtained by fitting the Paris law formula: ; In the formula, and is the experimental fitting constant, is the stress intensity factor range, is the crack growth factor of TA22 titanium alloy.

[0060] It should be further noted that the defect stress intensity factor is calculated by the following formula: ; In the formula, is the stress acting on the defect tip, is the half length of the defect, represents the defect stress intensity factor.

[0061] The prediction of the defect expansion size is as follows: ; In the formula, For the moment The defect size, is the initial defect size, is the material expansion rate constant, is the extended saturation factor.

[0062] It should be noted that the material extension rate constant is obtained through fatigue crack extension experiment to obtain crack extension rate data; and based on the Paris law formula Sure ; Introduce environmental correction factor based on the working environment of the material , the final calculation Conclude.

[0063] It should be further explained that the extension saturation factor is calculated by recording the stage when the crack extension approaches saturation. Sure ; and combined with the maximum allowable crack length and material properties calculation ; By introducing the environmental correction factor , the final calculation Conclude.

[0064] Step S70: Generate a test report based on the prediction results. The specific steps are as follows: According to the defect prediction results, the defect information is extracted, including the specific location of the defect, the defect type, the defect size, the defect expansion path and the defect evolution trend. The defect information is integrated and a test report is generated. The test report includes: a three-dimensional model of the defect distribution, marking the specific location, defect size and defect type of the defect; a dynamic curve chart of the defect expansion trend; after the test report is generated, the test report is fed back to the operator, who then maintains the pipe.

[0065] It should be further explained that the generation of the test report is based on a standardized data template, including the following parts: The three-dimensional model of defect distribution is generated by a three-dimensional modeling tool, with the location and range of defects marked with different colors; the dynamic curve chart of defect expansion trend visualizes the prediction results as an expansion trend curve changing over time, intuitively showing the future changes of defects; statistical information on defect type and size, lists the specific parameters and detection results of each type of defect in tabular form.

[0066] It should be further explained that the inspection report is transmitted to the operator in real time through the digital platform, and the operator formulates a corresponding maintenance plan based on the defect distribution and trend analysis results in the report.

[0067] At this point, a method for detecting internal and external surface defects of TA22 titanium alloy pipes has been completed.

[0068] See also Figure 2The present application further provides a TA22 titanium alloy pipe inner and outer surface defect detection system, comprising the following units: a data acquisition unit, used to deploy ultrasonic sensors, and obtain signal data of the inner and outer surfaces of the TA22 titanium alloy pipe according to the ultrasonic sensors; a denoising processing unit, used to perform denoising processing on the signal data using an adaptive filtering algorithm; an enhancement processing unit, used to perform enhancement processing on the denoised signal data using a time-frequency analysis algorithm; a defect extraction unit, which extracts defect features from the enhanced signal data using a convolutional neural network, and obtains defect features based on the extraction; a review and determination unit, which introduces the characteristic factors of the TA22 titanium alloy material to review and determine the defect features, and obtains the defect analysis results after the review and determination; a prediction unit, which predicts the expansion of the defect based on the defect analysis results after the review and determination; and a report generation unit, which generates a detection report based on the prediction results.

[0069] At this point, a TA22 titanium alloy pipe internal and external surface defect detection system has been completed.

[0070] It should be understood that the "one embodiment" or "an embodiment" or "a feasible implementation" or "some implementations" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the embodiments of the present invention. Therefore, "in one embodiment" or "in an embodiment" or "a feasible implementation" or "some implementations" appearing in various places throughout the specification do not necessarily refer to the same embodiment. In addition, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the steps and modules involved are not necessarily required for the embodiments of the present invention.

[0071] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by instructions. These instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0072] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0073] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0074] The above are only specific embodiments of the present invention, but the protection scope of the embodiments of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the embodiments of the present invention, which should be included in the protection scope of the embodiments of the present invention. Therefore, the protection scope of the embodiments of the present invention should be based on the protection scope of the claims.

Claims

1. A method for detecting inner and outer surface defects of TA22 titanium alloy pipes, characterized in that: These include: Arrange ultrasonic sensors to obtain signal data of the inner and outer surfaces of TA22 titanium alloy pipes according to the ultrasonic sensors; According to the signal data, an adaptive filtering algorithm is used to perform denoising; According to the denoised signal data, the time-frequency analysis algorithm is used to enhance it; According to the enhanced signal data, a convolutional neural network is used to extract defect features, and the defect features are obtained based on the extraction; The characteristic factors of TA22 titanium alloy material are introduced to review and determine the defect characteristics, and the defect analysis results after review and determination are obtained; Based on the defect analysis results after review and determination, predict the expansion of defects; Generate a test report based on the prediction results.

2. A method for detecting inner and outer surface defects of a TA22 titanium alloy pipe as claimed in claim 1, characterized in that: Arrange ultrasonic sensors and obtain signal data of the inner and outer surfaces of TA22 titanium alloy pipes according to the ultrasonic sensors. The specific steps are as follows: Ultrasonic sensors are evenly arranged on the inner and outer surfaces of TA22 titanium alloy pipes to form full coverage of detection signal data; The transmitting end of the ultrasonic sensor adjusts the transmitting angle so that the ultrasonic signal forms a uniformly distributed sound wave field on the surface of the pipe; The sensors at the receiving end are arranged in a circular distribution manner, evenly arranged around the outer surface of the pipe to ensure the spatial coverage of signal collection; The receiving end sensor adjusts the receiving angle and sensitivity in real time to adapt to the local changes on the pipe surface. The adjustment formula is: ； In the formula, For the The receiving angle of each receiving end sensor is adjusted. is the initial receiving angle, is the sensitivity parameter, which reflects the responsiveness of the receiving angle to surface changes. It is the local geometric variation of the pipe surface; the acquired signal data contains the morphological information of the pipe surface and the echo signal of the internal defects, and the signal data provides a data benchmark for subsequent steps.

3. The method for detecting inner and outer surface defects of a TA22 titanium alloy pipe according to claim 1, characterized in that: According to the signal data, an adaptive filtering algorithm is used to denoise it, and the denoising formula is: ； In the formula, the adaptive filtering algorithm uses the minimum mean square error algorithm to dynamically update the filter coefficients and optimize the signal-to-noise ratio of the signal data; represents the signal data after denoising, is the adaptive weight of the filter, is the input signal data, is the order of the filter.

4. A method for detecting inner and outer surface defects of a TA22 titanium alloy pipe as claimed in claim 3, characterized in that: According to the denoised signal data, the time-frequency analysis algorithm is used to enhance it, and the enhancement formula is: ； In the formula, short-time Fourier transform is used to perform time-frequency decomposition on the denoised signal data, enhance the signal strength of the low-frequency part, and suppress high-frequency noise; represents the time-frequency representation after short-time Fourier transform, represents the signal data after denoising; represents the window function; Indicates frequency, Represents the center position of the discrete time window.

5. A method for detecting inner and outer surface defects of a TA22 titanium alloy tube as claimed in claim 4, characterized in that: According to the enhanced signal data, a convolutional neural network is used to extract defect features, and the defect features are obtained based on the extraction. The specific steps are as follows: Configure the convolutional neural network structure, segment the data set, train and optimize the configured convolutional neural network, obtain the optimized convolutional neural network, input the enhanced signal data into the optimized convolutional neural network, and use the convolutional neural network to extract features from the enhanced signal data. Based on the extraction, the defect features are obtained and visualized.

6. A method for detecting inner and outer surface defects of a TA22 titanium alloy pipe as claimed in claim 5, characterized in that: The characteristic factors of TA22 titanium alloy material are introduced to review and determine the defect characteristics, and the defect analysis results after review and determination are obtained. The specific steps are as follows: According to the defect characteristics, the review and judgment are carried out, and the roughness correction factor is introduced to review the inner surface defect characteristics of TA22 titanium alloy pipes, specifically: ； In the formula, Indicates the comprehensive confidence of internal surface defect review, is the number of inner surface defect features, For the The matching value of the inner surface defect features, For the The weight of the inner surface defect feature, is the roughness correction factor of the inner surface of TA22 titanium alloy, and its calculation formula is: ； In the formula, is the roughness correction factor of the inner surface of TA22 titanium alloy, Indicates the inner surface The roughness of the place; The maximum roughness threshold allowed for the inner surface; For the internal surface defect feature review, the comprehensive confidence is calculated according to the formula ,when When , the inner surface detection results are determined to be consistent; Otherwise, it is marked as a divergence point. The defect features marked as divergence points will be fed back to the convolutional neural network and used to adjust the convolutional neural network model weights. The calculation formula for the inner surface judgment threshold is: ； In the formula, is the threshold for inner surface determination, is the basic judgment threshold, which is 0.85; is the deviation value of the current maximum roughness of the inner surface, is the maximum roughness threshold allowed for the inner surface; The fatigue factor was introduced to review the external surface defect characteristics of TA22 titanium alloy tubes, specifically: ； In the formula, Indicates the comprehensive confidence level of the external surface defect review; is the number of external surface defect features; For the The matching value of the external surface defect features, For the The weight of the external surface defect feature, is the outer surface fatigue factor, and its calculation formula is: ； In the formula, is the outer surface fatigue factor, is the yield strength of TA22 titanium alloy, For the Point stress distribution value; Indicates the comprehensive confidence level of the external surface defect review; Indicates the number of external surface defect features; For the review of external surface defect features, the comprehensive confidence is calculated according to the formula ;when When , the outer surface detection result is determined to be consistent; otherwise, it is marked as a divergence point. The defect features marked as divergence points will be fed back to the convolutional neural network and used to adjust the model parameters; the calculation formula for the outer surface judgment threshold is: ； In the formula, is the threshold for external surface determination, is the basic judgment threshold, which is consistent with the value of the inner surface basic judgment threshold; is the preset fatigue limit stress, is the maximum stress value currently measured, is the yield strength of TA22 titanium alloy.

7. A method for detecting inner and outer surface defects of a TA22 titanium alloy tube as claimed in claim 6, characterized in that: Based on the defect analysis results after review and judgment, the expansion of the defect is predicted. The specific steps are as follows: According to the defect analysis results, the defect expansion path is predicted, specifically: ； In the formula, Indicates that the defect is at time spatial location, is the initial position of the defect, is the initial expansion speed of the defect, is the crack growth factor of TA22 titanium alloy, is the defect stress intensity factor; The prediction of the defect expansion size is as follows: ； In the formula, For the moment The defect size, is the initial defect size, is the material expansion rate constant, is the extended saturation factor.

8. A method for detecting inner and outer surface defects of a TA22 titanium alloy pipe as claimed in claim 7, characterized in that: Generate a test report based on the prediction results. The specific steps are as follows: According to the defect prediction results, the defect information is extracted, including the specific location of the defect, the defect type, the defect size, the defect expansion path and the defect evolution trend. The defect information is integrated and a test report is generated. The test report includes: a three-dimensional model of the defect distribution, marking the specific location, defect size and defect type of the defect; a dynamic curve chart of the defect expansion trend; after the test report is generated, the test report is fed back to the operator, who then maintains the pipe.

9. A TA22 titanium alloy pipe internal and external surface defect detection system, characterized in that: The following units are included: A data acquisition unit, used to arrange ultrasonic sensors and acquire signal data of the inner and outer surfaces of the TA22 titanium alloy pipe according to the ultrasonic sensors; A denoising processing unit, used for denoising the signal data by using an adaptive filtering algorithm; An enhancement processing unit, used to enhance the denoised signal data by using a time-frequency analysis algorithm; A defect extraction unit is used to extract defect features from the enhanced signal data using a convolutional neural network, and obtain defect analysis results based on the extraction; A review and determination unit is used to review and determine the defect analysis result by using an image recognition algorithm to obtain the defect analysis result after review and determination; The prediction unit predicts the evolution trend and expansion of defects based on the defect analysis results after review and judgment; The report generation unit generates a detection report according to the prediction results.

Images