A valve leak prevention monitoring method

Abstract

The application discloses a valve leakage prevention monitoring method, steps comprising: obtaining a valve geometric model, establishing a material physical property parameter library and inputting medium initial injection rate and start-stop transient pressure-time working condition parameters; then carrying out fluid-solid-thermal transient coupling simulation on the geometric model, generating an initial injection time-varying theoretical transient thermodynamic atlas sequence and a temperature-time curve; extracting a temperature change interval and a change rate threshold of dynamic change in an initial flow stage based on simulation data; deploying a high-frame-rate infrared thermal imager on a valve sealing surface, synchronously collecting actual transient thermodynamic atlas sequences and temperature data; carrying out difference analysis after time sequence alignment of actual and theoretical thermodynamic atlas sequences, identifying abnormal temperature distribution areas of the sealing surface; comparing actual and theoretical temperature change rates, identifying abnormal events in the initial stage; and combining the abnormal area position and the abnormal event, early leakage risk grade early warning is carried out in the medium initial injection stage.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of valves, in particular to a valve leakage prevention monitoring method. BACKGROUND

[0002] In the industrial fields of petrochemical industry, electric power energy, etc., the valve in the pipeline system is a key component for controlling the on-off of fluid and parameters, and its sealing performance is directly related to production safety and economic benefits. In the valve leakage monitoring process of the existing valve monitoring method, the monitoring is mostly carried out after the stable flow of the medium in the valve, and in the initial flow stage of the medium in the valve, due to the intense heat exchange between the medium and the valve body, the temperature changes with time are relatively complex, and it is difficult to accurately determine whether the valve leaks, which may miss the best repair opportunity and cause safety accidents.

[0003] Therefore, it is necessary to provide a valve leakage prevention monitoring method to solve the problems mentioned in the background. SUMMARY

[0004] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a valve leakage prevention monitoring method, comprising:

[0005] S1, obtaining a geometric model of a valve to be tested, establishing a material physical property parameter library, and inputting the initial injection rate of the medium and the pressure-time working condition parameters of the start-stop transient process;

[0006] S2, performing flow-solid-thermal transient coupling simulation based on CFD and FEA software, and generating a theoretical transient thermal map sequence and a theoretical temperature-time change curve of the medium after the initial injection of the valve to be tested;

[0007] S3, extracting a theoretical temperature change interval threshold range and a theoretical temperature change rate threshold range based on the simulation data in time sequence, wherein the theoretical temperature change interval threshold range and the theoretical temperature change rate threshold range dynamically change with time in the initial flow stage;

[0008] S4, deploying a high-frame-rate infrared thermal imager in the valve sealing surface area, and synchronously collecting an actual transient thermal map sequence and an actual temperature change rate curve after the injection of the medium;

[0009] S5, after aligning the actual transient thermal map sequence and the theoretical transient thermal map sequence in time sequence, performing differential analysis on each pair of corresponding frames to identify the temperature distribution abnormal area of the sealing surface;

[0010] Comparing the actual temperature change rate curve with the theoretical temperature change rate threshold range to identify the temperature change rate abnormal event in the initial flow stage;

[0011] S6, based on the abnormal area of the sealing surface temperature distribution and the abnormal event of the temperature change rate, early leakage risk warning is performed in the initial stage of medium injection.

[0012] Preferably, the material property parameter library in step S1 includes valve body material parameters and flow medium physical property parameters, the valve body material parameters include density, thermal conductivity and specific heat capacity, and the flow medium physical property parameters include viscosity, thermal expansion coefficient and specific heat capacity.

[0013] Preferably, step S2 further comprises: performing flow-solid-thermal transient coupling simulation of the valve to be tested at different opening degrees.

[0014] Preferably, step S1 further comprises recording the cumulative running time of the valve to be tested, and dynamically correcting the material aging parameters according to the service life of the valve body.

[0015] Preferably, in step S2, the transient coupling simulation comprises:

[0016] S2.1, set the total simulation time length including the medium injection intense exchange stage and the subsequent heat transfer stabilization stage, simulate in the intense heat exchange stage using a first time step, and simulate in the heat transfer stabilization stage using a second time step, the first time step is smaller than the second time step;

[0017] S2.2, based on the valve sealing surface area, output a spatial cloud map sequence of dynamic temperature gradient distribution;

[0018] S2.3, synchronously generate a curve graph of the temperature change rate of the valve sealing surface area changing with time;

[0019] S2.4, correspond the spatial cloud map sequence of dynamic temperature gradient distribution and the temperature change rate curve graph according to the time axis, and construct a space-time correlated reference data set.

[0020] Preferably, in step S3, in the initial flow stage, the temperature change rate threshold range is greater than the temperature change rate threshold range in the stable flow stage, and the temperature change rate threshold range gradually becomes smaller with the increase of time.

[0021] Preferably, the step S4 further comprises:

[0022] High-frequency pressure sensors are arranged on the upstream and downstream of the valve to collect pressure decay curves after flow stop; step S5 combines pressure decay abnormalities and temperature change rate abnormalities to verify leakage.

[0023] Preferably, in step S5, the identification of the abnormal area of the sealing surface temperature distribution adopts a time sequence intelligent algorithm for temperature distribution abnormality identification, which comprises:

[0024] S5.1, using long short-term memory network to train the temperature sampling sequence of the valve sealing area under the historical non-leakage working condition, and extracting the key dynamic characteristics of the medium injection stage;

[0025] S5.2, the temperature sequence collected in real time is matched with the standard transient response curve output by the long short-term memory network in nonlinear time axis by a dynamic time warping algorithm, and the timing phase offset caused by the difference in valve operation speed is eliminated;

[0026] S5.3, calculate the point-by-point residual absolute value of the standard sequence and the real-time sequence processed by the dynamic time warping algorithm, when the residual absolute value continuously exceeds the preset first temperature deviation threshold for a time greater than the preset first duration threshold, or the single-point residual exceeds the preset second temperature deviation threshold, it is recorded as a residual abnormality mark period;

[0027] S5.4, the sealing surface temperature distribution abnormal area, temperature change rate abnormal event and residual abnormality mark period identified by differentiating the actual transient thermal map sequence of the high-frame-rate infrared thermal imager and the theoretical transient thermal map sequence are analyzed in space-time overlap, if there is a space-time intersection among the three, and the sealing surface temperature distribution abnormal area is located in the valve sealing surface structure range, and the occurrence time of the temperature change rate abnormal event and the residual abnormality mark period is earlier than the occurrence time of the pressure decay abnormality, then the leakage is determined.

[0028] Preferably, in step S6, the leakage risk level comprises:

[0029] Potential micro-leakage level, temperature change rate exceeds threshold range in initial flow stage but no pressure decay is detected;

[0030] Measurable leakage level, temperature change rate anomaly accompanied by pressure or flow anomaly;

[0031] Severe leakage level, temperature gradient of sealing surface temperature abnormal area exceeds safety threshold.

[0032] Preferably, the method further comprises step S7 of feeding the actual collected transient data to the simulation model to correct the medium injection rate boundary adjustment and the material transient thermal response parameters.

[0033] Compared with the prior art, the present application provides a valve leakage prevention monitoring method, which has the following beneficial effects:

[0034] In the present application, in view of the problem that the existing valve monitoring cannot accurately identify leakage in the initial medium flow stage (intense heat exchange period), through phased transient simulation, high-frame-rate infrared thermal imager and pressure sensor multi-source data synchronous acquisition, long short-term memory network and dynamic time warping algorithm analysis of temperature sequence characteristics, early warning of valve leakage is realized: in the "potential micro-permeation stage" with extremely small leakage, through threefold verification of temperature abnormal area, excessive change rate and pressure abnormal timing correlation to reduce false alarm rate, and covering different opening conditions of the valve, combined with dynamic correction model of material aging parameters, the monitoring accuracy is continuously optimized with running time; the production safety level and economic benefits in the fields of petrochemical industry, electric power energy and the like are improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 It is a schematic diagram of the overall structure of a valve leakage prevention monitoring method. DETAILED DESCRIPTION

[0036] In the industrial fields of petrochemical industry, electric power energy and the like, once the valve in the pipeline system leaks, it may cause safety accidents and economic losses, so accurate leakage prevention monitoring is crucial.

[0037] The method comprises the following steps: acquiring a valve geometric model, establishing a material physical property parameter library, and inputting medium initial injection rate and start-stop transient pressure-time working condition parameters; then performing fluid-solid-thermal transient coupling simulation on the geometric model to generate a theoretical transient thermodynamic spectrum sequence and a theoretical temperature-time change curve varying with time after initial injection; based on the simulation data, extracting the theoretical temperature change interval threshold range and the theoretical temperature change rate threshold range varying dynamically in the initial flow stage; deploying a high-frame-rate infrared thermal imager in the valve sealing surface area, and synchronously collecting actual transient thermodynamic spectrum sequence and actual temperature change rate curve; after time sequence alignment of the actual and theoretical thermodynamic feature map sequence, difference analysis is performed to identify the temperature distribution abnormal area of the sealing surface; comparing the temperature change rate curve with the theoretical temperature change rate threshold range to identify the temperature change rate abnormal event in the initial flow stage of the valve; and combining the temperature distribution abnormal area of the sealing surface and the temperature change rate abnormal event, early leakage risk grade warning is performed in the initial injection stage of the medium.

[0038] Specifically, referring to Figure 1 The present application provides a valve leakage prevention monitoring method, comprising:

[0039] Step S1: Basic data preparation: In the industrial field, for the valve to be tested, first use three-dimensional modeling software (such as SolidWorks, UG software, etc.) to build a valve geometric model according to the valve design drawings or actual measured dimensions. The model needs to include the valve body, sealing surface, valve stem, valve plate and other key structures. Then establish a material property parameter library, obtain the density, thermal conductivity, specific heat capacity and other parameters of the valve body material, as well as the viscosity, thermal expansion coefficient, specific heat capacity and other physical parameters of the flow medium through experimental measurement, consulting material manuals or technical data provided by the supplier. Then enter the initial injection rate of the medium, and obtain real-time data from the pipeline flow control system. The pressure-time working condition parameters of the start-stop transient process are collected and stored in real time by the pressure sensor installed on the pipeline, providing initial conditions for subsequent simulation;

[0040] Further, the cumulative running time of the valve to be tested is also recorded, and the material aging parameters are dynamically corrected according to the service life of the valve body. The specific material thermal conductivity correction formula is:

[0041] ;

[0042] Wherein, represents the thermal conductivity of the material after aging correction, unit: ; is the thermal conductivity of the material in the initial state, unit: ; is the thermal conductivity decay coefficient; t is the cumulative running time of the valve, unit: h.

[0043] Step S2: Simulation analysis and construction: Based on CFD and FEA software for fluid-solid-thermal transient coupling simulation. First, simulate the valve to be tested at different opening degrees (such as 25%, 50%, 75%, 100% opening) to simulate the fluid-solid-thermal coupling of the valve in different working conditions in actual operation.

[0044] S2.1, set the total simulation time including the medium injection intense exchange stage and the subsequent heat transfer steady stage. In the intense heat exchange stage (such as the first 5 minutes after the medium is injected into the valve), due to the rapid change of temperature, pressure and other parameters, a smaller first time step (such as 0.01 seconds) is used for simulation to capture subtle transient changes; in the heat transfer steady stage (when the temperature change rate gradually slows down), a larger second step (such as 0.1 seconds) is used for simulation to improve the calculation efficiency.

[0045] Wherein, in the intense exchange stage, the time step is set to satisfy the formula:

[0046] ;

[0047] wherein, CFL is the Courant number, a dimensionless number, used to measure the relationship between time and space steps in numerical calculation, to ensure the numerical stability in the calculation process; is the fluid velocity, with the unit of m / s; represents the time step set in the stage of intense heat exchange, with the unit of s; represents the size of the calculation grid, with the unit of m.

[0048] S2.2, for the valve sealing surface area, output the spatial cloud atlas sequence of dynamic temperature gradient distribution, intuitively display the temperature distribution of different positions in the sealing surface area at different times;

[0049] S2.3, synchronously generate the curve graph of temperature change rate changing with time, clearly reflect the trend of temperature change speed;

[0050] S2.4, correspond the spatial cloud atlas sequence of dynamic temperature gradient distribution and the curve graph of temperature change rate according to the time axis, construct the benchmark data set of space-time correlation, and provide comprehensive theoretical reference for subsequent monitoring.

[0051] Step S3: determining the judgment threshold: based on the simulation data of step S2, extracting the theoretical temperature change interval threshold range and the theoretical temperature change rate threshold range according to the time sequence. In the initial flow stage, due to the intense heat exchange between the medium and the valve body, the temperature changes with time is relatively complex, and the temperature change rate threshold range is greater than that in the stable flow stage. With the increase of time, the heat exchange gradually tends to be stable, and the temperature change rate threshold range gradually becomes smaller, for example, the temperature change rate threshold range is ±5℃ / s in the initial stage, and it is reduced to ±1℃ in the stable stage, which is used to more accurately reflect the normal temperature change of the valve in different running stages, and provide the judgment basis for abnormal identification.

[0052] Specifically, the temperature change rate calculation formula is:

[0053] ;

[0054] wherein, T represents the temperature change rate, with the unit of ℃ / s; represents the temperature value measured or calculated at the moment, with the unit of ℃; is the interval time, with the unit of s.

[0055] Step S4: Data collection: Deploy a high-frame-rate infrared thermal imager (such as the FLIRT series, GaoDe intelligent infrared thermal imager, etc.) at the valve sealing surface area, i.e., the valve sealing surface and valve stem area, with a frame rate set according to the temperature change rate after medium injection to ensure timely capture of transient temperature change data and actual transient thermal map sequences. At the same time, deploy high-frequency pressure sensors (such as Keller pressure sensors) on the upper part of the upstream and downstream pipelines of the valve for collecting pressure decay curves after flow stop. The pressure decay anomaly determination method is as follows: if there is no leakage, the pressure decay curve is gently declining, and if there is leakage, the pressure decay curve shows a stepwise sharp decline.

[0056] During the medium injection process, the infrared thermal imager synchronously collects actual transient thermal map sequences and actual temperature change rate curves, and the pressure sensor monitors pressure changes in real time, providing multi-dimensional data support for subsequent leakage verification. The collected data is denoised using a wavelet denoising algorithm to obtain the true characteristics of temperature change.

[0057] Step S5: Abnormal identification: After aligning the transient thermal map sequences with the theoretical transient thermal map sequences in time sequence, difference analysis is performed on each corresponding frame. The difference analysis is performed through image recognition algorithms (such as edge detection, threshold segmentation, etc.) to identify abnormal temperature distribution areas of the sealing surface, i.e., parts where the actual temperature distribution significantly differs from the theoretical model. Compare the actual temperature change rate curve with the theoretical temperature change rate threshold range. When the actual temperature change rate exceeds the theoretical temperature change rate threshold range, identify the initial flow-through stage temperature change rate anomaly event.

[0058] The identification of the abnormal temperature distribution area of the sealing surface uses a time sequence intelligent algorithm to identify the abnormal temperature distribution area of the sealing surface, which specifically includes:

[0059] S5.1, use a long short-term memory network (LSTM) to train the temperature sampling sequence of the valve sealing area under historical non-leakage working conditions, extract key dynamic features during the medium injection stage, and establish a temperature change model during normal operation. The key dynamic features include: temperature change trend features, temperature change periodicity features, and temperature distribution spatial features, etc.

[0060] S5.2, use a dynamic time warping algorithm (DTW) to perform nonlinear time axis matching between the real-time collected temperature sequence and the standard transient response curve output by the LSTM, eliminate the time sequence phase shift caused by differences in valve operation speed (such as different opening or closing speeds), and make the real-time data comparable to the standard model.

[0061] The calculation formula of the dynamic time warping algorithm (DTW) is as follows:

[0062] Distance matrix formula: ;

[0063] wherein, represents the square of the difference between the i-th element of the real-time temperature sequence X and the j-th element of the standard temperature sequence Y, which is used to measure the difference between the corresponding elements of the two sequences; represents the i-th temperature value in the real-time temperature sequence X={ , , }; represents the i-th temperature value in the real-time temperature sequence Y={ , , }。

[0064] ;

[0065] wherein, represents the element in the i-th row and j-th column of the cumulative distance matrix, which is the minimum cumulative distance between the first element to the i-th element of the real-time sequence and the first element to the j-th element of the standard sequence; As described above, by iteratively calculating the cumulative distance matrix, the minimum cumulative distance of the two sequences is finally obtained, realizing the nonlinear matching of the time axis.

[0066] S5.3, calculate the absolute value of the point-by-point residual error of the standard sequence and the real-time sequence after dynamic time warping algorithm processing, when the absolute value of the residual error continuously exceeds the preset first temperature deviation threshold (such as 2℃) for more than the preset first duration threshold (such as 5 seconds), or the single-point residual error exceeds the preset second temperature deviation threshold (such as 5℃), mark it as a residual error abnormality marked period;

[0067] S5.4, perform spatiotemporal overlap analysis on the sealing surface temperature distribution abnormal area, temperature change rate abnormal event, and residual error abnormality marked period identified by difference between the actual transient thermal map sequence of the high-frame-rate infrared thermal imager and the theoretical transient thermal map sequence, if there is a spatiotemporal intersection among the three, and the sealing surface temperature distribution abnormal area is located within the valve sealing surface structure range, and the occurrence time of the temperature change rate abnormal event and the residual error abnormality marked period is earlier than the occurrence time of the pressure decay abnormality, then trigger the leakage judgment, improve the accuracy and reliability of the leakage identification.

[0068] Step S6: risk warning: according to the deviation degree and duration of the sealing surface temperature distribution abnormal area and the temperature change rate abnormal event, early leakage risk level warning is carried out in the initial stage of medium injection. The specific risk levels are as follows:

[0069] Potential micro-leakage level: the temperature change rate in the initial flow stage exceeds the threshold range, but no pressure decay is detected, indicating that there may be a slight leakage trend, but the leakage amount is small and has not caused obvious pressure changes. The valve status needs to be closely monitored.

[0070] Detectable leakage level: abnormal temperature change rate accompanied by abnormal pressure or flow, at this time the leakage is relatively obvious, which can be detected by pressure sensor or flow sensor, and inspection and repair need to be arranged in time.

[0071] Severe leakage level, the temperature gradient of the abnormal temperature area of the sealing surface exceeds the safety threshold, indicating that the leakage is serious, which may cause serious decline in valve performance, and even cause safety accidents, and immediate shutdown is required.

[0072] Step S7: model optimization: the actual collected transient data (such as temperature data, pressure data, flow data, etc.) are fed back to the simulation model, the differences between the actual data and the theoretical simulation results are analyzed, and the medium injection rate boundary conditions and the material transient thermal response parameters are corrected. For example, if the actual temperature change rate is higher than the theoretical value, it may be that the medium injection rate is not accurate or the material thermal conductivity coefficient needs to be adjusted. By correcting these parameters, the simulation model is closer to the actual operation, and the accuracy and reliability of subsequent monitoring are improved.

[0073] The above is only the preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can make equivalent replacements or changes to the technical solutions and inventive concepts of the present application within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A method of monitoring a valve for leaks, the method comprising: The application relates to a method for early leakage risk warning of a valve, and belongs to the technical field of valve leakage risk warning. S1, obtaining a valve geometry model to be detected, establishing a material physical property parameter library, and inputting medium initial injection rate and pressure-time working condition parameters of start-stop transient processes; S2, performing flow-solid-heat transient coupling simulation based on CFD and FEA software, generating a theoretical transient thermal force spectrum sequence and a theoretical temperature-time change curve of the medium after initial injection into the valve to be detected; The transient coupling simulation comprises: S2.1, setting a total simulation time length containing a medium injection intense exchange stage and a subsequent heat transfer stabilization stage, simulating in a first time step in the intense heat exchange stage and simulating in a second time step in the heat transfer stabilization stage, wherein the first time step is smaller than the second time step; S2.2, outputting a spatial cloud picture sequence of dynamic temperature gradient distribution based on a valve sealing surface area; S2.3, synchronously generating a curve graph of valve sealing surface area temperature change rate change with time; S2.4, corresponding the spatial cloud picture sequence of dynamic temperature gradient distribution and the temperature change rate curve graph along a time axis to construct a time-space associated benchmark data set; S3, extracting a theoretical temperature change interval threshold range and a theoretical temperature change rate threshold range based on simulation data in a time sequence, wherein the theoretical temperature change interval threshold range and the theoretical temperature change rate threshold range dynamically change with time in an initial flow stage; S4, deploying a high-frame-rate infrared thermal imager in the valve sealing surface area, and synchronously collecting an actual transient thermal force spectrum sequence and an actual temperature change rate curve after medium injection; S5, after aligning the actual transient thermal force spectrum sequence and the theoretical transient thermal force spectrum sequence in time sequence, performing differential analysis on each pair of corresponding frames to identify a sealing surface temperature distribution abnormal area; Comparing the actual temperature change rate curve with the theoretical temperature change rate threshold range to identify a temperature change rate abnormal event in the initial flow stage; S6, based on the sealing surface temperature distribution abnormal area and the temperature change rate abnormal event, early leakage risk warning is performed in an initial medium injection stage.

2. The method of claim 1, wherein, The material physical property parameter library in the step S1 comprises valve body material parameters and flow medium physical property parameters, the valve body material parameters comprise density, thermal conductivity and specific heat capacity, and the flow medium physical property parameters comprise viscosity, thermal expansion coefficient and specific heat capacity.

3. The method of claim 1, wherein, The step S2 further comprises: performing flow-solid-heat transient coupling simulation of the valve to be detected in different opening degrees.

4. The method of claim 1, wherein, The step S1 further comprises recording a cumulative running time length of the valve to be detected, and dynamically correcting material aging parameters according to a service life of the valve body to be detected.

5. The method of claim 1, wherein, In the step S3, in the initial flow stage, the temperature change rate threshold range is greater than a temperature change rate threshold range in a stable flow stage, and the temperature change rate threshold range gradually becomes smaller with time growth.

6. The method of claim 1, wherein, The step S4 further comprises: Deploying high-frequency pressure sensors on the upstream and downstream of the valve to collect pressure decay curves after flow stoppage; The step S5 combines pressure decay abnormality and temperature change rate abnormality to verify leakage.

7. The method of claim 1 or 6, wherein, In the step S5, the identification of the sealing surface temperature distribution abnormal area is performed by using a time sequence intelligent algorithm, which comprises: S5.1, training the temperature sampling sequence of the valve sealing area under the historical non-leakage working condition by using the long short-term memory network, and extracting the key dynamic characteristics of the medium injection stage; S5.2, performing nonlinear time axis matching on the real-time collected temperature sequence and the standard transient response curve output by the long short-term memory network through the dynamic time warping algorithm, and eliminating the timing phase offset caused by the difference in valve operation speed; S5.3, calculating the point-by-point residual absolute value of the standard sequence and the real-time sequence processed by the dynamic time warping algorithm, and recording the residual abnormal marker period when the residual absolute value continuously exceeds the preset first temperature deviation threshold for a time greater than the preset first duration threshold, or the single-point residual exceeds the preset second temperature deviation threshold; S5.4, performing spatiotemporal overlap analysis on the sealing surface temperature distribution abnormal area, temperature change rate abnormal event, and residual abnormal marker period identified by differentiating the actual transient thermal map sequence of the high-frame-rate infrared thermal imager and the theoretical transient thermal map sequence, if there is a spatiotemporal intersection among the three, and the sealing surface temperature distribution abnormal area is located within the valve sealing surface structure range, and the occurrence time of the temperature change rate abnormal event and the residual abnormal marker period is earlier than the occurrence time of the pressure decay abnormality, then triggering the leakage judgment.

8. The method of claim 1, wherein, In step S6, the leakage risk level includes: Potential micro-leakage level, the temperature change rate in the initial flow stage exceeds the threshold range, but no pressure decay is detected; Measurable leakage level, temperature change rate abnormality accompanied by pressure or flow abnormality; Severe leakage level, the temperature gradient of the sealing surface temperature abnormal area exceeds the safety threshold.

9. The method of claim 1, wherein, The method further comprises step S7, feeding back the actually collected transient data to the simulation model, and correcting the medium injection rate boundary adjustment and the material transient thermal response parameters.

Images