Temperature compensation method, system and device for high-temperature molten salt pressure transmitter and storage medium

Abstract

The invention relates to the field of pressure transmitters, in particular to a temperature compensation method, system and device for a high-temperature molten salt pressure transmitter and a storage medium. Meanwhile, a sensor is used for collecting working data, after preprocessing, data-driven modeling and training are conducted through a support vector machine, then a temperature-pressure model and a data-driven model are fused, and an optimal fusion mode and weight distribution are determined according to experiments and data analysis. During actual work, data are collected in real time and input into the fusion model, and a compensated pressure measurement value is accurately calculated. According to the method, the temperature influence can be effectively compensated, the measurement precision is greatly improved, the method can adapt to a complex working environment, the stability and reliability of measurement are guaranteed through a data processing and model training mechanism, and a better scheme is provided for high-temperature molten salt pressure measurement.

Description

Technical Field

[0001] The present invention relates to the field of pressure transmitters, and particularly to a temperature compensation method, system, device and storage medium for a high-temperature molten salt pressure transmitter. Background Art

[0002] In industrial production, high-temperature molten salt pressure transmitters are widely used in process flows involving high-temperature molten salts, such as molten salt energy storage systems in the new energy field, high-temperature reaction process monitoring in chemical production, and other scenarios. High-temperature molten salts have special physical and chemical properties, and the temperature change range of their working environment is large and the working conditions are complex. In such an environment, accurate pressure measurement is crucial for ensuring production safety, optimizing production processes, and improving product quality. When existing high-temperature molten salt pressure transmitters measure pressure, they often ignore the changes in the physical properties of high-temperature molten salts with temperature and the influence of temperature on the material properties of sensitive elements, without considering the relationship between the density of molten salts and temperature, as well as the changes in the elastic modulus and thermal expansion coefficient of sensitive elements with temperature. As a result, when measuring pressure at different temperatures, it is impossible to accurately compensate for the measurement errors caused by temperature, resulting in low measurement accuracy and difficulty in meeting the high-precision measurement requirements of high-temperature molten salt pressure transmitters in complex working environments.

[0003] Therefore, it is necessary to propose a temperature compensation method, system, device and storage medium for a high-temperature molten salt pressure transmitter to solve the above problems. Summary of the Invention

[0004] The purpose of the present invention is to provide a temperature compensation method, system, device and storage medium for a high-temperature molten salt pressure transmitter to solve the problem that it is impossible to accurately compensate for the measurement errors caused by temperature due to the changes in the physical properties of high-temperature molten salts with temperature and the influence of temperature on the material properties of sensitive elements.

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

[0006] A temperature compensation method for a high-temperature molten salt pressure transmitter, the method includes:

[0007] Analyze the relationship between the changes in the physical properties of high-temperature molten salts with temperature and pressure measurement, and establish a temperature-pressure model based on physical principles in combination with the material properties of the sensitive elements of the pressure transmitter;

[0008] In the actual working environment of the high-temperature molten salt pressure transmitter, use sensors to collect working data;

[0009] Through data-driven by support vector machines, divide the working data into a training set and a test set, and use the training set and test set to train and test the data-driven model;

[0010] Fuse the temperature-pressure model with the data-driven model. The output of the temperature-pressure model is used as the input of the data-driven model. Combine experiments and data analysis to determine the optimal fusion method and weight allocation between the temperature-pressure model and the data-driven model.

[0011] During the actual operation of the high-temperature molten salt pressure transmitter, collect the data of the fusion model in real time. After inputting it into the fusion model, calculate the compensated pressure measurement value.

[0012] Preferably, the method further includes denoising and filtering preprocessing of the working data collected by the sensor.

[0013] Preferably, the parameters of the temperature-pressure model include the derived pressure measurement value P, temperature T, molten salt density ρ, elastic modulus E of the sensitive element. The sensitive element is a strain gauge. According to the density data of the high-temperature molten salt at different temperatures, use a densitometer to measure the density within a specific temperature range, and establish a relationship between the molten salt density ρ and the temperature T.

[0014] ρ = ρ0 + k1T + k2T 2 ;

[0015] Obtain the characteristic data of the elastic modulus E and thermal expansion coefficient α of the sensitive element, analyze the relationship between the characteristic data and temperature changes, and establish a relationship between the elastic modulus E and the temperature T.

[0016] E = E0(1 + k3T);

[0017] According to fluid mechanics and elasticity, construct the temperature-pressure model.

[0018]

[0019] where k1, k2, k3, and E0 are constant terms, g is the acceleration due to gravity, h is the height of the molten salt, and ΔT is the temperature change.

[0020] Preferably, among the working data collected by the sensor, the working data includes temperature, pressure, physical properties of the high-temperature molten salt, and parameters of the transmitter sensitive element.

[0021] Preferably, in the support vector machine data-driven model, the radial basis function is used as the kernel function. The kernel function is used to enable the support vector machine to handle nonlinear problems. The relationship of the kernel function is

[0022] K(X i , X) = exp(-γ||X - X i || 2 );

[0023] Based on the kernel function, construct a decision function. The decision function is used to predict the pressure measurement value. The relationship of the decision function is

[0024]

[0025] Construct the input vector of the support vector machine data-driven model. The input vector constitutes the input information of the data-driven model. The input vector is

[0026] X = [T, P, F1, F2,..., F n ;

[0027] where γ is the kernel function parameter, X is the input vector, X i is the support vector, ||X - X i || 2 is the square of the Euclidean distance between the input vector X and the support vector X i , n s is the number of support vectors, α i is the Lagrange multiplier, y i is the output value corresponding to the support vector X i , b is the bias term, T is the temperature, P is the pressure, F n are the physical properties of the high-temperature molten salt and the parameters of the transmitter sensing element.

[0028] Preferably, the physical properties of the high-temperature molten salt include the density and viscosity of the high-temperature molten salt, and the parameters of the transmitter sensing element include the elastic modulus and thermal expansion coefficient of the strain gauge.

[0029] Preferably, use the training set data to train the model. During the training process, continuously adjust the kernel function parameter γ, the Lagrange multiplier α i and the bias term b. Calculate the error between the model prediction result and the actual output of the training set by the gradient descent method, and adjust the parameters according to the gradient direction of the error to gradually reduce the error.

[0030] Preferably, a temperature compensation system for a high-temperature molten salt pressure transmitter includes:

[0031] A data acquisition module, which is used to collect working data by using a sensor in the actual working environment of the high-temperature molten salt pressure transmitter;

[0032] A data preprocessing module, which performs denoising and filtering preprocessing on the working data collected by the sensor to remove noise and interference in the data and improve the data quality;

[0033] A model construction module, which analyzes the relationship between the change of the physical properties of the high-temperature molten salt with temperature and pressure measurement, and combines the material properties of the sensing element of the pressure transmitter to establish a temperature-pressure model based on physical principles; at the same time, construct a support vector machine data-driven model;

[0034] The model training and testing module divides the working data into a training set and a testing set, uses the training set data to train a support vector machine data-driven model, and uses the testing set to test the trained model to evaluate the model performance;

[0035] The model fusion module fuses the temperature-pressure model with the data-driven model, and uses the output of the temperature-pressure model as the input of the data-driven model;

[0036] The compensation calculation module, when the high-temperature molten salt pressure transmitter is actually working, collects the data required by the fusion model in real time, and calculates the compensated pressure measurement value after inputting it into the fusion model.

[0037] Preferably, a temperature compensation device for a high-temperature molten salt pressure transmitter includes: a memory for storing a computer program; a processor for executing the computer program to implement a temperature compensation method for a high-temperature molten salt pressure transmitter according to any one of the claims.

[0038] Preferably, a computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, it implements a temperature compensation method for a high-temperature molten salt pressure transmitter according to any one of the claims.

[0039] The technical effects and advantages of the present invention:

[0040] 1. By using the physical properties of high-temperature molten salt, the material properties of the sensitive element, and the variation relationship between the two with temperature, a temperature-pressure model based on physical principles is established, and combined with a support vector machine data-driven model for fusion compensation, which realizes more accurate compensation for the influence of temperature on pressure measurement, meets the high-precision measurement requirements of high-temperature molten salt pressure transmitters in complex working environments, effectively reduces measurement errors, and improves the accuracy of measurement results.

[0041] 2. The data-driven model uses a support vector machine combined with a radial basis function, which can adapt to the changes in the temperature-pressure relationship of high-temperature molten salt pressure transmitters under different working conditions. The model fusion mechanism further enhances the adaptability to various working conditions, enabling the compensation method to better cope with the complex changes in actual work and ensuring the stability and reliability of measurement.

[0042] 3. The collected working data is preprocessed by denoising and filtering to remove noise and interference, improving the data quality, providing a reliable basis for model training and compensation calculation. The model training and testing process ensure the accuracy and generalization ability of the data-driven model. The model fusion determines the optimal method and weight through experiments and data analysis. The whole process ensures the reliability of the temperature compensation method and reduces the risk of measurement errors caused by temperature changes. Description of the Drawings

[0043] Figure 1 Schematic diagram of a temperature compensation method for a high-temperature molten salt pressure transmitter according to the present invention. Specific implementation manner

[0044] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with 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.

[0045] The present invention provides a temperature compensation method for a high-temperature molten salt pressure transmitter as shown in Figure 1 and includes the following steps:

[0046] S1: Analyze the relationship between the change of the physical properties of high-temperature molten salt with temperature and pressure measurement, and establish a temperature-pressure model based on physical principles in combination with the material properties of the sensitive element of the pressure transmitter.

[0047] S2: In the actual working environment of the high-temperature molten salt pressure transmitter, use the sensor to collect working data.

[0048] S3: Through data-driven by support vector machines, divide the working data into a training set and a test set, and use the training set and test set to train and test the data-driven model.

[0049] S4: Integrate the temperature-pressure model and the data-driven model. The output of the temperature-pressure model is used as the input of the data-driven model. Combine experiments and data analysis to determine the optimal integration method and weight allocation between the temperature-pressure model and the data-driven model.

[0050] S5: When the high-temperature molten salt pressure transmitter is actually working, collect the integrated model data in real time, and calculate the compensated pressure measurement value after inputting it into the integrated model.

[0051] Furthermore, the method also includes denoising and filtering preprocessing of the working data collected by the sensor.

[0052] Furthermore, the parameters of the temperature-pressure model include the deduced pressure measurement value P, temperature T, molten salt density ρ, elastic modulus E of the sensitive element. The sensitive element is a strain gauge. According to the density data of high-temperature molten salt at different temperatures, use a densitometer to measure the density within a specific temperature range, and establish a relationship between the molten salt density ρ and the temperature T,

[0053] ρ = ρ0 + k1T + k2T 2 ;

[0054] Obtain the characteristic data of the elastic modulus E and the coefficient of thermal expansion α of the sensitive element, analyze the relationship between the characteristic data and the temperature change, and establish the relationship between the elastic modulus E and the temperature T.

[0055] E = E0(1 + k3T);

[0056] According to hydrodynamics and elasticity, construct a temperature-pressure model.

[0057]

[0058] Among them, k1, k2, k3, and E0 are constant terms, g is the acceleration due to gravity, h is the height of the molten salt, and ΔT is the temperature change.

[0059] Furthermore, in the working data collected by the sensor, the working data includes temperature, pressure, physical properties of high-temperature molten salt, and parameters of the sensitive element of the transmitter. The physical properties of high-temperature molten salt include the density and viscosity of high-temperature molten salt, and the parameters of the sensitive element of the transmitter include the elastic modulus and coefficient of thermal expansion of the strain gauge.

[0060] Furthermore, in the support vector machine data-driven model, the radial basis function is used as the kernel function. The kernel function is used to enable the support vector machine to handle nonlinear problems. The relationship of the kernel function is

[0061] K(X i , X) = exp(-γ||X - X i || 2 );

[0062] Based on the kernel function, construct a decision function. The decision function is used to predict the pressure measurement value. The relationship of the decision function is

[0063]

[0064] Construct the input vector of the support vector machine data-driven model. The input vector constitutes the input information of the data-driven model. The input vector is

[0065] X = [T, P, F1, F2,..., F n ;

[0066] Among them, γ is the kernel function parameter, X is the input vector, X i is the support vector, ||X - X i || 2 is the square of the Euclidean distance between the input vector X and the support vector X i , n s is the number of support vectors, α i is the Lagrange multiplier, y i is the output value corresponding to the support vector X i and b is the bias term, T is the temperature, P is the pressure, Fn are the physical properties of high-temperature molten salt and the parameters of the sensitive element of the transmitter;

[0067] Furthermore, the model is trained using the training set data. During the training process, the kernel function parameter γ, the Lagrange multiplier α i and the bias term b are continuously adjusted. The error between the model prediction result and the actual output of the training set is calculated by the gradient descent method, and the parameters are adjusted according to the gradient direction of the error to gradually reduce the error.

[0068] In the embodiment of the present invention, the physical properties of high-temperature molten salt at different temperatures and the material properties of the sensitive element of the pressure transmitter are deeply studied, including the elastic modulus and the coefficient of thermal expansion. Through experimental measurement and theoretical analysis, the relationship between the density of molten salt and temperature and the relationship between the elastic modulus and temperature are established, and a temperature-pressure model based on physical principles is constructed according to the principles of fluid mechanics and elasticity theory; in the actual working environment of the high-temperature molten salt pressure transmitter, working data such as temperature, pressure, the physical properties of high-temperature molten salt and the parameters of the sensitive element of the transmitter are collected by sensors. To improve the data quality, preprocessing operations such as denoising and filtering are performed on the collected data to remove noise and interference in the data and provide reliable data for subsequent model training and analysis.

[0069] The support vector machine is used as the data-driven model, and the preprocessed working data is divided into a training set and a test set. The input vector is composed of temperature, pressure, the physical properties of high-temperature molten salt, and the parameters of the sensitive element of the transmitter, and the radial basis function is used as the kernel function to construct the decision function. During the training process, the kernel function parameter, the Lagrange multiplier, and the bias term are continuously adjusted by the gradient descent method to gradually reduce the error between the model prediction result and the actual output of the training set. After the training is completed, the test set is used to test the model to evaluate the performance of the model and ensure the accuracy and generalization ability of the model.

[0070] The temperature-pressure model based on physical principles is fused with the data-driven model, and the output of the temperature-pressure model is used as the input of the data-driven model. Through a large number of experiments and data analysis, the optimal fusion method and weight allocation of the two models are determined to give full play to the description ability of the physical model for physical processes and the fitting ability of the data-driven model for complex non-linear relationships.

[0071] When the high-temperature molten salt pressure transmitter is actually working, the data required by the fusion model is collected in real time, input into the fusion model for calculation, and the compensated pressure measurement value is obtained, effectively compensating for the influence of temperature on pressure measurement and improving the accuracy of pressure measurement.

[0072] By comprehensively considering the physical properties of high-temperature molten salts, the material properties of sensitive elements, and the variation relationship between the two with temperature, through the establishment and fusion of physical models and data-driven models, the influence of temperature on pressure measurement can be compensated more accurately. Compared with traditional methods, the accuracy of pressure measurement is greatly improved, meeting the high-precision measurement requirements of high-temperature molten salt pressure transmitters in complex working environments.

[0073] The present invention also provides a temperature compensation system for a high-temperature molten salt pressure transmitter, including:

[0074] A data acquisition module, which is used to collect working data by using sensors in the actual working environment of the high-temperature molten salt pressure transmitter;

[0075] A data preprocessing module, which performs denoising and filtering preprocessing on the working data collected by the sensors, removes noise and interference in the data, and improves the data quality;

[0076] A model construction module, which analyzes the relationship between the variation of the physical properties of high-temperature molten salts with temperature and pressure measurement, and combines the material properties of the sensitive elements of the pressure transmitter to establish a temperature-pressure model based on physical principles; at the same time, a support vector machine data-driven model is constructed;

[0077] A model training and testing module, which divides the working data into a training set and a testing set, uses the training set data to train the support vector machine data-driven model, and uses the testing set to test the trained model to evaluate the model performance;

[0078] A model fusion module, which fuses the temperature-pressure model and the data-driven model, and takes the output of the temperature-pressure model as the input of the data-driven model;

[0079] A compensation calculation module, which, when the high-temperature molten salt pressure transmitter is actually working, collects the data required by the fusion model in real time, and calculates the compensated pressure measurement value after inputting it into the fusion model.

[0080] A temperature compensation device for a high-temperature molten salt pressure transmitter, including: a memory for storing a computer program; a processor for executing the computer program to implement a temperature compensation method for a high-temperature molten salt pressure transmitter in an embodiment.

[0081] A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, a temperature compensation method for a high-temperature molten salt pressure transmitter in an embodiment is implemented.

[0082] The foregoing has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, various changes and improvements will occur to the present invention, and these changes and improvements fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. A temperature compensation method for a high-temperature molten salt pressure transmitter, characterized in that the method Including: Analyze the relationship between the physical properties of high-temperature molten salt changing with temperature and pressure measurement, and combine with the material properties of the sensitive element of the pressure transmitter to establish a temperature-pressure model based on physical principles; In the actual working environment of the high-temperature molten salt pressure transmitter, use the sensor to collect working data; Through data-driven by support vector machine, divide the working data into a training set and a test set, and use the training set and test set to train and test the data-driven model; Fuse the temperature-pressure model and the data-driven model. The output of the temperature-pressure model is used as the input of the data-driven model. Combine experiments and data analysis to determine the optimal fusion method and weight allocation between the temperature-pressure model and the data-driven model; When the high-temperature molten salt pressure transmitter is actually working, collect the fusion model data in real time, and calculate the compensated pressure measurement value after inputting it into the fusion model.

2. A temperature compensation method for a high-temperature molten salt pressure transmitter according to claim 1, characterized in that: The method also includes denoising and filtering preprocessing of the working data collected by the sensor.

3. A temperature compensation method for a high-temperature molten salt pressure transmitter according to claim 1, characterized in that: The parameters of the temperature-pressure model include the derived pressure measurement value P, temperature T, molten salt density ρ, elastic modulus E of the sensing element. The sensing element is a strain gauge. According to the density data of high-temperature molten salt at different temperatures, the density within a specific temperature range is measured using a densitometer, and a relationship between the molten salt density ρ and temperature T is established, ρ = ρ0 + k1T + k2T 2 ; Obtain the characteristic data of the elastic modulus E and the thermal expansion coefficient α of the sensitive element, analyze the relationship between the characteristic data and temperature change, and establish the relationship between the elastic modulus E and temperature T, E = E0(1 + k3T); According to fluid mechanics and elasticity, construct a temperature-pressure model, where k1, k2, k3, and E0 are constant terms, g is the acceleration due to gravity, h is the height of the molten salt, and ΔT is the temperature change.

4. A temperature compensation method for a high-temperature molten salt pressure transmitter according to claim 1, characterized in that: Among the working data collected by the sensor, the working data includes temperature, pressure, physical properties of high-temperature molten salt, and parameters of the sensitive element of the transmitter.

5. A temperature compensation method for a high-temperature molten salt pressure transmitter according to claim 1, characterized in that: In the support vector machine data-driven model, use the radial basis function as the kernel function. The kernel function is used to enable the support vector machine to handle nonlinear problems. The relationship of the kernel function is, K(X i ,X) = exp(-γ||X - X i || 2 ); Based on the kernel function, construct a decision function. The decision function is used to predict the pressure measurement value. The relationship of the decision function is, Construct the input vector of the support vector machine data-driven model. The input vector constitutes the input information of the data-driven model. The input vector is, X = [T, P, F1, F2,..., F n ; where γ is the kernel function parameter, X is the input vector, X i is the support vector, ||X - X i || 2 is the square of the Euclidean distance between the input vector X and the support vector X i , n s is the number of support vectors, α i is the Lagrange multiplier, y i is the output value corresponding to the support vector X i , b is the bias term, T is the temperature, P is the pressure, F n is the physical property of the high-temperature molten salt and the parameter of the sensitive element of the transmitter.

6. A temperature compensation method for a high-temperature molten salt pressure transmitter according to claim 5, characterized in that: The physical properties of high-temperature molten salt include the density and viscosity of high-temperature molten salt, and the parameters of the sensitive element of the transmitter include the elastic modulus and thermal expansion coefficient of the strain gauge.

7. A temperature compensation method for a high-temperature molten salt pressure transmitter according to any one of claims 1 or 5, characterized in that: The model is trained using the training set data. During the training process, the kernel function parameter γ, the Lagrange multiplier α i and the bias term b are continuously adjusted. The error between the model prediction result and the actual output of the training set is calculated by the gradient descent method, and the parameters are adjusted according to the gradient direction of the error to gradually reduce the error.

8. A temperature compensation system for a high-temperature molten salt pressure transmitter, characterized in that, Including: A data acquisition module, which is used to collect working data by using a sensor in the actual working environment of the high-temperature molten salt pressure transmitter; A data preprocessing module, which performs denoising and filtering preprocessing on the working data collected by the sensor, removes the noise and interference in the data, and improves the data quality; A model construction module, which analyzes the relationship between the physical properties of high-temperature molten salt changing with temperature and pressure measurement, and combines with the material properties of the sensitive element of the pressure transmitter to establish a temperature-pressure model based on physical principles; at the same time, constructs a support vector machine data-driven model; A model training and testing module, which divides the working data into a training set and a test set, uses the training set data to train the support vector machine data-driven model, and uses the test set to test the trained model to evaluate the model performance; A model fusion module, which fuses the temperature-pressure model and the data-driven model, and uses the output of the temperature-pressure model as the input of the data-driven model; The compensation calculation module, when the high-temperature molten salt pressure transmitter is actually working, collects the data required by the fusion model in real time, and after inputting it into the fusion model, calculates the compensated pressure measurement value.

9. A temperature compensation device for a high-temperature molten salt pressure transmitter, characterized in that, It includes: A memory for storing computer programs; A processor for executing the computer program to implement a temperature compensation method for a high-temperature molten salt pressure transmitter according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, it implements a temperature compensation method for a high-temperature molten salt pressure transmitter according to any one of claims 1 to 7.

Images