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

Abstract

The application discloses a high-pressure-resistant plastic butterfly valve real-time leakage monitoring system, comprising a collection module, a physical analysis module, a fusion module and an early warning module: the physical analysis module is used for conducting leakage test on the high-pressure-resistant plastic butterfly valve through physical mechanics analysis; the fusion module is used for carrying out deviation calculation on the static health benchmark, the dynamic health benchmark, the strain health benchmark line, the quiet benchmark line and the health torque benchmark, and obtaining specific performance characteristics in each leakage state through linear equation set and double-cosine finite integral inverse transformation. A multi-dimensional and refined health benchmark system is constructed according to the material characteristics of the high-pressure-resistant plastic butterfly valve; an advanced mathematical model based on multi-sensor data fusion, linear equation set and double-cosine finite integral inverse transformation is introduced, accurate identification, quantification and physical characteristic representation of the leakage state are realized, and the evaluation ability of the sealing performance under non-fluid working conditions is also possessed, so that a comprehensive and intelligent real-time leakage monitoring scheme is provided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of leakage monitoring, and in particular to a real-time leakage monitoring system for high-pressure plastic butterfly valves. BACKGROUND

[0002] The occurrence of leakage is inevitably accompanied by changes in the physical state (force, deformation, sound, vibration) of the valve and its surrounding fluid. By monitoring the abnormalities of these physical quantities, real-time early warning of leakage can be achieved. Acoustic signals are direct evidence of leakage, while torque and strain signals provide context and evidence of the cause, avoiding false positives from external vibration sources and the like. By monitoring the slow changes in torque and strain before the actual occurrence of leakage, potential risks can be warned in advance, and unplanned shutdowns can be converted into planned maintenance. From the initial health documentation of installation to the performance degradation tracking during operation, and finally to the failure alarm, the overall management of the health of the valve is achieved.

[0003] At present, the Chinese invention patent with the application number CN202510299365.7 discloses a valve monitoring method, device, storage medium and electronic device. The method comprises: determining a pipeline distribution map for transmitting supercritical carbon dioxide between a trapping device and a storage wellbore; identifying a plurality of valves to be monitored in the pipeline distribution map; acquiring real-time data collected by detection sensor assemblies at the plurality of valves, and evaluating the target probability of each valve occurring a leakage based on the real-time data; comparing the target probability with a preset leakage probability, and determining a monitoring result according to the comparison result. By adopting the above technical solution, the problem of low efficiency in discovering the leakage state of the valve connected to the pipeline in the transmission state is solved. Traditional leakage detection methods are often not sensitive to small leaks and are not timely. Especially for high-pressure plastic butterfly valves, deformation and leakage may occur inside and are not easy to detect. Leakage may cause medium loss, environmental pollution, safety accidents, and equipment damage. The elastic modulus of plastic materials is much lower than that of metals, and significant deformation may occur under high pressure. If this deformation exceeds the design range, it will cause the fitting relationship between the butterfly plate and the valve seat to be destroyed, eventually causing sealing failure and leakage. How to monitor this deformation during valve operation and determine whether it will cause leakage is a challenge. The sealing performance of the butterfly valve is highly dependent on the integrity and elasticity of the valve seat. The valve seat may age, wear or be eroded by the medium over a long period of use, resulting in its inability to provide sufficient sealing force and eventually 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 comprehensively assess the valve state. SUMMARY

[0004] The technical problem solved by the present application is that traditional leakage detection methods are often not sensitive to small leaks and are not timely in discovering leaks. In particular, for high-pressure plastic butterfly valves, deformation and leakage can occur internally and are not easy to detect. Leakage can lead to medium loss, environmental pollution, safety accidents, and equipment damage. The elastic modulus of plastic materials is much lower than that of metals, and significant deformation can easily occur under high pressure. If this deformation exceeds the design range, it can cause the fit between the butterfly plate and the valve seat to be destroyed, ultimately leading to seal failure and leakage. How to monitor this deformation during valve operation and determine whether it will cause leakage is a challenge. The sealing performance of a butterfly valve is highly dependent on the integrity and elasticity of the valve seat. The valve seat can age, wear, or be eroded by the medium over time, resulting in its inability to provide sufficient sealing force and ultimately causing leakage. Valve operation involves a variety of physical quantities, and data from different sensors are often isolated and difficult to analyze comprehensively, making it difficult to assess the valve state.

[0005] To solve the above technical problems, the present application provides the following technical solutions: a high-pressure-resistant plastic butterfly valve real-time leakage monitoring system, comprising a collection module, a physical analysis module, a fusion module, and a warning module:

[0006] The collection module is used to collect the structural information and leakage state of the high-pressure-resistant plastic butterfly valve.

[0007] The physical analysis module is used to perform leakage testing on the high-pressure-resistant plastic butterfly valve through physical and mechanical analysis.

[0008] The fusion module is used to calculate the deviations of the static health benchmark, the dynamic health benchmark, the strain health benchmark line, the quiet benchmark line, and the health torque benchmark, and to obtain the specific performance characteristics in each leakage state through linear equation systems and double-cosine finite integral inverse transformation.

[0009] The warning module is used to display the monitoring data of the valve in real time on the user interface.

[0010] Preferably, the collection module comprises:

[0011] The structural information and leakage state of the high-pressure-resistant plastic butterfly valve are collected in real time by a strain sensor group, a vibration sensor, a torque sensor, a pressure sensor, and a valve position sensor, all sensors are connected, and sensor signals are collected synchronously.

[0012] The structural information includes related information of the valve body, the butterfly plate, the valve seat, and the valve stem.

[0013] The leakage state includes structural deformation, fluid dynamic state change, and operating mechanical state change. Structural deformation includes stress concentration, fluid dynamic state change includes turbulent flow and acoustic vibration, and operating mechanical state change includes torque change.

[0014] Preferably, the static health benchmark is established, the establishing process comprising:

[0015] The butterfly valve is completely closed, and normal working pressure is applied to the upstream of the valve. The current strain benchmark and acoustic benchmark are collected, the strain benchmark including the readings of the strain gauges at this time, and the acoustic benchmark including the signal amplitude of the acoustic sensor at this time;

[0016] The dynamic health benchmark is established, the establishing process comprising:

[0017] In the pressurized state, the valve is completely operated for several cycles of full opening to full closing. The torque-valve position curve during the entire closing process is synchronously recorded. The peak torque in the last 5° of the closing stroke is extracted from the torque-valve position curve, and the peak torque represents the maximum torque required when the healthy sealing ring is normally compressed;

[0018] The static health benchmark and the dynamic health benchmark are stored in the butterfly valve judgment standard database.

[0019] Preferably, the analysis module comprises a strain monitoring unit, a high-frequency vibration monitoring unit, and a closing torque monitoring unit:

[0020] The strain monitoring unit comprises:

[0021] The strain values of the measuring points on the valve body at the center of the back of the butterfly plate, the outside of the connection between the valve body and the pipeline flange, and the two sides of the valve stem of the high-pressure-resistant plastic butterfly valve are monitored, and the monitoring process comprises:

[0022] The strain values of the measuring points on the valve body at the center of the back of the butterfly plate, the outside of the connection between the valve body and the pipeline flange, and the two sides of the valve stem of the high-pressure-resistant plastic butterfly valve under normal working pressure are measured on a new valve or a known intact valve, and the strain values are taken as the strain health benchmark line.

[0023] The strain values of the high-pressure-resistant plastic butterfly valve are monitored in real time. When the strain values increase at a constant speed for a duration exceeding a preset time threshold, or increase at a speed exceeding a preset speed threshold, or the strain values exceed a preset safety threshold, it indicates that the high-pressure-resistant plastic butterfly valve is in a structural deformation leakage state.

[0024] Preferably, the high-frequency vibration monitoring unit comprises:

[0025] The acoustic emission sensing data of the measuring points on the valve body and the pipeline downstream of the valve are monitored, and the monitoring process comprises:

[0026] When the valve is confirmed to be closed tightly, the amplitude of the background noise vibration is measured, and the amplitude is taken as a quiet baseline. The vibration signal of the high-pressure-resistant plastic butterfly valve is continuously monitored. When the signal amplitude in the preset frequency range is higher than the quiet baseline by more than a preset time threshold, it indicates that the high-pressure-resistant plastic butterfly valve is in a leakage state of dynamic state change of fluid.

[0027] The strength of the signal is positively correlated with the severity of the leakage.

[0028] Preferably, the valve closing torque monitoring unit comprises:

[0029] The driving current of the monitoring point on the actuator driving the valve stem is monitored, and the driving current is proportional to the torque,

[0030] The torque-angle curve of the new valve or the known intact valve from opening to complete closing under standard working conditions is recorded, and the torque-angle curve is taken as a healthy torque baseline. In each valve closing operation, a new torque-angle curve is recorded.

[0031] If the peak torque in the valve closing process decreases or increases by more than a preset peak torque threshold proportion compared with the healthy torque baseline corresponding to the valve closing reading, it indicates that the high-pressure-resistant plastic butterfly valve is in a leakage state of operating mechanics state change.

[0032] Preferably, the fusion module comprises:

[0033] The static health baseline, the dynamic health baseline, the strain health baseline, the quiet baseline and the healthy torque baseline are subjected to Min-Max standardization processing to obtain a baseline standard value. Real-time sensor signal acquisition and standardization processing are performed, and the standardization value of the acquisition result of the sensor signal is calculated. A deviation vector is formed by all the baseline standard values. The deviation vector is taken as the right side value of the linear equation, and the linear equation is solved to obtain a valve state combination solution. The valve state combination solution is subjected to double-cosine finite integral inverse transformation in each leakage state. The upper and lower limits of the structural deformation leakage state include the minimum and maximum values of the strain value and the monitoring time. The upper and lower limits of the fluid dynamic state change leakage state include the minimum and maximum values of the vibration signal amplitude and the monitoring time. The upper and lower limits of the operating mechanics state change leakage state include the minimum and maximum peak values of the torque-angle curve and the monitoring time.

[0034] Preferably, the unknowns of the linear equation correspond to the feature values of the abnormal sensor signal data amount of each leakage state corresponding to the static health baseline, the dynamic health baseline, the strain health baseline, the quiet baseline and the healthy torque baseline.

[0035] Preferably, the valve state combination solution under each leakage state is obtained by solving the linear equation set by Gaussian elimination method, the valve state combination solution represents the deviation degree of the current valve state from the health benchmark, and the valve state combination solution is inversely transformed back to the physical space according to the double-cosine finite integral inverse transformation formula to obtain the specific performance characteristics of each leakage state in the physical space.

[0036] Preferably, each monitoring data of the valve is displayed in real time on the user interface, an alarm is triggered according to the leakage judgment result, and a leakage diagnosis report is generated, the leakage diagnosis report includes a leakage type, an occurrence time, a severity, and a data trend chart, and all original data, benchmark data, standardized data, deviation data, and alarm results are stored.

[0037] Advantages of the present application: The present application clearly points out that the plastic valve has low elastic modulus, significant deformation under high pressure, and easy creep, and the system design fully considers these unique challenges of plastic materials, which is different from metal valve monitoring. The system can establish a benchmark and perform real-time monitoring under high pressure, ensuring effectiveness in actual working environment. A multi-dimensional health benchmark is established, which is obtained by strict testing under the health state of the valve, providing a quantitative reference point for subsequent real-time monitoring, so that the deviation of the valve state can be accurately calculated. Various sensor data such as strain, vibration, torque, pressure, and valve position are integrated to comprehensively monitor structural deformation, fluid dynamic state change, and operating mechanical state change. The deviation between the real-time collected data and the standardized health benchmark is calculated to quantify the abnormality degree of the valve state. The standardized deviation is used as the input of the linear equation set, and the valve state combination solution is obtained by solving, which represents the deviation degree of the current valve state from the health benchmark. The valve state combination solution is inversely transformed by double-cosine finite integral, and is inversely transformed back to the physical space, so that the specific performance characteristics of each leakage state in the physical space (such as combined performance of real-time deflection / deformation field) are obtained, realizing the conversion and quantification from abstract data to physical meaning. The system can identify and distinguish the leakage caused by structural deformation, fluid dynamic state change, and operating mechanical state change, and set specific discrimination standards for each type, not only detecting leakage, but also inversely transforming the leakage back to the physical space through a mathematical model, diagnosing and quantifying the type, severity, and occurrence position (through specific measuring points) of the leakage in a deeper level, for example, the sensitivity to small leakage. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 A basic flowchart of a high-pressure-resistant plastic butterfly valve real-time leakage monitoring system is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments.

[0040] Referring to Figure 1 For an embodiment of the present application, a high-pressure-resistant plastic butterfly valve real-time leakage monitoring system is provided, comprising a collection module, a physical analysis module, a fusion module and a warning module:

[0041] The collection module is used to collect the structural information and leakage state of the high-pressure-resistant plastic butterfly valve;

[0042] The physical analysis module is used to perform leakage testing on the high-pressure-resistant plastic butterfly valve through physical and mechanical analysis;

[0043] The fusion module is used to calculate the deviation of the static health benchmark, the dynamic health benchmark, the strain health benchmark line, the quiet benchmark line and the health torque benchmark, and obtain the specific performance characteristics under each leakage state through linear equation set and double cosine finite integral transformation;

[0044] The warning module is used to display the monitoring data of the valve in real time on the user interface.

[0045] A multi-dimensional and refined health benchmark system is constructed according to the material properties of the high-pressure-resistant plastic butterfly valve; an advanced mathematical model based on multi-sensor data fusion, linear equation set and double cosine finite integral transformation is introduced to realize accurate identification, quantification and physical characteristic representation of the leakage state; and the sealing performance under non-fluid working conditions can be evaluated, thereby providing a comprehensive and intelligent real-time leakage monitoring and diagnosis solution.

[0046] The collection module comprises:

[0047] The structural information and leakage state of the high-pressure-resistant plastic butterfly valve are collected in real time by the strain sensor group, the vibration sensor, the torque sensor, the pressure sensor and the valve position sensor, all the sensors are connected, and the sensor signals are collected synchronously;

[0048] The structural information includes the valve body, the butterfly plate, the valve seat and the valve stem;

[0049] The leakage state includes structural deformation, fluid dynamic state change and operating mechanical state change, the structural deformation includes stress concentration, the fluid dynamic state change includes turbulent flow and acoustic vibration, and the operating mechanical state change includes torque change.

[0050] The valve body is subjected to pipeline pressure and medium corrosion, and is the base of the overall structure;

[0051] The butterfly plate is directly in contact with the fluid and bears the positive and negative pressure difference, and is a main throttling and pressure bearing component. Under high pressure, the butterfly plate will be bent and deformed.

[0052] The valve seat is the key to sealing. When the butterfly plate is closed, it is tightly attached to the valve seat to form a seal. The plastic butterfly valve is a flexible or soft sealing material. The compression amount, uniformity and material state directly determine the sealing performance.

[0053] 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.

[0054] Structural deformation is particularly important for high-pressure 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 the butterfly plate exceeds the allowable range, the fitting geometry of the butterfly plate and the valve seat is destroyed, the seal fails, and leakage occurs.

[0055] The change in fluid dynamic state mainly analyzes the cavitation phenomenon, which is essentially caused by the local pressure of the fluid being lower than the vaporization pressure. When a small leakage occurs in the butterfly valve, the high-pressure fluid will pass through the narrow leakage channel (such as the gap between the butterfly plate and the valve seat) at a very high speed, forming a high-speed jet. This process will produce high-frequency vibration and acoustic emission. High-frequency vibration includes jet impact on the downstream pipe wall and valve body, and acoustic emission includes high-frequency noise generated by the collapse of cavitation bubbles.

[0056] Torque variation indicates that the friction of the sealing surface is an important part of the torque. If the valve seat is damaged or loses elasticity due to aging, the support and friction provided by the valve seat will decrease, resulting in an abnormal decrease in the torque at the end of the closed valve.

[0057] Establishing a static health benchmark, the establishment process includes:

[0058] Close the butterfly valve completely and apply normal working pressure to the upstream of the valve. In this embodiment, 80%-100% of the nominal pressure is applied. Collect the current strain benchmark and acoustic benchmark. The strain benchmark includes the readings of each strain gauge at this time, indicating the normal deformation of the healthy valve body under high pressure. The acoustic benchmark includes the signal amplitude of the acoustic sensor at this time. In a leak-free valve, this value should be very low background noise.

[0059] Establishing a dynamic health benchmark, the establishment process includes:

[0060] Under pressure, fully operate the valve for several full opening to full closing cycles, and record the torque-valve position curve during the entire closing process. Extract the peak torque in the last 5° of the closing stroke from the torque-valve position curve. The peak torque represents the maximum torque required when the healthy sealing ring is normally compressed.

[0061] The static health benchmark and the dynamic health benchmark are stored in a butterfly valve judgment criterion database.

[0062] The analysis module comprises a strain monitoring unit, a high-frequency vibration monitoring unit and a valve-closing torque monitoring unit.

[0063] The strain monitoring unit comprises:

[0064] The strain values of the measuring points on the valve body at the center of the back surface of the butterfly plate, the outside of the connection between the valve body and the pipeline flange and the two sides of the valve stem of the high-pressure-resistant plastic butterfly valve are monitored, and the monitoring process comprises:

[0065] The strain values of the measuring points on the valve body at the center of the back surface of the butterfly plate, the outside of the connection between the valve body and the pipeline flange and the two sides of the valve stem of the high-pressure-resistant plastic butterfly valve under normal working pressure are measured on a new valve or a known intact valve, and the strain values are taken as the strain health benchmark.

[0066] The strain values of the high-pressure-resistant plastic butterfly valve are monitored in real time, and when the strain values increase at a constant speed for a duration exceeding a preset time threshold or increase at a speed exceeding a preset speed threshold, or the strain values exceed a preset safety threshold, it indicates that the high-pressure-resistant plastic butterfly valve is in a structural deformation leakage state.

[0067] High pressure is the normal working condition of the butterfly valve, which will cause a certain elastic deformation. This deformation within the normal range is stable and predictable. If the valve material appears fatigue, creep (a typical characteristic of plastic) or a small crack, the rigidity will decrease, resulting in greater strain (deformation) under the same pressure. This abnormal deformation is an important precursor to leakage.

[0068] The center of the back surface of the butterfly plate is the position with the largest medium pressure and the most significant bending deformation, and the outside of the connection between the valve body and the pipeline flange is a high stress concentration area. Monitoring the valve body position on the two sides of the valve stem is to monitor whether the valve body is expanded under high pressure to cause deformation of the valve stem hole.

[0069] The high-frequency vibration monitoring unit comprises:

[0070] The acoustic emission sensing data of the measuring points on the valve body and the pipeline downstream of the valve are monitored, and the monitoring process comprises:

[0071] When the valve is confirmed to be tightly closed, the amplitude of the background noise vibration is measured, and the amplitude is taken as the quiet benchmark. The vibration signal of the high-pressure-resistant plastic butterfly valve is continuously monitored, and when the signal amplitude in the preset frequency range is higher than the quiet benchmark by more than a preset time threshold, it indicates that the high-pressure-resistant plastic butterfly valve is in a dynamic state change leakage state.

[0072] The strength of the signal is positively correlated with the severity of the leakage.

[0073] Because the direction of the leakage jet is toward the low pressure side (downstream), the signals on the valve body and piping downstream of the valve are strongest and clearest;

[0074] A properly closed valve, the internal fluid should be static or near static, the background noise is low. Once the leakage occurs, the high pressure medium will be ejected from the tiny gap, forming a strong turbulent and shear flow. This process will produce high frequency sound and vibration that the human ear can not hear but the sensor can clearly capture.

[0075] Extremely sensitive to small leaks, fast response, is the most direct method to determine whether it is leaking, the high-speed jet and cavitation induced by the sound vibration in terms of similar physical mechanisms.

[0076] The valve closing torque monitoring unit comprises:

[0077] The sealing of butterfly valve depends on the last few degrees of the closing stroke, especially the eccentric butterfly valve, at this time the butterfly plate extrudes the valve seat, generating a huge sealing force and the corresponding friction force, the peak value of this torque is the driver must overcome, if the valve seat loses elasticity or is partially missing due to aging, damage or being washed by the medium, the butterfly plate cannot be effectively supported, the extrusion stroke will be soft, resulting in a significant decrease in the peak torque required for sealing.

[0078] Monitoring the drive current of the measuring point on the actuator driving the valve stem, the drive current is proportional to the torque,

[0079] Record the torque-angle curve of the entire process from opening to complete closing of the new valve or the valve known to be good under standard working conditions, pay special attention to the peak torque in the last 5-10 degrees of the closing stroke, and use the torque-angle curve as the health torque reference. In each closing operation, record a new torque-angle curve;

[0080] If the peak torque in the closing process decreases or increases by more than a preset peak torque threshold percentage compared to the health torque reference corresponding to the closing reading, for example, more than 30%, it indicates that the high-pressure-resistant plastic butterfly valve is in a leak state of operating mechanics state change;

[0081] If the torque abnormally decreases, the valve seat has been damaged or excessively worn and cannot provide sufficient sealing force, and vice versa if the torque abnormally increases, it may be that impurities are stuck or parts are seized. Without using fluid, the health status of the sealing system is evaluated through the operation of the valve itself.

[0082] The fusion module comprises:

[0083] The static health benchmark, dynamic health benchmark, strain health baseline, quiet baseline and health torque benchmark are Min-Max standardized to obtain benchmark standard values, real-time sensor signal acquisition and standardization are performed, and the deviation of the standardized values of the acquisition results of the sensor signals from the benchmark standard values is calculated. All benchmark standard values form a deviation vector, and the deviation vector is used as the numerical value on the right side of the equation of the linear equation set. The linear equation set is solved to obtain a valve state combination solution. The valve state combination solution is subjected to double-cosine finite integral transformation in each leakage state. The upper and lower limits of the structural deformation leakage state include the minimum and maximum values of the strain values and the monitoring time. The upper and lower limits of the fluid dynamic state change leakage state include the minimum and maximum values of the amplitude of the vibration signal and the monitoring time. The upper and lower limits of the operating mechanics state change leakage state include the minimum and maximum peak values of the torque-angle curve and the monitoring time.

[0084] The linear equation set is in the form of Ax=b, where b is the deviation vector, x is the unknown vector to be solved, and A is the characteristic coefficient matrix. The linear equation set is solved to obtain a valve state combination solution x. The x vector represents the degree of deviation of the current state of the valve from the health benchmark or the contribution coefficient of each leakage mode in the characteristic space defined by the double-cosine finite integral transformation. Each component of the unknown x of the linear equation set corresponds to the double-cosine finite integral transformation of the valve state combination solution in each leakage state in the characteristic space established by the double-cosine finite integral transformation, which is further mapped to a leakage characteristic dimension with more physical meaning.

[0085] Each component of the unknown x of the linear equation set corresponds to the characteristic coefficient corresponding to the abnormal performance of each leakage state (structural deformation, fluid dynamic state change, operating mechanics state change) of the static health benchmark, dynamic health benchmark, strain health baseline, quiet baseline and health torque benchmark respectively or in relation to each other in the characteristic space established by the double-cosine finite integral transformation.

[0086] The characteristic coefficient matrix A is a pre-established characteristic mapping matrix, the dimension of which is determined according to the type, number of sensors and the number of defined leakage modes. The matrix is established by controlled testing of a large number of healthy valves and different degrees and types of leakage valves, collecting their sensor data under various operating conditions, and training or determining it using feature engineering and statistical analysis methods. The characteristic coefficient matrix A represents the linear coupling relationship of different leakage modes or characteristics on the measurement deviation of each sensor. Statistical analysis methods such as principal component analysis and linear regression analysis.

[0087] In a controlled experimental environment, known healthy valves and valves simulating different positions, different degrees, and different types of leakage are applied with different pressures, and complete data sets of all sensors are collected. The sensor data collected include strain, vibration, torque, pressure, and valve position. All collected data, including healthy benchmarks and leakage data, are subjected to Min-Max standardization, and the standardized deviation vectors of each leakage state sample relative to its corresponding healthy benchmark are calculated. Multivariate statistical methods such as PCA or linear regression analysis are applied to analyze the mapping relationship between these deviation vectors and the preset leakage modes (structural deformation, fluid dynamics change, operating mechanics change). For example, PCA can be used to find the main change direction of the deviation vector, which may correspond to a specific leakage mode; or through multivariate linear regression, the regression coefficient matrix obtained by taking the deviation vector as the independent variable and the preset leakage mode severity or characteristic value as the dependent variable can be used as the characteristic coefficient matrix A.

[0088] For example, the transformation quantity related to deflection is extracted from the valve state combination solution, and inverse transformation is performed to obtain the real-time deflection or deformation field in the physical space.

[0089] The health status of the valve is defined as a set of benchmark standard values, and the deviation of any real-time monitoring data from these benchmarks is considered as an abnormal signal. After standardization, these abnormal signals are used as the right side input of the linear equation system representing the current state of the valve, and the solution of this linear equation system is obtained. The solution represents the deviation of the current state of the valve from the health benchmark, and finally, the combination solution is inverse transformed back to the physical space and compared with the preset leakage threshold to identify and quantify the leakage state.

[0090] A multi-dimensional health benchmark is established, which is obtained through strict testing under the healthy state of the valve, providing a quantitative reference point for subsequent real-time monitoring, so that the deviation of the valve state can be accurately calculated.

[0091] The unknowns of the linear equation system correspond to the characteristic values of the abnormal sensor signal data of each leakage state corresponding to the static health benchmark, the dynamic health benchmark, the strain health benchmark line, the quiet benchmark line, and the health torque benchmark.

[0092] The linear equation system is solved by Gaussian elimination method to obtain the valve state combination solution under each leakage state, which represents the deviation of the current valve state from the health benchmark. According to the double cosine finite integral inverse transformation formula, the valve state combination solution is inverse transformed back to the physical space to obtain the specific performance characteristics of each leakage state in the physical space.

[0093] For example, the transformation quantity related to deflection is extracted from the valve state combination solution, and inverse transformation is performed to obtain the real-time deflection / deformation field in the physical space.

[0094] The health status of the valve is defined as a set of reference standard values. Any deviation of real-time monitoring data from these references is considered as an abnormal signal. These abnormal signals, after standardization, are used as the right side input of a linear equation system representing the current state of the valve. Solving this linear equation system, a valve state combination solution in the frequency domain is obtained, which represents the deviation of the current state of the valve from the health reference. Finally, this combination solution is inversely transformed back to the physical space and compared with the pre-set leakage threshold to identify and quantify the leakage state.

[0095] Real-time display of various monitoring data of the valve on the user interface, triggering different levels of alarm according to the leakage judgment result, generating detailed leakage diagnosis report including leakage type, occurrence time, severity and data trend chart, storing all original data, reference data, standardized data, deviation data and judgment result.

[0096] The application clearly points out the characteristics of plastic valves, such as low elastic modulus, significant deformation under high pressure, and easy creep, and the system design fully considers these unique challenges of plastic materials, which are different from metal valve monitoring. The system can establish a reference and conduct real-time monitoring under high pressure, ensuring effectiveness in actual working environment. Not only static health reference (strain, acoustics), but also dynamic health reference (torque-valve position curve and peak torque in operation cycle), strain health reference line and quiet reference line are included, constructing a multi-dimensional healthy valve behavior model. The establishment process of static and dynamic reference is described in detail, such as collecting strain / acoustic data under pressure with full closing, and recording torque-valve position curve under pressure with full opening and full closing cycle, making the reference more operational and accurate. Various sensor data such as strain, vibration, torque, pressure and valve position are integrated to achieve comprehensive monitoring of structural deformation, fluid dynamic state change and operating mechanical state change. The deviation calculation between real-time collected data and standardized health reference quantifies the abnormality degree of valve state. The standardized deviation is used as the input of a linear equation system, and the "valve state combination solution" representing the deviation of the current state of the valve from the health reference is obtained. Double cosine finite integral transformation is performed on the "valve state combination solution", and then it is inversely transformed back to the physical space, so that the specific performance characteristics (such as real-time deflection / deformation field) of each leakage state in the physical space are obtained, realizing the conversion and quantification from abstract data to physical meaning. The system can identify and distinguish the leakage caused by structural deformation, fluid dynamic state change and operating mechanical state change, and set specific discrimination standards for each type, not only detecting leakage, but also through mathematical model inverse transformation back to physical space, diagnosing and quantifying the type, severity and occurrence position (through specific measuring points) of the leakage in a deeper level, such as sensitivity to small leakage.

[0097] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (or computer- readable storage media) having computer-usable program code embodied in the medium. The medium can be any available storage media that can be accessed by a computer. By way of example, and not limitation, such computer-usable storage media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other storage medium(s) that can be used to carry or store desired computer program code in the form of instructions or data structures and that can be accessed by a computer. Also, the present application can be embodied in a computer program product that can be traded as goods or merchandise, through a computer-based platform or Figure 1 one or more functions specified in the flow or flows and / or blocks Figure 1 one or more functions specified in the flow or flows and / or blocks

[0098] It should be noted that the above-mentioned embodiments are only used to illustrate but not to limit the technical solutions of the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A real-time leak monitoring system for high pressure plastic butterfly valves, characterized in that, It comprises a collection module, a physical analysis module, a fusion module and an early warning module: The collection module is used for collecting the structural information and the leakage state of the high-pressure-resistant plastic butterfly valve; The collection module comprises: The structural information and the leakage state of the high-pressure-resistant plastic butterfly valve are collected in real time through a strain sensor group, a vibration sensor, a torque sensor, a pressure sensor and a valve position sensor, all the sensors are connected, and the sensor signals are collected synchronously; The structural information comprises relevant information of a valve body, a butterfly plate, a valve seat and a valve rod; The leakage state comprises structural deformation, fluid power state change and operation mechanics state change, the structural deformation comprises stress concentration, the fluid power state change comprises turbulent flow and acoustic vibration, and the operation mechanics state change comprises torque change; The physical analysis module is used for performing a leakage test on the high-pressure-resistant plastic butterfly valve through physical mechanics analysis; The fusion module is used for performing deviation calculation based on a static health benchmark, a dynamic health benchmark, a strain health benchmark line, a quiet benchmark line and a health torque benchmark, and obtaining specific performance characteristics in each leakage state through linear equation sets and double-cosine finite integral inverse transformation; The early warning module is used for displaying the monitoring data of the valve on a user interface in real time; A static health benchmark is established, and the establishment process comprises: The butterfly valve is completely closed, normal working pressure is applied to the upstream of the valve, and the current strain benchmark and acoustic benchmark are collected, the strain benchmark comprises readings of the strain gauges at this time, and the acoustic benchmark comprises signal amplitude of the acoustic sensor at this time; A dynamic health benchmark is established, and the establishment process comprises: In the pressurized state, the valve is completely operated for several times of full opening to full closing, the torque-valve position curve in the whole closing process is recorded synchronously, the peak torque in the last 5° of the closing stroke is extracted from the torque-valve position curve, and the peak torque represents the maximum torque required when the health sealing ring is normally compressed; On a new valve or a known intact valve, the strain values of the measuring points on the valve body at the center of the back of the butterfly plate, the outside of the valve body and the flange connection of the pipeline, and the two sides of the valve rod under the normal working pressure are measured, and the strain values are taken as the strain health benchmark line; When the valve is confirmed to be tightly closed, the amplitude of the background noise vibration is measured, and the amplitude of the vibration is taken as the quiet benchmark line; The torque-angle curve of the new valve or the known intact valve from opening to complete closing under the standard working condition is recorded, and the torque-angle curve is taken as the health torque benchmark; The fusion module comprises: The static health benchmark, dynamic health benchmark, strain health baseline, quiet baseline and health torque benchmark are Min-Max standardized to obtain benchmark standard values, real-time sensor signal acquisition and standardization are performed, and the standardization values of the acquisition results of the sensor signals and the deviations of the benchmark standard values are calculated, all the deviations are combined to form a deviation vector, the deviation vector is taken as the numerical value on the right side of the linear equation, the linear equation is solved to obtain a valve state combination solution, and the valve state combination solution is subjected to double-cosine finite integral inverse transformation in each leakage state, the upper and lower limits of the structural deformation leakage state include the maximum and minimum values of the strain values, the upper and lower limits of the fluid dynamic state change leakage state include the maximum and minimum values of the amplitude of the vibration signal, and the upper and lower limits of the operating mechanical state change leakage state include the maximum peak value and the minimum peak value of the torque-angle curve. The linear equation is in the form of Ax=b, wherein b is the deviation vector, x is an unknown number vector to be solved, and A is a characteristic coefficient matrix. The characteristic coefficient matrix A is a pre-established characteristic mapping matrix. The linear equation is solved to obtain a valve state combination solution x.

2. The real-time leakage monitoring system of the high-pressure-resistant plastic butterfly valve according to claim 1, wherein: The static health benchmark and the dynamic health benchmark are stored in a butterfly valve judgment standard database.

3. The high pressure resistant plastic butterfly valve real time leak monitoring system of claim 2, wherein, The analysis module comprises a strain monitoring unit, a high-frequency vibration monitoring unit and a valve-closing torque monitoring unit. The strain monitoring unit comprises: The strain values of the measuring points on the valve body on the center of the back of the disc, the outer side of the valve body and the pipeline flange connection and the two sides of the valve stem of the high-pressure-resistant plastic butterfly valve are monitored, and the monitoring process comprises: The strain values of the measuring points on the valve body on the center of the back of the disc, the outer side of the valve body and the pipeline flange connection and the two sides of the valve stem of the high-pressure-resistant plastic butterfly valve under the normal working pressure are measured on a new valve or a known intact valve, and the strain values are taken as the strain health baseline. The strain values of the high-pressure-resistant plastic butterfly valve are monitored in real time, and when the strain values increase at a constant speed for a duration exceeding a preset time threshold or at a speed exceeding a preset speed threshold, or the strain values exceed a preset safety threshold, it indicates that the high-pressure-resistant plastic butterfly valve is in a structural deformation leakage state.

4. The high pressure resistant plastic butterfly valve real time leak monitoring system of claim 3, wherein, The high-frequency vibration monitoring unit comprises: The acoustic emission sensing data of the measuring points on the valve body and the pipeline downstream of the valve are monitored, and the monitoring process comprises: When the valve is confirmed to be closed tightly, the amplitude of the background noise vibration is measured, and the amplitude is taken as the quiet baseline. The vibration signal of the high-pressure-resistant plastic butterfly valve is continuously monitored, and when the signal amplitude in the preset frequency range is higher than the quiet baseline by more than a preset time threshold, it indicates that the high-pressure-resistant plastic butterfly valve is in a fluid dynamic state change leakage state. The strength of the signal is positively correlated with the severity of the leakage.

5. The high pressure resistant plastic butterfly valve real time leak monitoring system of claim 4, wherein, The valve-closing torque monitoring unit comprises: The driving current of the measuring point on the actuator driving the valve stem is monitored, and the driving current is proportional to the torque. The torque-angle curve of the new valve or the known good valve from opening to full closing under standard working conditions is recorded as a health torque reference, and a new torque-angle curve is recorded in each valve closing operation; If the peak torque in the valve closing process decreases or increases by more than a preset peak torque threshold ratio compared to the health torque reference corresponding to the valve closing reading, it indicates that the high-pressure-resistant plastic butterfly valve is in a leakage state with changes in operating mechanics.

6. The real-time leakage monitoring system of the high-pressure-resistant plastic butterfly valve according to claim 5, wherein: The valve state combination solution in each leakage state is obtained by solving the linear equation set by Gaussian elimination method, which represents the deviation degree of the current valve state from the static health reference, the dynamic health reference, the strain health reference line, the quiet reference line and the health torque reference, and the valve state combination solution is inversely transformed back to the physical space according to the double cosine finite integral inverse transformation formula to obtain the specific performance characteristics of each leakage state in the physical space.

7. The high pressure resistant plastic butterfly valve real time leak monitoring system of claim 6, wherein, The monitoring data of the valve is displayed in real time on the user interface, the alarm is triggered according to the leakage judgment result, the leakage diagnosis report is generated, the leakage diagnosis report includes the leakage type, the occurrence time, the severity and the data trend chart, all original data, reference data, standardized data, deviation data and alarm results are stored.

Images