MEMS pressure sensor nonlinear correction method, system, equipment and medium

The support vector machine is optimized through the meme particle swarm optimization algorithm, and a nonlinear correction model is established, which solves the problem of nonlinear error of MEMS pressure sensor, improves measurement accuracy and reduces costs, and achieves efficient nonlinear correction effect.

CN119085931APending Publication Date: 2024-12-06NANJING GAOHUA TECH
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411206974.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

During the manufacturing process, MEMS pressure sensors produce nonlinear errors due to discreteness, inconsistent resistance temperature coefficient and environmental factors, resulting in a decrease in accuracy. The traditional accuracy compensation method cannot meet the needs of high-precision measurement.

Method used

The meme particle swarm optimization algorithm is used to optimize the parameters of the support vector machine, establish a nonlinear correction model, and perform nonlinear correction by inputting the output value of the sensor, and converting the output value before compensation into the output value after compensation by using the slack variable and constraint conditions to achieve non-compensation. Linear correction.

Benefits of technology

It improves the measurement accuracy of the MEMS pressure sensor, reduces the frequency of hardware updates, reduces production costs and equipment maintenance costs, and enhances the convergence speed and accuracy of the algorithm.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085931A_ABST
    Figure CN119085931A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides an MEMS pressure sensor nonlinear correction method, system and device and a medium. The method comprises the following steps: acquiring an output value of the MEMS pressure sensor; inputting the output value into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor; wherein the nonlinear correction model is pre-established by performing parameter optimization on the support vector machine through a memetic particle swarm optimization algorithm. According to the embodiment of the invention, an efficient MPSO-SVM nonlinear correction algorithm is utilized to carry out nonlinear compensation of the MEMS pressure sensor, the problems of small samples and nonlinearity are well solved, the diversity of particle swarms is kept, and adaptive adjustment is adopted, so that the ergodicity of the algorithm in a solution search space is improved. The measurement precision of an existing MEMS pressure sensor is improved through a software algorithm, and the hardware updating frequency can be reduced, so that the production cost of the pressure sensor and the equipment maintenance cost are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present disclosure belong to the technical field of nonlinear correction of pressure sensors, and specifically relate to a nonlinear correction method, system, device and medium for a MEMS pressure sensor. Background Art

[0002] MEMS pressure sensors are composed of sensitive elements and signal conversion circuits. The sensitive elements are used to detect the deformation caused by pressure, while the signal conversion circuit converts this mechanical deformation into an electrical signal output. MEMS pressure sensors have been widely used in defense, aerospace, automobile, biomedicine and other fields due to their high precision, small size and easy batch manufacturing.

[0003] The nonlinear problem mainly originates from the discreteness of the sensor manufacturing process, the inconsistency of the resistance temperature coefficient, and the influence of environmental factors such as temperature and humidity. In addition, the limitations of the sensor's own material and process conditions, as well as factors such as packaging stress, will also introduce additional stress, causing the resistance value of the varistor to change, thereby generating nonlinear characteristics. The nonlinear error of the MEMS pressure sensor is closely related to its accuracy. The larger the nonlinear error, the lower the accuracy. Traditional accuracy compensation methods cannot meet the needs of high-precision measurements. Summary of the invention

[0004] The embodiments of the present disclosure aim to solve at least one of the technical problems existing in the prior art and provide a MEMS pressure sensor nonlinear correction method, system, device and medium.

[0005] One aspect of the present disclosure provides a nonlinear correction method for a MEMS pressure sensor, the method comprising:

[0006] Get the output value of the MEMS pressure sensor;

[0007] The output value is input into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor; wherein,

[0008] The nonlinear correction model is pre-established by optimizing the parameters of a support vector machine using a memetic particle swarm optimization algorithm.

[0009] Furthermore, the nonlinear correction model is pre-established by optimizing the parameters of a support vector machine using a memetic particle swarm optimization algorithm, including:

[0010] M1, initialize the population size, maximum evolutionary generations, initial position and initial velocity of the particle swarm optimization algorithm, and initialize the error penalty parameters and Gaussian kernel parameters of the support vector machine;

[0011] M2, initialize the position and speed of particles, determine the number of particles, the initial value of the inertia factor, the maximum allowed number of iterations, the acceleration coefficient, the best position component of the corresponding dimension experienced by the initialized particles at different speeds, and the best position experienced by the current particle group at different speeds in the solution space;

[0012] M3. Calculate the individual extreme value of each particle and obtain the best position component of the corresponding dimension experienced by each particle at different speeds;

[0013] M4, evaluate the objective function of each particle, select the best individual extreme value as the global extreme value, obtain the best position experienced by the current particle group in the solution space at different speeds, and use the extreme value corresponding to the particle as the optimal parameter of the support vector machine in the next iteration;

[0014] M5. Update the speed and position of each particle and calculate the fitness value of each particle; if the fitness value is better than the current individual extreme value of the particle, set the best position component of the corresponding dimension experienced by the particle at different speeds as the position of the particle, and update the individual extreme value; if the best individual extreme value of all particles is better than the current global extreme value, set the best position experienced by the particle group in the solution space at different speeds as the position of the particle, and update the global extreme value, inertia weight, position and speed;

[0015] M6: Determine whether the end condition of the memetic particle swarm optimization algorithm is met. If so, stop the iteration; if the deviation exceeds the preset target, return to M3 for parameter optimization.

[0016] Furthermore, the termination condition of the memetic particle swarm optimization algorithm is that the best position experienced by the current particle swarm in the solution space at different speeds reaches a preset threshold, the number of iterations reaches a maximum number, and the error reaches any one of preset requirements.

[0017] Furthermore, the step of inputting the output value into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor includes:

[0018] Establishing a data set; the data set includes a pre-compensation output value and a post-compensation output value of the pressure sensor;

[0019] Introduce slack variables, establish constraints, and obtain the correction function;

[0020] The correction function is used to convert the pre-compensation output value into the post-compensation output value, thereby obtaining a nonlinear correction value of the MEMS pressure sensor.

[0021] Another aspect of the present disclosure provides a MEMS pressure sensor nonlinear correction system, the system comprising:

[0022] An acquisition module, used to obtain the output value of the MEMS pressure sensor;

[0023] The correction module is used to input the output value into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor; wherein the nonlinear correction model is pre-established by performing parameter optimization on a support vector machine using a memetic particle swarm optimization algorithm.

[0024] Furthermore, the system also includes a model module, which is used to optimize the parameters of the support vector machine by using a memetic particle swarm optimization algorithm to pre-establish the nonlinear correction model;

[0025] The model module is specifically used for:

[0026] M1, initialize the population size, maximum evolutionary generations, initial position and initial velocity of the particle swarm optimization algorithm, and initialize the error penalty parameters and Gaussian kernel parameters of the support vector machine;

[0027] M2, initialize the position and speed of particles, determine the number of particles, the initial value of the inertia factor, the maximum allowed number of iterations, the acceleration coefficient, the best position component of the corresponding dimension experienced by the initialized particles at different speeds, and the best position experienced by the current particle group at different speeds in the solution space;

[0028] M3. Calculate the individual extreme value of each particle and obtain the best position component of the corresponding dimension experienced by each particle at different speeds;

[0029] M4, evaluate the objective function of each particle, select the best individual extreme value as the global extreme value, obtain the best position experienced by the current particle group in the solution space at different speeds, and use the extreme value corresponding to the particle as the optimal parameter of the support vector machine in the next iteration;

[0030] M5. Update the speed and position of each particle and calculate the fitness value of each particle; if the fitness value is better than the current individual extreme value of the particle, set the best position component of the corresponding dimension experienced by the particle at different speeds as the position of the particle, and update the individual extreme value; if the best individual extreme value of all particles is better than the current global extreme value, set the best position experienced by the particle group in the solution space at different speeds as the position of the particle, and update the global extreme value, inertia weight, position and speed;

[0031] M6: Determine whether the end condition of the memetic particle swarm optimization algorithm is met. If so, stop the iteration; if the deviation exceeds the preset target, return to M3 for parameter optimization.

[0032] Furthermore, the termination condition of the memetic particle swarm optimization algorithm is that the best position experienced by the current particle swarm in the solution space at different speeds reaches a preset threshold, the number of iterations reaches a maximum number, and the error reaches any one of preset requirements.

[0033] Furthermore, the correction module is specifically used for:

[0034] Establishing a data set; the data set includes a pre-compensation output value and a post-compensation output value of the pressure sensor;

[0035] Introduce slack variables, establish constraints, and obtain the correction function;

[0036] The correction function is used to convert the pre-compensation output value into the post-compensation output value, thereby obtaining a nonlinear correction value of the MEMS pressure sensor.

[0037] Another aspect of the present disclosure provides an electronic device, comprising:

[0038] at least one processor; and,

[0039] The memory communicatively connected to the at least one processor is used to store one or more programs, and when the one or more programs are executed by the at least one processor, the at least one processor can implement the MEMS pressure sensor nonlinear correction method described above.

[0040] Another aspect of the present disclosure provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned nonlinear correction method for a MEMS pressure sensor.

[0041] The nonlinear correction method, system, device and medium of a MEMS pressure sensor of the disclosed embodiment utilizes the efficient MPSO-SVM nonlinear correction algorithm to perform nonlinear compensation of the MEMS pressure sensor. SVM solves the problem of small sample and nonlinearity well. It introduces a speed variable coefficient adjustment factor based on PSO, adjusts the relationship between the search speed and the reference speed, maintains the diversity of the particle swarm, and adopts adaptive adjustment to improve the traversal of the algorithm in the solution search space, obtains the global optimum, and improves the convergence speed and algorithm accuracy. By improving the measurement accuracy of existing MEMS pressure sensors through software algorithms, the frequency of hardware updates can be reduced, thereby reducing the production cost of pressure sensors and the equipment maintenance cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a flow chart of a nonlinear correction method for a MEMS pressure sensor according to an embodiment of the present disclosure;

[0043] Figure 2It is a structural schematic diagram of a nonlinear correction system for a MEMS pressure sensor according to another embodiment of the present disclosure;

[0044] Figure 3 The figure is a schematic diagram of the structure of an electronic device according to another embodiment of the present disclosure. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0046] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0047] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0048] It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the concepts of the present disclosure. As used in this disclosure, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0049] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present disclosure, and therefore cannot be used to limit the protection scope of the present disclosure.

[0050] like Figure 1 As shown, an embodiment of the present disclosure provides a nonlinear correction method for a MEMS pressure sensor, comprising:

[0051] Step S1, obtaining the output value of the MEMS pressure sensor.

[0052] Specifically, the MEMS pressure sensor converts the mechanical deformation after being pressed into an electrical signal output, and this embodiment obtains a digital signal output value converted from an analog quantity of the electrical signal.

[0053] Step S2, inputting the output value into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor; wherein the nonlinear correction model is pre-established by performing parameter optimization on a support vector machine using a memetic particle swarm optimization algorithm.

[0054] Specifically, this embodiment uses a nonlinear correction model based on the Memetic Particle Swarm Optimization (MPSO) and Support Vector Machine (SVM) to reduce the nonlinear output of the MEMS pressure sensor. First, the SVM parameters are searched and optimized using MPSO, i.e., parameter optimization, and then an SVM error correction model of the nonlinear mapping relationship between the output and the voltage is established. Finally, the nonlinear correction of the MEMS pressure sensor is realized by approximating any nonlinear function through SVM.

[0055] Furthermore, the steps of optimizing the SVM parameters by MPSO to establish a nonlinear correction model include:

[0056] Step M1, initializing the population size, maximum evolutionary generations, initial position and initial velocity of the particle swarm optimization algorithm, and initializing the error penalty parameter and Gaussian kernel parameter of the support vector machine;

[0057] Step M2: Initialize the particle position x id and speed v id , determine the number of particles N, the initial value of the inertia factor ω, and the maximum allowed number of iterations k max , acceleration coefficients c1 and c2, initialize the best position component P of the dth dimension experienced by particle i at different speeds id , the best position P that the particle swarm has experienced in the solution space at different speeds gd ;

[0058] Step M3: Calculate the individual extreme value (fitness value) of each particle to obtain the best position component P of the corresponding dimension experienced by each particle at different speeds. id ;

[0059]

[0060] Where: y i is the target output of the ith particle, y k is the actual output of the ith particle, and n is the number of samples in the training set;

[0061] Step M4: Evaluate the objective function of each particle, select the best individual extreme value as the global extreme value, and obtain the best position P that the current particle group has experienced in the solution space at different speeds. gd , the extreme value corresponding to the particle is used as the optimal parameter of SVM in the next iteration;

[0062] Step M5: Update the speed and position of each particle and calculate the fitness value of each particle; if the fitness value is better than the current individual extreme value of the particle, then the best position component P of the corresponding dimension experienced by the particle at different speeds is calculated. id Set to the position of the particle and update the individual extreme value; if the best individual extreme value among all particles is better than the current global extreme value, set the best position P experienced by the particle swarm in the solution space at different speeds gd is the position of the particle, and updates the global extreme value, updates the inertia weight according to the following formula (2), and updates the position and velocity according to the following formula (3) and formula (4);

[0063]

[0064] Where: δ is a positive coefficient to adjust the change rate of the inertia factor ω, kmax is the upper limit of the number of iterations; ω 0 is the upper limit of ω(k), k is the current number of iterations;

[0065]

[0066] In the formula, ω is the inertia factor, which controls the weight of the speed; c1 and c2 are acceleration coefficients; r1 and r2 are random numbers between the interval [0,1]; is the reference velocity component of particle i in the dth dimension; is the search velocity component of particle i in the dth dimension; a(m) is the velocity variable coefficient adjustment factor, where m = 1~j, j is the velocity interval number; is the reference position component of particle i in the dth dimension; is the search position component of particle i in the dth dimension, m = 1~j; P id is the best position component of the dth dimension experienced by particle i at different speeds; P gd is the best position that the particle swarm has experienced in the solution space at different speeds; V max is the maximum speed of the particle flying;

[0067] a(m) can be further expressed as:

[0068]

[0069] Step M6: determine whether the end condition of the memetic particle swarm optimization algorithm is met. If so, stop the iteration; if the deviation exceeds the preset target, return to M3 for parameter optimization.

[0070] Furthermore, the nonlinear correction scheme of the pressure sensor implemented by using the MPSO-SVM nonlinear correction model established above includes the following steps:

[0071] N1, let the data set be {y i ,z i}, i = 1, 2, ..., n, the output of the pressure sensor before compensation is y i ; The output of the pressure sensor after compensation is z i , solve the regression function of formula (5);

[0072] f*(y)=ω·φ(y)+b (5)

[0073] Where φ(y) represents the nonlinear change from y→φ(y), that is, from the input space to the high-dimensional feature space; ω is the weight vector, whose dimension is the dimension of the high-dimensional space; ω·φ(y) represents the inner product of the vector, and b is the threshold.

[0074] N2. Introduce slack variables ξ≥0, ξ*≥0, transform the optimization problem into the minimization problem of formula (6), and solve the weight vector ω and threshold b in formula (5);

[0075]

[0076] The constraints are:

[0077]

[0078] In formula (7), C is the penalty coefficient. The larger the C is, the greater the penalty for samples with training errors greater than ε. ε is the insensitive loss function coefficient, which specifies the error requirement of the regression function. The smaller the value is, the smaller the error of the regression function is and the higher the regression accuracy is.

[0079] N3, the transformation minimization optimization problem is solved in the dual form of equation (8), and the Lagrange operator α, α is introduced * , establish the Lagrange function;

[0080]

[0081] The constraints are:

[0082]

[0083] N4. Solve equation (9) to obtain equation (10), and then obtain the regression function equation (11);

[0084]

[0085] In formula (11), K(y,y i )=φ(y)·φ(y i ) is the kernel function that satisfies the Mercer condition.

[0086] A nonlinear correction method for a MEMS pressure sensor in an embodiment of the present disclosure uses an efficient MPSO-SVM nonlinear correction algorithm to perform nonlinear compensation for the MEMS pressure sensor. SVM solves the problem of small samples and nonlinearity well. It introduces a speed variable coefficient adjustment factor based on PSO, adjusts the relationship between the search speed and the reference speed, maintains the diversity of the particle swarm, and uses adaptive adjustment to improve the traversal of the algorithm in the solution search space, obtains the global optimum, and improves the convergence speed and algorithm accuracy. By improving the measurement accuracy of existing MEMS pressure sensors through software algorithms, the frequency of hardware updates can be reduced, thereby reducing the production cost of pressure sensors and the equipment maintenance cost.

[0087] like Figure 2 As shown, another embodiment of the present disclosure provides a MEMS pressure sensor nonlinear correction system, comprising:

[0088] An acquisition module 210 is used to acquire an output value of a MEMS pressure sensor;

[0089] The correction module 220 is used to input the output value into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor; wherein the nonlinear correction model is pre-established by performing parameter optimization on a support vector machine using a memetic particle swarm optimization algorithm.

[0090] For example, Figure 2 As shown, the system further includes a model module 230, which is used to optimize the parameters of the support vector machine by using a memetic particle swarm optimization algorithm to pre-establish the nonlinear correction model;

[0091] The model module 230 is specifically used for:

[0092] M1, initialize the population size, maximum evolutionary generations, initial position and initial velocity of the particle swarm optimization algorithm, and initialize the error penalty parameters and Gaussian kernel parameters of the support vector machine;

[0093] M2, initialize the position and speed of particles, determine the number of particles, the initial value of the inertia factor, the maximum allowed number of iterations, the acceleration coefficient, the best position component of the corresponding dimension experienced by the initialized particles at different speeds, and the best position experienced by the current particle group at different speeds in the solution space;

[0094] M3. Calculate the individual extreme value of each particle and obtain the best position component of the corresponding dimension experienced by each particle at different speeds;

[0095] M4, evaluate the objective function of each particle, select the best individual extreme value as the global extreme value, obtain the best position experienced by the current particle group in the solution space at different speeds, and use the extreme value corresponding to the particle as the optimal parameter of the support vector machine in the next iteration;

[0096] M5. Update the speed and position of each particle and calculate the fitness value of each particle; if the fitness value is better than the current individual extreme value of the particle, set the best position component of the corresponding dimension experienced by the particle at different speeds as the position of the particle, and update the individual extreme value; if the best individual extreme value of all particles is better than the current global extreme value, set the best position experienced by the particle group in the solution space at different speeds as the position of the particle, and update the global extreme value, inertia weight, position and speed;

[0097] M6: Determine whether the end condition of the memetic particle swarm optimization algorithm is met. If so, stop the iteration; if the deviation exceeds the preset target, return to M3 for parameter optimization.

[0098] Exemplarily, the termination condition of the memetic particle swarm optimization algorithm is that the best position experienced by the current particle swarm in the solution space at different speeds reaches a preset threshold, the number of iterations reaches a maximum number, and the error reaches a preset requirement.

[0099] Exemplarily, the correction module 220 is specifically used for:

[0100] Establishing a data set; the data set includes a pre-compensation output value and a post-compensation output value of the pressure sensor;

[0101] Introduce slack variables, establish constraints, and obtain the correction function;

[0102] The correction function is used to convert the pre-compensation output value into the post-compensation output value, thereby obtaining a nonlinear correction value of the MEMS pressure sensor.

[0103] Specifically, a MEMS pressure sensor nonlinear correction system in an embodiment of the present disclosure is used to implement the MEMS pressure sensor nonlinear correction method described in the above embodiments. The specific implementation process has been described in detail in the above embodiments and will not be repeated here.

[0104] like Figure 3 As shown, another embodiment of the present disclosure provides an electronic device, including:

[0105] At least one processor 301; and a memory 302 communicatively connected to the at least one processor 301, for storing one or more programs, which, when executed by the at least one processor 301, enable the at least one processor 301 to implement the MEMS pressure sensor nonlinear correction method described above.

[0106] The memory 302 and the processor 301 are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors 301 and the memory 302 together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor 301 is transmitted on a wireless medium through an antenna, and further, the antenna also receives data and transmits the data to the processor 301.

[0107] The processor 301 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management and other control functions. The memory 302 can be used to store data used by the processor 301 when performing operations.

[0108] Yet another embodiment of the present disclosure provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned nonlinear correction method for a MEMS pressure sensor.

[0109] The computer-readable storage medium may be included in the system or electronic device of the present disclosure, or may exist independently.

[0110] Computer-readable storage media may be any tangible media that contains or stores a program, which may be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. More specific examples include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, optical fiber, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0111] The computer-readable storage medium may also include a data signal propagated in baseband or as part of a carrier wave, in which the computer-readable program code is carried. Specific examples include but are not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0112] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A nonlinear correction method for a MEMS pressure sensor, characterized in that: The method comprises: Get the output value of the MEMS pressure sensor; The output value is input into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor; wherein, The nonlinear correction model is pre-established by optimizing the parameters of a support vector machine using a memetic particle swarm optimization algorithm.

2. The method according to claim 1, characterized in that The nonlinear correction model is pre-established by optimizing the parameters of a support vector machine using a memetic particle swarm optimization algorithm, including: M1, initialize the population size, maximum evolutionary generations, initial position and initial velocity of the particle swarm optimization algorithm, and initialize the error penalty parameters and Gaussian kernel parameters of the support vector machine; M2, initialize the position and speed of particles, determine the number of particles, the initial value of the inertia factor, the maximum allowed number of iterations, the acceleration coefficient, the best position component of the corresponding dimension experienced by the initialized particles at different speeds, and the best position experienced by the current particle group at different speeds in the solution space; M3. Calculate the individual extreme value of each particle and obtain the best position component of the corresponding dimension experienced by each particle at different speeds; M4, evaluate the objective function of each particle, select the best individual extreme value as the global extreme value, obtain the best position experienced by the current particle group in the solution space at different speeds, and use the extreme value corresponding to the particle as the optimal parameter of the support vector machine in the next iteration; M5. Update the speed and position of each particle and calculate the fitness value of each particle; if the fitness value is better than the current individual extreme value of the particle, set the best position component of the corresponding dimension experienced by the particle at different speeds as the position of the particle, and update the individual extreme value; if the best individual extreme value of all particles is better than the current global extreme value, set the best position experienced by the particle group in the solution space at different speeds as the position of the particle, and update the global extreme value, inertia weight, position and speed; M6: Determine whether the end condition of the memetic particle swarm optimization algorithm is met. If so, stop the iteration; if the deviation exceeds the preset target, return to M3 for parameter optimization.

3. The method according to claim 2, characterized in that The termination condition of the memetic particle swarm optimization algorithm is that the best position experienced by the current particle swarm in the solution space at different speeds reaches a preset threshold, the number of iterations reaches a maximum number, and the error reaches any one of the preset requirements.

4. The method according to any one of claims 1 to 3, characterized in that: The step of inputting the output value into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor includes: Establishing a data set; the data set includes a pre-compensation output value and a post-compensation output value of the pressure sensor; Introduce slack variables, establish constraints, and obtain the correction function; The correction function is used to convert the pre-compensation output value into the post-compensation output value, thereby obtaining a nonlinear correction value of the MEMS pressure sensor.

5. A MEMS pressure sensor nonlinear correction system, characterized in that: The system comprises: An acquisition module, used to obtain the output value of the MEMS pressure sensor; The correction module is used to input the output value into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor; wherein the nonlinear correction model is pre-established by performing parameter optimization on a support vector machine using a memetic particle swarm optimization algorithm.

6. The system according to claim 5, characterized in that The system also includes a model module, which is used to optimize the parameters of the support vector machine by using a memetic particle swarm optimization algorithm to pre-establish the nonlinear correction model; The model module is specifically used for: M1, initialize the population size, maximum evolutionary generations, initial position and initial velocity of the particle swarm optimization algorithm, and initialize the error penalty parameters and Gaussian kernel parameters of the support vector machine; M2, initialize the position and speed of particles, determine the number of particles, the initial value of the inertia factor, the maximum allowed number of iterations, the acceleration coefficient, the best position component of the corresponding dimension experienced by the initialized particles at different speeds, and the best position experienced by the current particle group at different speeds in the solution space; M3. Calculate the individual extreme value of each particle and obtain the best position component of the corresponding dimension experienced by each particle at different speeds; M4, evaluate the objective function of each particle, select the best individual extreme value as the global extreme value, obtain the best position experienced by the current particle group in the solution space at different speeds, and use the extreme value corresponding to the particle as the optimal parameter of the support vector machine in the next iteration; M5. Update the speed and position of each particle and calculate the fitness value of each particle; if the fitness value is better than the current individual extreme value of the particle, set the best position component of the corresponding dimension experienced by the particle at different speeds as the position of the particle, and update the individual extreme value; if the best individual extreme value of all particles is better than the current global extreme value, set the best position experienced by the particle group in the solution space at different speeds as the position of the particle, and update the global extreme value, inertia weight, position and speed; M6: Determine whether the end condition of the memetic particle swarm optimization algorithm is met. If so, stop the iteration; if the deviation exceeds the preset target, return to M3 for parameter optimization.

7. The system according to claim 6, characterized in that The termination condition of the memetic particle swarm optimization algorithm is that the best position experienced by the current particle swarm in the solution space at different speeds reaches a preset threshold, the number of iterations reaches a maximum number, and the error reaches any one of the preset requirements.

8. The system according to any one of claims 5 to 7, characterized in that: The correction module is specifically used for: Establishing a data set; the data set includes a pre-compensation output value and a post-compensation output value of the pressure sensor; Introduce slack variables, establish constraints, and obtain the correction function; The correction function is used to convert the pre-compensation output value into the post-compensation output value, thereby obtaining a nonlinear correction value of the MEMS pressure sensor.

9. An electronic device, characterized in that: include: at least one processor; as well as, A memory communicatively connected to the at least one processor, for storing one or more programs, which, when executed by the at least one processor, enables the at least one processor to implement the MEMS pressure sensor nonlinear correction method according to any one of claims 1 to 4.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the nonlinear correction method for a MEMS pressure sensor according to any one of claims 1 to 4 is implemented.

Citation Information

Cited By

  • Pressure response data calibration method and device and computer equipment

    CN119803769A

  • A method of pressure measurement for a MEMS pressure sensor

    CN122900757A