A method and device for measuring the pressure of a natural gas steel pipeline using ultrasonic waves

Abstract

The present invention discloses a method and device for measuring the pressure of a natural gas steel pipeline using ultrasound, comprising the following steps: S1: measuring the echo amplitude and pressure of the pipeline using an ultrasonic measuring device; S2: screening the measured echo amplitude and pressure values to obtain echo amplitude and pressure values that are sensitive to changes; S3: establishing an echo amplitude-pressure model based on the screened echo amplitude and pressure values; and S4: inputting the actual echo amplitude into the established model to obtain the actual pressure of the pipeline. The present invention uses ultrasound to measure the echo amplitude and pressure values, establishes an echo amplitude-pressure model using a BP neural network, performs error correction on the established model, and derives a new echo amplitude-pressure model. The actual pressure of the pipeline can be determined by measuring the actual echo amplitude of the pipeline using the model, thereby enabling pipeline pressure to be detected anytime and anywhere without disrupting the stress conditions of the pipeline.

Description

Technical Field

[0001] The present invention relates to the field of ultrasonic measurement, and more particularly to a method and device for measuring the pressure of a natural gas steel pipeline using ultrasonic waves. Background Art

[0002] In recent years, with the rapid development of natural gas pipeline construction and the increasing length of pipelines, unpredictable conditions have become increasingly common during operation. In cities, natural gas plays a vital role as a vital source of energy for the daily lives of residents and a key raw material or energy source for industrial production. However, damage to a natural gas pipeline can lead to a direct outage of natural gas supply, resulting in significant economic losses and inconvenience for residents. Therefore, timely locating and repairing damaged pipelines is a top priority. During natural gas pipeline maintenance, the internal status (gas pressure) must be determined to ensure the safety of hot work operations and to prevent secondary accidents (explosions caused by hot work).

[0003] However, the following problems exist in the actual work of the gas transmission management office: (1) During the construction process, there are often parallel pipelines of the same specifications on site. One section needs to be shut down for maintenance, while the other section is in use. Since it is impossible to know which pipeline needs to be shut down for maintenance, it is impossible to confirm the operating pipeline. (2) During the natural gas pipeline cleaning operation, when a ball is stuck, it is necessary to use the nitrogen injection method to determine the location of the stuck ball. The current method used is to drill a hole in the natural gas pipeline to determine the pipeline condition. However, drilling a hole in the natural gas pipeline destroys the structure of the natural gas pipeline, and ultimately the hole needs to be replaced or welded, resulting in greater workload and economic losses.

[0004] Therefore, how to research and design a method and device for measuring the pressure of natural gas steel pipelines using ultrasound is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and device for measuring the pressure of a natural gas steel pipeline using ultrasonic waves, so as to detect the pipeline pressure anytime and anywhere without destroying the stress condition of the pipeline.

[0006] The above technical objectives of the present invention are achieved through the following technical solutions: A method for measuring the pressure of a natural gas steel pipeline using ultrasound, comprising the following steps:

[0007] S1: Use ultrasonic measuring device to measure the echo amplitude and pressure value of the pipeline;

[0008] S2: screening the measured echo amplitude and pressure value to obtain the echo amplitude and pressure value that are sensitive to changes;

[0009] S3: establishing an echo amplitude-pressure model using the screened echo amplitude and pressure values;

[0010] S4: Input the actual echo amplitude according to the established model to obtain the actual pressure value of the pipeline.

[0011] In the prior art, pressure testing of natural gas pipelines requires drilling holes in the pipelines, which damages the structure of the pipelines. The present invention proposes a method of measuring the echo amplitude and pressure value of the pipelines using a measuring device, screening out the echo amplitude and pressure values that are sensitive to changes, and establishing an echo amplitude-pressure model based on the screened data. When measuring the pressure value of a certain pipeline, only the echo amplitude of the pipeline needs to be measured and applied to the model to obtain the actual pressure value of the pipeline, thus avoiding damage to the stress structure of the pipeline.

[0012] Furthermore, the specific steps for measuring the echo amplitude and pressure value of the pipeline are as follows:

[0013] S21: Select a natural gas pipeline with adjustable pressure and randomly select three to five measurement locations on the pipeline;

[0014] S22: Use a grinding wheel to grind off the protective paint on the pipe, and use an ultrasonic thickness gauge to measure the wall thickness at the measurement location;

[0015] S23: Place the ultrasonic probe in the auxiliary fixture, then connect the circuit, turn on the power, and place the ultrasonic probe on the pipeline to observe the waveform through the oscilloscope;

[0016] S24: Fix the ultrasonic probe to the pipe using an auxiliary clamp;

[0017] S25: Control the pipeline pressure by increasing or decreasing the pressure at equal intervals, and display the real-time pressure on the pressure gauge;

[0018] S26: measuring the amplitude of the echo signal under different pressures through an oscilloscope, and collecting and storing the echo signal through the oscilloscope;

[0019] S27: The amplitude data of the echo collected by the oscilloscope is displayed by the processor.

[0020] Furthermore, the specific steps of the process of establishing the echo amplitude-pressure model are as follows:

[0021] Select one of the third, fourth and fifth echo amplitudes for modeling, and the remaining echo amplitudes can be modeled according to the following method;

[0022] The echo amplitude and pressure value of different measurement areas are trained by BP neural network, where the input is the echo amplitude of different measurement areas and the output is the pressure value;

[0023] After the network is trained, the uniform interpolation method is used to generate more than 10,000 sets of echo amplitudes between the maximum and minimum amplitudes, and the echo amplitudes are sent to the trained BP neural network, and the network automatically outputs the pressure value.

[0024] The echo amplitude-pressure model was established by least squares fitting, and the relationship between echo amplitude and pressure value was obtained as follows: P = 1.1068a 2 -14.818a+48.409, where a is the average of the echo amplitudes of multiple regions, and P is the pressure value.

[0025] Furthermore, different thicknesses of pipes are set to calibrate the ultrasonic echo amplitude. When using ultrasonic pressure measurement, the thickness of the pipe is first measured, and then when performing pressure detection, the corresponding amplitude is subtracted. The difference is the amplitude related to the pipe pressure.

[0026] Furthermore, the echo amplitude-pressure model is modified according to the influence of the pipe wall thickness on the measurement. The modified model is shown as follows: P = 1.1068 (cT) 2 +2.29|cT|, where P is the pressure value, c is the amplitude corresponding to the pressure, and T is the amplitude corresponding to the pipe wall thickness.

[0027] Furthermore, the establishment of the BP neural network includes the following steps:

[0028] Step 1: Establish the network input and define the third echo amplitude of N areas as the network input. It is expressed as the following formula: input = [area1_amplitud_3,area2_amplitude_3,…,areaN_amplitude_3], where input represents input, area1 in area1_amplitude_3 represents area 1, amplitude_3 represents the third echo amplitude, and so on for the remaining echo amplitudes.

[0029] Step 2: Construct a BP neural network and forward propagate the network. The BP neural network consists of three layers: input layer, hidden layer, and output layer. The weights, thresholds, and activation functions are used to transfer data between layers. The process is expressed as follows: Among them, output is the output from layer k-1 to layer k, f is the activation function, that is, tan h, ω kj represents the jth weight of the kth layer, a j is the input, b kis the threshold of the kth layer;

[0030] Step 3: Calculate the performance index and sensitivity. If the performance index is less than the set root mean square error, the network training ends, otherwise proceed to the next step.

[0031] Step 4: Backpropagate through network sensitivity;

[0032] Step 5: Update the network weights and thresholds using the approximate steepest descent method;

[0033] Step 6: Go back to step 2 and start training the neural network again;

[0034] The above steps are iterated repeatedly until the error meets the accuracy or the set number of iterations is reached, and the network training ends.

[0035] Furthermore, a device for measuring the pressure of a natural gas steel pipeline using ultrasonic waves comprises:

[0036] A power supply module, an excitation circuit module, a receiving circuit module, an oscilloscope, an ultrasonic probe, an auxiliary fixture, and an FPGA system module, wherein the auxiliary fixture is used to fix the ultrasonic probe on the pipeline;

[0037] The power supply module is electrically connected to the excitation circuit module and the FPGA system module, the FPGA system module is communicatively connected to the excitation circuit module and the receiving circuit module, the receiving circuit module is communicatively connected to the oscilloscope, and the excitation circuit module is communicatively connected to the ultrasound probe.

[0038] During measurement, the ultrasonic probe is first fixed to the pipeline using an auxiliary clamp. The power module provides power to the excitation circuit module and the FPGA system module. The FPGA system module sends a control timing to ensure that the excitation circuit module and the receiving circuit module continue to operate stably. The excitation circuit module sends an excitation voltage to drive the ultrasonic probe to emit ultrasonic waves. The receiving circuit module amplifies and filters the ultrasonic waves received by the ultrasonic probe and transmits them to the oscilloscope to complete the ultrasonic measurement.

[0039] Furthermore, the FPGA system module is used to control the timing so that the timing voltages of the excitation circuit module and the receiving circuit module are output continuously and stably.

[0040] Furthermore, the receiving circuit module includes an amplifying circuit module and a bandpass filtering circuit module. The amplifying circuit module is used to amplify the echo amplitude, and the bandpass filtering circuit module is used to remove echo noise.

[0041] Furthermore, the ultrasonic probe is used to emit ultrasonic waves, and the oscilloscope is used to collect amplitude data of echoes.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention proposes the development of ultrasonic testing equipment for non-destructive pressure testing. This device can detect pipeline pressure anytime and anywhere without destroying the pipeline stress conditions;

[0044] 2. The present invention proposes to construct a pressure measurement model to obtain a relationship between ultrasonic amplitude and pipeline pressure. When the pressure value of a certain pipeline needs to be detected, it is only necessary to measure the amplitude corresponding to the wall thickness and the amplitude corresponding to the pressure value through an ultrasonic device, and then substitute them into the relationship to obtain the pressure value of the pipeline. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0046] Figure 1 This is a modeling flow chart of the echo amplitude-pressure model of the present invention;

[0047] Figure 2 It is a structural principle diagram of the device of the present invention;

[0048] Figure 3 This is a structural diagram of the auxiliary fixture of the present invention;

[0049] Figure 4 A schematic diagram of network training of the present invention;

[0050] Figure 5 This is a fitting relationship diagram of the echo amplitude and pressure value of the present invention. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0052] It should be noted that when a component is referred to as being “fixed to” or “disposed on” another component, it can be directly on the other component or indirectly on the other component. When a component is referred to as being “connected to” another component, it can be directly or indirectly connected to the other component.

[0053] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention.

[0054] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0055] Example 1: A method for measuring the pressure of a natural gas steel pipeline using ultrasound, such as Figure 1 As shown,

[0056] The method comprises the following steps: S1: measuring the echo amplitude and pressure value of the pipeline by using an ultrasonic measuring device; S2: screening the measured echo amplitude and pressure value to obtain echo amplitude and pressure value that are sensitive to changes; S3: establishing an echo amplitude-pressure model based on the screened echo amplitude and pressure value; S4: inputting the actual echo amplitude according to the established model to obtain the actual pressure value of the pipeline.

[0057] The specific steps for measuring the echo amplitude and pressure value of the pipeline are as follows:

[0058] S21: Select a natural gas pipeline with adjustable pressure and randomly select three to five measurement locations on the pipeline;

[0059] S22: Use a grinding wheel to grind off the protective paint on the pipe, and use an ultrasonic thickness gauge to measure the wall thickness at the measurement location;

[0060] S23: Place the ultrasonic probe in the auxiliary fixture, then connect the circuit, turn on the power, and place the ultrasonic probe on the pipeline to observe the waveform through the oscilloscope;

[0061] S24: Fix the ultrasonic probe to the pipe using an auxiliary clamp;

[0062] S25: Control the pipeline pressure by increasing or decreasing the pressure at equal intervals, and display the real-time pressure on the pressure gauge;

[0063] S26: measuring the amplitude of the echo signal under different pressures through an oscilloscope, and collecting and storing the echo signal through the oscilloscope;

[0064] S27: The amplitude data of the echo collected by the oscilloscope is displayed by the processor.

[0065] The specific steps of establishing the echo amplitude-pressure model are as follows:

[0066] Select one of the third, fourth and fifth echo amplitudes for modeling, and the remaining echo amplitudes can be modeled according to the following method;

[0067] The echo amplitude and pressure value of different measurement areas are trained by BP neural network, where the input is the echo amplitude of different measurement areas and the output is the pressure value;

[0068] After the network is trained, the uniform interpolation method is used to generate more than 10,000 sets of echo amplitudes between the maximum and minimum amplitudes, and the echo amplitudes are sent to the trained BP neural network, and the network automatically outputs the pressure value.

[0069] The echo amplitude-pressure model was established by least squares fitting, and the relationship between echo amplitude and pressure value was obtained as follows: P = 1.1068a 2 -14.818a+48.409, where a is the average of the echo amplitudes of multiple regions, and P is the pressure value.

[0070] The measured echo amplitudes include the first, second, third, fourth and fifth echo amplitudes. Since the waveform errors of the first echo amplitude and the second echo amplitude are large, any one of the third, fourth and fifth echo amplitudes is selected for modeling.

[0071] The ultrasonic echo amplitude is calibrated by setting pipes of different thicknesses. When using ultrasonic pressure measurement, the thickness of the pipe is first measured, and then when performing pressure detection, the corresponding amplitude is subtracted. The difference is the amplitude related to the natural gas pressure.

[0072] Since the effect of gas pressure in the pipeline on pipeline deformation is negligible, the influence of natural gas pressure on ultrasonic echo amplitude and the influence of wall thickness on echo amplitude are independent of each other. Based on this, different pipe thicknesses are set to calibrate the ultrasonic echo amplitude. When using ultrasonic pressure measurement, the pipeline thickness is first measured, and then when performing pressure testing, the corresponding amplitude is subtracted. The difference is the amplitude related to natural gas pressure.

[0073] The echo amplitude-pressure model is modified according to the influence of pipe wall thickness on the measurement. The modified model is shown as follows: P = 1.1068 (cT) 2 +2.29|cT|, where P is the pressure value, c is the amplitude corresponding to the pressure, and T is the amplitude corresponding to the pipe wall thickness.

[0074] The establishment of BP neural network includes the following steps:

[0075] Step 1: Establish the network input and define the third echo amplitude of N areas as the network input. It is expressed as the following formula: input = [area1_amplitud_3,area2_amplitude_3,…,areaN_amplitude_3], where input represents input, area1 in area1_amplitude_3 represents area 1, amplitude_3 represents the third echo amplitude, and so on for the remaining echo amplitudes.

[0076] Step 2: Construct a BP neural network and forward propagate the network. The BP neural network consists of three layers: input layer, hidden layer, and output layer. The weights, thresholds, and activation functions are used to transfer data between layers. The process is expressed as follows: Among them, output is the output from layer k-1 to layer k, f is the activation function, that is, tan h, ω kj represents the jth weight of the kth layer, a j is the input, b k is the threshold of the kth layer;

[0077] Step 3: Calculate the performance index and sensitivity. If the performance index is less than the set root mean square error, the network training ends, otherwise proceed to the next step.

[0078] Step 4: Backpropagate through network sensitivity;

[0079] Step 5: Use the approximate steepest descent method to update the network weights and thresholds.

[0080] Step 6: Go back to step 2 and start training the neural network again;

[0081] The above steps are iterated repeatedly until the error meets the accuracy or the set number of iterations is reached, and the network training ends.

[0082] Example 2: A device for measuring the pressure of a natural gas steel pipeline using ultrasonic waves, such as Figure 2 As shown,

[0083] It includes: a power supply module, an excitation circuit module, a receiving circuit module, an oscilloscope, an ultrasonic probe, an auxiliary fixture, and an FPGA system module. The auxiliary fixture is used to fix the ultrasonic probe on the pipeline.

[0084] The power supply module is electrically connected to the excitation circuit module and the FPGA system module, the FPGA module is communicatively connected to the excitation circuit module and the receiving circuit module, the receiving circuit module is communicatively connected to the oscilloscope, and the excitation circuit module is communicatively connected to the ultrasound probe.

[0085] During measurement, the ultrasonic probe is first fixed to the pipeline using an auxiliary clamp. The power module provides power to the excitation circuit module and the FPGA system module. The FPGA system module sends a control timing to ensure that the excitation circuit module and the receiving circuit module continue to operate stably. The excitation circuit module sends an excitation voltage to drive the ultrasonic probe to emit ultrasonic waves. The receiving circuit module amplifies and filters the ultrasonic waves received by the ultrasonic probe and transmits them to the oscilloscope to complete the ultrasonic measurement.

[0086] The FPGA system module is used to control the timing so that the timing voltage of the excitation circuit module and the receiving circuit module is output continuously and stably.

[0087] The receiving circuit module includes an amplifying circuit module and a bandpass filtering circuit module. The amplifying circuit module is used to amplify the echo amplitude, and the bandpass filtering circuit module is used to remove the noise of the echo.

[0088] The ultrasonic probe is used to emit ultrasonic waves, and the oscilloscope is used to collect the amplitude data of the echo.

[0089] In order to facilitate the description of the specific effects achieved by the present invention, Figure 3 As shown, a steel pipe identical to the natural gas pipeline was first selected and cut into sections with round bottoms welded to each end to form a sealed container. A hole was then drilled in the pipe and a valve and pressure gauge were installed. The valve was used to inject and release gas, and the pressure gauge was used to display pressure. The experiment was conducted in a constant and adjustable temperature environment. During the experiment, the ultrasonic probe was placed on probe hole 1 of the auxiliary fixture, and either interface 3a or 3b was opened. The separated fixture was then placed on the pipe wall and 3a or 3b was closed. Pads were placed under 2a, 2b, 2c, and 2d, aligning them with the circular holes. Four identical pads were tightened with bolts through 2a, 2b, 2c, and 2d. Finally, a bolt was screwed into hole 4 to secure the ultrasonic probe to the natural gas pipeline.

[0090] Then, a total of 100 sets of data of the third echo amplitude at different pressure values in three areas were randomly collected, including data of pressure increase and pressure decrease, with a pressure range of 0-5MPa. Then, the amplitudes of the three areas and the corresponding pressure values were sent to the BP neural network for training. The training accuracy of the BP neural network was set to 0.001, the number of training times was 5000, and 75 sets of data were selected as training sets to train the neural network with an R value of 0.97447. The trained neural network was saved, and the remaining 25 sets of data were used as test sets to test the neural network. Figure 4 As shown in the figure, the accuracy is 96%, and the experiment shows that the training effect is very good.

[0091] Then, 10,000 sets of input data, i.e., amplitudes of different regions, are inserted between the maximum and minimum amplitudes using uniform interpolation, and the data are fed into the trained BP neural network to generate 10,000 sets of output data, i.e., pressure values. This is done to make the data large enough to meet the requirements of mathematical statistics, and to plot the amplitude and pressure values in a graph, as shown in Figure 1. Figure 5 shown.

[0092] Finally, the amplitude and pressure values are fitted by the least square method to obtain the echo amplitude and pressure model as follows: P = 1.1068a 2 -14.818a+48.409, where a is the average of the echo amplitudes of multiple regions, and P is the pressure value.

[0093] To further illustrate the practical detection effect of the present invention, a natural gas pressure test was conducted at a gas transmission station. First, a pipeline coated with protective paint was polished. After the protective paint was removed, a probe was installed at the location. Then, the amplitude was collected using an oscilloscope. Taking into account the influence of pipeline wall thickness, the above relationship was modified to obtain the following formula: P = 1.1068(c-T² + 2.29|cT|), where P is the pressure value, c is the amplitude corresponding to the pressure, and T is the amplitude corresponding to the pipeline wall thickness.

[0094] The obtained amplitude is substituted into the above formula to calculate the pressure value. Experiments show that the average error between the pressure value calculated by the model and the actual pressure is 0.03MPa, while the error requirement in actual measurement can be met within 0.5MPa.

[0095] In summary, the above demonstrates the effectiveness of the method proposed and the model established in this invention.

[0096] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for measuring the pressure of a natural gas steel pipeline using ultrasound, characterized in that: The following steps are involved: S1: Use ultrasonic measuring device to measure the echo amplitude and pressure value of the pipeline; S2: screening the measured echo amplitude and pressure value to obtain the echo amplitude and pressure value that are sensitive to changes; S3: Establish an echo amplitude-pressure model with the screened echo amplitude and pressure value; wherein, the specific steps of the echo amplitude-pressure model establishment process are as follows: select one of the third, fourth and fifth echo amplitudes for modeling, and the remaining echo amplitudes can be modeled according to the following method; BP The neural network is trained on the echo amplitude and pressure value of different measurement areas, where the input is the echo amplitude of different measurement areas and the output is the pressure value. After the network is trained, the uniform interpolation method is used to generate more than 10,000 groups of echo amplitudes between the maximum and minimum amplitudes, and the echo amplitudes are sent to the trained network. BP In the neural network, the pressure value is automatically output by the network; the echo amplitude-pressure model is established based on the least squares fitting method, and the relationship between the echo amplitude and the pressure value is obtained as follows: ,in, a is the average value of the echo amplitudes in multiple regions, P is the pressure value; S4: Input the actual echo amplitude according to the established model to obtain the actual pressure value of the pipeline.

2. The method for measuring the pressure of a natural gas steel pipeline using ultrasound according to claim 1, characterized in that: The specific steps for measuring the echo amplitude and pressure value of the pipeline are as follows: S21: Select a natural gas pipeline with adjustable pressure and randomly select three to five measurement locations on the pipeline; S22: Use a grinding wheel to grind off the protective paint on the pipe, and use an ultrasonic thickness gauge to measure the wall thickness at the measurement location; S23: Place the ultrasonic probe in the auxiliary fixture, then connect the circuit, turn on the power, and place the ultrasonic probe on the pipeline to observe the waveform through the oscilloscope; S24: Fix the ultrasonic probe to the pipe using an auxiliary clamp; S25: Control the pipeline pressure by increasing or decreasing the pressure at equal intervals, and display the real-time pressure on the pressure gauge; S26: measuring the amplitude of the echo signal under different pressures through an oscilloscope, and collecting and storing the echo signal through the oscilloscope; S27: The echo amplitude data collected by the oscilloscope is displayed by the processor.

3. The method for measuring the pressure of a natural gas steel pipeline using ultrasound according to claim 1, characterized in that: The ultrasonic echo amplitude is calibrated by setting pipes of different thicknesses. When using ultrasonic pressure measurement, the thickness of the pipe is first measured, and then when performing pressure detection, the corresponding amplitude is subtracted. The difference is the amplitude related to the pipe pressure.

4. The method for measuring the pressure of a natural gas steel pipeline using ultrasound according to claim 3, characterized in that: The echo amplitude-pressure model is modified according to the influence of pipe wall thickness on the measurement. The modified model is shown in the following formula ： ,in, P is the pressure value, c is the amplitude corresponding to the pressure ，T is the amplitude corresponding to the pipe wall thickness.

5. The method for measuring the pressure of a natural gas steel pipeline using ultrasound according to claim 1, characterized in that: described BP The creation of a neural network includes the following steps: Step 1: Establish network input and define N The third echo amplitude of each region is used as the network input and is expressed as follows: ,in, input Indicates input, area 1_ amplitude _3 in area 1 represents area 1, amplitude _3 represents the third echo amplitude, and the remaining echo amplitudes are similar; Step 2: Build BP Neural Network, Network Forward Propagation, BP A neural network consists of three layers: the input layer, the hidden layer, and the output layer. The weights, thresholds, and activation functions act together to transfer data. The process is expressed as follows: ;in, output yes k -1 floor to k The output of the layer, f is the activation function, that is, tan h, Indicates the k Layer j weights, For input, For the k The threshold of the layer; Step 3: Calculate the performance index and sensitivity of the network. If the performance index is less than the set root mean square error, the network training ends, otherwise proceed to the next step. Step 4: Backpropagate through network sensitivity; Step 5: Use the steepest descent method to update the network weights and thresholds; Step 6: Go back to step 2 and start training the neural network again; The above steps are iterated repeatedly until the error meets the accuracy or the set number of iterations is reached, and the network training ends.

6. A device for measuring the pressure of a natural gas steel pipeline using ultrasound, used to perform the method for measuring the pressure of a natural gas steel pipeline using ultrasound as claimed in any one of claims 1 to 5, characterized in that: The device includes: A power supply module, an excitation circuit module, a receiving circuit module, an oscilloscope, an ultrasonic probe, an auxiliary fixture, and an FPGA system module, wherein the auxiliary fixture is used to fix the ultrasonic probe on the pipeline; The power supply module is electrically connected to the excitation circuit module and the FPGA system module, the FPGA system module is communicatively connected to the excitation circuit module and the receiving circuit module, the receiving circuit module is communicatively connected to the oscilloscope, and the excitation circuit module is communicatively connected to the ultrasound probe.

7. The device for measuring the pressure of a natural gas steel pipeline using ultrasonic waves according to claim 6, characterized in that: The FPGA system module is used to control the timing so that the timing voltages of the excitation circuit module and the receiving circuit module are output continuously and stably.

8. The device for measuring the pressure of a natural gas steel pipeline using ultrasonic waves according to claim 6, characterized in that: The receiving circuit module includes an amplifying circuit module and a bandpass filtering circuit module. The amplifying circuit module is used to amplify the echo amplitude, and the bandpass filtering circuit module is used to remove echo noise.

9. The device for measuring the pressure of a natural gas steel pipeline using ultrasonic waves according to claim 6, characterized in that: The ultrasonic probe is used to emit ultrasonic waves, and the oscilloscope is used to collect amplitude data of echoes.

Images