An Electric Valve Operation Optimization Method and System Based on Real-Time Data Analysis

Abstract

The present invention discloses a method and system for optimizing the operation of an electric valve based on real-time data analysis, specifically relating to the technical field of valve control. By monitoring the operation state of the electric valve, analyzing the non-linear hysteresis effect, and evaluating the influence on the valve response accuracy; at the same time, analyzing the microscopic fatigue state of the mechanical components of the electric valve and evaluating the fatigue accumulation degree of the mechanical components. By comprehensively analyzing the non-linear hysteresis effect and the mechanical fatigue accumulation degree, it is judged whether the electric valve has inefficient operation. When there is inefficient operation, by analyzing the fluid flow data, evaluating the matching degree between the opening degree of the electric valve and the fluid flow, and analyzing the stress distribution gradient of the sealing surface, evaluating the attenuation degree of the sealing performance of the electric valve. By comprehensively evaluating the matching degree between the opening degree of the electric valve and the flow rate and the attenuation degree of the sealing performance, the operation efficiency of the electric valve is evaluated, which can effectively improve the operation stability and accuracy of the electric valve and achieve efficient operation.

Description

Technical Field

[0001] The present invention relates to the technical field of valve control. More specifically, the present invention relates to a method and system for optimizing the operation of an electric valve based on real-time data analysis. Background Art

[0002] Traditional methods for optimizing the control of electric valves usually rely on fixed opening settings or adjust the working state of the valves based on simple sensor data. However, these methods often fail to accurately reflect the complex situations faced by the valves during actual operation, such as non-linear hysteresis effects, fatigue accumulation of mechanical components, and attenuation of sealing performance. As a result, problems such as inefficient operation and slow response of electric valves exist.

[0003] To solve the above problems, a method and system for optimizing the operation of an electric valve based on real-time data analysis are provided. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a method and system for optimizing the operation of an electric valve based on real-time data analysis to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for optimizing the operation of an electric valve based on real-time data analysis, comprising the following steps:

[0007] By monitoring the operating state of the electric valve, analyzing the non-linear hysteresis effect of the electric valve, and evaluating the influence of the non-linear hysteresis effect on the response accuracy of the electric valve;

[0008] Performing a microscopic fatigue state analysis on the mechanical components of the electric valve to evaluate the degree of microscopic mechanical fatigue accumulation of the electric valve;

[0009] Based on the influence of the non-linear hysteresis effect on the response accuracy of the electric valve and the degree of microscopic mechanical fatigue accumulation of the electric valve, determining whether the electric valve has inefficient operation;

[0010] When the electric valve has inefficient operation: analyzing the fluid flow data of the electric valve to evaluate the matching degree between the opening degree of the electric valve and the fluid flow; by analyzing the stress distribution gradient of the sealing surface of the electric valve, evaluating the degree of attenuation of the sealing performance of the electric valve.

[0011] Performing a comprehensive analysis on the matching degree between the opening degree of the electric valve and the fluid flow and the degree of attenuation of the sealing performance of the electric valve to evaluate the operating efficiency of the electric valve.

[0012] In a preferred embodiment, by monitoring the operating state of the electric valve, analyzing the non-linear hysteresis effect of the electric valve, and evaluating the impact of the non-linear hysteresis effect on the response accuracy of the electric valve, specifically:

[0013] Monitor the real-time operating state of the electric valve to obtain key data;

[0014] Calculate the hysteresis time difference between the change in the valve control signal and the response of the electric valve:

[0015] Use a data analysis algorithm to model the non-linear hysteresis effect during the operation of the valve, and quantify the degree of influence of the non-linear hysteresis effect on the response accuracy of the electric valve: Define the response error coefficient, and the calculation formula is: ; where is the response error coefficient; is the evaluation period; represents the response error at time .

[0016] In a preferred embodiment, conduct a microscopic fatigue state analysis of the mechanical components of the electric valve to evaluate the degree of microscopic mechanical fatigue accumulation of the electric valve, specifically:

[0017] Use a high-resolution scanning electron microscope to scan the surface of the key mechanical components of the electric valve to obtain microscopic structure images;

[0018] Apply an image processing algorithm to denoise, enhance the contrast, and detect the edges of the obtained microscopic structure images;

[0019] Use a machine learning model to identify the fatigue crack characteristics in the microscopic structure images;

[0020] Measure the crack parameter data, construct a fatigue life model of the mechanical components, and evaluate the degree of fatigue accumulation.

[0021] In a preferred embodiment, based on the influence of the non-linear hysteresis effect on the response accuracy of the electric valve and the degree of microscopic mechanical fatigue accumulation of the electric valve, determine whether the electric valve is operating inefficiently, specifically:

[0022] When the response error coefficient is greater than the response error coefficient threshold and the fatigue accumulation coefficient is greater than the fatigue accumulation coefficient threshold, it is determined that the electric valve is operating inefficiently; otherwise, it is determined that the electric valve is not operating inefficiently.

[0023] In a preferred embodiment, analyze the fluid flow data of the electric valve to evaluate the matching degree between the opening degree of the electric valve and the fluid flow, specifically:

[0024] Install a flow sensor to collect the fluid flow data of the electric valve in real time;

[0025] Record the opening degree of the electric valve, including the actual opening and the set opening of the valve;

[0026] Preprocess the collected fluid flow data to remove noise and abnormal data;

[0027] Construct a mathematical model between the valve opening degree and the fluid flow data, and analyze the matching degree between the valve opening degree and the fluid flow data.

[0028] In a preferred embodiment, evaluate the attenuation degree of the sealing performance of the electric valve by analyzing the stress distribution gradient of the sealing surface of the electric valve, specifically:

[0029] Use a stress sensor to monitor the sealing surface of the electric valve in real time and collect the stress data on the sealing surface;

[0030] Using the finite element analysis method, based on the collected stress data, calculate the stress distribution gradient of each point on the sealing surface;

[0031] Identify the stress concentration area by analyzing the stress distribution gradient;

[0032] Conduct a correlation analysis between the stress distribution gradient and the sealing performance of the electric valve to quantify the influence degree of the stress distribution on the sealing effect: Define the performance attenuation coefficient, and the calculation formula is:

[0033] ; where is the performance attenuation coefficient; , is an empirical constant; is the total number of stress concentration areas; is the th area of the stress concentration area; is the th average stress distribution gradient of the stress concentration area.

[0034] In a preferred embodiment, conduct a comprehensive analysis of the matching degree between the opening degree of the electric valve and the fluid flow and the attenuation degree of the sealing performance of the electric valve to evaluate the operation efficiency of the electric valve, specifically:

[0035] Normalize the determination coefficient corresponding to the matching degree between the opening degree of the electric valve and the fluid flow and the performance attenuation coefficient corresponding to the attenuation degree of the sealing performance of the electric valve respectively, and calculate the normalized determination coefficient and performance attenuation coefficient. The calculation formula is: ; where is the operation efficiency coefficient; is the determination coefficient; is the performance attenuation coefficient; is the adjustment parameter for the performance decay coefficient;

[0036] A preset operating efficiency coefficient threshold is used to compare the operating efficiency coefficient with the operating efficiency coefficient threshold:

[0037] When the operating efficiency coefficient is greater than or equal to the operating efficiency coefficient threshold, it indicates that the operating efficiency of the electric valve is high;

[0038] When the operating efficiency coefficient is less than the operating efficiency coefficient threshold, it indicates that the operating efficiency of the electric valve is low.

[0039] On the other hand, the present invention provides an electric valve operation optimization system based on real-time data analysis, including a response accuracy evaluation module, a fatigue accumulation evaluation module, an inefficient operation judgment module, a matching degree evaluation module, a performance decay evaluation module, and a comprehensive analysis module;

[0040] The response accuracy evaluation module monitors the operating state of the electric valve, analyzes the non-linear hysteresis effect of the electric valve, and evaluates the influence of the non-linear hysteresis effect on the response accuracy of the electric valve;

[0041] The fatigue accumulation evaluation module conducts a microscopic fatigue state analysis of the mechanical components of the electric valve and evaluates the degree of microscopic mechanical fatigue accumulation of the electric valve;

[0042] The inefficient operation judgment module determines whether the electric valve has inefficient operation based on the influence of the non-linear hysteresis effect on the response accuracy of the electric valve and the degree of microscopic mechanical fatigue accumulation of the electric valve;

[0043] When the electric valve has inefficient operation: the matching degree evaluation module analyzes the fluid flow data of the electric valve and evaluates the matching degree between the opening degree of the electric valve and the fluid flow; the performance decay evaluation module evaluates the degree of sealing performance decay of the electric valve by analyzing the stress distribution gradient of the sealing surface of the electric valve.

[0044] The comprehensive analysis module comprehensively analyzes the matching degree between the opening degree of the electric valve and the fluid flow and the degree of sealing performance decay of the electric valve, and evaluates the operating efficiency of the electric valve.

[0045] The technical effects and advantages of the electric valve operation optimization method and system based on real-time data analysis of the present invention:

[0046] By monitoring the operating status of the electric valve in real time, analyzing the non-linear hysteresis effect, and conducting a microscopic fatigue state analysis of the mechanical components of the electric valve, it is possible to accurately evaluate the response accuracy and fatigue accumulation degree of the electric valve, timely detect potential inefficient operation problems, and avoid the limitations of manual inspection and periodic maintenance in traditional methods. Secondly, by analyzing the fluid flow data of the electric valve and the stress distribution gradient of the sealing surface of the electric valve, it is possible to comprehensively evaluate the operating efficiency of the electric valve, provide a scientific basis for optimizing the control strategy, thereby improving the valve adjustment accuracy, providing a more reliable and economical operation optimization plan for the electric valve, and having important economic and environmental benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Schematic diagram of an electric valve operation optimization method based on real-time data analysis according to the present invention;

[0048] Figure 2 Schematic diagram of the structure of an electric valve operation optimization system based on real-time data analysis according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0050] Embodiment 1:

[0051] Figure 1 An electric valve operation optimization method based on real-time data analysis according to the present invention is provided, which includes the following steps:

[0052] By monitoring the operating status of the electric valve, analyzing the non-linear hysteresis effect of the electric valve, and evaluating the influence of the non-linear hysteresis effect on the response accuracy of the electric valve;

[0053] Conduct a microscopic fatigue state analysis of the mechanical components of the electric valve, and evaluate the degree of microscopic mechanical fatigue accumulation of the electric valve;

[0054] According to the influence of the non-linear hysteresis effect on the response accuracy of the electric valve and the degree of microscopic mechanical fatigue accumulation of the electric valve, determine whether the electric valve has inefficient operation;

[0055] When the electric valve has inefficient operation: analyze the fluid flow data of the electric valve to evaluate the matching degree between the opening degree of the electric valve and the fluid flow; evaluate the degree of sealing performance attenuation of the electric valve by analyzing the stress distribution gradient of the sealing surface of the electric valve.

[0056] Comprehensively analyze the matching degree between the opening degree of the electric valve and the fluid flow and the attenuation degree of the sealing performance of the electric valve, and evaluate the operation efficiency of the electric valve.

[0057] Specifically, by monitoring the operating state of the electric valve, analyze the non-linear hysteresis effect of the electric valve, and evaluate the influence of the non-linear hysteresis effect on the response accuracy of the electric valve, including:

[0058] Monitor the real-time operating state of the electric valve and obtain key data: Real-time monitor the operating data of the electric valve through sensors installed on the electric valve. These sensors are used to collect signals such as current, voltage, and the switch state of the electric valve. These signals reflect the working state of the electric valve and its interaction with the external environment. Specifically, the current signal reflects the load condition of the electric valve, and the voltage signal reflects the operating condition of the electric valve drive system. The switch state of the electric valve is directly related to the action and response of the valve.

[0059] Use high-precision sensors and real-time data acquisition devices to ensure the accuracy and real-time nature of data acquisition. The collected data will be updated at a certain frequency.

[0060] Calculate the lag time difference between the change of the valve control signal and the response of the electric valve: Evaluate the hysteresis effect between the electric valve control signal and the actual response of the valve. In the process of controlling the electric valve, the lag between the input signal and the valve response is inevitable. This hysteresis effect may be caused by multiple factors, including the mechanical structure of the valve itself, the inertia of the valve drive system, hydrodynamic characteristics, and control response delay, etc.

[0061] To quantify this hysteresis effect, by comparing the time difference between the valve control signal and the valve response in real time, calculate its lag time, and define the control signal of the electric valve as and the actual response signal of the valve as ; where represents the time variable, and calculate the lag time through the following steps:

[0062] Signal matching: Use the cross-correlation analysis method to calculate the correlation between the control signal and the response signal to determine the preliminary position of the lag;

[0063] Lag calculation: Calculate the time difference between the control signal and the response signal through the peak detection algorithm to obtain the lag time , and the calculation formula is: ; where represents the lag time, that is, the time difference between the valve control signal and the valve response; represents the time offset; Is a mathematical function.

[0064] By calculating the correlation between the control signal and the response signal, the lag time between the control signal and the response signal is found, that is, the time delay for the electric valve to respond to the control signal.

[0065] Use a data analysis algorithm to model the non-linear lag effect during the operation of the valve, and quantify the degree of influence of the non-linear lag effect on the response accuracy of the electric valve: After obtaining the lag time, use a data analysis algorithm to model the non-linear lag effect of the electric valve. The non-linear lag effect of the electric valve is not a linear relationship, but the result of the combined action of multiple factors, so a non-linear modeling method is used to accurately describe its behavior.

[0066] The modeling method adopted is the non-linear autoregressive integrated sliding mode control model. The non-linear autoregressive integrated sliding mode control model is a non-linear model widely used in system identification, which can effectively capture the complex non-linear characteristics in the valve control process.

[0067] The form of the non-linear autoregressive integrated sliding mode control model is: ; where, represents a non-linear function used to describe the complex relationship between the control signal and the response signal; represents the delay order of the valve response signal, that is, the number of past response signals included in the model; represents the delay order of the control signal, that is, the number of past control signals included in the model.

[0068] The non-linear autoregressive integrated sliding mode control model fits the non-linear response characteristics of the electric valve through historical data, and continuously adjusts the model parameters through an optimization algorithm to predict the ideal response of the electric valve .

[0069] After completing the modeling of the non-linear lag effect, calculate the response error of the electric valve at different time points. The response error is defined as the difference between the control signal and the actual response, and the calculation formula is: ; where, represents the response error at time ; represents the ideal response of the electric valve predicted by the non-linear autoregressive integrated sliding mode control model.

[0070] Define the response error coefficient to evaluate the influence of the non-linear lag effect on the response accuracy of the electric valve, and its calculation formula is: ; where, is the response error coefficient; is the evaluation period, that is, the length of the time period for evaluating the response accuracy of the electric valve; Indicates at time of the response error.

[0071] The larger the response error coefficient, the greater the deviation between the actual response and the expected control result after the electric valve receives the control signal, which means that there is an obvious non-linear hysteresis effect during the operation of the valve, resulting in valve response lag or over-regulation. A larger response error coefficient may be caused by factors such as the mechanical structure of the valve and the inertia of the valve drive system. As the non-linear hysteresis effect increases, it is difficult for the valve to accurately follow the change of the control signal during actual operation, thus affecting the overall stability of the valve. A larger response error coefficient may lead to serious control disorders and reduce the response accuracy of the valve.

[0072] Specifically, conduct a microscopic fatigue state analysis of the mechanical components of the electric valve to evaluate the degree of microscopic mechanical fatigue accumulation of the electric valve, including:

[0073] Use a high-resolution scanning electron microscope to perform a surface scan of the key mechanical components of the electric valve to obtain microscopic structure images: In the microscopic fatigue analysis of the electric valve, a high-resolution scanning electron microscope is used to perform a detailed surface scan of the key mechanical components of the electric valve (such as valve stems, valve seats, seals, etc.) to obtain their microscopic structure images. The high-resolution scanning electron microscope forms an image by scanning an electron beam on the surface of the object and capturing the signals generated by the interaction of electrons, with ultra-high resolution, capable of revealing the morphology and distribution of the component surface and its microscopic cracks.

[0074] To ensure clear and accurate image data, the key components of the electric valve need to be cleaned to remove surface contamination or oil stains. The scanning process is usually carried out in a high-vacuum environment to ensure that tiny cracks and fatigue signs on the component surface can be captured.

[0075] Apply image processing algorithms to denoise, enhance contrast, and detect edges of the obtained microscopic structure images: The obtained microscopic structure images need to be preliminarily processed to improve the image quality and extract key information such as fatigue cracks. Remove the noise signal in the image through denoising algorithms, usually using spatial filtering (such as mean filtering, Gaussian filtering, etc.) or frequency-domain filtering (such as Fourier transform) methods. After denoising, the image will be clearer, which helps to identify cracks and their morphology.

[0076] Apply methods to enhance contrast to improve the visibility of cracks and surface textures in the image. Commonly used algorithms include histogram equalization, contrast stretching, etc. Use edge detection algorithms (such as Sobel operator, Canny edge detection, etc.) to further process the enhanced image. Through edge detection, the edge information of tiny cracks in the image can be accurately identified.

[0077] Identifying fatigue crack features in microstructural images using a machine learning model: After image processing, a machine learning model is employed to identify fatigue crack features in the images. By training a deep learning model (such as a convolutional neural network) using a large dataset of labeled crack images, the model can recognize the patterns and locations of fatigue cracks in the images. During the training process, the network optimizes the parameters through backpropagation to improve the accuracy of crack identification.

[0078] Through the machine learning model, it is possible to accurately find tiny crack features in the image and extract their morphological information, including parameters such as the length, width, depth of the crack, and the crack propagation path.

[0079] Measuring crack parameter data, constructing a fatigue life model for mechanical components, and evaluating the degree of fatigue accumulation: After identifying the crack features, a quantitative analysis of the cracks is carried out. The length 、width and depth of the crack are key parameters for evaluating the degree of fatigue accumulation. Measuring the geometric features of the crack:

[0080] , the length of the crack, is usually measured along the main direction of the crack;

[0081] , the width of the crack, is usually measured at the opening of the crack;

[0082] , the depth of the crack, is usually measured perpendicular to the surface of the component.

[0083] To accurately evaluate the degree of fatigue accumulation of mechanical components, a finite element analysis method is used for simulation. By discretizing the geometric model of the mechanical components of the electric valve, a finite element mesh is established, and corresponding mechanical loads and boundary conditions are applied to the model for fatigue analysis.

[0084] Combining the crack parameter data, a fatigue accumulation coefficient is defined to evaluate the degree of fatigue accumulation, and its calculation formula is: ; where, represents the fatigue accumulation coefficient; is a constant of the material of the mechanical components of the electric valve; is the fatigue limit stress; is the fatigue constant of the material of the mechanical components of the electric valve, reflecting the fatigue behavior of the material.

[0085] The larger the fatigue accumulation coefficient is, the higher the degree of micro-mechanical fatigue accumulation of the electric valve during operation, which means that the key mechanical components of the valve, such as the valve stem, valve seat and seal, have endured a large amount of cyclic stress and strain, resulting in the gradual expansion and accumulation of fatigue cracks in the microstructure. A high fatigue accumulation coefficient indicates that the fatigue of these components is approaching the design limit, increasing the risk of material fracture or functional failure. A larger fatigue accumulation coefficient may stem from frequent opening and closing operations, high-load operating conditions or insufficient fatigue tolerance of the material itself. The increase in the fatigue accumulation coefficient also reflects the degree of wear and aging of the valve during long-term use, suggesting that timely maintenance or component replacement is needed to prevent sudden failures.

[0086] Specifically, based on the influence of the non-linear hysteresis effect on the response accuracy of the electric valve and the degree of micro-mechanical fatigue accumulation of the electric valve, it is determined whether the electric valve is operating inefficiently, including:

[0087] A preset response error coefficient threshold is set, and the response error coefficient is compared with the response error coefficient threshold:

[0088] When the response error coefficient is greater than the response error coefficient threshold, it indicates that the non-linear hysteresis effect during the operation of the electric valve affects the response accuracy of the electric valve, resulting in a large deviation between the actual response and the expected control result;

[0089] When the response error coefficient is less than or equal to the response error coefficient threshold, it indicates that the non-linear hysteresis effect during the operation of the electric valve does not affect the response accuracy of the electric valve, and the deviation between the actual response and the expected control result of the electric valve is within an acceptable range;

[0090] A preset fatigue accumulation coefficient threshold is set, and the fatigue accumulation coefficient is compared with the fatigue accumulation coefficient threshold:

[0091] When the fatigue accumulation coefficient is greater than the fatigue accumulation coefficient threshold, it indicates that the degree of micro-mechanical fatigue accumulation of the electric valve during operation is high. At this time, the mechanical properties and structural integrity of the electric valve are greatly affected, which may lead to the risk of failure of the electric valve under high load or frequent operation;

[0092] When the fatigue accumulation coefficient is less than or equal to the fatigue accumulation coefficient threshold, it indicates that the degree of micro-mechanical fatigue accumulation of the electric valve during operation is low. At this time, the fatigue damage degree of the mechanical components of the electric valve during operation is low, and the crack propagation and material deterioration in the microstructure do not reach a dangerous level, and the electric valve can operate under normal working conditions;

[0093] When the response error coefficient is greater than the response error coefficient threshold and the fatigue accumulation coefficient is greater than the fatigue accumulation coefficient threshold, it is determined that the electric valve is operating inefficiently; otherwise, it is determined that the electric valve is not operating inefficiently.

[0094] Specifically, analyze the fluid flow rate data of the electric valve to evaluate the matching degree between the opening degree of the electric valve and the fluid flow, including:

[0095] Collect the fluid flow rate data of the electric valve in real time by installing a flow sensor: Install a high-precision flow sensor at the key position of the electric valve. The high-precision flow sensor can monitor and collect the flow rate data in real time when the fluid passes through the valve, including parameters such as flow velocity, flow rate fluctuation, and fluid pressure.

[0096] The selection of the flow sensor is based on the working environment of the electric valve and the fluid characteristics. For example, for a fluid environment with high pressure and high temperature, a flow sensor that can withstand high temperature and high pressure should be selected to ensure the accuracy and reliability of data collection. The data collection frequency is set to 100 times per second to ensure that the dynamic changes of fluid flow can be captured and meet the requirements of high-precision evaluation.

[0097] Record the opening degree of the electric valve, including the actual opening degree and the set opening degree of the valve: The opening degree of the electric valve is divided into the actual opening degree and the set opening degree. The actual opening degree refers to the current physical opening degree of the valve, usually expressed in degrees or percentages; the set opening degree is the target opening degree set according to the demand instruction.

[0098] Preprocess the collected fluid flow rate data to remove noise and abnormal data: The preprocessing steps include:

[0099] Use the wavelet transform method to denoise the fluid flow rate data. The wavelet transform can separate the noise components in the signal, retain the useful flow information, and improve the signal-to-noise ratio of the data;

[0100] Apply an anomaly detection algorithm based on statistical analysis, such as the Z-score method, to identify and eliminate the outliers in the fluid flow rate data;

[0101] Use the exponentially weighted moving average method to smooth the processed flow rate data and reduce the short-term fluctuations of the data.

[0102] Construct a mathematical model between the valve opening degree and the fluid flow rate data to analyze the matching degree between the valve opening degree and the fluid flow rate data: There are different sampling frequencies or time delays between the fluid flow rate data and the opening degree data. Synchronize the two sets of data through interpolation or resampling methods to ensure that the flow rate value at each time point corresponds to an opening degree value.

[0103] According to the relationship characteristics between the valve opening and the flow rate, a support vector regression model is selected for modeling, and its mathematical expression is: ; where is the predicted flow rate value; is the opening data of the electric valve; is the th weight parameter of the support vector; is the kernel function; is the bias term of the support vector regression model; is the total number of support vectors; represents the opening data of the electric valve corresponding to the

[0104] th support vector. The historical data is used to train the support vector regression model. The synchronized opening data of the electric valve is used as the input, and the predicted flow rate value and are used as the output. The model parameters are optimized by minimizing the prediction error.

[0105] During the training process, the cross-validation method is adopted to evaluate the generalization ability of the model to ensure the prediction accuracy of the model on unknown data. Using the trained support vector regression model, the opening data of the currently operating electric valve is predicted to obtain the predicted flow rate . The predicted flow rate is compared with the actual flow rate ; where is the coefficient of determination; is the actual flow rate value of the th sample; is the predicted flow rate value of the th sample; is the average value of the actual flow rate values; is the total number of acquisitions of the flow rate data, which is calculated according to the acquisition time and the acquisition frequency.

[0106] The larger the coefficient of determination, the higher the matching degree between the valve opening and the fluid flow rate data. When the value of the coefficient of determination is close to 1, it indicates that the opening degree of the electric valve can effectively control the fluid flow rate, and the valve adjustment action can accurately respond to the demand of the fluid flow rate.

[0107] Specifically, by analyzing the stress distribution gradient of the sealing surface of the electric valve, the attenuation degree of the sealing performance of the electric valve is evaluated, including:

[0108] Use stress sensors to monitor the sealing surface of the electric valve in real time and collect stress data on the sealing surface: Install high-precision stress sensors on the sealing surface of the electric valve to achieve real-time monitoring of the stress state of the sealing surface. These stress sensors include strain gauges and piezoelectric sensors, which can accurately measure the stress changes on the sealing surface during operation. The strain gauge measures stress by detecting the tiny deformation of the sealing surface material under force, and the piezoelectric sensor obtains stress information by sensing the charge change caused by stress changes.

[0109] The data collected by the sensors includes the stress values at each point, including longitudinal stress , transverse stress and normal stress . These stress components together reflect the stress distribution on the sealing surface under different working conditions.

[0110] Using the finite element analysis method, based on the collected stress data, calculate the stress distribution gradient at each point on the sealing surface: After obtaining the stress data of the sealing surface, use the finite element analysis method to calculate the stress distribution gradient at each point on the sealing surface, including:

[0111] According to the geometric structure and material properties of the electric valve, construct a finite element model of the sealing surface. The finite element model includes the geometric details of all key components and accurately reflects the mechanical parameters such as the elastic modulus and Poisson's ratio of the material;

[0112] Perform mesh division on the finite element model, usually using a high-density mesh to improve the calculation accuracy. The fineness of the mesh division directly affects the calculation accuracy of the stress distribution gradient;

[0113] According to the actual working conditions, set the boundary conditions and apply external loads to the finite element model; the boundary conditions include fixed supports, symmetry conditions, etc., and the loads include internal pressure, operating torque, etc.;

[0114] Use finite element analysis software to solve the finite element model to obtain the stress distribution data at each point on the sealing surface; the calculation formula for the stress distribution gradient is: ; where represents the stress distribution gradient; is the longitudinal stress, representing the stress component along the length direction of the sealing surface; is the transverse stress, representing the stress component along the width direction of the sealing surface; is the normal stress, representing the stress component perpendicular to the sealing surface.

[0115] The stress distribution gradient calculated by finite element analysis can intuitively reflect the stress changes at different positions on the sealing surface. A higher stress distribution gradient indicates a drastic stress change, while a lower stress distribution gradient indicates a gentle stress change, and the sealing surface is in a relatively stable stress state.

[0116] Identify the stress concentration areas by analyzing the stress distribution gradient: The stress concentration areas refer to the parts where the stress distribution gradient is significantly higher than that of the surrounding areas, usually located at the edges of the sealing surfaces. By setting a stress gradient threshold, filter out the areas where the stress distribution gradient is greater than the stress gradient threshold.

[0117] For the identified stress concentration areas, extract their geometric features and stress distribution features, such as the area of the region , the average stress distribution gradient , etc., for the correlation analysis of the sealing performance.

[0118] Conduct a correlation analysis between the stress distribution gradient and the sealing performance of the electric valve, and quantify the influence degree of the stress distribution on the sealing effect: Define the performance attenuation coefficient, and its calculation formula is: ; where is the performance attenuation coefficient; , is an empirical constant obtained through data fitting; is the total number of stress concentration areas; is the th area of the stress concentration area; is the th average stress distribution gradient of the stress concentration area.

[0119] The larger the performance attenuation coefficient, the more serious the attenuation degree of the sealing performance of the electric valve and the worse the sealing effect. With the long-term operation of the electric valve, the stress borne by the sealing surface gradually accumulates, and the stress concentration areas increase. As the performance attenuation coefficient increases, the sealing performance of the electric valve will not be able to meet the requirements, which may cause equipment failures or safety risks. Appropriate maintenance and replacement measures must be taken to ensure the stability and safety of the equipment.

[0120] Specifically, conduct a comprehensive analysis of the matching degree between the opening degree of the electric valve and the fluid flow and the attenuation degree of the sealing performance of the electric valve, and evaluate the operation efficiency of the electric valve, including:

[0121] Normalize the determination coefficient corresponding to the matching degree between the opening degree of the electric valve and the fluid flow and the performance attenuation coefficient corresponding to the attenuation degree of the sealing performance of the electric valve respectively, and calculate the normalized determination coefficient and performance attenuation coefficient. The calculation formula is: ; where is the operation efficiency coefficient; is the determination coefficient; is the performance attenuation coefficient; is the adjustment parameter of the performance attenuation coefficient.

[0122] Preset the threshold of the operating efficiency coefficient, and compare the operating efficiency coefficient with the threshold of the operating efficiency coefficient:

[0123] When the operating efficiency coefficient is greater than or equal to the threshold of the operating efficiency coefficient, it indicates that the operating efficiency of the electric valve is high; the electric valve can continue to operate normally without adjustment or replacement;

[0124] When the operating efficiency coefficient is less than the threshold of the operating efficiency coefficient, it indicates that the operating efficiency of the electric valve is low; a lower operating efficiency coefficient means that the electric valve may not be able to accurately respond to changes in fluid flow, the control effect does not meet the expectations, which may lead to pressure fluctuations, unstable flow, resulting in energy waste or abnormal operation. It is necessary to check, debug or repair the electric valve to restore its normal working efficiency; possible measures include adjusting the valve opening, repairing or replacing the sealing components.

[0125] Embodiment 2:

[0126] The difference between Embodiment 2 and Embodiment 1 of the present invention is that this embodiment introduces an electric valve operation optimization system based on real-time data analysis.

[0127] Figure 2 The structural schematic diagram of an electric valve operation optimization system based on real-time data analysis of the present invention is given. An electric valve operation optimization system based on real-time data analysis includes a response accuracy evaluation module, a fatigue accumulation evaluation module, an inefficient operation judgment module, a matching degree evaluation module, a performance degradation evaluation module, and a comprehensive analysis module;

[0128] The response accuracy evaluation module monitors the operating state of the electric valve, analyzes the non-linear hysteresis effect of the electric valve, and evaluates the influence of the non-linear hysteresis effect on the response accuracy of the electric valve;

[0129] The fatigue accumulation evaluation module conducts a microscopic fatigue state analysis of the mechanical components of the electric valve and evaluates the degree of microscopic mechanical fatigue accumulation of the electric valve;

[0130] The inefficient operation judgment module determines whether the electric valve has inefficient operation based on the influence of the non-linear hysteresis effect on the response accuracy of the electric valve and the degree of microscopic mechanical fatigue accumulation of the electric valve;

[0131] When the electric valve has inefficient operation: the matching degree evaluation module analyzes the fluid flow data of the electric valve and evaluates the matching degree between the opening degree of the electric valve and the fluid flow; the performance degradation evaluation module evaluates the degree of sealing performance degradation of the electric valve by analyzing the stress distribution gradient of the sealing surface of the electric valve.

[0132] The comprehensive analysis module comprehensively analyzes the matching degree between the opening degree of the electric valve and the fluid flow and the attenuation degree of the sealing performance of the electric valve, and evaluates the operation efficiency of the electric valve.

[0133] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation. Where the present invention is not described, it is applicable to the prior art.

Claims

1. A method for optimizing the operation of an electric valve based on real-time data analysis, characterized in that: The steps include: By monitoring the operating status of the electric valve, the nonlinear hysteresis effect of the electric valve is analyzed, and the impact of the nonlinear hysteresis effect on the response accuracy of the electric valve is evaluated; Conduct micro fatigue state analysis on the mechanical parts of the electric valve to evaluate the accumulation of micro mechanical fatigue of the electric valve; Combined with the crack parameter data, the fatigue accumulation coefficient is defined and the calculation formula is: ;in, represents the fatigue accumulation coefficient; The constant of the material of the mechanical parts of the electric valve; is the fatigue limit stress; is the fatigue constant of the material of the mechanical parts of the electric valve; According to the influence of nonlinear hysteresis effect on the response accuracy of electric valve and the accumulation degree of micro-mechanical fatigue of electric valve, it is judged whether the electric valve has inefficient operation; When the electric valve operates inefficiently: analyze the fluid flow data of the electric valve to evaluate the matching degree between the opening degree of the electric valve and the fluid flow; evaluate the degree of attenuation of the sealing performance of the electric valve by analyzing the stress distribution gradient of the sealing surface of the electric valve; A comprehensive analysis is conducted on the matching degree between the opening degree of the electric valve and the fluid flow and the degree of attenuation of the sealing performance of the electric valve to evaluate the efficiency of the electric valve operation.

2. The method for optimizing the operation of an electric valve based on real-time data analysis according to claim 1, characterized in that: By monitoring the operating status of the electric valve, analyzing the nonlinear hysteresis effect of the electric valve, and evaluating the impact of the nonlinear hysteresis effect on the response accuracy of the electric valve, specifically: Monitor the real-time operating status of electric valves and obtain key data; Calculate the lag time difference between the change in the valve control signal and the motorized valve response: The nonlinear hysteresis effect during valve operation is modeled using a data analysis algorithm to quantify the impact of the nonlinear hysteresis effect on the response accuracy of the electric valve: the response error coefficient is defined and the calculation formula is: ;in, is the response error coefficient; For the evaluation cycle; Indicates at time response error.

3. The method for optimizing the operation of an electric valve based on real-time data analysis according to claim 2, characterized in that: The micro fatigue state of the mechanical parts of the electric valve is analyzed to evaluate the accumulation of micro mechanical fatigue of the electric valve, specifically: Use a high-resolution scanning electron microscope to scan the surface of key mechanical parts of the electric valve and obtain microstructure images; Apply image processing algorithms to remove noise, enhance contrast and detect edges on acquired microstructure images; Using machine learning models to identify fatigue crack features in microstructural images; Measure crack parameter data, build fatigue life models of mechanical components, and evaluate the degree of fatigue accumulation.

4. The method for optimizing the operation of an electric valve based on real-time data analysis according to claim 3 is characterized in that: According to the influence of nonlinear hysteresis effect on the response accuracy of electric valve and the accumulation degree of micro-mechanical fatigue of electric valve, it is judged whether the electric valve has inefficient operation, specifically: When the response error coefficient is greater than the response error coefficient threshold, and the fatigue accumulation coefficient is greater than the fatigue accumulation coefficient threshold, it is determined that the electric valve is operating inefficiently; otherwise, it is determined that the electric valve is not operating inefficiently.

5. The method for optimizing the operation of an electric valve based on real-time data analysis according to claim 4, characterized in that: Analyze the fluid flow data of the electric valve to evaluate the matching degree between the opening degree of the electric valve and the fluid flow, specifically: Collect the fluid flow data of the electric valve in real time by installing flow sensors; Record the opening degree of the electric valve, including the actual opening degree and the set opening degree of the valve; Preprocess the collected fluid flow data to remove noise and abnormal data; A mathematical model between valve opening and fluid flow data is constructed to analyze the matching degree between valve opening and fluid flow data.

6. The method for optimizing the operation of an electric valve based on real-time data analysis according to claim 5, characterized in that: By analyzing the stress distribution gradient of the sealing surface of the electric valve, the degree of attenuation of the sealing performance of the electric valve is evaluated, specifically: Use stress sensors to monitor the sealing surface of the electric valve in real time and collect stress data on the sealing surface; Using the finite element analysis method, based on the collected stress data, the stress distribution gradient of each point on the sealing surface is calculated; Identify stress concentration areas by analyzing stress distribution gradients; The stress distribution gradient is correlated with the sealing performance of the electric valve to quantify the influence of stress distribution on the sealing effect: the performance attenuation coefficient is defined and the calculation formula is: ;in, is the performance attenuation coefficient; is an empirical constant; is the total number of stress concentration areas; For the The area of ​​the stress concentration region; For the The average stress distribution gradient in the stress concentration area.

7. The method for optimizing the operation of an electric valve based on real-time data analysis according to claim 6, characterized in that: Comprehensively analyze the matching degree between the opening degree of the electric valve and the fluid flow and the attenuation degree of the sealing performance of the electric valve to evaluate the efficiency of the electric valve operation, specifically: The determination coefficient corresponding to the matching degree between the opening degree of the electric valve and the fluid flow and the performance attenuation coefficient corresponding to the sealing performance attenuation degree of the electric valve are normalized respectively, and the normalized determination coefficient and performance attenuation coefficient are calculated. The calculation formula is: ;in, is the operating efficiency coefficient; is the coefficient of determination; is the performance attenuation coefficient; is the adjustment parameter of the performance attenuation coefficient; The operating efficiency coefficient threshold is preset, and the operating efficiency coefficient is compared with the operating efficiency coefficient threshold: When the operating efficiency coefficient is greater than or equal to the operating efficiency coefficient threshold, it means that the operating efficiency of the electric valve is high; When the operating efficiency coefficient is less than the operating efficiency coefficient threshold, it indicates that the operating efficiency of the electric valve is low.

8. An electric valve operation optimization system based on real-time data analysis, used to implement an electric valve operation optimization method based on real-time data analysis as described in any one of claims 1 to 7, characterized in that: It includes response accuracy assessment module, fatigue accumulation assessment module, inefficient operation judgment module, matching degree assessment module, performance attenuation assessment module and comprehensive analysis module; The response accuracy evaluation module monitors the operating status of the electric valve, analyzes the nonlinear hysteresis effect of the electric valve, and evaluates the impact of the nonlinear hysteresis effect on the response accuracy of the electric valve; The fatigue accumulation assessment module performs microscopic fatigue state analysis on the mechanical components of the electric valve and assesses the degree of microscopic mechanical fatigue accumulation of the electric valve; The inefficient operation judgment module judges whether the electric valve is inefficiently operated according to the influence of the nonlinear hysteresis effect on the response accuracy of the electric valve and the accumulation degree of microscopic mechanical fatigue of the electric valve; When the electric valve operates inefficiently: the matching degree evaluation module analyzes the fluid flow data of the electric valve to evaluate the matching degree between the opening degree of the electric valve and the fluid flow; The performance attenuation evaluation module evaluates the degree of sealing performance attenuation of the electric valve by analyzing the stress distribution gradient of the sealing surface of the electric valve; The comprehensive analysis module conducts a comprehensive analysis on the matching degree between the opening degree of the electric valve and the fluid flow and the attenuation degree of the sealing performance of the electric valve, and evaluates the efficiency of the operation of the electric valve.

Images