Real-time leakage monitoring system for high-pressure-resistant plastic butterfly valve

Abstract

The invention discloses a real-time leakage monitoring system for a high-pressure-resistant plastic butterfly valve. The real-time leakage monitoring system comprises an acquisition module, a physical analysis module, a fusion module and an early warning module, wherein the physical analysis module is used for carrying out a leakage test on the high-pressure-resistant plastic butterfly valve through physical and mechanical analysis; and the fusion module is used for performing deviation calculation on the static health benchmark, the dynamic health benchmark, the strain health benchmark, the quiet benchmark and the health torque benchmark, and obtaining specific performance characteristics in each leakage state through a linear equation set and double-cosine finite integral transformation. Aiming at the material characteristics of the high-pressure-resistant plastic butterfly valve, a multi-dimensional and refined health reference system is constructed; an advanced mathematical model based on multi-sensor data fusion, a linear equation set and double-cosine finite integral transformation is introduced, and accurate recognition, quantification and physical characteristic representation of the leakage state are achieved; and the sealing performance can be evaluated under a non-fluid working condition, so that a comprehensive and intelligent real-time leakage monitoring scheme is provided.

Description

Technical Field

[0001] This invention relates to the technical field of leakage monitoring, and more particularly to a real-time leakage monitoring system for high-pressure resistant plastic butterfly valves. Background Technology

[0002] Leakage inevitably involves changes in the physical state (force, deformation, sound, vibration) of the valve and the surrounding fluid. Real-time early warning of leaks can be achieved by monitoring anomalies in these physical quantities. Acoustic signals provide direct evidence of leakage, while torque and strain signals provide context and causal evidence, avoiding false alarms from single sensors caused by external vibration sources. Before a leak actually occurs, monitoring slow changes in torque and strain provides early warning of potential risks, transforming unplanned downtime into planned maintenance. From initial health documentation during installation to performance degradation tracking during operation, and finally to failure alarms, comprehensive management of valve health is achieved.

[0003] Currently, Chinese invention patent application number CN202510299365.7 discloses a valve monitoring method, device, storage medium, and electronic device. The method includes: determining a pipeline distribution map for the transmission of supercritical carbon dioxide between the capture equipment and the storage well; identifying multiple valves to be monitored in the pipeline distribution map; acquiring real-time data collected by detection sensing components at multiple valves, and assessing the target probability of leakage for each valve based on the real-time data; comparing the target probability with a preset leakage probability, and determining the monitoring result based on the comparison result. This technical solution solves the problem of low efficiency in detecting leakage at valves connected to pipelines during transmission in related technologies. Traditional leakage detection methods are often insensitive to minute leaks and fail to detect them in a timely manner. Especially for high-pressure plastic butterfly valves, deformation and leakage may occur internally and are difficult to detect. Leakage can lead to media loss, environmental pollution, safety accidents, and equipment damage. The elastic modulus of plastic materials is much lower than that of metals, making them prone to significant deformation under high pressure. If this deformation exceeds the design range, it can disrupt the fit between the butterfly plate and the valve seat, ultimately leading to sealing failure and leakage. Monitoring this deformation during valve operation and determining whether it will lead to leakage is a challenge. The sealing performance of a butterfly valve is highly dependent on the integrity and resilience of the valve seat. Over time, the valve seat may age, wear, or be eroded by the medium, rendering it unable to provide sufficient sealing force and ultimately causing leakage. Valve operation involves multiple physical quantities, and data from different sensors are often isolated and difficult to analyze comprehensively, resulting in an inability to fully assess the valve's condition. Summary of the Invention

[0004] The technical problem addressed by this invention is that traditional leak detection methods are often insensitive to minute leaks, leading to delayed detection. This is especially true for high-pressure plastic butterfly valves, where deformation and leakage can occur internally and are difficult to detect. Leaks can result in media loss, environmental pollution, safety accidents, and equipment damage. The elastic modulus of plastic materials is much lower than that of metals, making them prone to significant deformation under high pressure. If this deformation exceeds the design range, it can disrupt the fit between the butterfly plate and the valve seat, ultimately causing seal failure and leakage. Monitoring this deformation during valve operation and determining whether it will lead to leakage is a challenge. The sealing performance of butterfly valves is highly dependent on the integrity and elasticity of the valve seat. Long-term use can cause the valve seat to age, wear, or be eroded by the media, rendering it unable to provide sufficient sealing force and ultimately causing leakage. Valve operation involves multiple physical quantities, and data from different sensors are often isolated, making comprehensive analysis difficult and hindering a complete assessment of the valve's condition.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a real-time leakage monitoring system for high-pressure resistant plastic butterfly valves, comprising a data acquisition module, a physical analysis module, a fusion module, and an early warning module. The acquisition module is used to acquire structural information and leakage status of the high-pressure resistant plastic butterfly valve; The physical analysis module is used to perform leakage tests on high-pressure resistant plastic butterfly valves through physical and mechanical analysis. The fusion module is used to calculate the deviation of static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark and health torque benchmark, and obtain the specific performance characteristics of each leakage state through linear equation system and bicosine finite integral transformation; The early warning module is used to display various monitoring data of the valve in real time on the user interface.

[0006] Preferably, the acquisition module includes: The structural information and leakage status of the high-pressure resistant plastic butterfly valve are collected in real time through strain sensor group, vibration sensor, torque sensor, pressure sensor and valve position sensor, and all sensors are connected to collect sensor signals synchronously. The structural information includes the valve body, butterfly plate, valve seat, and valve stem; The leakage state includes structural deformation, hydrodynamic state changes, and operational mechanical state changes. Structural deformation includes stress concentration, hydrodynamic state changes include turbulence and acoustic vibration, and operational mechanical state changes include torque changes.

[0007] Preferably, a static health baseline is established, and the establishment process includes: Completely close the butterfly valve and apply normal working pressure upstream of the valve. Collect the current strain reference and acoustic reference. The strain reference includes the readings of each strain gauge at this time, and the acoustic reference includes the signal amplitude of the acoustic sensor at this time. Establish dynamic health benchmarks. The process includes: Under pressure, the valve is operated completely for several cycles from fully open to fully closed, and the torque-valve position curve is recorded synchronously throughout the entire valve closing process. The peak torque within the last 5° of the valve closing stroke is extracted from the torque-valve position curve. The peak torque represents the maximum torque required when the healthy sealing ring is normally compressed. The static health benchmark and dynamic health benchmark are stored in the butterfly valve judgment standard database.

[0008] Preferably, the analysis module includes a strain monitoring unit, a high-frequency vibration monitoring unit, and a valve closing torque monitoring unit: The strain monitoring unit includes: The strain values ​​of the measuring points on the valve body, including the center of the back of the butterfly plate, the outer side of the valve body at the connection between the valve body and the pipeline flange, and both sides of the valve stem, are monitored in the high-pressure resistant plastic butterfly valve. The monitoring process includes: On new valves or valves known to be in good condition, measure the strain values ​​at the center of the back of the butterfly plate, the outer side of the valve body at the connection between the valve body and the pipeline flange, and both sides of the valve stem on the valve body of the high-pressure resistant plastic butterfly valve under normal operating pressure, and use the strain values ​​as the strain health baseline. The strain value of the high-pressure resistant plastic butterfly valve is monitored in real time. When the strain value increases at a constant rate for a duration exceeding a preset time threshold, or increases at a rate exceeding a preset speed threshold, or the strain value exceeds a preset safety threshold, it indicates that the high-pressure resistant plastic butterfly valve is in a state of structural deformation and leakage.

[0009] Preferably, the high-frequency vibration monitoring unit includes: The monitoring process involves monitoring acoustic emission sensor data at measurement points on the valve body and pipeline downstream of the valve. When the valve is confirmed to be tightly closed, the amplitude of background noise vibration is measured and used as the quiet baseline. The vibration signal of the high-pressure resistant plastic butterfly valve is continuously monitored. When the amplitude of the signal within the preset frequency range is higher than the quiet baseline for more than a preset time threshold, it indicates that the fluid in the high-pressure resistant plastic butterfly valve is in a leakage state with changing dynamic state. The strength of the signal is positively correlated with the severity of the leakage.

[0010] Preferably, the valve closing torque monitoring unit includes: The drive current at a measuring point on the actuator that drives the valve stem is monitored; the drive current is proportional to the torque. Record the torque-angle curve of a new valve or a known intact valve from opening to complete closing under standard operating conditions. Use the torque-angle curve as a healthy torque benchmark. Record a new torque-angle curve for each valve closing operation. If the peak torque during the valve closing process decreases or increases by more than the preset peak torque threshold ratio compared to the healthy torque benchmark of the corresponding valve closing reading, it indicates that the high-pressure resistant plastic butterfly valve is in a leakage state due to changes in its operating mechanical state.

[0011] Preferably, the fusion module includes: The static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark, and healthy torque benchmark are standardized using Min-Max to obtain benchmark standard values. Real-time sensor signal acquisition and standardization are performed, and the deviation between the standardized value of the sensor signal acquisition result and the benchmark standard value is calculated. All benchmark standard values ​​are combined into a deviation vector. The deviation vector is used as the right-hand side of the linear equation system to solve the linear equation system, obtaining the valve state combination solution. The valve state combination solution is then subjected to a double cosine finite integral transformation under various leakage states. The upper and lower limits of the leakage state due to structural deformation include the minimum and maximum values ​​of strain and the monitoring time. The upper and lower limits of the leakage state due to changes in fluid dynamic state include the minimum and maximum values ​​of vibration signal amplitude and the monitoring time. The upper and lower limits of the leakage state due to changes in operational mechanical state include the minimum and maximum peak values ​​of the torque-angle curve and the monitoring time.

[0012] Preferably, the unknowns of the linear equation system correspond to the characteristic values ​​of the abnormal sensor signal data quantities for each leakage state corresponding to the static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark, and healthy torque benchmark.

[0013] Preferably, the linear equations are solved by Gaussian elimination to obtain the valve state combination solution under each leakage state. The valve state combination solution represents the degree of deviation of the current valve state from the health benchmark. The valve state combination solution is then inversely transformed back to the physical space according to the inverse transformation formula of the double cosine finite integral to obtain the specific performance characteristics of each leakage state in the physical space. The specific performance characteristics include the sensor signal data under each leakage state.

[0014] Preferably, the various monitoring data of the valve are displayed in real time on the user interface. An alarm is triggered based on the leakage judgment result, and a leakage diagnosis report is generated. The leakage diagnosis report includes the leakage type, occurrence time, severity, and data trend graph, and stores all raw data, baseline data, standardized data, deviation data, and alarm results.

[0015] The beneficial effects of this invention are as follows: This application explicitly points out that plastic valves have characteristics such as low elastic modulus, significant deformation under high pressure, and easy creep. The system design fully considers these unique challenges of plastic materials, distinguishing it from metal valve monitoring. The system can establish a benchmark under high pressure and perform real-time monitoring, ensuring effectiveness in actual working environments. Multi-dimensional health benchmarks are established, obtained through rigorous testing under valve health conditions, providing quantitative reference points for subsequent real-time monitoring, allowing for precise calculation of valve state deviations. Data from multiple sensors, including strain, vibration, torque, pressure, and valve position, are integrated to achieve comprehensive monitoring of structural deformation, changes in hydrodynamic state, and changes in operational mechanics. Deviation calculations are performed between real-time acquired data and standardized health benchmarks to quantify the degree of valve state anomaly. The standardized deviation is used as input to a system of linear equations to obtain a "valve state combination solution," representing the degree of deviation between the current valve state and the health benchmark. The system employs a double cosine finite integral transform on the "valve state combination solution" and then inversely transforms it back to physical space to obtain the specific characteristics of each leakage state in physical space (e.g., the combination manifests as real-time deflection / deformation field). This achieves the transformation and quantification from abstract data to physical meaning. The system can identify and distinguish leaks caused by structural deformation, changes in hydrodynamic state, and changes in operational mechanics state, and sets specific discrimination criteria for each type. It not only detects leaks but also, through inverse transformation of the mathematical model back to physical space, performs deeper diagnosis and quantification of the type, severity, and location of the leak (via specific measuring points), such as sensitivity to minute leaks. Attached Figure Description

[0016] Figure 1 This is a basic flowchart of a real-time leakage monitoring system for a high-pressure resistant plastic butterfly valve provided in one embodiment of the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0018] Reference Figure 1 As one embodiment of the present invention, a real-time leakage monitoring system for high-pressure resistant plastic butterfly valves is provided, including a data acquisition module, a physical analysis module, a fusion module, and an early warning module: The acquisition module is used to acquire structural information and leakage status of the high-pressure resistant plastic butterfly valve; The physical analysis module is used to perform leakage tests on high-pressure resistant plastic butterfly valves through physical and mechanical analysis. The fusion module is used to calculate the deviation of static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark and health torque benchmark, and obtain the specific performance characteristics of each leakage state through linear equation system and bicosine finite integral transformation; The early warning module is used to display various monitoring data of the valve in real time on the user interface.

[0019] Based on the material properties of high-pressure resistant plastic butterfly valves, a multi-dimensional and refined health benchmark system was constructed. An advanced mathematical model based on multi-sensor data fusion, linear equations, and bicosine finite integral transformation was introduced to achieve accurate identification, quantification, and physical characterization of leakage status. It also has the ability to evaluate sealing performance under non-fluid conditions, thus providing a comprehensive and intelligent real-time leakage monitoring and diagnosis solution.

[0020] The acquisition module includes: The structural information and leakage status of the high-pressure resistant plastic butterfly valve are collected in real time through strain sensor group, vibration sensor, torque sensor, pressure sensor and valve position sensor, and all sensors are connected to collect sensor signals synchronously. The structural information includes the valve body, butterfly plate, valve seat, and valve stem; The leakage state includes structural deformation, hydrodynamic state changes, and operational mechanical state changes. Structural deformation includes stress concentration, hydrodynamic state changes include turbulence and acoustic vibration, and operational mechanical state changes include torque changes.

[0021] The valve body serves as the base for the overall structure, bearing the pressure of the pipeline and the corrosion of the medium. The butterfly plate is in direct contact with the fluid and bears the pressure difference between the positive and negative directions. It is the main throttling and pressure-bearing component. Under high pressure, the butterfly plate will bend and deform. The valve seat is the key to sealing. When the butterfly plate is closed, it fits tightly with the valve seat to form a seal. Plastic butterfly valves use elastic or soft sealing materials, and their compression, uniformity, and material state directly determine the sealing performance. The valve stem is used to transmit torque and drive the butterfly plate to rotate. The connection between the valve stem and the valve body is also a potential leakage point. Structural deformation is particularly important for high-pressure resistant plastic butterfly valves. The elastic modulus of plastic is much lower than that of metal, and its deformation will be very significant under high pressure. When the deformation of the valve body or butterfly plate exceeds the design allowable range, the fit geometry between the butterfly plate and the valve seat is destroyed, the seal fails, and leakage occurs.

[0022] The analysis of fluid dynamic state changes mainly focuses on cavitation, which is essentially caused by the local fluid pressure being lower than the vaporization pressure. When a butterfly valve experiences a minor leak, the high-pressure fluid will pass through the narrow leak channel (such as the gap between the butterfly plate and the valve seat) at extremely high speed, forming a high-speed jet. This process generates high-frequency vibrations and acoustic emissions. The high-frequency vibrations include the jet impacting the downstream pipe wall and valve body, while the acoustic emissions include intense turbulence and the possible collapse of cavitation bubbles, which will emit high-frequency noise.

[0023] Torque variation indicates that the friction of the sealing surface is an important component of torque. If the valve seat is damaged or ages and loses its elasticity, the support and friction provided by the valve seat will decrease, resulting in an abnormally low torque at the end of the valve closure.

[0024] Establishing static health benchmarks involves the following process: Completely close the butterfly valve and apply normal working pressure upstream of the valve. In this embodiment, apply 80%-100% of the nominal pressure and collect the current strain reference and acoustic reference. The strain reference includes the readings of each strain gauge at this time, representing the normal deformation of a healthy valve body under high pressure. The acoustic reference includes the signal amplitude of the acoustic sensor at this time. In a leak-free valve, this value should be extremely low background noise. Establish dynamic health benchmarks. The process includes: Under pressure, the valve is operated completely for several cycles from fully open to fully closed, and the torque-valve position curve is recorded synchronously throughout the entire valve closing process. The peak torque within the last 5° of the valve closing stroke is extracted from the torque-valve position curve. The peak torque represents the maximum torque required when the healthy sealing ring is normally compressed. The static health benchmark and dynamic health benchmark are stored in the butterfly valve judgment standard database.

[0025] The analysis module includes a strain monitoring unit, a high-frequency vibration monitoring unit, and a valve closing torque monitoring unit. The strain monitoring unit includes: The strain values ​​of the measuring points on the valve body, including the center of the back of the butterfly plate, the outer side of the valve body at the connection between the valve body and the pipeline flange, and both sides of the valve stem, are monitored in the high-pressure resistant plastic butterfly valve. The monitoring process includes: On new valves or valves known to be in good condition, measure the strain values ​​at the center of the back of the butterfly plate, the outer side of the valve body at the connection between the valve body and the pipeline flange, and both sides of the valve stem on the valve body of the high-pressure resistant plastic butterfly valve under normal operating pressure, and use the strain values ​​as the strain health baseline. The strain value of the high-pressure resistant plastic butterfly valve is monitored in real time. When the strain value increases at a constant rate for a duration exceeding a preset time threshold, or increases at a rate exceeding a preset speed threshold, or the strain value exceeds a preset safety threshold, it indicates that the high-pressure resistant plastic butterfly valve is in a state of structural deformation and leakage.

[0026] High pressure is the normal operating condition for butterfly valves, which will cause them to undergo a certain amount of elastic deformation. This deformation is stable and predictable within the normal range. If the valve material experiences fatigue, creep (a typical characteristic of plastics), or microcracks, its stiffness will decrease, leading to greater strain (deformation) under the same pressure. This abnormal deformation is an important precursor to leakage.

[0027] The center of the back of the butterfly plate is the position that bears the greatest pressure from the medium and has the most significant bending deformation. The outer side of the connection between the valve body and the pipeline flange is a high stress concentration area. Monitoring the valve body position on both sides of the valve stem is to monitor whether the valve body is stretched open under high pressure, causing deformation of the valve stem hole.

[0028] The high-frequency vibration monitoring unit includes: The monitoring process involves monitoring acoustic emission sensor data at measurement points on the valve body and pipeline downstream of the valve. When the valve is confirmed to be tightly closed, the amplitude of background noise vibration is measured and used as the quiet baseline. The vibration signal of the high-pressure resistant plastic butterfly valve is continuously monitored. When the amplitude of the signal within the preset frequency range is higher than the quiet baseline for more than a preset time threshold, it indicates that the fluid in the high-pressure resistant plastic butterfly valve is in a leakage state with changing dynamic state. The strength of the signal is positively correlated with the severity of the leakage.

[0029] Because the direction of the leakage jet is towards the low-pressure side (downstream), the signal on the valve body and pipeline downstream of the valve is the strongest and clearest; A properly closed valve should have a still or nearly still internal fluid with very low background noise. In the event of a leak, high-pressure media will be ejected from the tiny gap, creating intense turbulence and shear flow. This process generates high-frequency sound waves and vibrations that are difficult for the human ear to hear but can be clearly detected by sensors.

[0030] It is extremely sensitive to minute leaks and has a fast response speed, making it the most direct method to determine whether a leak is in progress. The high-speed jet generated by the leak has a similar physical mechanism to cavitation in inducing acoustic vibration.

[0031] The valve closing torque monitoring unit includes: The sealing of a butterfly valve depends on the last few degrees of its closing stroke, especially for eccentric butterfly valves. At this point, the butterfly plate squeezes the valve seat, generating a huge sealing force and corresponding friction. The peak torque of this force is something the actuator must overcome. If the valve seat loses its elasticity or is partially missing due to aging, damage, or erosion by the medium, the butterfly plate cannot be effectively supported, the squeezing stroke will soften, and the peak torque required for sealing will decrease significantly.

[0032] The drive current at a measuring point on the actuator that drives the valve stem is monitored; the drive current is proportional to the torque. Record the torque-angle curve of a new valve or a known intact valve from opening to full closing under standard operating conditions, paying particular attention to the peak torque in the last 5-10 degrees of valve closing stroke. Use the torque-angle curve as a healthy torque benchmark, and record a new torque-angle curve for each valve closing operation. If the peak torque during the valve closing process decreases or increases by more than the preset peak torque threshold ratio compared to the healthy torque benchmark corresponding to the valve closing reading, for example, by more than 30%, it indicates that the high-pressure resistant plastic butterfly valve is in a leakage state due to changes in the operating mechanical state. If the torque decreases abnormally, the valve seat may be damaged or excessively worn, unable to provide sufficient sealing force. Conversely, if the torque increases abnormally, it may indicate that impurities are stuck or components are seized. The health of the sealing system can be assessed by observing the valve's operation itself without using fluid.

[0033] The fusion module includes: The static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark, and healthy torque benchmark are standardized using Min-Max to obtain benchmark standard values. Real-time sensor signal acquisition and standardization are performed, and the deviation between the standardized value of the sensor signal acquisition result and the benchmark standard value is calculated. All benchmark standard values ​​are combined into a deviation vector. The deviation vector is used as the right-hand side of the linear equation system to solve the linear equation system, obtaining the valve state combination solution. The valve state combination solution is then subjected to a double cosine finite integral transformation under various leakage states. The upper and lower limits of the leakage state due to structural deformation include the minimum and maximum values ​​of strain and the monitoring time. The upper and lower limits of the leakage state due to changes in fluid dynamic state include the minimum and maximum values ​​of vibration signal amplitude and the monitoring time. The upper and lower limits of the leakage state due to changes in operational mechanical state include the minimum and maximum peak values ​​of the torque-angle curve and the monitoring time.

[0034] The linear equation system is in the form Ax=b, where b is the deviation vector, x is the unknown vector to be solved, and A is the characteristic coefficient matrix. Solving the linear equation system yields the valve state combination solution x. This x vector represents the degree of deviation of the current valve state from the health baseline or the contribution coefficient of each leakage mode in the feature space defined by the double cosine finite integral transformation. Each component of the unknown x in the linear equation system corresponds to the valve state combination solution in the feature space established by the double cosine finite integral transformation under each leakage state, so as to further map it to a more physically meaningful leakage feature dimension. Each component of the unknown x in the linear equation system corresponds to the characteristic coefficients of the abnormal manifestations of each leakage state (structural deformation, hydrodynamic state change, operational mechanical state change) in the characteristic space established by the double cosine finite integral transformation. The characteristic space is the static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark and health torque benchmark, respectively or mutually related to each other.

[0035] The characteristic coefficient matrix A is a pre-established characteristic mapping matrix. Its dimensions are determined according to the sensor type, number, and number of defined leakage modes. The matrix is ​​established by conducting controlled tests on a large number of healthy valves and valves with different degrees and types of leakage, collecting sensor data under various operating conditions, and training or determining it using feature engineering and statistical analysis methods. The characteristic coefficient matrix A characterizes the linear coupling relationship between different leakage modes or features on the measurement deviation of each sensor. Statistical analysis methods include principal component analysis and linear regression analysis. In a controlled experimental environment, different pressures were applied to known healthy valves and valves simulating different locations, degrees, and types of leakage. Complete datasets from all sensors were collected, including data on strain, vibration, torque, pressure, and valve position. All collected data (including healthy baseline and leakage data) were Min-Max standardized, and the standardized deviation vector of each leakage state sample relative to its corresponding healthy baseline was calculated. Multivariate statistical methods such as PCA or linear regression analysis were applied to analyze the mapping relationship between these deviation vectors and preset leakage modes (structural deformation, hydrodynamic changes, operational mechanics changes). For example, PCA can identify the main directions of change in the deviation vectors, which may correspond to specific leakage modes; or, through multiple linear regression, the deviation vector can be used as the independent variable, and the severity or eigenvalue of the preset leakage mode as the dependent variable, and the resulting regression coefficient matrix can be used as the characteristic coefficient matrix A.

[0036] For example, the transformation quantity related to deflection can be extracted from the valve state combination solution, and the inverse transformation can be performed to obtain the real-time deflection or deformation field in physical space.

[0037] The health status of the valve is defined as a set of benchmark values. Any deviation of real-time monitoring data from these benchmarks is considered an abnormal signal. After standardization, these abnormal signals are used as the right-hand input of a linear equation system characterizing the current state of the valve. Solving this linear equation system yields a combined solution of the valve state in the frequency domain. This solution represents the degree of deviation of the current valve state from the health benchmark. Finally, this combined solution is inversely transformed back to the physical space and compared with a preset leakage threshold to identify and quantify the leakage state.

[0038] Multi-dimensional health benchmarks were established. These benchmarks were obtained through rigorous testing under the valve's health condition, providing quantitative reference points for subsequent real-time monitoring, and enabling the deviation of the valve's condition to be calculated accurately.

[0039] The unknowns of the linear equation system correspond to the characteristic values ​​of the abnormal sensor signal data quantities for each leakage state corresponding to the static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark, and healthy torque benchmark.

[0040] The linear equations are solved by Gaussian elimination to obtain the valve state combination solution under each leakage state. The valve state combination solution represents the degree of deviation of the current valve state from the health benchmark. The valve state combination solution is inversely transformed back to the physical space according to the double cosine finite integral inverse transform formula to obtain the specific performance characteristics of each leakage state in the physical space.

[0041] For example, the transformation quantity related to deflection can be extracted from the valve state combination solution, and the inverse transformation can be performed to obtain the real-time deflection / deformation field in physical space.

[0042] The valve's health status is defined by a set of benchmark values. Any deviation of real-time monitoring data from these benchmarks is considered an anomaly signal. These anomaly signals, after standardization, serve as the right-hand input to a system of linear equations characterizing the valve's current state. Solving this system of linear equations yields a combined solution of the valve's state in the frequency domain, representing the degree of deviation between the valve's current state and the health benchmarks. Finally, this combined solution is inversely transformed back to physical space and compared with a preset leakage threshold to identify and quantify the leakage state.

[0043] The system displays various monitoring data of the valve in real time on the user interface, triggers alarms of different levels based on the leakage judgment results, generates detailed leakage diagnosis reports, including leakage type, occurrence time, severity and data trend graphs, and stores all raw data, baseline data, standardized data, deviation data and judgment results.

[0044] This application explicitly points out the characteristics of plastic valves, such as low elastic modulus, significant deformation under high pressure, and easy creep. The system design fully considers these unique challenges of plastic materials, distinguishing it from metal valve monitoring. The system can establish benchmarks and perform real-time monitoring under high pressure, ensuring effectiveness in actual working environments. It includes not only static health benchmarks (strain, acoustics) but also dynamic health benchmarks (torque-valve position curves and peak torque during operating cycles), strain health benchmarks, and quietness benchmarks, constructing a multi-dimensional healthy valve behavior model. The establishment process of static and dynamic benchmarks is described in detail, such as collecting strain / acoustic data under pressure with the valve fully closed, and recording torque-valve position curves under pressure with full-open and full-close cycles, making the benchmarks more operable and accurate. It integrates data from multiple sensors, including strain, vibration, torque, pressure, and valve position, to achieve comprehensive monitoring of structural deformation, changes in hydrodynamic state, and changes in operational mechanics. The deviation between the real-time acquired data and the standardized health benchmarks is calculated to quantify the degree of valve state anomaly. The standardized deviation is used as input to a system of linear equations to obtain a "valve state combination solution," representing the degree of deviation between the current valve state and the health benchmark. The system employs a double cosine finite integral transform on the "valve state combination solution" and then inversely transforms it back to physical space to obtain the specific characteristics of each leakage state in physical space (such as real-time deflection / deformation field). This achieves the transformation and quantification from abstract data to physical meaning. The system can identify and distinguish leaks caused by structural deformation, changes in hydrodynamic state, and changes in operational mechanics state, and sets specific discrimination criteria for each type. It not only detects leaks but also performs a deeper diagnosis and quantification of the type, severity, and location of the leak (through specific measuring points) through inverse transformation of the mathematical model back to physical space, such as sensitivity to minute leaks.

[0045] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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 can 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 Red-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 storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0046] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A real-time leakage monitoring system for high-pressure resistant plastic butterfly valves, characterized in that, It includes a data acquisition module, a physical analysis module, a data fusion module, and an early warning module. The acquisition module is used to acquire structural information and leakage status of the high-pressure resistant plastic butterfly valve; The physical analysis module is used to perform leakage tests on high-pressure resistant plastic butterfly valves through physical and mechanical analysis. The fusion module is used to calculate the deviation of static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark and health torque benchmark, and obtain the specific performance characteristics of each leakage state through linear equation system and bicosine finite integral transformation; The early warning module is used to display various monitoring data of the valve in real time on the user interface.

2. The real-time leakage monitoring system for high-pressure resistant plastic butterfly valves as described in claim 1, characterized in that, The acquisition module includes: The structural information and leakage status of the high-pressure resistant plastic butterfly valve are collected in real time through strain sensor group, vibration sensor, torque sensor, pressure sensor and valve position sensor, and all sensors are connected to collect sensor signals synchronously. The structural information includes the valve body, butterfly plate, valve seat, and valve stem; The leakage state includes structural deformation, hydrodynamic state changes, and operational mechanical state changes. Structural deformation includes stress concentration, hydrodynamic state changes include turbulence and acoustic vibration, and operational mechanical state changes include torque changes.

3. The real-time leakage monitoring system for high-pressure resistant plastic butterfly valves as described in claim 2, characterized in that: Establishing static health benchmarks involves the following process: Completely close the butterfly valve and apply normal working pressure upstream of the valve. Collect the current strain reference and acoustic reference. The strain reference includes the readings of each strain gauge at this time, and the acoustic reference includes the signal amplitude of the acoustic sensor at this time. Establish dynamic health benchmarks. The process includes: Under pressure, the valve is operated completely for several cycles from fully open to fully closed, and the torque-valve position curve is recorded synchronously throughout the entire valve closing process. The peak torque within the last 5° of the valve closing stroke is extracted from the torque-valve position curve. The peak torque represents the maximum torque required when the healthy sealing ring is normally compressed. The static health benchmark and dynamic health benchmark are stored in the butterfly valve judgment standard database.

4. The real-time leakage monitoring system for high-pressure resistant plastic butterfly valves as described in claim 3, characterized in that, The analysis module includes a strain monitoring unit, a high-frequency vibration monitoring unit, and a valve closing torque monitoring unit. The strain monitoring unit includes: The strain values ​​of the measuring points on the valve body, including the center of the back of the butterfly plate, the outer side of the valve body at the connection between the valve body and the pipeline flange, and both sides of the valve stem, are monitored in the high-pressure resistant plastic butterfly valve. The monitoring process includes: On new valves or valves known to be in good condition, measure the strain values ​​at the center of the back of the butterfly plate, the outer side of the valve body at the connection between the valve body and the pipeline flange, and both sides of the valve stem on the valve body of the high-pressure resistant plastic butterfly valve under normal operating pressure, and use the strain values ​​as the strain health baseline. The strain value of the high-pressure resistant plastic butterfly valve is monitored in real time. When the strain value increases at a constant rate for a duration exceeding a preset time threshold, or increases at a rate exceeding a preset speed threshold, or the strain value exceeds a preset safety threshold, it indicates that the high-pressure resistant plastic butterfly valve is in a state of structural deformation and leakage.

5. The real-time leakage monitoring system for high-pressure resistant plastic butterfly valves as described in claim 4, characterized in that, The high-frequency vibration monitoring unit includes: The monitoring process involves monitoring acoustic emission sensor data at measurement points on the valve body and pipeline downstream of the valve. When the valve is confirmed to be tightly closed, the amplitude of background noise vibration is measured and used as the quiet baseline. The vibration signal of the high-pressure resistant plastic butterfly valve is continuously monitored. When the amplitude of the signal within the preset frequency range is higher than the quiet baseline for more than a preset time threshold, it indicates that the fluid in the high-pressure resistant plastic butterfly valve is in a leakage state with changing dynamic state. The strength of the signal is positively correlated with the severity of the leakage.

6. The real-time leakage monitoring system for high-pressure resistant plastic butterfly valves as described in claim 5, characterized in that, The valve closing torque monitoring unit includes: The drive current at a measuring point on the actuator that drives the valve stem is monitored; the drive current is proportional to the torque. Record the torque-angle curve of a new valve or a known intact valve from opening to complete closing under standard operating conditions. Use the torque-angle curve as a healthy torque benchmark. Record a new torque-angle curve for each valve closing operation. If the peak torque during the valve closing process decreases or increases by more than the preset peak torque threshold ratio compared to the healthy torque benchmark of the corresponding valve closing reading, it indicates that the high-pressure resistant plastic butterfly valve is in a leakage state due to changes in its operating mechanical state.

7. The real-time leakage monitoring system for high-pressure resistant plastic butterfly valves as described in claim 6, characterized in that, The fusion module includes: The static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark, and healthy torque benchmark are standardized using Min-Max to obtain benchmark standard values. Real-time sensor signal acquisition and standardization are performed, and the deviation between the standardized value of the sensor signal acquisition result and the benchmark standard value is calculated. All benchmark standard values ​​are combined into a deviation vector. The deviation vector is used as the right-hand side of the linear equation system to solve the linear equation system, obtaining the valve state combination solution. The valve state combination solution is then subjected to a double cosine finite integral transformation under various leakage states. The upper and lower limits of the leakage state due to structural deformation include the minimum and maximum values ​​of strain and the monitoring time. The upper and lower limits of the leakage state due to changes in fluid dynamic state include the minimum and maximum values ​​of vibration signal amplitude and the monitoring time. The upper and lower limits of the leakage state due to changes in operational mechanical state include the minimum and maximum peak values ​​of the torque-angle curve and the monitoring time.

8. The real-time leakage monitoring system for high-pressure resistant plastic butterfly valves as described in claim 7, characterized in that: The unknowns of the linear equation system correspond to the characteristic values ​​of the abnormal sensor signal data quantities for each leakage state corresponding to the static health benchmark, dynamic health benchmark, strain health benchmark, quiet benchmark, and healthy torque benchmark.

9. The real-time leakage monitoring system for high-pressure resistant plastic butterfly valves as described in claim 8, characterized in that: The linear equations are solved by Gaussian elimination to obtain the valve state combination solution under each leakage state. The valve state combination solution represents the degree of deviation of the current valve state from the health benchmark. The valve state combination solution is inversely transformed back to the physical space according to the inverse transformation formula of the double cosine finite integral to obtain the specific performance characteristics of each leakage state in the physical space. The specific performance characteristics include the sensor signal data under each leakage state.

10. The real-time leakage monitoring system for high-pressure resistant plastic butterfly valves as described in claim 9, characterized in that, The system displays various monitoring data of the valve in real time on the user interface, triggers alarms based on leakage judgment results, and generates a leakage diagnosis report. The leakage diagnosis report includes leakage type, occurrence time, severity, and data trend graph, and stores all raw data, baseline data, standardized data, deviation data, and alarm results.

Images