Temperature compensation method and system for temperature and pressure integrated sensor

Abstract

The application discloses a temperature compensation method and system for a temperature and pressure integrated sensor, calibrates sensor data, obtains pressure output U p and temperature output U t under different pressures and different temperatures, processes the pressure output U p and the temperature output U t , extracts pressure output U t corresponding to different input pressures P under the same temperature output U p , fits the relationship between the pressure output U p and the input pressure P, obtains polynomial fitting coefficients, determines the relationship between the polynomial fitting coefficients and the temperature by using a relevant vector machine, determines the polynomial fitting coefficients according to the temperature output U t in a group of sensor data, and obtains compensated pressure values according to the polynomial fitting coefficients and the pressure output U p . By combining the polynomial fitting and the relevant vector machine, the temperature compensation precision of the sensor is greatly improved.

Description

Technical Field

[0001] This invention belongs to the field of sensor temperature compensation technology, specifically relating to a temperature compensation method and system for an integrated temperature and pressure sensor. Background Technology

[0002] High-precision pressure measurement is a prerequisite for process control and safety monitoring in industrial fields, thus creating a significant demand for high-precision pressure sensors. Piezoresistive pressure sensors, with their high sensitivity, high accuracy, fast response, and small size, have become the preferred choice for pressure measurement systems in industrial applications. However, due to the characteristics of semiconductor materials and processing techniques, piezoresistive pressure sensors are prone to temperature drift, leading to a non-linear relationship between the measured pressure and the output voltage. Therefore, temperature compensation is necessary for piezoresistive pressure sensors.

[0003] Common temperature compensation methods include hardware compensation and software compensation. Hardware compensation suffers from drawbacks such as poor versatility, difficulty in adjustment, and low accuracy. Software compensation offers high accuracy, flexibility, and lower cost, and mainly includes numerical analysis and machine learning methods. Numerical analysis methods often employ interpolation and polynomial fitting, offering strong interpretability and simple operation, but with limited nonlinear fitting capabilities and low accuracy. Machine learning methods often use neural networks, capable of performing complex nonlinear modeling with high accuracy, but prone to overfitting with small datasets, and suffer from complex optimization processes and long training times.

[0004] Data acquisition is fundamental to developing software compensation models. Traditional data acquisition processes often involve placing platinum resistance thermometers around the pressure chip for temperature measurement. However, this method cannot reflect the real-time temperature of the pressure chip and requires a long holding time for the pressure chip and platinum resistance thermometer to reach thermal equilibrium before data acquisition can begin. This results in poor continuity, high time costs, and difficulties in acquiring large-scale data, thus affecting model accuracy. Summary of the Invention

[0005] The technical problem to be solved by this invention is to address the shortcomings of the prior art by providing a temperature compensation method and system using an integrated temperature and pressure sensor. The method uses an integrated temperature and pressure sensor to collect data, and the model combines correlation vector machine and polynomial fitting to solve the technical problems of poor performance of existing software compensation models and low temperature compensation accuracy caused by difficulties in large-scale data acquisition.

[0006] The present invention adopts the following technical solution:

[0007] A temperature compensation method for an integrated temperature and pressure sensor includes the following steps:

[0008] S1. Calibrate the sensor data to obtain the pressure output U under different pressures and temperatures. p and temperature output U t ;

[0009] S2, The pressure output U obtained in step S1 p and temperature output U t Process and extract the output U at the same temperature. t Pressure output U corresponding to different input pressures P p Fitted pressure output U p The relationship between the input pressure P and the polynomial fitting coefficients are obtained.

[0010] S3. Use a correlation vector machine to determine the relationship between the polynomial fitting coefficients obtained in step S2 and the temperature, and output U based on the temperature from a set of sensor data. t Determine the polynomial fitting coefficients, and then use the polynomial fitting coefficients and pressure output U as the basis for the determination. p The pressure value after compensation.

[0011] Specifically, step S1 is as follows:

[0012] S101. Select pressure points uniformly within the range of the integrated temperature and pressure sensor;

[0013] S102. Power the sensor with a constant current source and apply a constant pressure to the sensor for each pressure calibration point P;

[0014] S103. Continuously heat or cool the sensor within its operating temperature range, and measure the voltage U representing the pressure output under the same input pressure P. p and the voltage U representing the temperature output t ;

[0015] S104. When the temperature of the temperature chamber reaches the upper or lower limit of the sensor's operating temperature, repeat steps S102 and S103 until all pressure calibration point data have been measured.

[0016] Furthermore, in step S101, the pressure calibration point is between 0%FS and 100%FS.

[0017] Specifically, step S2 is as follows:

[0018] S201. Process the data obtained in step S1;

[0019] S202, Extracting the same temperature U t Output U corresponding to different pressures P p ;

[0020] S203. Use the least squares method to fit the pressure P and output U at the same temperature. p Based on the relationship between them, a polynomial fitting function is derived;

[0021] S204. Obtain the coefficient matrix based on the polynomial fitting function.

[0022] Furthermore, in step S201, data processing includes filtering to remove duplicate data.

[0023] Furthermore, in step S203, the polynomial fitting function is specifically as follows:

[0024]

[0025] Where P is the input standard pressure, U p The voltage value represents the pressure output, n is the number of temperature points, and C i,k is the fitting coefficient, i = 1, 2, ..., n, and k is the fitting order.

[0026] Furthermore, in step S204, the coefficient matrix of the polynomial fitting function is:

[0027]

[0028] Specifically, step S3 is as follows:

[0029] S301. Construct a relevant vector machine sample dataset by taking temperature Ut as input and the polynomial coefficients at the corresponding temperature as output.

[0030] S302. Divide the sample dataset into a training sample set and a test sample set and perform normalization processing;

[0031] S303. Select the kernel function of the relevant vector machine and train the training samples;

[0032] S304. Test using the trained correlation vector machine test samples;

[0033] S305. Substitute the coefficients output by the correlation vector machine into the relationship between the input pressure and the output voltage to obtain the compensated accuracy.

[0034] Furthermore, in step S301, the sample dataset is:

[0035]

[0036] Among them, Ut n C represents the temperature values ​​at different temperature points. i,k is the fitting coefficient, i = 1, 2, ..., n, and k is the fitting order.

[0037] Secondly, embodiments of the present invention provide a temperature compensation system for an integrated temperature and pressure sensor, comprising:

[0038] The calibration module calibrates the sensor data to obtain the pressure output U under different pressures and temperatures.p and temperature output U t ;

[0039] The fitting module adapts the pressure output U obtained from the calibration module. p and temperature output U t Process and extract the output U at the same temperature. t Pressure output U corresponding to different input pressures P p Fitted pressure output U p The relationship between the input pressure P and the polynomial fitting coefficients are obtained.

[0040] The compensation module uses a correlation vector machine to determine the relationship between the polynomial fitting coefficients obtained by the fitting module and the temperature, and outputs U based on the temperature from a set of sensor data. t Determine the polynomial fitting coefficients, and then use the polynomial fitting coefficients and pressure output U as the basis for the determination. p The pressure value after compensation.

[0041] Compared with the prior art, the present invention has at least the following beneficial effects:

[0042] A temperature compensation method for an integrated temperature and pressure sensor is proposed, which divides the compensation process of the integrated temperature and pressure sensor into three steps. The compensation steps are clear, concise, and easy to operate.

[0043] Furthermore, by employing an integrated temperature and pressure sensor, temperature and pressure data can be acquired simultaneously without the need for heat preservation, overcoming the problem of traditional pressure sensors requiring prolonged heat preservation during data acquisition. Moreover, through continuous heating and cooling, a large amount of experimental data can be obtained in a short time, laying the foundation for the establishment of a high-precision temperature compensation model.

[0044] Furthermore, setting the pressure calibration point between 0%FS and 100%FS ensures the integrity of the sensor data, making the compensation method effective throughout the entire range of the sensor.

[0045] Furthermore, traditional temperature compensation methods explore the relationship between sensor input pressure, temperature, and output voltage. This method divides this process into two stages: the first stage explores the relationship between input pressure and output voltage (step S2), and the second stage incorporates the effect of temperature (step S3). When the temperature remains constant, the sensor's input-output linearity is very high. This approach of dividing the compensation process into two steps utilizes this characteristic of the sensor to improve the accuracy of sensor compensation.

[0046] Furthermore, to eliminate the impact of environmental noise on the sensor output, the data is filtered. Because quantization errors exist during data acquisition by the experimental equipment, many data points are duplicated; removing duplicate data reduces the computational load.

[0047] Furthermore, when the temperature remains constant, the sensor's input and output linearity is very high. Based on this characteristic, polynomial fitting is used for the sensor's input pressure and output voltage at the same temperature, which ensures accuracy while avoiding the use of complex machine learning models.

[0048] Furthermore, setting the coefficients of the polynomial fitting function to matrix form forms the basis for constructing the subsequent related vector machine sample dataset.

[0049] Furthermore, by employing a correlation vector machine with fewer parameters and faster computation speed, the problems of complex and time-consuming optimization process and slow convergence in traditional machine learning are overcome, thereby reducing time costs while ensuring compensation accuracy.

[0050] Furthermore, training the correlation vector machine requires sample data, so temperature is used as input and the polynomial coefficients at this temperature are used as output to construct the correlation vector machine sample dataset.

[0051] It is understandable that the beneficial effects of the second aspect mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0052] In summary, this invention shortens the temperature compensation time of pressure sensors by employing an integrated temperature and pressure sensor, which can simultaneously acquire temperature and pressure data without the need for heat preservation, overcoming the problem of long-term heat preservation required in the data acquisition process of traditional pressure sensors. Furthermore, it utilizes a correlation vector machine with fewer parameters and faster computation speed, overcoming the problems of complex and time-consuming optimization processes and slow convergence in traditional machine learning, thus reducing time costs. Secondly, it improves the temperature compensation accuracy of pressure sensors. Through continuous heating and cooling, a large amount of experimental data can be obtained in a short time, laying the foundation for the establishment of a high-precision temperature compensation model. Finally, considering the insufficient nonlinear fitting ability of traditional numerical analysis methods and the overfitting problem of machine learning methods, based on the sensor's own output characteristics, by combining polynomial fitting and a correlation vector machine, the temperature compensation accuracy of the sensor is greatly improved.

[0053] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0054] Figure 1 This is a circuit schematic diagram of the integrated temperature and pressure sensor of the present invention;

[0055] Figure 2 This is a flowchart of the data calibration process for the integrated temperature and pressure sensor of the present invention;

[0056] Figure 3 This is a calibration data diagram of the integrated temperature and pressure sensor of the present invention at 0 MPa;

[0057] Figure 4This is a graph showing the relationship between the coefficient C0 and temperature.

[0058] Figure 5 This is the error graph after temperature compensation. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0061] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0062] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this invention generally indicates that the preceding and following objects have an "or" relationship.

[0063] It should be understood that although terms such as first, second, third, etc., may be used in the embodiments of the present invention to describe the preset range, these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from one another. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0064] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0065] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0066] This invention discloses a temperature compensation method for an integrated temperature and pressure sensor, comprising the following steps:

[0067] S1. Calibrate the sensor data to obtain U, representing the pressure output, under different pressures and temperatures. p and U, representing the temperature output t ;

[0068] S101. Select pressure points uniformly within the range of the integrated temperature and pressure sensor, wherein the pressure calibration points are between 0%FS and 100%FS;

[0069] S102. Place the sensor in the temperature chamber and power it with a constant current source. For each pressure calibration point P, apply a constant pressure to the sensor using a piston pressure gauge.

[0070] S103. The temperature chamber continuously heats or cools down within the sensor's operating temperature range, measuring the voltage U representing the pressure output under the same input pressure P. p and the voltage U representing the temperature output t ;

[0071] S104. When the temperature of the temperature chamber reaches the upper or lower limit of the sensor's operating temperature, repeat steps S102 and S103 until all pressure calibration point data have been measured.

[0072] S2. Process the measured data and extract the temperature U. t The output U corresponding to different input pressures P p Fitting U p The relationship between P and the polynomial fitting coefficients is used to obtain the polynomial fitting coefficients.

[0073] S201. Process the data collected in step S1, including filtering and removing duplicate data.

[0074] S202, Extracting the same temperature U t Output U corresponding to different pressures P p .

[0075] S203. Use the least squares method to fit the pressure P and output U at the same temperature. p Based on the relationship between them, the polynomial fitting function is derived, namely:

[0076]

[0077] Where P is the input standard pressure, U p The voltage value represents the pressure output, n is the number of temperature points, and C i,k is the fitting coefficient, i = 1, 2, ..., n, and k is the fitting order.

[0078] S204. The coefficient matrix obtained from the polynomial fitting function is as follows:

[0079]

[0080] S3. Use the correlation vector machine to obtain the relationship between each coefficient and temperature.

[0081] S301. Using temperature Ut as input and the polynomial coefficients at this temperature as output, construct a relevant vector machine sample dataset. The sample dataset is as follows:

[0082]

[0083] S302. Divide the sample dataset into a training sample set and a test sample set and perform normalization processing;

[0084] S303. Select the kernel function of the relevant vector machine and train the training samples;

[0085] S304. Test using the trained correlation vector machine test samples;

[0086] S305. Substitute the coefficients output by the correlation vector machine into the relationship between the input pressure and the output voltage to obtain the compensated accuracy.

[0087] In another embodiment of the present invention, a temperature compensation system for an integrated temperature and pressure sensor is provided. This system can be used to implement the above-mentioned temperature compensation method for the integrated temperature and pressure sensor. Specifically, the temperature compensation system for the integrated temperature and pressure sensor includes a calibration module, a fitting module, and a compensation module.

[0088] The calibration module calibrates the sensor data to obtain the pressure output U under different pressures and temperatures. p and temperature output U t ;

[0089] The fitting module adapts the pressure output U obtained from the calibration module. p and temperature output U t Process and extract the output U at the same temperature. t Pressure output U corresponding to different input pressures P p Fitted pressure output U p The relationship between the input pressure P and the polynomial fitting coefficients are obtained.

[0090] The compensation module uses a correlation vector machine to determine the relationship between the polynomial fitting coefficients obtained by the fitting module and the temperature, and outputs U based on the temperature from a set of sensor data. t Determine the polynomial fitting coefficients, and then use the polynomial fitting coefficients and pressure output U as the basis for the determination. p The pressure value after compensation.

[0091] In another embodiment of the present invention, a terminal device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used for the operation of a temperature compensation method for an integrated temperature and pressure sensor, including:

[0092] The sensor data is calibrated to obtain the pressure output U under different pressures and temperatures. p and temperature output U t ; for pressure output U p and temperature output U t Process and extract the output U at the same temperature. t Pressure output U corresponding to different input pressures Pp Fitted pressure output U p The relationship between the input pressure P and the polynomial fitting coefficients is obtained; the relationship between the polynomial fitting coefficients and temperature is determined using a correlation vector machine; and the temperature output U is determined based on a set of sensor data. t Determine the polynomial fitting coefficients, and then use the polynomial fitting coefficients and pressure output U as the basis for the determination. p The pressure value after compensation.

[0093] In another embodiment of the present invention, a storage medium is also provided, specifically a computer-readable storage medium (memory). This computer-readable storage medium is a memory device in a terminal device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and extended storage media supported by the terminal device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device.

[0094] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the temperature compensation method for the integrated temperature and pressure sensor in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps:

[0095] The sensor data is calibrated to obtain the pressure output U under different pressures and temperatures. p and temperature output U t ; for pressure output U p and temperature output U t Process and extract the output U at the same temperature. t Pressure output U corresponding to different input pressures P p Fitted pressure output U p The relationship between the input pressure P and the polynomial fitting coefficients is obtained; the relationship between the polynomial fitting coefficients and temperature is determined using a correlation vector machine; and the temperature output U is determined based on a set of sensor data. t Determine the polynomial fitting coefficients, and then use the polynomial fitting coefficients and pressure output U as the basis for the determination. p The pressure value after compensation.

[0096] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0097] Please see Figure 1 ,

[0098] The four force-sensitive resistors in a silicon piezoresistive pressure sensor form a Wheatstone bridge. A platinum resistance thermometer (PT500) is connected to one end of the bridge to measure temperature. By integrating the platinum resistance thermometer onto the pressure chip using MEMS technology, a temperature-pressure integrated sensor is formed. This ensures that the temperature of the platinum resistance thermometer and the pressure diaphragm remain consistent at all times, which is beneficial for collecting large amounts of data.

[0099] Specifically, a constant current source is used to power the temperature and pressure sensor. In this case, the output voltage across bridge terminals b and d reflects the input pressure, i.e.:

[0100] U p =U bd (2)

[0101] The voltage to ground at terminal c of the bridge is the voltage across the platinum resistance circuit, reflecting the temperature around the bridge, i.e.:

[0102] U t =U c (3)

[0103] Figure 2The calibration process for the sensor data begins by selecting several pressure calibration points within the pressure sensor's range. In this example, the integrated temperature and pressure sensor has a pressure range of 0–20 MPa, and the selected calibration points are 0 MPa, 5 MPa, 10 MPa, 15 MPa, and 20 MPa. The sensor is then mounted on a pressure extension device, which is placed in a temperature chamber. No pressure is applied to the sensor (0 MPa). The temperature range of this integrated temperature and pressure sensor is 0–80°C. The temperature chamber is continuously heated from 0°C to 80°C, and the pressure output (Up) and temperature output (Ut) at 0 MPa are measured. After the heating is complete, a piston gauge applies a pressure of 5 MPa to the sensor, and the temperature chamber is continuously cooled from 80°C to 0°C, with Up and Ut measured again. This process is repeated until Up and Ut at all pressure calibration points have been measured.

[0104] Next, the obtained data is processed. Due to limitations of the experimental equipment, the data contains noise and many duplicate points. Therefore, filtering and removal of duplicate data are necessary. In this example, mean filtering is used. Figure 3 This is the processed data at 0 MPa. Extract the U at the same temperature. t Different voltage outputs U p When the temperature remains constant, the linearity of a piezoresistive pressure sensor is inherently high; therefore, numerical analysis can be used to fit the relationship between the input pressure and the output voltage. This example uses a quadratic polynomial function to fit the relationship between the output voltage Up and the input pressure P at the same temperature, i.e.:

[0105]

[0106] Figure 4 For coefficient C i,0 The relationship between temperature and temperature exhibits strong nonlinearity, making traditional numerical analysis methods inadequate for fitting the desired values. The correlation vector machine (CRM), an algorithm based on sparse Bayesian theory, possesses a sparser framework and fewer kernel function constraints, offering advantages such as strong generalization ability, fewer parameters, and high speed. Therefore, a CRM model is used to fit the relationship between the coefficients and temperature, i.e.:

[0107] (C0,C1,C2)=f(Ut) (5)

[0108] Among them, C m =[C 1,m C 2,m C i,m ,…C n,m ]',m=0,1,2.

[0109] The following describes the steps for building the relevant vector machine model. Using temperature Ut as input and the polynomial coefficients at this temperature as output, a sample dataset is constructed. The sample dataset is as follows:

[0110]

[0111] First, the sample dataset is divided into a training sample set and a test sample set in a 3:1 ratio. The training set is used to train the relevant vector machine model, and the test set is used to test the model's performance. Then, the data in both the training and test sample sets are normalized. The normalization formula is:

[0112]

[0113] Where x is the data that needs to be normalized, x min x is the minimum value of the data. max y represents the maximum value of the data, and y represents the normalized value.

[0114] Next, the kernel function of the correlation vector machine is selected; in this example, a Gaussian kernel function is chosen, and the kernel width parameter is randomly initialized. The correlation vector machine is used to train the training sample set, and then used to test the test samples. Finally, the output of the correlation vector machine is denormalized. The root mean square error of the prediction results of each coefficient on the training and test sets after processing is shown in Table 1 below:

[0115] Table 1: Prediction Results of Correlation Vector Machine

[0116] <![CDATA[C0 training set]]> 0.0012 <![CDATA[C0 Test Set]]> 0.0015 <![CDATA[C1 training set]]> 0.0003 <![CDATA[C1 Test Set]]> 0.0003 <![CDATA[C2 training set]]> 0.0003 <![CDATA[C2 Test Set]]> 0.0004

[0117] It is evident that the root mean square error of the correlation vector machine in predicting each coefficient is small, indicating no overfitting and high prediction accuracy.

[0118] For a set of calibration data (P, Ut, Up) of a temperature and pressure sensor, substituting Ut into equation (5) yields the coefficients of each polynomial. Substituting these coefficients into equation (4) yields the compensated P'. Comparing P' and P gives the compensation accuracy. Sensor linearity is used as the evaluation standard for compensation accuracy, i.e.

[0119]

[0120] Among them, P span The pressure range measured by the sensor is 20 MPa in this example.

[0121] Figure 5 The final compensation error of this method is 0.0074 MPa, with a linearity of 0.037%.

[0122] The relationship between polynomial coefficients and temperature, if not using a high-precision correlation vector machine but instead employing a traditional polynomial fitting method, yields the results shown in Table 2.

[0123] Table 2: Polynomial Prediction Results

[0124] C0 training set 0.0364 0.0355 C0 test set 0.0397 0.0383 C1 training set 0.0025 0.0025 C1 test set 0.0026 0.0023 C2 training set <![CDATA[3.7955×10 -5 ]]> <![CDATA[3.7470×10 -5 ]]> C2 test set <![CDATA[3.8191×10 -5 ]]> <![CDATA[3.7088×10 -5 ]]>

[0125] As can be seen from the table, fitting the relationship between the coefficients and temperature using a quadratic polynomial yields high prediction accuracy for coefficient C2, but low accuracy for coefficients C0 and C1. Even with increasing the fitting order to use a cubic polynomial, the prediction accuracy is still not as good as that of the correlation vector machine.

[0126] If the sensor's temperature compensation is not divided into two steps, but instead directly seeks the relationship between input pressure, output voltage, and operating temperature, Table 3 shows the linearity and model setup time when using neural networks, genetic algorithms to optimize neural networks, and polynomial fitting compensation.

[0127] Table 3: Linearity and Modeling Time of Different Compensation Methods

[0128]

[0129] Table 3 shows that neural networks and polynomial fitting have short modeling times but low compensation accuracy. Genetic algorithms improve the compensation accuracy of neural networks, but the modeling time is 187.31 seconds, which is very time-consuming. In contrast, the proposed method has a modeling time of only 14.76 seconds, significantly reducing the compensation time while achieving higher compensation accuracy.

[0130] In summary, this invention provides a temperature compensation method and system for an integrated temperature and pressure sensor. Employing this integrated sensor, it can simultaneously acquire temperature and pressure data without the need for heat preservation, overcoming the problem of long-term heat preservation required in traditional pressure sensor data acquisition. Furthermore, it utilizes a correlation vector machine (LRM) with fewer parameters and faster computation speed, overcoming the complex and time-consuming optimization process and slow convergence issues in traditional machine learning. The final compensation model takes only 14.76 seconds, reducing time costs. Through continuous heating and cooling, a large amount of experimental data can be obtained in a short time, laying the foundation for establishing a high-precision temperature compensation model. Considering the insufficient nonlinear fitting ability of traditional numerical analysis methods and the overfitting problem of machine learning methods, based on the sensor's output characteristics, the temperature compensation is divided into two steps: polynomial fitting of the relationship between output voltage and temperature, and incorporating the temperature effect through a correlation vector machine. This significantly improves the sensor's temperature compensation accuracy, ultimately increasing the sensor's linearity to 0.037%FS, which is higher than the accuracy of commonly used numerical analysis and neural networks.

[0131] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0132] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0133] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0134] In the embodiments provided by this invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0135] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0136] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0137] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0138] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0139] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0140] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0141] The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made to the technical solution based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A temperature compensation method for an integrated temperature and pressure sensor, characterized in that, Includes the following steps: S1. Calibrate the sensor data to obtain pressure outputs under different pressures and temperatures. U p and temperature output U t ; S2, Pressure output obtained in step S1 U p and temperature output U t Process and extract the output at the same temperature. U t Different input pressures P Corresponding pressure output U p Fitting pressure output U p The relationship between the input pressure P and the polynomial fitting coefficients are obtained. S3. Use a correlation vector machine to determine the relationship between the polynomial fitting coefficients obtained in step S2 and the temperature, and output the temperature based on a set of sensor data. U t Determine the polynomial fitting coefficients, based on the polynomial fitting coefficients and pressure output. U p The pressure value after compensation.

2. The temperature compensation method for the integrated temperature and pressure sensor according to claim 1, characterized in that, Step S1 is as follows: S101. Select pressure points uniformly within the range of the integrated temperature and pressure sensor; S102. Power the sensor with a constant current source and apply a constant pressure to the sensor for each pressure calibration point P; S103. Continuously heat up or cool down within the sensor's operating temperature range, and measure the voltage representing the pressure output under the same input pressure P. U p and the voltage representing the temperature output U t ; S104. When the temperature of the temperature chamber reaches the upper or lower limit of the sensor's operating temperature, repeat steps S102 and S103 until all pressure calibration point data have been measured.

3. The temperature compensation method for the integrated temperature and pressure sensor according to claim 2, characterized in that, In step S101, the pressure calibration point is between 0%FS and 100%FS.

4. The temperature compensation method for the integrated temperature and pressure sensor according to claim 1, characterized in that, Step S2 is as follows: S201. Process the data obtained in step S1; S202, Extracting samples from the same temperature U t Output corresponding to different pressures P U p ; S203. Use the least squares method to fit the pressure P and output at the same temperature. U p Based on the relationship between them, a polynomial fitting function is derived; S204. Obtain the coefficient matrix based on the polynomial fitting function.

5. The temperature compensation method for the integrated temperature and pressure sensor according to claim 4, characterized in that, In step S201, data processing includes filtering to remove duplicate data.

6. The temperature compensation method for the integrated temperature and pressure sensor according to claim 4, characterized in that, In step S203, the polynomial fitting function is specifically as follows: Where P is the input standard pressure, U p The voltage value represents the pressure output, and n is the number of temperature points. is the fitting coefficient, i=1,2,…n, and k is the fitting order.

7. The temperature compensation method for the integrated temperature and pressure sensor according to claim 4, characterized in that, In step S204, the coefficient matrix of the polynomial fitting function is: Where n is the number of temperature points, is the fitting coefficient, i=1,2,…n, and k is the fitting order.

8. The temperature compensation method for the integrated temperature and pressure sensor according to claim 1, characterized in that, Step S3 is as follows: S301. Construct a relevant vector machine sample dataset by taking temperature Ut as input and the polynomial coefficients at the corresponding temperature as output. S302. Divide the sample dataset into a training sample set and a test sample set and perform normalization processing; S303. Select the kernel function of the relevant vector machine and train the training samples; S304. Test using the trained correlation vector machine test samples; S305, Substitute the coefficients output by the correlation vector machine into the input pressure P and the pressure output. U p The relationship between them is used to obtain the accuracy after compensation.

9. The temperature compensation method for the integrated temperature and pressure sensor according to claim 8, characterized in that, In step S301, the sample dataset is: Where n is the number of temperature points, These are the temperature values ​​at different temperature points. is the fitting coefficient, i=1,2,…n, and k is the fitting order.

10. A temperature compensation system for an integrated temperature and pressure sensor, characterized in that, include: The calibration module calibrates the sensor data to obtain pressure outputs under different pressures and temperatures. U p and temperature output U t ; The fitting module adapts the pressure output obtained from the calibration module. U p and temperature output U t Process and extract the output at the same temperature. U t Different input pressures P Corresponding pressure output U p Fitting pressure output U p The relationship between the input pressure P and the polynomial fitting coefficients are obtained. The compensation module uses a correlation vector machine to determine the relationship between the polynomial fitting coefficients obtained by the fitting module and the temperature, and outputs the temperature based on a set of sensor data. U t Determine the polynomial fitting coefficients, based on the polynomial fitting coefficients and pressure output. U p The pressure value after compensation.

Images