Numerical simulation method and system for internal flow characteristics of regulating valve

Abstract

The invention provides a numerical simulation method and system for internal flow characteristics of a regulating valve, and relates to the technical field of regulating valves, and the method comprises the steps: arranging a plurality of flow sensors and pressure sensors in the regulating valve; controlling an executing mechanism to adjust a valve based on a positioner, and obtaining a flow characteristic curve; according to the method, a deep learning model is established, the deep learning model is trained, and the flow characteristics of the regulating valve are simulated by using the deep learning model, so that the problems that in the process of analyzing the flow characteristics of the regulating valve in the prior art, flow data of the regulating valve cannot be accurately and comprehensively acquired, and the flow characteristics of the regulating valve cannot be accurately analyzed are solved. The flow characteristics are obtained only through the relative flow, a correction basis is lacked when the flow characteristics deviate, meanwhile, an analysis method used after the flow data of the regulating valve are obtained in the prior art is not intelligent enough, and the flow characteristics obtained after analysis are kept unchanged all the time. And the device cannot be matched with the actual condition of the regulating valve.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of regulating valves, in particular to a regulating valve internal flow characteristic numerical simulation method and system. BACKGROUND

[0002] The regulating valve refers to a valve used for regulating process parameters such as medium flow, pressure, temperature, and liquid level in the field of industrial automation process control, and automatically adjusting the opening of the valve according to the control signal in the automation system, so as to realize the regulation of medium flow, pressure, temperature, and liquid level. The flow characteristic of the regulating valve refers to the relationship between the relative flow of the medium flowing through the regulating valve and the opening of the regulating valve under the condition that the pressure difference between the two ends of the regulating valve is kept constant.

[0003] The existing improvement for the flow characteristic of the regulating valve is usually to simulate the numerical value of the flow valve under different working conditions, and to calculate the flow valve based on the simulated parameters. For example, in the Chinese patent with the publication number CN113420514A, a multi-stage pressure reducing regulating valve internal flow characteristic numerical simulation method is disclosed. According to the flow characteristics of the multi-stage pressure reducing regulating valve, an effective numerical calculation method is established. The calculation results can reflect the change law of the internal flow of the valve, and provide a theoretical basis and reference for the reasonable design of the pressure reducing valve. In the above method and the existing technology, in the process of analyzing the flow characteristic of the regulating valve, the flow data of the regulating valve is not accurate and comprehensive enough. Only the relative flow is used to obtain the flow characteristic, which lacks correction basis when the flow characteristic deviates. At the same time, the analysis method used after obtaining the flow data of the regulating valve in the existing technology is not intelligent enough, so that the flow characteristic obtained after analysis always remains unchanged, which cannot be consistent with the actual situation of the regulating valve. Therefore, it is necessary to improve the method for analyzing the flow characteristic of the regulating valve. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application aims to provide a regulating valve internal flow characteristic numerical simulation method and system, which solves the problem that the flow data of the regulating valve is not accurate and comprehensive enough in the process of analyzing the flow characteristic of the regulating valve in the prior art, only the relative flow is used to obtain the flow characteristic, which lacks correction basis when the flow characteristic deviates, and the analysis method used after obtaining the flow data of the regulating valve in the existing technology is not intelligent enough, so that the flow characteristic obtained after analysis always remains unchanged, which cannot be consistent with the actual situation of the regulating valve.

[0005] In order to achieve the above-mentioned purpose, the present application provides a regulating valve internal flow characteristic numerical simulation method, which comprises:

[0006] The rheological extraction method is used to simulate the flow characteristic data of the regulating valve, and a flow characteristic curve is obtained based on the simulation of the flow characteristic data.

[0007] A deep learning model is established, and the deep learning model is trained based on the flow characteristic curve. The trained deep learning model is used to simulate the flow characteristics of the regulating valve.

[0008] A plurality of flow sensors and pressure sensors are arranged in the regulating valve.

[0009] The liquid flowing in the regulating valve is referred to as a flow medium. The pipe opening where the flow medium enters the valve body is referred to as an input port, and the pipe opening where the flow medium exits the valve body is referred to as an output port.

[0010] Flow sensors are placed in the pipelines corresponding to the input port and the output port, respectively, and are referred to as input sensors and output sensors, respectively. The flow sensors are used to collect the speed of the flow medium passing through.

[0011] A pressure sensor is placed in the valve core of the valve body. When the valve body contains multiple valve cores, the pressure sensor is placed in the valve core closest to the input sensor.

[0012] Further, the rheological extraction method is used to simulate the flow characteristic data of the regulating valve, and the flow characteristic curve of the regulating valve is obtained, including: adjusting the valve based on the positioner control actuator.

[0013] The positioner control actuator is used to adjust the opening of the valve to 0, and the flow medium is introduced into the input port of the valve body.

[0014] The opening of the valve is gradually increased, and the collection results of the input sensor, the output sensor, and the pressure sensor are obtained.

[0015] The rheological extraction method is used to obtain the flow characteristic curve of the regulating valve based on the collection results of the input sensor, the output sensor, and the pressure sensor.

[0016] Further, the rheological extraction method includes:

[0017] During the process of increasing the opening of the valve from 0 to 100%, the opening of the valve starts to increase by one percentage point from 0. The opening of the valve is stopped and the opening of the valve at this time is recorded as an intermittent opening. When the opening of the valve is at the intermittent opening and continues for a standard collection duration, the opening of the valve is continued to increase until the opening of the valve is increased to 100%.

[0018] All intermittent openings obtained during the increase of the opening of the valve are sequentially recorded as intermittent opening 1 to intermittent opening T from small to large.

[0019] For any intermittent opening T1 from intermittent opening 1 to intermittent opening T, the collected data of the input sensor within the standard collection time corresponding to the intermittent opening T1 is recorded as intermittent input data T1SR, the collected data of the output sensor within the standard collection time corresponding to the intermittent opening T1 is recorded as intermittent output data T1SC, and the collected data of the pressure sensor within the standard collection time corresponding to the intermittent opening T1 is recorded as intermittent pressure data T1YL, where T1 is a positive integer greater than or equal to 1 and less than or equal to T.

[0020] Furthermore, the rheological extraction method further comprises:

[0021] For the intermittent input data T1SR: establish a plane rectangular coordinate system, recorded as the input analysis coordinate system, where the unit of the X-axis of the input analysis coordinate system is time, and the unit of the Y-axis of the input analysis coordinate system is flow rate; based on the flow rate of the circulating medium collected within the standard collection time in the intermittent input data T1SR, draw a corresponding curve in the input analysis coordinate system, recorded as the intermittent input curve T1RQ;

[0022] The leftmost point and the rightmost point of the intermittent input curve T1RQ are respectively recorded as points L~T1RQ and points R~T1RQ, and the value corresponding to the X-axis coordinate of points R~T1RQ minus the X-axis coordinate corresponding to points L~T1RQ is the standard collection time. The line segment formed by connecting points L~T1RQ and points R~T1RQ is recorded as the intermittent input line segment T1RD, and the Y-axis coordinate corresponding to the midpoint of the intermittent input line segment T1RD is recorded as the intermittent input flow rate T1RS.

[0023] The intermittent input flow rates corresponding to the intermittent input data of all intermittent openings are obtained and recorded as intermittent input flow rates 1RS to intermittent input flow rates TRS, respectively.

[0024] Furthermore, the rheological extraction method further comprises:

[0025] For the intermittent output data T1SC: establish a plane rectangular coordinate system, recorded as the output analysis coordinate system, wherein the unit of the X-axis of the output analysis coordinate system is time, and the unit of the Y-axis of the output analysis coordinate system is flow rate; based on the flow rate of the circulating medium collected within the standard collection time in the intermittent output data T1SC, draw a corresponding curve in the output analysis coordinate system, recorded as the intermittent output curve T1CQ;

[0026] The leftmost point and rightmost point of the intermittent output curve T1CQ are respectively denoted as points L-T1CQ and points R-T1CQ, and the value corresponding to the X-axis coordinate of points R-T1CQ minus the X-axis coordinate corresponding to points L-T1CQ is the standard acquisition time. The line segment formed by connecting points L-T1CQ and points R-T1CQ is denoted as the intermittent output line segment T1CD, and the Y-axis coordinate corresponding to the midpoint of the intermittent output line segment T1CD is denoted as the intermittent output flow rate T1CS.

[0027] The intermittent output flow rates corresponding to the intermittent output data of all intermittent openings are obtained and recorded as intermittent output flow rates 1CS to intermittent output flow rates TCS respectively.

[0028] Furthermore, the rheological extraction method further comprises:

[0029] For the intermittent pressure data T1YL: the maximum pressure received by the pressure sensor in the intermittent pressure data T1YL is recorded as the intermittent pressure peak value T1FZ;

[0030] The intermittent pressure peak values ​​corresponding to all intermittent pressure data are obtained and recorded as intermittent pressure peak value 1FZ to intermittent pressure peak value TFZ respectively.

[0031] Furthermore, the rheological extraction method further comprises:

[0032] Establish a plane rectangular coordinate system, which is recorded as the flow analysis coordinate system, where the unit of the X-axis of the flow analysis coordinate system is the valve opening, and the unit of the Y-axis is the flow rate;

[0033] Based on the intermittent input flow rate corresponding to each intermittent opening, point marking is performed in the flow analysis coordinate system, and the marked points are recorded in ascending order based on the horizontal coordinate as input point 1SRD to input point TSRD; based on the intermittent output flow rate corresponding to each intermittent opening, point marking is performed in the flow analysis coordinate system, and the marked points are recorded in ascending order based on the horizontal coordinate as output point 1SCD to output point TSCD;

[0034] For any input point T1SRD from input point 1SRD to input point TSRD, the average value of the ordinate of the input point T1SRD and the ordinate of the output point T1SCD is recorded as the input-output mean value T1, and the point corresponding to (intermittent opening T1, input-output mean value T1) is recorded as the input-output mean point T1JD, where the intermittent opening T1 is the abscissa of the input point T1SRD and the output point T1SCD;

[0035] Obtain the average inlet and outlet points corresponding to all input points, and record the curve formed by all the average inlet and outlet points as the inlet and outlet flow curve.

[0036] Furthermore, the rheological extraction method further comprises:

[0037] After obtaining the in-out flow curve, the opening of the valve is adjusted to 0 again, and the in-out flow curve is obtained multiple times based on the obtaining method of the in-out flow curve while keeping the flow medium unchanged, and all in-out flow curves are recorded as in-out flow curve 1 to in-out flow curve C;

[0038] For any one of the in-out flow curves 2 to C-1, for any one of the in-out mean points α in the in-out flow curve C1, the mean value judgment formula is used to process the in-out mean point α and reassign the ordinate of the in-out mean point α, and the mean value judgment formula is Wherein, α i is the ordinate of the in-out mean point α, and α i-1 is the ordinate of the point in the in-out flow curve C1-1 whose abscissa is equal to the in-out mean point α; all in-out mean points in the in-out flow curve C1 are processed based on the processing method of the in-out mean point α, and after processing, the in-out flow curve C1+1 is processed based on the processing method of the in-out flow curve C1, and the same is true for the in-out flow curve C, and the obtained in-out flow curve C is recorded as the flow characteristic curve.

[0039] Further, a deep learning model is established, and the deep learning model is trained based on the flow characteristic curve, and the trained deep learning model is used to simulate the flow characteristics of the regulating valve, including:

[0040] Establishing a deep learning model;

[0041] Training the deep learning model based on the flow characteristic curve;

[0042] Using the trained deep learning model to simulate the flow of the flow medium in the regulating valve, and using the flow extraction method to obtain the flow characteristic curve, and recording the obtained flow characteristic curve as the flow characteristics of the regulating valve.

[0043] Further, training the deep learning model based on the flow characteristic curve includes:

[0044] The flow extraction method and the flow characteristic curve are input into the deep learning model, and the flow characteristic curve is reacquired using the flow extraction method based on the deep learning model, and is recorded as a new simulation curve;

[0045] The new simulation curve and the flow characteristic curve are placed in the same flow analysis coordinate system, and for any one of the intermittent openings 1 to T in the flow analysis coordinate system, when the ordinate of the new simulation curve is not equal to the ordinate of the flow characteristic curve, the intermittent opening T1 is recorded as the calibration opening, and the calibration method is used to adjust the ordinate corresponding to the calibration opening in the flow characteristic curve based on the calibration opening.

[0046] The calibration method includes: recording the intermittent pressure peak value of the intermittent pressure data corresponding to the calibration opening in the rheological extraction method corresponding to the flow characteristic curve as the standard calibration peak value;

[0047] The intermittent pressure peak value of the intermittent pressure data corresponding to the calibration opening in the rheological extraction method corresponding to the new simulation curve is recorded as the new simulation peak value;

[0048] When the standard calibration peak value is equal to the new simulation peak value, the vertical coordinate corresponding to the standard opening in the flow characteristic curve is replaced by the vertical coordinate corresponding to the standard opening in the new simulation curve;

[0049] When the standard calibration peak value is not equal to the new simulation peak value, the vertical coordinate corresponding to the standard opening in the flow characteristic curve is not replaced;

[0050] Obtain all calibration openings whose abscissas are intermittent opening 1 to intermittent opening T in the flow analysis coordinate system, perform processing based on all calibration openings using a calibration method, and continue to use the calibration method to adjust the ordinate of the flow characteristic curve based on the flow characteristic curve obtained after processing and a new simulation curve re-obtained by the deep learning model using a rheological extraction method;

[0051] When the flow characteristic curve processed by the calibration method and the new simulation curve re-obtained by the deep learning model using the rheological extraction method are placed in the same flow analysis coordinate system, and all intermittent openings with the horizontal coordinates from intermittent opening 1 to intermittent opening T in the flow analysis coordinate system are not the calibrated openings, the deep learning model is recorded as a deep learning model that has completed training.

[0052] Beneficial effects of the present invention: The present invention first sets multiple flow sensors and pressure sensors in the regulating valve; then controls the actuator based on the positioner to regulate the valve, and obtains a flow characteristic curve based on the valve changes and the acquisition results of the flow sensor and the pressure sensor; finally, establishes a deep learning model, and trains the deep learning model based on the flow characteristic curve, and uses the trained deep learning model to simulate the flow characteristics of the regulating valve. The advantage of this is that by using flow sensors and pressure sensors to collect data, it is possible to obtain the flow characteristics based on the flow sensor while obtaining the data collected by the pressure sensor related to the flow characteristics, thereby helping to correct the flow characteristics based on the data collected by the pressure sensor when the flow characteristics are subsequently corrected. By obtaining the flow characteristic curve and learning based on the flow characteristic curve through the deep learning model, the learned deep learning model can simulate a flow characteristic that is more in line with the actual situation of the regulating valve, thereby assisting the staff to perform more accurate work.

[0053] Advantages of additional aspects of the present invention will be given in part in the description of the following specific embodiments, and in part will become apparent from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0055] Figure 1 This is a principle block diagram of a numerical simulation system for flow characteristics inside a regulating valve according to the present invention;

[0056] Figure 2 A flowchart of the steps of a numerical simulation method for flow characteristics inside a regulating valve according to the present invention;

[0057] Figure 3 Schematic diagram of obtaining intermittent input flow rate of the present invention;

[0058] Figure 4 It is a schematic diagram of obtaining the inlet and outlet flow curves of the present invention. DETAILED DESCRIPTION

[0059] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0060] It should be noted that the terms used herein are for describing particular embodiments only and are not intended to limit the exemplary embodiments according to the present invention.

[0061] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0062] Example 1, first aspect, please refer to Figure 1 As shown, the present invention provides a numerical simulation system for flow characteristics inside a regulating valve, including a sensor deployment module, a characteristic curve acquisition module, and a model training module;

[0063] The sensor deployment module is used to set multiple flow sensors and pressure sensors in the regulating valve;

[0064] The sensor deployment module is configured with a sensor deployment strategy, which includes:

[0065] The liquid flowing through the regulating valve is recorded as the circulating medium; the pipe opening through which the circulating medium is input into the valve body is recorded as the input port, and the pipe opening through which the circulating medium is output from the valve body is recorded as the output port;

[0066] A flow sensor is arranged in the pipeline corresponding to the input port and the output port, and is respectively denoted as an input sensor and an output sensor, wherein the flow sensor is configured to collect the speed of the passing flow medium;

[0067] A pressure sensor is arranged in the valve core of the valve body, wherein when the valve body contains multiple valve cores, the pressure sensor is arranged in the valve core closest to the input sensor;

[0068] In the specific implementation process, when the regulating valve can pass in both directions, the valve port corresponding to the valve core where the pressure sensor is arranged is the input port, so as to ensure that the pressure sensor can receive the pressure of the flow medium acting on the valve core when the flow medium passes into the regulating valve;

[0069] The regulating valve comprises a positioner and an actuator, the positioner is configured to receive a stroke control signal required for opening and closing the valve, and then control the actuator to output a corresponding stroke, and a characteristic curve acquisition module is configured to control the actuator based on the positioner, and acquire a flow characteristic curve based on the change of the valve and the collection results of the flow sensor and the pressure sensor;

[0070] The characteristic curve acquisition module is configured with a characteristic curve acquisition strategy, and the characteristic curve acquisition strategy comprises:

[0071] The opening degree of the valve is adjusted to 0 by using the positioner to control the actuator, and the flow medium is passed into the input port of the valve body;

[0072] The opening degree of the valve is gradually increased, and the collection results of the input sensor, the output sensor and the pressure sensor are acquired;

[0073] The flow characteristic curve of the regulating valve is acquired by using a flow variation extraction method based on the collection results of the input sensor, the output sensor and the pressure sensor.

[0074] The flow variation extraction method comprises:

[0075] In the process that the opening degree of the valve is increased from 0 to 100%, the opening degree of the valve is increased by a unit percentage from 0, the increase of the opening degree of the valve is stopped, and the opening degree of the valve at this time is denoted as an intermittent opening degree, when the opening degree of the valve is at the intermittent opening degree and lasts for a standard collection time, the opening degree of the valve is continued to be increased until the opening degree of the valve is increased to 100%;

[0076] In the specific implementation process, the unit percentage and the standard collection time can be adjusted according to actual analysis requirements, in this embodiment, the unit percentage is set to 1%, and the standard collection time is set to 5s, that is, the opening degree of the valve is increased by 1% from 0, the increase of the opening degree of the valve is stopped for 5s, the opening degree of the valve is continued to be increased after 5s, and the opening degree of the valve is increased to 100%, and it is calculated that the number of intermittent opening degrees is 100;

[0077] All intermittent openings obtained during the increase of the valve opening are recorded from small to large as intermittent opening 1 to intermittent opening T;

[0078] For any intermittent opening T1 from intermittent opening 1 to intermittent opening T, the collected data of the input sensor within the standard collection time corresponding to the intermittent opening T1 is recorded as intermittent input data T1SR, the collected data of the output sensor within the standard collection time corresponding to the intermittent opening T1 is recorded as intermittent output data T1SC, and the collected data of the pressure sensor within the standard collection time corresponding to the intermittent opening T1 is recorded as intermittent pressure data T1YL, where T1 is a positive integer greater than or equal to 1 and less than or equal to T.

[0079] Rheological extraction methods also include:

[0080] For the intermittent input data T1SR: establish a plane rectangular coordinate system, recorded as the input analysis coordinate system, where the unit of the X-axis of the input analysis coordinate system is time, and the unit of the Y-axis of the input analysis coordinate system is flow rate; based on the flow rate of the circulating medium collected within the standard collection time in the intermittent input data T1SR, draw a corresponding curve in the input analysis coordinate system, recorded as the intermittent input curve T1RQ;

[0081] The leftmost point and the rightmost point of the intermittent input curve T1RQ are respectively recorded as points L~T1RQ and points R~T1RQ, and the value corresponding to the X-axis coordinate of points R~T1RQ minus the X-axis coordinate corresponding to points L~T1RQ is the standard collection time. The line segment formed by connecting points L~T1RQ and points R~T1RQ is recorded as the intermittent input line segment T1RD, and the Y-axis coordinate corresponding to the midpoint of the intermittent input line segment T1RD is recorded as the intermittent input flow rate T1RS.

[0082] In the specific implementation process, please refer to Figure 3 As shown, TT1 is the intermittent input curve, the time occupied by the horizontal axis length corresponding to TT2 is the standard acquisition time, TT3 is the intermittent input line segment, TT4 is the midpoint of the intermittent input line segment, and TT5 is the intermittent input flow rate;

[0083] The intermittent input flow rates corresponding to the intermittent input data of all intermittent openings are obtained and recorded as intermittent input flow rates 1RS to intermittent input flow rates TRS, respectively.

[0084] Rheological extraction methods also include:

[0085] For the intermittent output data T1SC: establish a plane rectangular coordinate system, recorded as the output analysis coordinate system, wherein the unit of the X-axis of the output analysis coordinate system is time, and the unit of the Y-axis of the output analysis coordinate system is flow rate; based on the flow rate of the circulating medium collected within the standard collection time in the intermittent output data T1SC, draw a corresponding curve in the output analysis coordinate system, recorded as the intermittent output curve T1CQ;

[0086] The leftmost point and rightmost point of the intermittent output curve T1CQ are respectively denoted as points L-T1CQ and points R-T1CQ, and the value corresponding to the X-axis coordinate of points R-T1CQ minus the X-axis coordinate corresponding to points L-T1CQ is the standard acquisition time. The line segment formed by connecting points L-T1CQ and points R-T1CQ is denoted as the intermittent output line segment T1CD, and the Y-axis coordinate corresponding to the midpoint of the intermittent output line segment T1CD is denoted as the intermittent output flow rate T1CS.

[0087] Obtain the intermittent output flow rates corresponding to the intermittent output data of all intermittent openings, and record them as intermittent output flow rates 1CS to intermittent output flow rates TCS respectively;

[0088] In the specific implementation process, the method for obtaining the intermittent output flow rate is consistent with the method for obtaining the intermittent input flow rate;

[0089] Rheological extraction methods also include:

[0090] For the intermittent pressure data T1YL: the maximum pressure received by the pressure sensor in the intermittent pressure data T1YL is recorded as the intermittent pressure peak value T1FZ;

[0091] In the specific implementation process, by obtaining the intermittent pressure peak, the pressure-related data corresponding to each intermittent opening can be obtained, thereby providing data support for the subsequent correction of the flow characteristic curve;

[0092] The intermittent pressure peak values ​​corresponding to all intermittent pressure data are obtained and recorded as intermittent pressure peak value 1FZ to intermittent pressure peak value TFZ respectively.

[0093] Rheological extraction methods also include:

[0094] Establish a plane rectangular coordinate system, which is recorded as the flow analysis coordinate system, where the unit of the X-axis of the flow analysis coordinate system is the valve opening, and the unit of the Y-axis is the flow rate;

[0095] Based on the intermittent input flow rate corresponding to each intermittent opening degree, point marking is carried out in the flow analysis coordinate system, and the points marked by the point marking are sequentially recorded as input point 1SRD to input point TSRD based on the horizontal coordinates from small to large; based on the intermittent output flow rate corresponding to each intermittent opening degree, point marking is carried out in the flow analysis coordinate system, and the points marked by the point marking are sequentially recorded as output point 1SCD to output point TSCD based on the horizontal coordinates from small to large;

[0096] For any one of the input points T1SRD to TTSRD, the average value of the longitudinal coordinates of the input point T1SRD and the output point T1SCD is recorded as the input-output average value T1, and the point corresponding to (intermittent opening degree T1, input-output average value T1) is recorded as the input-output average point T1JD, wherein the intermittent opening degree T1 is the horizontal coordinate of the input point T1SRD and the output point T1SCD.

[0097] In the specific implementation process, for example, in a data processing process, the intermittent opening degree 5 is 5%, the longitudinal coordinate of the input point 5SRD is 3 m / s, and the longitudinal coordinate of the output point 5SCD is 2 m / s. The input-output average value 5 is 2.5 m / s, and the point corresponding to (5, 2.5) in the flow analysis coordinate system is recorded as the input-output average point 5JD.

[0098] Obtain all input points corresponding to the input-output average point, and record the curve formed by all input-output average points as the input-output flow curve.

[0099] In the specific process, please refer to Figure 4 , wherein FF1 to FF8 are intermittent opening degrees 1 to 8, the points corresponding to Δ are input points, the points corresponding to □ are output points, and the curve corresponding to FF9 is the input-output flow curve.

[0100] After obtaining the input-output flow curve, the opening of the valve is adjusted to 0 again, and the input-output flow curve is obtained multiple times under the condition that the flow medium remains unchanged based on the input-output flow curve obtaining method. All input-output flow curves are recorded as input-output flow curve 1 to input-output flow curve C.

[0101] For any one of the input-output flow curves 2 to C-1, for any one of the input-output average points α in the input-output flow curve C1, the mean value judgment formula is used to process the input-output average point α, and the longitudinal coordinate of the input-output average point α is re-assigned. , wherein α i is the longitudinal coordinate of the input-output average point α, and α i-1It is the ordinate of the point in the inlet and outlet flow curve C1-1 whose abscissa is equal to the inlet and outlet average point α; all the inlet and outlet average points in the inlet and outlet flow curve C1 are processed based on the processing method of the inlet and outlet average point α, and after processing, the inlet and outlet flow curve C1+1 is processed based on the processing method of the inlet and outlet flow curve C1, and so on until the inlet and outlet flow curve C is processed. The obtained inlet and outlet flow curve C is recorded as the flow characteristic curve.

[0102] In the specific implementation process, for example, in a data processing, the coordinates of an inlet and outlet average point α in the inlet and outlet flow curve C1 are obtained as (60°, 2m / s), and the vertical coordinate of the point with a horizontal coordinate of 60° in the inlet and outlet flow curve C1-1 is 2.1m / s. After processing through the mean judgment formula, the vertical coordinate of the inlet and outlet average point α is reassigned to 2.05m / s.

[0103] The model training module is used to establish a deep learning model, train the deep learning model based on the flow characteristic curve, and use the trained deep learning model to simulate the flow characteristics of the control valve.

[0104] The model training module is equipped with model building and optimization strategies, which include:

[0105] Building deep learning models;

[0106] Train the deep learning model based on traffic characteristic curves;

[0107] The rheological extraction method and the flow characteristic curve are input into the deep learning model, and the flow characteristic curve is re-obtained using the rheological extraction method based on the deep learning model and recorded as a new simulation curve;

[0108] During the specific implementation process, whenever the deep learning model uses the rheological extraction method to re-acquire the flow characteristic curve, the valve opening of the regulating valve is adjusted to 0 and the circulating medium is reintroduced. The flow characteristic curve is re-acquired based on the data collected by the pressure sensor and the flow sensor during the process of increasing the valve opening;

[0109] The new simulation curve and the flow characteristic curve are placed in the same flow analysis coordinate system. For any intermittent opening T1 between intermittent opening 1 and intermittent opening T in the flow analysis coordinate system, when the ordinate when the abscissa in the new simulation curve is intermittent opening T1 is not equal to the ordinate when the abscissa in the flow characteristic curve is intermittent opening T1, the intermittent opening T1 is recorded as the calibration opening. Based on the calibration opening, the ordinate corresponding to the abscissa in the flow characteristic curve is adjusted using the calibration method;

[0110] The calibration method includes: recording the intermittent pressure peak value of the intermittent pressure data corresponding to the calibration opening in the rheological extraction method corresponding to the flow characteristic curve as the standard calibration peak value;

[0111] The intermittent pressure peak value of the intermittent pressure data corresponding to the calibration opening degree in the rheological extraction method of the new simulation curve is recorded as a new simulation peak value;

[0112] When the standard calibration peak value is equal to the new simulation peak value, the ordinate corresponding to the standard opening degree in the flow characteristic curve is replaced by the ordinate corresponding to the standard opening degree in the new simulation curve.

[0113] In the specific implementation process, when the standard calibration peak value is equal to the new simulation peak value, it indicates that under the condition of the same intermittent pressure peak value, the flow rate represented by the ordinate corresponding to the standard opening degree in the flow characteristic curve may differ from the newly acquired flow rate due to changes in external environment and other reasons, and therefore the newly acquired data should be taken as the basis, i.e., the ordinate corresponding to the standard opening degree in the new simulation curve is replaced.

[0114] When the standard calibration peak value is not equal to the new simulation peak value, the ordinate corresponding to the standard opening degree in the flow characteristic curve is not replaced.

[0115] In the specific implementation process, for example, in one data processing, the calibration opening degree is intermittent opening degree 5, the intermittent pressure peak value of the intermittent pressure data corresponding to intermittent opening degree 5 in the analysis process of the rheological extraction method used in acquiring the flow characteristic curve is 10 N, and the intermittent pressure peak value of the intermittent pressure data corresponding to intermittent opening degree 5 in the analysis process of the rheological extraction method used in acquiring the new simulation curve is 8 N, and therefore the ordinate corresponding to the standard opening degree in the flow characteristic curve is not replaced.

[0116] The model establishment and optimization strategy further includes:

[0117] All calibration opening degrees from intermittent opening degree 1 to intermittent opening degree T in the flow analysis coordinate system are acquired, and based on all the calibration opening degrees, the calibration method is used for processing, and based on the flow characteristic curve obtained after processing and the new simulation curve re-acquired by the deep learning model using the rheological extraction method, the calibration method is used to adjust the ordinate in the flow characteristic curve.

[0118] When the flow characteristic curve processed by the calibration method and the new simulation curve re-acquired by the deep learning model using the rheological extraction method are placed in the same flow analysis coordinate system, if all the intermittent opening degrees from intermittent opening degree 1 to intermittent opening degree T in the flow analysis coordinate system are not calibration opening degrees, the deep learning model is recorded as a deep learning model that has completed training.

[0119] The trained deep learning model is used to simulate the flow of the medium in the control valve, and the rheological extraction method is used to obtain the flow characteristic curve. The obtained flow characteristic curve is recorded as the flow characteristic of the control valve;

[0120] In the specific implementation process, since the flow characteristic of the regulating valve is defined as the relationship between the relative flow of the medium flowing through the regulating valve and its opening, and the unit of the Y-axis of the coordinate system where the flow characteristic curve is located is flow velocity, in actual processing, when the flow characteristic curve is recorded as the flow characteristic, the ordinate of the flow characteristic curve can be converted from flow velocity to relative flow and then the flow characteristic curve is recorded as the flow characteristic. For example, the ordinate of a point A in the flow characteristic curve is 1m / s and the slope is 2, and the relative flow corresponding to the medium flowing through the regulating valve with a speed of 1m / s and an acceleration of 2m / s2 is 1m 3 , then change the vertical coordinate of point A to 1m 3 , all points in the flow characteristic curve are processed accordingly based on the processing method of point A, and the processed flow characteristic curve is recorded as the flow characteristic, and the vertical axis unit of the coordinate system where the flow characteristic is located becomes the relative flow.

[0121] Example 2, second aspect, please refer to Figure 2 As shown, the present invention also provides a method for numerically simulating flow characteristics inside a regulating valve, comprising:

[0122] Step S1: installing a plurality of flow sensors and pressure sensors in the regulating valve.

[0123] Step S1 includes: step S101, recording the liquid circulating in the regulating valve as a circulating medium; recording the pipe opening for inputting the circulating medium in the valve body as an input port, and recording the pipe opening for outputting the circulating medium in the valve body as an output port;

[0124] Step S102: placing flow sensors in the pipes corresponding to the input port and the output port, respectively referred to as the input sensor and the output sensor, wherein the flow sensors are used to collect the velocity of the circulating medium;

[0125] Step S103: placing a pressure sensor in the valve core of the valve body. When the valve body contains multiple valve cores, the pressure sensor is placed in the valve core closest to the input sensor.

[0126] Step S2: adjusting the valve based on the positioner control actuator, and obtaining a flow characteristic curve based on the valve change and the acquisition results of the flow sensor and the pressure sensor.

[0127] Step S2 includes: step S201, using a positioner to control the actuator to adjust the valve opening to 0, and passing the circulating medium into the input port of the valve body;

[0128] Step S202, gradually increasing the valve opening and acquiring the acquisition results of the input sensor, output sensor, and pressure sensor;

[0129] Step S203 : obtaining a flow characteristic curve of the regulating valve using a rheological extraction method based on the acquisition results of the input sensor, the output sensor, and the pressure sensor.

[0130] The rheological extraction method includes: step S2031, during the process of increasing the valve opening from 0 to 100%, each time the valve opening increases by a unit percentage starting from 0, the valve opening is stopped from increasing and the valve opening at this time is recorded as intermittent opening; when the valve opening is in the intermittent opening and continues for the standard collection time, the valve opening is continued to increase until the valve opening is increased to 100%;

[0131] All intermittent openings obtained during the increase of the valve opening are recorded from small to large as intermittent opening 1 to intermittent opening T;

[0132] Step S2032, for any intermittent opening T1 from intermittent opening 1 to intermittent opening T, the collected data of the input sensor within the standard collection time corresponding to the intermittent opening T1 when the valve opening is in the intermittent opening T1 is recorded as intermittent input data T1SR, the collected data of the output sensor within the standard collection time corresponding to the intermittent opening T1 when the valve opening is in the intermittent opening T1 is recorded as intermittent output data T1SC, and the collected data of the pressure sensor within the standard collection time corresponding to the intermittent opening T1 when the valve opening is in the intermittent opening T1 is recorded as intermittent pressure data T1YL, wherein T1 is a positive integer greater than or equal to 1 and less than or equal to T.

[0133] Step S2033: For the intermittent input data T1SR: establish a plane rectangular coordinate system, denoted as the input analysis coordinate system, wherein the unit of the X-axis of the input analysis coordinate system is time, and the unit of the Y-axis of the input analysis coordinate system is flow rate; based on the flow rate of the circulating medium collected within the standard collection time in the intermittent input data T1SR, draw a corresponding curve in the input analysis coordinate system, denoted as the intermittent input curve T1RQ;

[0134] Step S2034: The leftmost point and the rightmost point of the intermittent input curve T1RQ are respectively designated as points L-T1RQ and points R-T1RQ. The X-axis coordinate corresponding to points R-T1RQ minus the X-axis coordinate corresponding to points L-T1RQ is the standard acquisition duration. The line segment formed by connecting points L-T1RQ and points R-T1RQ is designated as the intermittent input line segment T1RD. The Y-axis coordinate corresponding to the midpoint of the intermittent input line segment T1RD is designated as the intermittent input flow rate T1RS.

[0135] The intermittent input flow rates corresponding to the intermittent input data of all intermittent openings are obtained and recorded as intermittent input flow rates 1RS to intermittent input flow rates TRS, respectively.

[0136] Step S2035: For the intermittent output data T1SC, a rectangular coordinate system is established, denoted as the output analysis coordinate system, wherein the unit of the X-axis of the output analysis coordinate system is time, and the unit of the Y-axis of the output analysis coordinate system is flow rate; a corresponding curve is drawn in the output analysis coordinate system based on the flow rate of the circulating medium collected within the standard collection time in the intermittent output data T1SC, denoted as the intermittent output curve T1CQ;

[0137] The leftmost point and rightmost point of the intermittent output curve T1CQ are respectively denoted as points L-T1CQ and points R-T1CQ, and the value corresponding to the X-axis coordinate of points R-T1CQ minus the X-axis coordinate corresponding to points L-T1CQ is the standard acquisition time. The line segment formed by connecting points L-T1CQ and points R-T1CQ is denoted as the intermittent output line segment T1CD, and the Y-axis coordinate corresponding to the midpoint of the intermittent output line segment T1CD is denoted as the intermittent output flow rate T1CS.

[0138] Step S2036: Obtain the intermittent output flow rates corresponding to the intermittent output data of all intermittent openings, and record them as intermittent output flow rates 1CS to intermittent output flow rates TCS.

[0139] Step S2037, for the intermittent pressure data T1YL: record the maximum pressure received by the pressure sensor in the intermittent pressure data T1YL as the intermittent pressure peak value T1FZ;

[0140] The intermittent pressure peak values ​​corresponding to all intermittent pressure data are obtained and recorded as intermittent pressure peak value 1FZ to intermittent pressure peak value TFZ respectively.

[0141] Step S2038: Establish a plane rectangular coordinate system, which is recorded as the flow analysis coordinate system, wherein the unit of the X axis of the flow analysis coordinate system is the valve opening, and the unit of the Y axis is the flow rate;

[0142] Based on the intermittent input flow rate corresponding to each intermittent opening, point marking is performed in the flow analysis coordinate system, and the marked points are recorded in ascending order based on the horizontal coordinate as input point 1SRD to input point TSRD; based on the intermittent output flow rate corresponding to each intermittent opening, point marking is performed in the flow analysis coordinate system, and the marked points are recorded in ascending order based on the horizontal coordinate as output point 1SCD to output point TSCD;

[0143] Step S2039: For any input point T1SRD from input point 1SRD to input point TSRD, record the average of the ordinates of input point T1SRD and output point T1SCD as input-output mean value T1, and record the point corresponding to (intermittent opening T1, input-output mean value T1) as input-output mean point T1JD, where intermittent opening T1 is the abscissa of input point T1SRD and output point T1SCD.

[0144] Obtain the average inlet and outlet points corresponding to all input points, and record the curve formed by all the average inlet and outlet points as the inlet and outlet flow curve.

[0145] Step S20391: After obtaining the inlet and outlet flow curves, the valve opening is readjusted to 0, and multiple inlet and outlet flow curves are obtained based on the inlet and outlet flow curve acquisition method while keeping the circulating medium unchanged. All inlet and outlet flow curves are recorded as inlet and outlet flow curves 1 to inlet and outlet flow curves C.

[0146] For any inlet and outlet flow curve C1 from the inlet and outlet flow curve 2 to the inlet and outlet flow curve C-1, for any inlet and outlet mean point α in the inlet and outlet flow curve C1, the inlet and outlet mean point α is processed using the mean judgment formula and the vertical coordinate of the inlet and outlet mean point α is reassigned. The mean judgment formula is: Among them, α i is the vertical coordinate of the entry and exit point α, i-1 It is the ordinate of the point in the inlet and outlet flow curve C1-1 whose abscissa is equal to the inlet and outlet average point α; all the inlet and outlet average points in the inlet and outlet flow curve C1 are processed based on the processing method of the inlet and outlet average point α, and after processing, the inlet and outlet flow curve C1+1 is processed based on the processing method of the inlet and outlet flow curve C1, and so on until the inlet and outlet flow curve C is processed. The obtained inlet and outlet flow curve C is recorded as the flow characteristic curve.

[0147] Step S3: Establish a deep learning model, train the deep learning model based on the flow characteristic curve, and use the trained deep learning model to simulate the flow characteristics of the regulating valve.

[0148] Step S3 includes: step S301, establishing a deep learning model;

[0149] Step S302: training a deep learning model based on the flow characteristic curve;

[0150] Step S302 includes: step S3021, inputting the rheological extraction method and the flow characteristic curve into the deep learning model, and re-obtaining the flow characteristic curve using the rheological extraction method based on the deep learning model, and recording it as a new simulation curve;

[0151] Step S3022: Place the new simulation curve and the flow characteristic curve in the same flow analysis coordinate system. For any intermittent opening T1 between intermittent opening 1 and intermittent opening T in the flow analysis coordinate system, if the ordinate when the abscissa in the new simulation curve is intermittent opening T1 is not equal to the ordinate when the abscissa in the flow characteristic curve is intermittent opening T1, record the intermittent opening T1 as the calibration opening, and adjust the ordinate corresponding to the calibrated opening in the flow characteristic curve using a calibration method based on the calibration opening.

[0152] The calibration method includes: recording the intermittent pressure peak value of the intermittent pressure data corresponding to the calibration opening in the rheological extraction method corresponding to the flow characteristic curve as the standard calibration peak value;

[0153] The intermittent pressure peak value of the intermittent pressure data corresponding to the calibration opening in the rheological extraction method corresponding to the new simulation curve is recorded as the new simulation peak value;

[0154] When the standard calibration peak value is equal to the new simulation peak value, the vertical coordinate corresponding to the standard opening in the flow characteristic curve is replaced by the vertical coordinate corresponding to the standard opening in the new simulation curve;

[0155] When the standard calibration peak value is not equal to the new simulation peak value, the vertical coordinate corresponding to the standard opening in the flow characteristic curve is not replaced.

[0156] Step S3023, obtaining all calibration openings whose horizontal coordinates are intermittent opening 1 to intermittent opening T in the flow analysis coordinate system, and processing them using the calibration method based on all the calibration openings. Based on the flow characteristic curve obtained after processing and the new simulation curve re-obtained by the deep learning model using the rheological extraction method, the vertical coordinate of the flow characteristic curve is further adjusted using the calibration method;

[0157] Step S3024, when the flow characteristic curve processed by the calibration method and the new simulation curve re-obtained by the deep learning model using the rheological extraction method are placed in the same flow analysis coordinate system, when all intermittent openings with the horizontal coordinates from intermittent opening 1 to intermittent opening T in the flow analysis coordinate system are not the calibrated openings, the deep learning model is recorded as a deep learning model that has completed training.

[0158] In step S303, the trained deep learning model is used to simulate the flow of the circulating medium in the regulating valve, and a flow characteristic curve is obtained using a rheological extraction method. The obtained flow characteristic curve is recorded as the flow characteristic of the regulating valve.

[0159] Working principle: First, multiple flow sensors and pressure sensors are set in the control valve; then the valve is adjusted based on the positioner control actuator, and the flow characteristic curve is obtained based on the valve changes and the acquisition results of the flow sensor and pressure sensor; finally, a deep learning model is established and trained based on the flow characteristic curve, and the trained deep learning model is used to simulate the flow characteristics of the control valve.

[0160] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium may be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0161] The above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or perform equivalent replacements on some of the technical features thereof. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A numerical simulation method for flow characteristics inside a regulating valve, characterized in that: include: The flow characteristic data of the regulating valve is simulated using a rheological extraction method, and a flow characteristic curve is obtained based on the simulation of the flow characteristic data; Establish a deep learning model, train it based on the flow characteristic curve, and use the trained deep learning model to simulate the flow characteristics of the control valve; A plurality of flow sensors and pressure sensors are arranged in the regulating valve; The liquid flowing through the regulating valve is recorded as the circulating medium; the pipe opening through which the circulating medium is input into the valve body is recorded as the input port, and the pipe opening through which the circulating medium is output from the valve body is recorded as the output port; Flow sensors are placed in the pipes corresponding to the input port and the output port, respectively denoted as input sensors and output sensors, wherein the flow sensors are used to collect the velocity of the circulating medium; A pressure sensor is placed in the valve core of the valve body. When the valve body contains multiple valve cores, the pressure sensor is placed in the valve core closest to the input sensor.

2. The method for numerical simulation of internal flow characteristics of a regulating valve according to claim 1, characterized in that: The flow characteristic data of the regulating valve is simulated by using the rheological extraction method, and the flow characteristic curve of the regulating valve is obtained, including: regulating the valve based on the positioner control actuator; Use the positioner to control the actuator to adjust the valve opening to 0, and pass the circulating medium into the input port of the valve body; Gradually increase the valve opening and obtain the data collected by the input sensor, output sensor, and pressure sensor; Based on the acquisition results of the input sensor, output sensor and pressure sensor, the flow characteristic curve of the regulating valve is obtained using the rheological extraction method.

3. The method for numerically simulating internal flow characteristics of a regulating valve according to claim 2, characterized in that: The rheological extraction method comprises: In the process of increasing the valve opening from 0 to 100%, the valve opening is stopped from increasing for each unit percentage increase from 0 and the valve opening at this time is recorded as intermittent opening. When the valve opening is in intermittent opening and continues for the standard collection time, the valve opening is continued to increase until the valve opening is increased to 100%; All intermittent openings obtained during the increase of the valve opening are recorded from small to large as intermittent opening 1 to intermittent opening T; For any intermittent opening T1 from intermittent opening 1 to intermittent opening T, the collected data of the input sensor within the standard collection time corresponding to the intermittent opening T1 is recorded as intermittent input data T1SR, the collected data of the output sensor within the standard collection time corresponding to the intermittent opening T1 is recorded as intermittent output data T1SC, and the collected data of the pressure sensor within the standard collection time corresponding to the intermittent opening T1 is recorded as intermittent pressure data T1YL, where T1 is a positive integer greater than or equal to 1 and less than or equal to T.

4. The method for numerically simulating flow characteristics inside a regulating valve according to claim 3, characterized in that: The rheological extraction method further comprises: For the intermittent input data T1SR: establish a plane rectangular coordinate system, recorded as the input analysis coordinate system, where the unit of the X-axis of the input analysis coordinate system is time, and the unit of the Y-axis of the input analysis coordinate system is flow rate; based on the flow rate of the circulating medium collected within the standard collection time in the intermittent input data T1SR, draw a corresponding curve in the input analysis coordinate system, recorded as the intermittent input curve T1RQ; The leftmost point and the rightmost point of the intermittent input curve T1RQ are respectively recorded as points L~T1RQ and points R~T1RQ, and the value corresponding to the X-axis coordinate of points R~T1RQ minus the X-axis coordinate corresponding to points L~T1RQ is the standard collection time. The line segment formed by connecting points L~T1RQ and points R~T1RQ is recorded as the intermittent input line segment T1RD, and the Y-axis coordinate corresponding to the midpoint of the intermittent input line segment T1RD is recorded as the intermittent input flow rate T1RS. The intermittent input flow rates corresponding to the intermittent input data of all intermittent openings are obtained and recorded as intermittent input flow rates 1RS to intermittent input flow rates TRS, respectively.

5. The method for numerical simulation of internal flow characteristics of a regulating valve according to claim 4, characterized in that: The rheological extraction method further comprises: For the intermittent output data T1SC: establish a plane rectangular coordinate system, recorded as the output analysis coordinate system, wherein the unit of the X-axis of the output analysis coordinate system is time, and the unit of the Y-axis of the output analysis coordinate system is flow rate; based on the flow rate of the circulating medium collected within the standard collection time in the intermittent output data T1SC, draw a corresponding curve in the output analysis coordinate system, recorded as the intermittent output curve T1CQ; The leftmost point and rightmost point of the intermittent output curve T1CQ are respectively denoted as points L-T1CQ and points R-T1CQ, and the value corresponding to the X-axis coordinate of points R-T1CQ minus the X-axis coordinate corresponding to points L-T1CQ is the standard acquisition time. The line segment formed by connecting points L-T1CQ and points R-T1CQ is denoted as the intermittent output line segment T1CD, and the Y-axis coordinate corresponding to the midpoint of the intermittent output line segment T1CD is denoted as the intermittent output flow rate T1CS. The intermittent output flow rates corresponding to the intermittent output data of all intermittent openings are obtained and recorded as intermittent output flow rates 1CS to intermittent output flow rates TCS respectively.

6. The method for numerically simulating flow characteristics inside a regulating valve according to claim 5, characterized in that: The rheological extraction method further comprises: For the intermittent pressure data T1YL: the maximum pressure received by the pressure sensor in the intermittent pressure data T1YL is recorded as the intermittent pressure peak value T1FZ; The intermittent pressure peak values ​​corresponding to all intermittent pressure data are obtained and recorded as intermittent pressure peak value 1FZ to intermittent pressure peak value TFZ respectively.

7. The method for numerically simulating flow characteristics inside a regulating valve according to claim 6, characterized in that: The rheological extraction method further comprises: Establish a plane rectangular coordinate system, which is recorded as the flow analysis coordinate system, where the unit of the X-axis of the flow analysis coordinate system is the valve opening, and the unit of the Y-axis is the flow rate; Based on the intermittent input flow rate corresponding to each intermittent opening, point marking is performed in the flow analysis coordinate system, and the marked points are recorded in ascending order based on the horizontal coordinate as input point 1SRD to input point TSRD; based on the intermittent output flow rate corresponding to each intermittent opening, point marking is performed in the flow analysis coordinate system, and the marked points are recorded in ascending order based on the horizontal coordinate as output point 1SCD to output point TSCD; For any input point T1SRD from input point 1SRD to input point TSRD, the average value of the ordinate of the input point T1SRD and the ordinate of the output point T1SCD is recorded as the input-output mean value T1, and the point corresponding to (intermittent opening T1, input-output mean value T1) is recorded as the input-output mean point T1JD, where the intermittent opening T1 is the abscissa of the input point T1SRD and the output point T1SCD; Obtain the average inlet and outlet points corresponding to all input points, and record the curve formed by all the average inlet and outlet points as the inlet and outlet flow curve.

8. The method for numerically simulating flow characteristics inside a regulating valve according to claim 7, characterized in that: The rheological extraction method further comprises: After obtaining the inlet and outlet flow curves, the valve opening is readjusted to 0, and based on the inlet and outlet flow curve acquisition method, the inlet and outlet flow curves are acquired multiple times while keeping the flow medium unchanged, and all the inlet and outlet flow curves are recorded as inlet and outlet flow curves 1 to inlet and outlet flow curves C respectively; For any inlet and outlet flow curve C1 from the inlet and outlet flow curve 2 to the inlet and outlet flow curve C-1, for any inlet and outlet mean point α in the inlet and outlet flow curve C1, the inlet and outlet mean point α is processed using the mean judgment formula and the vertical coordinate of the inlet and outlet mean point α is reassigned. The mean judgment formula is: Among them, α i is the vertical coordinate of the entry and exit point α, i-1 It is the ordinate of the point in the inlet and outlet flow curve C1-1 whose abscissa is equal to the inlet and outlet average point α; all the inlet and outlet average points in the inlet and outlet flow curve C1 are processed based on the processing method of the inlet and outlet average point α, and after processing, the inlet and outlet flow curve C1+1 is processed based on the processing method of the inlet and outlet flow curve C1, and so on until the inlet and outlet flow curve C is processed. The obtained inlet and outlet flow curve C is recorded as the flow characteristic curve.

9. The method for numerically simulating internal flow characteristics of a regulating valve according to claim 8, characterized in that: A deep learning model is established and trained based on the flow characteristic curve. The trained deep learning model is used to simulate the flow characteristics of the control valve, including: Building deep learning models; Train the deep learning model based on traffic characteristic curves; The trained deep learning model is used to simulate the circulation of the circulating medium in the control valve, and the rheological extraction method is used to obtain the flow characteristic curve, which is recorded as the flow characteristic of the control valve.

10. The method for numerical simulation of internal flow characteristics of a regulating valve according to claim 9, characterized in that: Training a deep learning model based on traffic characteristic curves includes: The rheological extraction method and the flow characteristic curve are input into the deep learning model, and the flow characteristic curve is re-obtained using the rheological extraction method based on the deep learning model and recorded as a new simulation curve; The new simulation curve and the flow characteristic curve are placed in the same flow analysis coordinate system. For any intermittent opening T1 between intermittent opening 1 and intermittent opening T in the flow analysis coordinate system, when the ordinate when the abscissa in the new simulation curve is intermittent opening T1 is not equal to the ordinate when the abscissa in the flow characteristic curve is intermittent opening T1, the intermittent opening T1 is recorded as the calibration opening. Based on the calibration opening, the ordinate corresponding to the abscissa in the flow characteristic curve is adjusted using the calibration method; The calibration method includes: recording the intermittent pressure peak value of the intermittent pressure data corresponding to the calibration opening in the rheological extraction method corresponding to the flow characteristic curve as the standard calibration peak value; The intermittent pressure peak value of the intermittent pressure data corresponding to the calibration opening in the rheological extraction method corresponding to the new simulation curve is recorded as the new simulation peak value; When the standard calibration peak value is equal to the new simulation peak value, the vertical coordinate corresponding to the standard opening in the flow characteristic curve is replaced by the vertical coordinate corresponding to the standard opening in the new simulation curve; When the standard calibration peak value is not equal to the new simulation peak value, the vertical coordinate corresponding to the standard opening in the flow characteristic curve is not replaced; Obtain all calibration openings whose abscissas are intermittent opening 1 to intermittent opening T in the flow analysis coordinate system, perform processing based on all calibration openings using a calibration method, and continue to use the calibration method to adjust the ordinate of the flow characteristic curve based on the flow characteristic curve obtained after processing and a new simulation curve re-obtained by the deep learning model using a rheological extraction method; When the flow characteristic curve processed by the calibration method and the new simulation curve re-obtained by the deep learning model using the rheological extraction method are placed in the same flow analysis coordinate system, and all intermittent openings with the horizontal coordinates from intermittent opening 1 to intermittent opening T in the flow analysis coordinate system are not the calibrated openings, the deep learning model is recorded as a deep learning model that has completed training.

Images