A rapid detection method for the tensile performance of PE gas pipelines

Abstract

The present invention relates to the technical field of pipeline detection, and discloses a rapid detection method for the tensile performance of PE gas pipelines, including: installing ultrasonic transducers on the surface of the PE gas pipeline, exciting ultrasonic guided waves and collecting signals, and extracting characteristics such as the elastic modulus and wave velocity of the pipeline through time-frequency analysis; then analyzing the signals through a deep learning model (CNN+LSTM) to construct a tensile strength prediction model. Compared with traditional destructive tests, this method can quickly and nondestructively predict the tensile strength of pipelines at the construction site, and has high precision (±5%), achieving accurate assessment of the pipeline state under complex environments. The deep learning model can process pipeline data under various specifications, materials, and climatic conditions, ensuring the wide adaptability and high stability of this method, greatly improving work efficiency and the safety of pipeline detection. At the same time, the present invention dynamically optimizes the predicted value through an error correction mechanism to ensure the result accuracy and enhance the reliability of the prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline performance detection, and in particular to a rapid detection method for the tensile performance of PE gas pipelines. Background Art

[0002] PE gas pipelines are an important part of the urban gas transmission system, and their long-term stable operation is directly related to public safety. The tensile strength of the pipeline is an important parameter for judging its structural safety, and usually, the service life is evaluated by detecting the tensile performance of the pipeline material. However, most of the traditional detection methods are destructive tests. Although these methods are accurate, they have the following problems:

[0003] 1. Destructive testing: Traditional tensile strength tests require sampling of the pipeline and measuring the tensile strength through physical tensile tests. This method not only causes pipeline damage but also cannot perform real-time monitoring after pipeline installation, bringing high costs and time delays to subsequent maintenance and repair. At the same time, sampling and destructive testing cannot perform large-scale and rapid detection on in-service pipelines, restricting their popularization in practical applications.

[0004] 2. Limitations of ultrasonic guided wave technology: To solve the problems of traditional destructive testing, ultrasonic guided wave technology has gradually been adopted in the industry for non-destructive testing. Ultrasonic guided wave technology can effectively detect internal defects or performance changes in the pipeline by exciting ultrasonic signals in the pipeline and monitoring the propagation characteristics of the signals. However, most of the existing ultrasonic guided wave detection methods rely on manual analysis, and there are large subjectivity and uncertainty in the signal processing process, resulting in limited accuracy of the results. At the same time, the adaptability of this method in complex environments is poor, especially under the influence of different pipeline specifications, material types, and environmental factors, its effect is difficult to guarantee.

[0005] 3. Application challenges of artificial intelligence technology: In recent years, artificial intelligence has been applied to the processing and analysis of ultrasonic guided wave signals, and the degree of automation and accuracy of signal processing can be improved through technologies such as deep learning. However, in the training process of the existing artificial intelligence-based detection technology, the training data usually used are standard data in the laboratory environment and do not effectively combine the actual usage data of on-site pipelines, resulting in poor generalization ability and adaptability of the model. In addition, the models in the existing technology have insufficient adaptability to various environmental factors (such as temperature, humidity, pipeline aging, etc.) and are difficult to provide high-precision and stable prediction results in practical applications. Summary of the Invention

[0006] The technical problem solved by the present invention is to provide a rapid detection method for the tensile performance of PE gas pipelines to solve the problems raised in the above background art in view of the defects existing in the above-mentioned prior art.

[0007] To solve the above technical problems, the technical solutions adopted by the present invention are as follows: A rapid detection method for the tensile performance of a PE gas pipeline, characterized in that: the method comprises the following steps:

[0008] Step 1, install at least one ultrasonic transducer on the surface of the PE gas pipeline, which is used to excite ultrasonic guided waves to propagate along the axial direction of the pipeline and excite stress waves inside the pipeline. Among them, the ultrasonic transducer is a piezoelectric transducer or a laser transducer, and the excitation frequency of the ultrasonic wave is between 10 kHz and 500 kHz, and the ultrasonic wave signal can propagate along the axial direction of the pipeline and interact with the stress waves inside the pipeline;

[0009] Step 2, use at least one ultrasonic receiving sensor to collect the ultrasonic reflection signal and transmission signal after propagating through the pipeline, and record the propagation characteristics of the ultrasonic wave signal in real time. The propagation characteristics of the ultrasonic wave signal include signal attenuation, frequency shift, propagation time and reflection mode parameters;

[0010] Step 3, perform feature extraction on the collected ultrasonic wave signal through a signal processing module, perform time-frequency analysis on the signal using wavelet transform or Fourier transform, and extract the elastic modulus, wave velocity, attenuation factor and frequency characteristics of the pipeline as candidate feature parameters for the tensile strength of the pipeline;

[0011] Step 4, based on the extracted candidate feature parameters, use a deep learning algorithm to analyze the ultrasonic wave signal through a convolutional neural network CNN and a long short-term memory network LSTM, and construct a pipeline tensile strength prediction model. Among them, the prediction model is obtained by training with historical experimental data, and the historical experimental data includes standard tensile strength data of PE pipelines under different materials, thicknesses, strain rates and environmental conditions;

[0012] Step 5, perform real-time prediction on the ultrasonic wave signal through the prediction model to calculate the tensile strength of the pipeline;

[0013] Step 6, if the predicted result of the tensile strength is lower than the set threshold, automatically generate maintenance suggestions and transmit them to the monitoring platform or on-site operators through a communication interface for subsequent maintenance operations to avoid possible pipeline fracture or air leakage risks.

[0014] As a further solution of the present invention, in step 5, performing real-time prediction on the ultrasonic wave signal through the prediction model to calculate the tensile strength of the pipeline specifically includes the following sub-steps:

[0015] s1, input data: Take the ultrasonic wave signal feature parameters extracted in step 3 as input data and input them into the tensile strength prediction model; among them, the ultrasonic wave signal feature parameters include elastic modulus , wave velocity , attenuation factor and frequency characteristics ;

[0016] s2, Feature extraction and processing: Deeply extract time-domain and frequency-domain features through the convolutional neural network CNN, and combine the long short-term memory network LSTM to model the time-series data of the signal, further learning the elastic behavior of the pipeline and the dynamic changes in its tensile strength; and this process updates the weights of the neural network through the optimized backpropagation algorithm;

[0017] s3, Tensile strength prediction model calculation: Use the trained CNN and LSTM models to analyze and calculate the input signal features to obtain the predicted value of the pipeline's tensile strength, and the predicted value is calculated through the following formula:

[0018]

[0019] where: is the weight coefficient matrix obtained through training with historical data, used for weight optimization and correction of the prediction results;

[0020] s4, Weight coefficient adjustment: By comparing the error between historical experimental data and the predicted value, use the least squares method or other appropriate regression algorithms to dynamically adjust the weight coefficients in the prediction model , to ensure the accuracy of the prediction results and the compliance with the actual tensile strength;

[0021] s5, Tensile strength output: Output the predicted value of the tensile strength of the adjusted model as the current tensile performance index of the pipeline and make subsequent maintenance decisions.

[0022] As a further solution of the present invention, the frequency range of the ultrasonic signal is 20 kHz to 300 kHz to improve the sensitivity to pipeline materials and enhance the penetrability of the signal.

[0023] As a further solution of the present invention, the ultrasonic transducer is a piezoelectric transducer, and the piezoelectric transducer is made of PZT lead titanate material, having high sensitivity and meeting the working requirements under high-temperature environments.

[0024] As a further solution of the present invention, the signal processing module includes a time-domain analysis and a frequency-domain analysis unit. The time-domain analysis unit is used to extract the time features of the signal, and the frequency-domain analysis unit is used to extract the frequency features of the signal to further optimize the feature extraction of the signal.

[0025] As a further solution of the present invention, the deep learning model is a convolutional neural network CNN, and the CNN model includes at least three convolutional layers, pooling layers and fully connected layers to achieve in-depth learning of signal features and accurate prediction of tensile properties.

[0026] As a further solution of the present invention, the training data of the prediction model is derived from multi-experimental data including different environmental temperatures, humidities, pipe materials and their manufacturing process parameters, and data normalization is performed to ensure data consistency.

[0027] As a further solution of the present invention, the deep learning algorithm is trained and optimized by the gradient descent method, and the cross-validation method is used to verify the generalization ability of the model to reduce the overfitting phenomenon.

[0028] As a further solution of the present invention, the tensile strength prediction result is combined with the actual use environmental conditions of the pipe, and risk assessment is carried out by setting different thresholds. If the prediction result is lower than the safety threshold, maintenance suggestions are automatically generated and transmitted to relevant operators through the communication interface.

[0029] As a further solution of the present invention, the acquisition of ultrasonic reflection signals and transmission signals includes preprocessing the signals to remove background noise, and the noise removal methods include but are not limited to band-pass filters and wavelet transforms to ensure high-quality processing of the signals.

[0030] Compared with the prior art, the beneficial effects of the present invention are as follows: By combining ultrasonic guided wave technology with deep learning algorithms, rapid non-destructive detection of the tensile properties of PE gas pipelines is achieved. Not only is it unnecessary to take destructive samples of the pipeline, but also the tensile strength of the pipeline can be directly predicted through the ultrasonic signals collected in real time. Using a deep learning model (CNN + LSTM) to accurately analyze the time-frequency characteristics of the signals enables the prediction accuracy to reach ±5%, and it has extremely strong adaptability to complex environments, capable of quickly completing the evaluation of tensile properties at the construction site, greatly improving work efficiency and the safety of pipeline detection; By using the deep learning model to make real-time predictions on ultrasonic signals and simultaneously adopting an error correction mechanism, combining standard experimental data to correct the predicted value of the tensile strength, the high accuracy of the prediction results is ensured. The error correction method dynamically adjusts the predicted value through optimization algorithms such as the least squares method to ensure that the error between the predicted value of the tensile strength and the true value is always controlled within a predetermined range; and it can adapt to a variety of specifications and environmental conditions, being applicable to PE gas pipelines of different thicknesses and different material grades, and being able to effectively handle the prediction of the tensile strength of pipelines under various climates and strain rates. Since a large amount of historical experimental data and diverse experimental environments are considered during the training process of the deep learning model, this method has extremely high adaptability to various environmental changes and different types of pipelines, and can maintain high accuracy and high stability in a wider range of actual application scenarios; and it can adapt to a variety of specifications and environmental conditions, being applicable to PE gas pipelines of different thicknesses and different material grades, and being able to effectively handle the prediction of the tensile strength of pipelines under various climates and strain rates. Since a large amount of historical experimental data and diverse experimental environments are considered during the training process of the deep learning model, this method has extremely high adaptability to various environmental changes and different types of pipelines, and can maintain high accuracy and high stability in a wider range of actual application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0032] Figure 1 It is a schematic structural diagram of the PE gas pipeline tensile property detection system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0034] Please refer to Figure 1 , in the embodiments of the present invention, a rapid detection method for the tensile performance of a PE gas pipeline is characterized in that the method includes the following steps:

[0035] Step 1, install at least one ultrasonic transducer on the surface of the PE gas pipeline to excite ultrasonic guided waves to propagate along the axial direction of the pipeline and excite stress waves inside the pipeline. Among them, the ultrasonic transducer is a piezoelectric transducer or a laser transducer, and the excitation frequency of the ultrasonic wave is between 10 kHz and 500 kHz, and the ultrasonic wave signal can propagate along the axial direction of the pipeline and interact with the stress wave inside the pipeline;

[0036] Step 2, use at least one ultrasonic receiving sensor to collect the ultrasonic reflection signal and transmission signal after passing through the pipeline, and record the propagation characteristics of the ultrasonic wave signal in real time. The propagation characteristics of the ultrasonic wave signal include signal attenuation, frequency shift, propagation time, and reflection mode parameters;

[0037] Step 3, perform feature extraction on the collected ultrasonic wave signal through a signal processing module, perform time-frequency analysis on the signal using wavelet transform or Fourier transform, and extract the elastic modulus, wave velocity, attenuation factor, and frequency characteristics of the pipeline as candidate feature parameters for the tensile strength of the pipeline;

[0038] Step 4, based on the extracted candidate feature parameters, use a deep learning algorithm to analyze the ultrasonic wave signal through a convolutional neural network CNN and a long short-term memory network LSTM, and construct a pipeline tensile strength prediction model. Among them, the prediction model is obtained by training with historical experimental data, and the historical experimental data includes standard tensile strength data of PE pipelines under different materials, thicknesses, strain rates, and environmental conditions;

[0039] Step 5, perform real-time prediction on the ultrasonic wave signal through the prediction model to calculate the tensile strength of the pipeline;

[0040] Step 6, if the predicted tensile strength result is lower than the set threshold, automatically generate maintenance suggestions and transmit them to the monitoring platform or on-site operators through a communication interface for subsequent maintenance operations to avoid possible pipeline breakage or air leakage risks.

[0041] As a further solution of the present invention, in step 5, the tensile strength of the pipeline is calculated by performing real-time prediction on the ultrasonic signal through the prediction model, which specifically includes the following sub-steps:

[0042] s1, Input data: The ultrasonic signal characteristic parameters extracted in step 3 are used as input data and transmitted into the tensile strength prediction model; wherein, the ultrasonic signal characteristic parameters include elastic modulus , wave velocity , attenuation factor and frequency characteristics ;

[0043] s2, Feature extraction and processing: The time-domain and frequency-domain features are deeply extracted through a convolutional neural network (CNN), and the long short-term memory network (LSTM) is combined to model the time-series data of the signal, further learning the elastic behavior of the pipeline and the dynamic changes of its tensile strength; and in this process, the weights of the neural network are updated by optimizing the backpropagation algorithm;

[0044] s3, Tensile strength prediction model calculation: Using the trained CNN and LSTM models, the input signal features are analyzed and calculated to obtain the predicted value of the pipeline's tensile strength, and the predicted value is calculated through the following formula:

[0045]

[0046] where: is the weight coefficient matrix obtained by training with historical data, which is used for weight optimization and correction of the prediction result;

[0047] s4, Weight coefficient adjustment: By comparing the error between the historical experimental data and the predicted value, the least squares method or other appropriate regression algorithms are used to dynamically adjust the weight coefficients in the prediction model to ensure the accuracy of the prediction result and its conformity with the actual tensile strength;

[0048] s5, Tensile strength output: The adjusted model outputs the predicted value of the tensile strength as the current tensile performance index of the pipeline and subsequent maintenance decisions are made.

[0049] As a further solution of the present invention, the frequency range of the ultrasonic signal is 20 kHz to 300 kHz to improve the sensitivity to pipeline materials and enhance the penetrability of the signal.

[0050] As a further solution of the present invention, the ultrasonic transducer is a piezoelectric transducer, and the piezoelectric transducer is made of PZT lead titanate material, which has high sensitivity and meets the working requirements under high-temperature environments.

[0051] As a further solution of the present invention, the signal processing module includes a time-domain analysis and a frequency-domain analysis unit. The time-domain analysis unit is used to extract the time features of the signal, and the frequency-domain analysis unit is used to extract the frequency features of the signal to further optimize the feature extraction of the signal.

[0052] As a further solution of the present invention, the deep learning model is a convolutional neural network CNN, and the CNN model includes at least three convolutional layers, pooling layers and fully connected layers to achieve in-depth learning of signal features and accurate prediction of tensile properties.

[0053] As a further solution of the present invention, the training data of the prediction model is derived from multivariate experimental data including different environmental temperatures, humidities, pipe materials and their manufacturing process parameters, and data normalization is performed to ensure data consistency.

[0054] As a further solution of the present invention, the deep learning algorithm is trained and optimized by the gradient descent method, and the cross-validation method is used to verify the generalization ability of the model to reduce the overfitting phenomenon.

[0055] As a further solution of the present invention, the tensile strength prediction result is combined with the actual use environmental conditions of the pipeline, and risk assessment is carried out by setting different thresholds. If the prediction result is lower than the safety threshold, maintenance suggestions are automatically generated and transmitted to relevant operators through the communication interface.

[0056] As a further solution of the present invention, the acquisition of ultrasonic reflection signals and transmission signals includes preprocessing the signals to remove background noise, and the noise removal methods include but are not limited to band-pass filters and wavelet transforms to ensure high-quality processing of the signals. [[ID=!

[0057] Embodiment 1: This embodiment provides a rapid detection method for improving the tensile properties of PE gas pipelines to achieve accurate and non-destructive detection of the tensile strength of pipelines and adapt to various environmental and material conditions.

[0058] Step 1: Installation of ultrasonic transducers and signal excitation.

[0059] First, at least one ultrasonic transducer is installed on the surface of the PE gas pipeline. The ultrasonic transducer adopts a piezoelectric transducer or a laser transducer, and the working frequency is set between 20 kHz and 300 kHz. This frequency range ensures that ultrasonic waves can effectively penetrate the pipeline material and interact with the stress waves inside the pipeline, thereby providing necessary signal features for subsequent detection.

[0060] In this step, the ultrasonic transducer excites ultrasonic guided waves to propagate along the axial direction of the pipeline and triggers the stress waves inside the pipeline, thereby exciting the tiny vibrations on the pipeline surface. This operation is used to initially obtain the basic data of the pipeline state.

[0061] Step 2: Ultrasonic signal acquisition and feature extraction.

[0062] Use at least one ultrasonic receiving sensor to collect the ultrasonic reflection signal and transmission signal after propagation through the pipeline. The propagation characteristics of the signal include parameters such as attenuation, frequency shift, propagation time, and reflection mode. These signal characteristics are crucial for subsequent analysis and reflect the material properties, thickness, and internal defects of the pipeline.

[0063] Through the time-domain and frequency-domain analysis units, the signal is finely processed. The time-domain analysis unit extracts the time characteristics of the signal, while the frequency-domain analysis unit extracts the frequency characteristics. The combination of the two forms comprehensive characteristic data of the pipeline state, providing accurate candidate characteristics for subsequent tensile strength prediction.

[0064] Step 3: Time-frequency analysis and signal processing of characteristic parameters.

[0065] The ultrasonic signal characteristic parameters (such as elastic modulus , wave velocity , attenuation factor , frequency characteristics ) extracted in Step 2 enter the signal processing module. In this step, wavelet transform or Fourier transform is used to perform time-frequency analysis on the signal. These methods can efficiently extract information such as the elastic modulus and wave velocity of the pipeline and form characteristic data that can be used for tensile strength prediction.

[0066] Wavelet transform can provide high-resolution time-frequency domain analysis, which helps to capture rapidly changing signal characteristics; Fourier transform performs spectral analysis on the signal, further enhancing the understanding of the pipeline state.

[0067] Step 4: Deep learning model training and prediction.

[0068] Based on the characteristic parameters extracted in Step 3, a deep learning model is used for tensile strength prediction. This model combines a convolutional neural network (CNN) and a long short-term memory network (LSTM) to process time-domain characteristics and frequency-domain characteristics respectively. The convolutional neural network (CNN) includes at least three convolutional layers, pooling layers, and fully connected layers, which are used to extract the spatial characteristics of the signal from the time domain and frequency domain. The convolutional neural network (CNN) is responsible for extracting the spatial characteristics of the signal, and the LSTM network is used to analyze the time series data of the signal to accurately model the dynamic elastic behavior and tensile strength of the pipeline.

[0069] This deep learning model is trained with a large amount of historical experimental data, including factors such as different materials, pipeline thicknesses, and environmental conditions (such as temperature and humidity), to ensure that the model can adapt to various pipeline specifications and environmental impacts.

[0070] Step 5: Real-time prediction and tensile strength calculation.

[0071] After the model training is completed, the trained CNN and LSTM models are used to predict the collected real-time signals and calculate the tensile strength of the pipeline. The prediction result is obtained through the formula:

[0072]

[0073] where, represents the predicted tensile strength, is the elastic modulus of the pipeline, is the wave velocity, is the attenuation factor, is the frequency feature, is the weight coefficient matrix obtained by training with historical experimental data. The weight coefficient reflects the relationship between different pipeline parameters and the tensile strength, and is obtained through training and optimization.

[0074] Step 6: Optimization of prediction results and dynamic adjustment.

[0075] By comparing with historical experimental data, the error correction mechanism is used to optimize the prediction results. The least squares method or other regression algorithms are used to dynamically adjust the prediction error and optimize the weight coefficient matrix to ensure the accuracy of the prediction results. The process of dynamic adjustment includes a feedback mechanism, that is, by comparing the error between the predicted value and the actual tensile strength value, the prediction ability of the model is continuously corrected.

[0076] Step 7: Generation of maintenance suggestions and risk assessment.

[0077] After the prediction results are obtained, if the predicted value of the tensile strength is lower than the set safety threshold, the system will automatically generate maintenance suggestions. These maintenance suggestions are transmitted to the monitoring platform or on-site operators through the communication interface. This can take timely measures to avoid possible pipeline fracture or air leakage risks and ensure the safe operation of the pipeline system.

[0078] Example 3: In this example, we further refined the rapid detection method for the tensile properties of PE gas pipelines based on ultrasonic guided waves and deep learning algorithms. For example, to improve the signal quality and reduce noise interference, we used a combination of a band-pass filter and wavelet transform to preprocess the ultrasonic reflection and transmission signals. Specifically, the band-pass filter first removes high-frequency and low-frequency noises, ensuring that the core frequency components of the signal are effectively retained. Then, wavelet transform is applied for multi-resolution analysis to further extract important features in the signal. Especially in the analysis of non-stationary signals, it can effectively identify the features of short-time transforms. This step ensures the high quality of the ultrasonic signal and reduces the influence of signal quality fluctuations in complex environments.

[0079] And to improve the accuracy and stability of the prediction model, the deep learning network in this example adopted a combination of a convolutional neural network (CNN) and a long short-term memory network (LSTM). The convolutional neural network (CNN) includes at least three convolutional layers, pooling layers, and fully connected layers, which are used to extract the spatial features of the signal from the time domain and frequency domain. The CNN part is responsible for extracting local features from the time domain and frequency domain, while the LSTM part plays a role in the modeling of time series data. Especially when dealing with the dynamic changes of the signal time series, it can accurately capture the tensile behavior of the pipeline. During the model training process, we normalized the data to ensure data consistency under different experimental environments and reduce the influence of factors such as temperature, humidity, and pipeline material. Through the cross-validation method, we verified the generalization ability of the model and effectively reduced the overfitting phenomenon. And during the tensile strength prediction process, by comparing with historical experimental data, the least squares method was used to correct the predicted values. Specifically, the least squares method calculates the error between the historical experimental data and the predicted values and dynamically adjusts the weight coefficients in the prediction model. This process optimizes the parameters of the neural network through the backpropagation algorithm to ensure that the error between the prediction result and the actual tensile strength remains within the set tolerance range. Through this dynamic optimization mechanism, it can effectively cope with complex and changing environmental conditions and further improve the adaptability of the model.

[0080] In the application scenario of the construction site, multiple ultrasonic transducers can be, for example, snap-connected and fixedly installed on the surface of the PE pipeline to excite ultrasonic guided waves. After the ultrasonic signal propagates through the pipeline, it is collected by multiple ultrasonic receiving sensors. The signal processing module performs real-time processing and analysis on the collected signals to extract parameters such as elastic modulus, wave velocity, attenuation factor, and frequency characteristics. The deep learning model analyzes these features through CNN and LSTM models, predicts the tensile strength of the pipeline in real time, and transmits the prediction results to the monitoring platform. Once the prediction result is lower than the set safety threshold, the system automatically generates maintenance suggestions and promptly notifies the on-site staff for subsequent processing, thus avoiding the risk of pipeline fracture or air leakage due to insufficient tensile strength. When training the deep learning model, experimental data from different environmental conditions and pipeline types are used, including various factors such as temperature, humidity, strain rate, and pipeline material. These data are strictly screened and standardized to ensure data consistency and comparability. With the support of large-scale experimental data, the model can provide reliable prediction results under different pipeline specifications and environmental conditions, and has strong generalization ability to adapt to the changing environment of the construction site.

[0081] Example 4: In this embodiment, we further optimize the signal processing flow, model training method, and weight coefficient adjustment mechanism. Specifically, at least one ultrasonic transducer is installed on the surface of the PE gas pipeline. The transducer is a piezoelectric transducer or a laser transducer, and the excitation frequency range is set to 20 kHz to 300 kHz. This frequency range ensures that ultrasonic waves can effectively penetrate the pipeline and excite stress waves inside the pipeline. The transducer generates minute vibrations on the pipeline surface through the excitation signal, thereby obtaining information on the stress waves inside the pipeline and providing necessary data support for subsequent signal collection and analysis.

[0082] After the ultrasonic signal propagates through the pipeline, at least one ultrasonic receiving sensor will receive the reflected signal and the transmitted signal. The propagation characteristics of these signals include attenuation, frequency shift, propagation time, etc., which are closely related to factors such as the material properties, thickness, and internal defects of the pipeline. Through time-domain and frequency-domain analysis, these signal characteristics are extracted to form the state data of the pipeline. Specifically, the time-domain analysis unit extracts the time characteristics of the signal, and the frequency-domain analysis unit is responsible for extracting the frequency characteristics of the signal. For the extracted ultrasonic signal characteristics, wavelet transform or Fourier transform is used to perform time-frequency analysis on the signal. Wavelet transform can provide high-resolution time-frequency domain analysis, especially suitable for capturing rapidly changing signal characteristics; while Fourier transform helps to perform spectral analysis on the signal, further optimizing the understanding of the pipeline state. The goal of this process is to extract key pipeline characteristic parameters from the original signal, such as elastic modulus, wave velocity, attenuation factor, and frequency characteristics, etc. After extracting the pipeline characteristic parameters, deep learning algorithms (Convolutional Neural Network CNN and Long Short-Term Memory Network LSTM) are used to further analyze these characteristics. CNN is responsible for processing local characteristics in the time domain and frequency domain, and LSTM is specifically used to analyze the time series characteristics of the signal, capturing the dynamic elastic behavior of the pipeline and changes in tensile strength. These models are trained with historical experimental data, including factors such as different materials, pipeline thickness, environmental conditions (such as temperature, humidity), etc., to ensure that the models can operate stably under various pipeline specifications and environmental changes.

[0083] Then, the trained CNN and LSTM models are used to predict the tensile strength of the ultrasonic signal collected in real time. This prediction is based on the characteristic parameters output by the model to calculate the tensile strength of the pipeline. To ensure the prediction accuracy, when the predicted value deviates from the true value, the model will automatically perform error correction. At this time, the error correction mechanism compares the historical experimental data with the current predicted value, and adjusts the weight coefficients in the model through a regression algorithm (such as the least squares method) to reduce the prediction error. This process dynamically optimizes the weight coefficients to ensure the accuracy and reliability of the tensile strength prediction. Once the prediction result is lower than the set safety threshold, the system will automatically generate maintenance suggestions. These suggestions will be transmitted to the on-site operators through the communication interface to guide them in pipeline inspection and maintenance. Through the risk assessment system, combined with the current environmental conditions and the predicted tensile strength value, the system can evaluate whether there is a potential risk of pipeline fracture or air leakage. If the risk is too high, the system will provide relevant maintenance measures to ensure the safe operation of the pipeline system.

[0084] In the present invention, unless otherwise clearly defined and limited, terms such as "installation", "setting", "connection", "fixation", "swivel connection" and the like shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two components or the interaction relationship between two components. Unless otherwise clearly defined, for those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0085] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention.

Claims

1. A rapid detection method for the tensile properties of PE gas pipelines, characterized in that: The method comprises the following steps: Step 1, install at least one ultrasonic transducer on the surface of the PE gas pipeline, which is used to excite ultrasonic guided waves to propagate along the axial direction of the pipeline and excite stress waves inside the pipeline. Wherein, the ultrasonic transducer is a piezoelectric transducer or a laser transducer, and the excitation frequency of the ultrasonic guided wave is between 10 kHz and 500 kHz, and the ultrasonic guided wave signal can propagate along the axial direction of the pipeline and interact with the stress wave inside the pipeline; Step 2, use at least one ultrasonic receiving sensor to collect the ultrasonic reflection signal and transmission signal after propagating through the pipeline, and record the propagation characteristics of the ultrasonic signal in real time. The propagation characteristics of the ultrasonic signal include signal attenuation, frequency shift, propagation time, and reflection mode parameters; Step 3, perform feature extraction on the collected ultrasonic signal through a signal processing module, perform time-frequency analysis on the signal using wavelet transform or Fourier transform, and extract the elastic modulus, wave velocity, attenuation factor, and frequency characteristics of the pipeline as candidate characteristic parameters for the tensile strength of the pipeline; Step 4, based on the extracted candidate characteristic parameters, use a deep learning algorithm to analyze the ultrasonic signal through a convolutional neural network CNN and a long short-term memory network LSTM, and construct a pipeline tensile strength prediction model. Wherein, the prediction model is obtained by training with historical experimental data, and the historical experimental data includes standard tensile strength data of PE pipelines under different materials, thicknesses, strain rates, and environmental conditions; Step 5, perform real-time prediction on the ultrasonic signal through the prediction model to calculate the tensile strength of the pipeline; Step 6, if the predicted tensile strength result is lower than the set threshold, automatically generate a maintenance suggestion and transmit it to the monitoring platform or on-site operators through a communication interface; Wherein, in Step 5, performing real-time prediction on the ultrasonic signal through the prediction model to calculate the tensile strength of the pipeline specifically includes the following sub-steps: s1, Input data: The ultrasonic signal characteristic parameters extracted in step 3 are used as input data and fed into the tensile strength prediction model. Among them, the ultrasonic signal characteristic parameters include elastic modulus , wave velocity , attenuation factor and frequency characteristics ; s2, Feature extraction and processing: Deeply extract time-domain and frequency-domain features through a convolutional neural network CNN, and combine a long short-term memory network LSTM to model the time-series data of the signal, and further learn the elastic behavior of the pipeline and the dynamic change of its tensile strength; and update the weights of the neural network through an optimized backpropagation algorithm; s3. Tensile strength prediction model calculation: Using the trained CNN and LSTM models, analyze and calculate the input signal features to obtain the predicted value of the pipeline's tensile strength. The predicted value is calculated by the following formula: Wherein: is a weight coefficient matrix obtained by training with historical data, and is used for weight optimization and correction of prediction results; S4, Weight coefficient adjustment: By comparing the error between historical experimental data and predicted values, the least squares method or other appropriate regression algorithms are used to dynamically adjust the weight coefficients in the prediction model ; s5, Tensile strength output: Output the predicted value of the tensile strength of the adjusted model as the current tensile property index of the pipeline and make subsequent maintenance decisions; wherein, the frequency range of the ultrasonic signal is 20 kHz to 300 kHz.

2. The rapid detection method for the tensile property of a PE gas pipeline according to claim 1, characterized in that The ultrasonic transducer is a piezoelectric transducer, and the piezoelectric transducer is made of PZT lead titanate material.

3. The rapid detection method for the tensile property of a PE gas pipeline according to claim 1, characterized in that, The signal processing module includes a time-domain analysis unit and a frequency-domain analysis unit. The time-domain analysis unit is used to extract the time features of the signal, and the frequency-domain analysis unit is used to extract the frequency features of the signal.

4. A rapid detection method for the tensile properties of a PE gas pipeline according to claim 1, characterized in that, The deep learning model is a convolutional neural network CNN, and the CNN model includes at least three convolutional layers, pooling layers, and fully connected layers.

5. The rapid detection method for the tensile property of a PE gas pipeline according to claim 1, characterized in that, The training data of the prediction model comes from multivariate experimental data including different environmental temperatures, humidities, pipeline materials, and their manufacturing process parameters, and data normalization processing is used to ensure data consistency.

6. A rapid detection method for the tensile performance of a PE gas pipeline according to claim 1, characterized in that, The deep learning algorithm is trained and optimized by the gradient descent method, and the cross-validation method is used to verify the generalization ability of the model.

7. A rapid detection method for the tensile performance of a PE gas pipeline according to claim 1, characterized in that, The tensile strength prediction results are combined with the actual usage environmental conditions of the pipeline, and risk assessment is carried out by setting different thresholds. If the prediction result is lower than the safety threshold, maintenance suggestions are automatically generated and transmitted to relevant operators through the communication interface.

8. A rapid detection method for the tensile performance of a PE gas pipeline according to claim 1, characterized in that, The acquisition of ultrasonic reflection signals and transmission signals includes preprocessing the signals to remove background noise, and the noise removal methods include band-pass filters and wavelet transforms.

Images