CN112949212B - Pressure sensor temperature compensation method and computer readable storage medium - Google Patents
Pressure sensor temperature compensation method and computer readable storage medium Download PDFInfo
- Publication number
- CN112949212B CN112949212B CN202110386532.3A CN202110386532A CN112949212B CN 112949212 B CN112949212 B CN 112949212B CN 202110386532 A CN202110386532 A CN 202110386532A CN 112949212 B CN112949212 B CN 112949212B
- Authority
- CN
- China
- Prior art keywords
- pressure sensor
- pressure
- population
- temperature compensation
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L19/00—Details of, or accessories for, apparatus for measuring steady or quasi-steady pressure of a fluent medium insofar as such details or accessories are not special to particular types of pressure gauges
- G01L19/04—Means for compensating for effects of changes of temperature, i.e. other than electric compensation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Measuring Fluid Pressure (AREA)
Abstract
The invention discloses a temperature compensation method for a pressure sensor, which comprises the following steps: (1) acquiring a corresponding relation between pressure deviation and temperature change under different output voltages, and taking the corresponding relation as a training sample; (2) obtaining a DCQPSO-MKRVM model by using the training sample; (3) inputting the training sample into a DCQPSO-MKRVM model to obtain a pressure deviation estimation model of a corresponding pressure sensor; (4) and calculating the estimated pressure deviation value by combining the theoretical pressure value under the corresponding voltage, completing the temperature compensation of the pressure sensor, and obtaining the real pressure-voltage response curve of the pressure sensor under different temperatures. The invention also discloses a computer readable storage medium including the pressure sensor temperature compensation method. The invention can effectively improve the estimation precision, improve the temperature compensation precision after estimation, simultaneously reserve the output characteristic of the pressure sensor and ensure the stable and reliable work of the pressure sensor.
Description
Technical Field
The invention belongs to the field of temperature compensation of pressure sensors, and particularly relates to a temperature compensation method of a pressure sensor and a computer readable storage medium.
Background
In weather and environmental science, pressure plays an important role in activities such as weather forecasting, climate analysis, environmental evolution analysis, aerospace applications, and the like. Due to the characteristics of low cost, good precision, high sensitivity, good linearity, small volume, mature manufacturing technology and the like, silicon piezoresistive pressure sensors have become the most common micro-electromechanical system devices and widely used flexible pressure sensors in the fields of medical treatment, automobile industry and the like. However, due to the nature of the materials, many piezoresistive pressure sensors limit the temperature range in which they can be used due to their excessively high temperature sensitivity. Therefore, temperature compensation must be carried out, and in the current research, there are several methods for realizing temperature compensation, such as hardware compensation, software compensation and mixed software and hardware compensation.
In contrast, although the hardware compensation method is easier to implement and takes less time, it has the defects of low compensation precision and no online compensation, and has higher cost and larger equipment volume.
As software compensation methods, there are two basic methods: analytical methods and artificial intelligence methods. Analytical methods including look-up tables, interpolation and surface fitting are relatively easy to implement in sensor circuits, but these methods may face the following dilemma: with the increase of the fitting order, the number of interpolation nodes is increased sharply; as the measurement accuracy increases, the ill-posed problem of solving the normal equation increases.
The artificial intelligence method comprises an artificial neural network, a support vector machine and a correlation vector machine.
Empirical risk minimization principles and gradient descent iterations are the basis of artificial neural networks, which may lead to defects in the modeling process such as dimensionality, local minima, under-fitting, or over-fitting.
The relevance vector machine is a Bayesian rule-based machine learning algorithm, and has a sparser framework and fewer kernel function constraints, so that the estimation time is shorter. Meanwhile, the performance of the correlation vector machine is greatly influenced by the kernel function, and the generalization performance of the single-core correlation vector machine is easy to fall into a suboptimal state, so that estimation errors are caused, and the estimation precision is reduced.
Disclosure of Invention
The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, and to provide a temperature compensation method for a pressure sensor and a computer-readable storage medium, which have a good temperature compensation effect and can maintain the output characteristics of the pressure sensor while compensating for temperature differences.
The technical scheme adopted for solving the technical problem is that the temperature compensation method of the pressure sensor is characterized by comprising the following steps of:
s1: obtaining the corresponding relation between pressure deviation and temperature change under different output voltages through a temperature-pressure stress test, and taking the corresponding relation as a training sample;
s2: optimizing a multi-core related vector machine based on a dynamic chaotic quantum particle swarm algorithm by using a training sample to obtain a DCQPSO-MKRVM model;
s2-1: initializing a dynamic chaotic quantum particle swarm algorithm by using a random particle swarm, and mapping the weight of a multi-core function in a multi-core related vector machine to a particle position to participate in the optimization process;
s2-2: generating a new population array by the fitness value and the dynamic parameter value Lambda of each particleDividing the population into two populations of a traditional quantum particle swarm and a dynamic chaotic particle swarm;
s2-3: calculating coefficient in the iterative process of t being more than 0.5I and less than 0.9IJudging whether the algorithm is premature convergence, wherein I is a set region iteration value, t is the current iteration frequency, if the algorithm is premature convergence, the local optimal dilemma is escaped by using additional I-time chaotic search, and after a better fitness value is found, the global optimal position is replaced, and corresponding positions are respectively set;
s2-4: continuously calculating a next population position matrix, performing traditional quantum particle swarm search on the first M- Λ particles, searching all the remaining particles in a chaotic space, and updating the particle positions, wherein M is the size of the population;
and S2-5, repeatedly executing the steps S2-1-S2-4 until an iteration stop condition is met, and taking the finally obtained population global optimal position as the weight of the multi-core function in the multi-core correlation vector machine.
S3: inputting the training sample into a DCQPSO-MKRVM model to obtain a pressure deviation estimation model of a corresponding pressure sensor;
s4: and calculating the estimated pressure deviation value by combining the theoretical pressure value under the corresponding voltage to complete the temperature compensation of the pressure sensor and obtain the real pressure-voltage response curve of the pressure sensor under different temperatures.
Further, S1 includes:
by Δ P ═ P measured -P rated Obtaining a pressure deviation value, wherein P measured Representing input pressure values, P, measured at different temperatures and at different output voltages rated And represents the input pressure value corresponding to the output voltage under the rated condition.
Further, S2-1 includes the steps of:
s2-1-1: the multi-core function expression in the multi-core correlation vector machine isWherein, K G (x,x i ) Is a kernel of Gaussian function, K p (x,x i ) Is a polynomial nucleus, v j And v r Weight coefficients of a Gaussian function kernel and a polynomial kernel, respectively, and are satisfied in the method
S2-1-2: byDetermining a chaotic population solution space variable Y', wherein Y k ∈[0,1],a=0.5,Y'=(X max -X min )·Y k +X min Wherein Y' is E [ X ] min ,X max ],X min And X max Respectively, represent the boundaries of the population variable solution space in the method.
Further, S2-2 includes the steps of:
s2-2-1: byObtaining the fitness value of each particle in the population, wherein M is the size of the population and delta P i Is the actual pressure deviation value of the pressure sensor at different temperatures,the estimated pressure deviation values of the models under different temperatures of the pressure sensor are obtained;
s2-2-2: byUpdating dynamic parameters in the algorithm, wherein M is the size of the population, and j is the dimension of the particle;
s2-2-3: generating new population arraysThe first M-Lambda populations are populations in a traditional quantum particle swarm optimization algorithm, and the rest particle swarm is a chaotic population in the method;
and, the chaotic population is defined as follows:
wherein xi is the weight of chaos factor and m is the weight of chaos factor bestj And Y' is a chaotic population solution space variable as a global optimal position.
Further, step S2-3 includes the steps of:
s2-3-1: byCalculating coefficientsWherein f is i All fitness values for an already existing population, f mean Is the average of fitness values of the presence population,
s2-3-2. mixingComparing with the expected coefficient delta set in the method to judge whether the premature convergence occurs or not, if so, judging whether the premature convergence occurs or notAnd t is more than 0.5I and less than 0.9I, the algorithm is judged to be premature and converged at the moment;
s2-3-3, if it is judged to be premature convergence, the formulaJumping out of local optimum, where xi (t) ═ 0.1 Xxi (t-1),t∈[1,I]When a better fitness value is obtainedThereafter, the global optimal position is updated.
Further, S4 includes:
byObtaining a real pressure-voltage response curve after temperature compensation, wherein P real Representing the true pressure value, P, after temperature compensation rated Indicating the pressure value corresponding to the output voltage under nominal conditions,indicating the estimated pressure deviation value.
A computer readable storage medium having stored thereon program instructions which, when executed by a processor, implement the pressure sensor temperature compensation method.
The temperature compensation method is software compensation, realizes on-line compensation, has low cost, obtains the relation between the pressure deviation value and the temperature change value under different output voltages through the measured pressure-voltage response under different temperatures, adopts a dynamic chaotic quantum particle swarm algorithm to optimize the multi-core correlation vector machine as a training sample, effectively improves the estimation precision, improves the temperature compensation precision after estimation, simultaneously reserves the output characteristic of the pressure sensor, and ensures the stable and reliable work of the pressure sensor.
Drawings
FIG. 1 is a schematic flow diagram of an embodiment of the present invention;
FIG. 2 is a schematic illustration of a pressure deviation calculation according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an equivalent model of a pressure sensor in an embodiment of the invention;
FIG. 4 is a schematic structural diagram of a stress test in an embodiment of the present invention;
FIG. 5 is a graph comparing the estimation error of an embodiment of the present invention with different methods.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention will be described in further detail below with reference to the accompanying figures 1-5 and examples.
Embodiments of a method for temperature compensation of a pressure sensor
Referring to fig. 1, the present embodiment includes the steps of:
the method comprises the following steps: the input pressure values at different temperatures and different output voltages are collected through a thermostat, a barometer and an oscilloscope. Referring to fig. 2, when the output voltage is constant, the input pressure value varies with the temperature, where Δ P is equal to P measured -P rated Obtaining a pressure deviation value of the method, and then obtaining a training sample by normalizing the pressure deviation value delta P;
step two: constructing a multi-core related vector machine, wherein the kernel function is as follows:
in this embodiment, J ═ 3 and R ═ 4 are selected, that is, a kernel function of the multi-core correlation vector machine in the embodiment of the present invention is formed by three gaussian kernels and four polynomial kernels;
step three: training and optimizing weight coefficient { v ] of kernel function of multi-core correlation vector machine by adopting dynamic chaotic quantum particle swarm algorithm through training samples j ,v r And the iterative optimization steps are as follows:
1) initializing a dynamic chaotic quantum particle swarm algorithm by using a random particle swarm, and mapping the weight of a multi-core function in a multi-core related vector machine to a particle position to participate in the optimization process;
2) generating a new population array by the fitness value and the dynamic parameter value Lambda of each particleDividing the population into two populations of a traditional quantum particle swarm and a dynamic chaotic particle swarm;
the fitness function formula is as follows:
wherein M is the population size, Δ P i Is the actual pressure deviation value of the pressure sensor under different temperatures,the estimated pressure deviation values of the models under different temperatures of the pressure sensor are obtained;
the dynamic parameter value lambda is selected as follows:
wherein M is the population size and j is the particle dimension;
the group array is composed as follows:
the first M-Lambda populations are populations in a traditional quantum particle swarm optimization algorithm, and the rest particle swarms are chaotic populations in the method;
the chaotic population definition formula is as follows:
Y'=(X max -X min )·Y k +X min
wherein, Y k ∈[0,1],a=0.5,Y'∈[X min ,X max ],X min And X max Respectively representing the boundary of a population variable solution space in the method, xi is the weight of a chaotic factor, and m is the weight of a chaotic factor bestj Is a global optimal position;
3) calculating coefficient in the iterative process of t being more than 0.5I and less than 0.9IJudging whether the algorithm is precocious convergence, wherein I is a set region iteration value, t is the current iteration number, if the algorithm is precocious convergence, the local optimal dilemma is escaped by using additional I-order chaotic search, and after a better fitness value is found, the global optimal position is replaced, and corresponding positions are respectively set;
wherein f is i For all fitness values of an already existing population, f mean Is the average of fitness values of the presence population,
if it isAnd t is more than 0.5I and less than 0.9I, the premature convergence is judged, and a local optimal formula is skipped as follows:
where xi (t) is 0.1 Xxi (t-1), and t is in [1, I ]]When a better fitness value is obtainedAnd then updating the global optimal position.
4) Continuously calculating a next population position matrix, performing traditional quantum particle swarm search on the first M-Lambda particles, searching all the remaining particles in a chaotic space, and updating the positions of the particles;
5) and (4) repeatedly executing the steps 1) to 4) until an iteration stop condition is met, and taking the finally obtained population global optimal position as the weight of the multi-core function in the multi-core correlation vector machine.
Step four: obtaining a multi-core correlation vector machine model determined by pressure deviation values when the temperature changes under different output voltages, and substituting a training sample into the optimized multi-core correlation vector machine model for training to obtain an estimated pressure deviation value;
step five: substituting the estimated pressure deviation value into the following formula to obtain a final temperature compensation result,
wherein, P real Representing the true pressure value, P, after temperature compensation rated Indicating the pressure value corresponding to the output voltage under nominal conditions,the estimated pressure deviation value is indicated.
The temperature compensation method for the pressure sensor provided by the embodiment of the invention comprises the following steps:
(1) the data processing module is used for respectively acquiring pressure deviation values under different output voltages at different temperatures, and normalizing the deviation values to form a training sample;
(2) the training module is used for training and optimizing weight coefficients of kernel functions of the multi-core related vector machine by adopting a dynamic chaotic quantum particle swarm optimization method to obtain an optimized multi-core related vector machine model so as to carry out pressure deviation estimation through the optimized multi-core related vector machine;
(3) and the temperature compensation module is used for calculating by adopting the estimated pressure deviation value and a pressure value corresponding to the output voltage under the rated condition to obtain a real pressure input value so as to complete temperature compensation.
Analysis of Experimental results
The piezoresistive pressure sensor adopted in the embodiment of the invention is an MPX2000 series pressure sensor, and the equivalent model of the piezoresistive pressure sensor is shown in the attached figure 3. In the experiment, the temperature was stepped from-50 ℃ to 150 ℃ every 2 ℃ by a plurality of sets of pressure sensors, the external pressure was controlled at each temperature, the fixed values of 10mV,15mV,20mV,25mV, 30mV,35mV, and 40mV of input voltage were kept constant, and the relationship between the pressure deviation and the temperature change in each output voltage was obtained, 10 sets of data were taken at each output voltage, 5 sets were taken as training data, 5 sets were taken as control data, and the experimental structure was as shown in fig. 4.
After normalization processing is carried out on the obtained experimental data, a multi-core correlation vector machine is optimized by adopting a dynamic chaotic quantum particle swarm algorithm as a training sample, and the optimized multi-core correlation vector machine is substituted for training to obtain pressure deviation values estimated under different output voltages, errors of three different estimation methods under the condition that the output voltage is 10mV are shown in a figure 4, and the precision of estimation results under all the output voltages is shown in a table 1, wherein MAE represents an average absolute error, and MRA represents average correlation accuracy.
TABLE 1 pressure deviation estimation error at all output voltages
Output voltage (mV) | | MRA | |
5 | 0.0043 | 98.2% | |
10 | 0.0018 | 99.5% | |
15 | 0.0046 | 98.1% | |
20 | 0.0079 | 97.3% | |
25 | 0.0018 | 99.4% | |
30 | 0.0035 | 98.6% | |
35 | 0.0104 | 96.5% | |
40 | 0.0102 | 96.7% |
As can be seen from fig. 4 and table 1, the overall comparison shows that the estimation error of MKRVM is smaller, and the estimation accuracy of the MKRVM is as high as 99.5%, which indicates that the piezoresistive pressure sensor temperature compensation method based on the dynamic chaotic quantum particle swarm optimization multi-core correlation vector machine provided by the invention obtains a better temperature compensation effect, and provides a new idea and method for the pressure sensor temperature compensation method.
It should be noted that, according to the implementation requirement, each step/component described in the present application can be divided into more steps/components, and two or more steps/components or partial operations of the steps/components can be combined into new steps/components to achieve the purpose of the present invention.
Embodiments of a computer-readable storage medium having a method for pressure sensor temperature compensation
The computer-readable storage medium of the present embodiment has stored thereon program instructions that, when executed by a processor, implement the pressure sensor temperature compensation method of the above-described embodiment.
The pressure sensor temperature compensation method of the present invention can be implemented in hardware, firmware, or as software or computer code storable in a recording medium such as a CD, ROM, RAM, floppy disk, hard disk, or magneto-optical disk, or as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware such as ASIC or FPGA. It is understood that a computer, processor, microprocessor controller, or programmable hardware includes memory components (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code that, when accessed and executed by a computer, processor, or hardware, implements the processing methods described herein. Further, when a general-purpose computer accesses code for implementing the processes shown herein, execution of the code transforms the general-purpose computer into a special-purpose computer for performing the processes shown herein.
It will be understood by those skilled in the art that the foregoing is merely a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included within the scope of the present invention.
Claims (7)
1. A method of temperature compensation for a pressure sensor, comprising the steps of:
s1: obtaining the corresponding relation between pressure deviation and temperature change under different output voltages through a temperature-pressure stress test, and taking the corresponding relation as a training sample;
s2: optimizing a multi-core related vector machine based on a dynamic chaotic quantum particle swarm algorithm by using a training sample to obtain a DCQPSO-MKRVM model;
s2-1: initializing a dynamic chaotic quantum particle swarm algorithm by using a random particle swarm, and mapping the weight of a multi-core function in a multi-core related vector machine to a particle position to participate in the optimization process;
s2-2: generating a new population array by the fitness value and the dynamic parameter value Lambda of each particleDividing the population into two populations of a traditional quantum particle swarm and a dynamic chaotic particle swarm;
s2-3: calculating coefficient in the iterative process of t being more than 0.5I and less than 0.9IJudging whether the algorithm is premature convergence, wherein I is a set region iteration value, t is the current iteration frequency, if the algorithm is premature convergence, the local optimal dilemma is escaped by using additional I-time chaotic search, and after a better fitness value is found, the global optimal position is replaced, and corresponding positions are respectively set;
s2-4: continuously calculating a next population position matrix, performing traditional quantum particle swarm search on the first M- Λ particles, searching all the remaining particles in a chaotic space, and updating the particle positions, wherein M is the size of the population;
s2-5: repeatedly executing the steps S2-1-S2-4 until an iteration stop condition is met, and taking the finally obtained global optimal position of the population as the weight of a multi-core function in the multi-core correlation vector machine;
s3: inputting the training sample into a DCQPSO-MKRVM model to obtain a pressure deviation estimation model of a corresponding pressure sensor;
s4: and calculating the estimated pressure deviation value by combining the theoretical pressure value under the corresponding voltage to complete the temperature compensation of the pressure sensor and obtain the real pressure-voltage response curve of the pressure sensor under different temperatures.
2. The pressure sensor temperature compensation method of claim 1, wherein S1 includes:
by Δ P ═ P measured -P rated Obtaining a pressure deviation value, wherein P measured Representing input pressure values, P, measured at different temperatures and at different output voltages rated And represents the input pressure value corresponding to the output voltage under the rated condition.
3. The pressure sensor temperature compensation method of claim 1, wherein S2-1 includes the steps of:
s2-1-1: the multi-core function expression in the multi-core correlation vector machine isWherein, K G (x,x i ) Is a kernel of Gaussian function, K p (x,x i ) Is a polynomial nucleus, v j And v r Weight coefficients of a Gaussian function kernel and a polynomial kernel, respectively, and are satisfied in the method
4. The pressure sensor temperature compensation method of claim 1, wherein S2-2 includes the steps of:
s2-2-1: byObtaining the fitness value of each particle in the population, wherein M is the size of the population and delta P i Is the actual pressure deviation value of the pressure sensor at different temperatures,the estimated pressure deviation values of the models under different temperatures of the pressure sensor are obtained;
s2-2-2: byUpdating dynamic parameters in the algorithm, wherein M is the size of the population, and j is the dimension of the particle;
s2-2-3: generating new population arraysThe first M-Lambda populations are populations in a traditional quantum particle swarm optimization algorithm, and the rest particle swarms are chaotic populations in the method;
and, the chaotic population is defined as follows:
wherein xi is the weight of chaos factor and m is the weight of 0,1 bestj And Y' is a chaotic population solution space variable as a global optimal position.
5. The pressure sensor temperature compensation method of claim 1, wherein the step S2-3 includes the steps of:
s2-3-1, prepared fromCalculating coefficientsWherein f is i All fitness values for an already existing population, f mean Is the average of fitness values of the presence population,
s2-3-2. mixingComparing the expected coefficient delta with the expected coefficient delta set in the method to judge whether the premature convergence occurs or not, if so, judging whether the premature convergence occurs or notAnd t is more than 0.5I and less than 0.9I, the algorithm is judged to be premature and converged at the moment;
6. The pressure sensor temperature compensation method of claim 1, wherein S4 includes:
byObtaining a real pressure-voltage response curve after temperature compensation, wherein P real Representing the true pressure value, P, after temperature compensation rated Indicating the pressure value corresponding to the output voltage under nominal conditions,indicating the estimated pressure deviation value.
7. A computer readable storage medium having stored thereon program instructions which, when executed by a processor, carry out the pressure sensor temperature compensation method of any of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110386532.3A CN112949212B (en) | 2021-04-12 | 2021-04-12 | Pressure sensor temperature compensation method and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110386532.3A CN112949212B (en) | 2021-04-12 | 2021-04-12 | Pressure sensor temperature compensation method and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112949212A CN112949212A (en) | 2021-06-11 |
CN112949212B true CN112949212B (en) | 2022-09-27 |
Family
ID=76231661
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110386532.3A Active CN112949212B (en) | 2021-04-12 | 2021-04-12 | Pressure sensor temperature compensation method and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112949212B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114791334B (en) * | 2022-04-20 | 2023-09-05 | 浙江大学 | Calibration simplifying method of pressure sensor |
CN116296047B (en) * | 2023-04-03 | 2023-09-29 | 淮阴工学院 | Temperature compensation improvement method of monocrystalline silicon pressure transmitter |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105258839A (en) * | 2015-10-30 | 2016-01-20 | 南京信息工程大学 | Array type air pressure measurement compensation device and method based on quantum particle swarm wavelet neural network |
CN105469138A (en) * | 2015-11-10 | 2016-04-06 | 南京航空航天大学 | Control system performer fault diagnosis method based on particle swarms and support vector machine |
CN110779597A (en) * | 2019-11-13 | 2020-02-11 | 国网甘肃省电力公司检修公司 | High-precision measuring device and method for liquid level of transformer oil tank based on pressure sensor |
CN111380649A (en) * | 2020-03-30 | 2020-07-07 | 金陵科技学院 | Vehicle multi-dimensional force sensor decoupling method based on PSO (particle swarm optimization) optimization LSSVM (least squares support vector machine) |
CN112085146A (en) * | 2020-09-10 | 2020-12-15 | 武汉大学 | Service life prediction method of MKRVM (multi-level read-only memory) to RF-MEMS (radio frequency-micro-electromechanical systems) switch based on DE-QPSO (Degrees-Quadrature-time-delay Quadrature-time-of-use mechanism) |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7483795B2 (en) * | 2004-08-10 | 2009-01-27 | Robertshaw Controls Company | Pressure and temperature compensation algorithm for use with a piezo-resistive strain gauge type pressure sensor |
US8886489B2 (en) * | 2009-05-12 | 2014-11-11 | Georgia Tech Research Corporation | Motion detecting method and device |
-
2021
- 2021-04-12 CN CN202110386532.3A patent/CN112949212B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105258839A (en) * | 2015-10-30 | 2016-01-20 | 南京信息工程大学 | Array type air pressure measurement compensation device and method based on quantum particle swarm wavelet neural network |
CN105469138A (en) * | 2015-11-10 | 2016-04-06 | 南京航空航天大学 | Control system performer fault diagnosis method based on particle swarms and support vector machine |
CN110779597A (en) * | 2019-11-13 | 2020-02-11 | 国网甘肃省电力公司检修公司 | High-precision measuring device and method for liquid level of transformer oil tank based on pressure sensor |
CN111380649A (en) * | 2020-03-30 | 2020-07-07 | 金陵科技学院 | Vehicle multi-dimensional force sensor decoupling method based on PSO (particle swarm optimization) optimization LSSVM (least squares support vector machine) |
CN112085146A (en) * | 2020-09-10 | 2020-12-15 | 武汉大学 | Service life prediction method of MKRVM (multi-level read-only memory) to RF-MEMS (radio frequency-micro-electromechanical systems) switch based on DE-QPSO (Degrees-Quadrature-time-delay Quadrature-time-of-use mechanism) |
Non-Patent Citations (4)
Title |
---|
A Study of Compensation for Temporal and Spatial Physical Temperature Variation in Total Power Radiometers;Chun-Sik Chae .etal;《IEEE Sensors Journal》;20120630;第12卷(第6期);2306-2312页 * |
基于QPSO稀疏化LSSVM的压力传感器温度补偿研究;李冀 等;《传感技术学报》;20200228;第33卷(第2期);227-237页 * |
基于优化相关向量机的化工装备故障预测方法;郁鹏 等;《现代化工》;20170531;第37卷(第5期);189-192页 * |
基于最小二乘支持向量机的硅压阻式传感器温度补偿;杨遂军 等;《传感技术学报》;20160430;第29卷(第04期);500-505页 * |
Also Published As
Publication number | Publication date |
---|---|
CN112949212A (en) | 2021-06-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112949212B (en) | Pressure sensor temperature compensation method and computer readable storage medium | |
CN110659722B (en) | Electric vehicle lithium ion battery health state estimation method based on AdaBoost-CBP neural network | |
CN112101530B (en) | Neural network training method, device, equipment and storage medium | |
CN110874502B (en) | Aerospace product reliability assessment method based on multi-stage test data reduction | |
Huang et al. | Advanced mean-field theory of the restricted Boltzmann machine | |
CN107621269A (en) | Fiber Optic Gyroscope Temperature Drift error compensating method | |
CN113156263B (en) | Cable state monitoring method and storage medium | |
CN111638034B (en) | Strain balance temperature gradient error compensation method and system based on deep learning | |
CN112733435A (en) | Whole vehicle size matching deviation prediction method based on multi-model fusion | |
CN114964313A (en) | RVM-based fiber optic gyroscope temperature compensation method | |
CN112016242A (en) | Distributed parameter thermal process temperature prediction method based on data driving | |
CN114964571A (en) | Pressure sensor temperature compensation method based on improved wolf algorithm | |
CN113343559B (en) | Reliability analysis method for response surface of iterative reweighted least square method extreme learning machine | |
CN111294922B (en) | Method and device for accurately positioning wireless sensor network nodes in grading and rapid mode | |
CN112580855A (en) | Cable group steady-state temperature rise prediction method based on self-adaptive variation PSO-BP neural network | |
CN117030944A (en) | Formaldehyde concentration prediction method, terminal equipment and medium for avoiding ethanol interference | |
CN109635452B (en) | Efficient multimodal random uncertainty analysis method | |
CN113804833B (en) | Universal electronic nose drift calibration method based on convex set projection and extreme learning machine | |
CN114155354B (en) | Method and device for reconstructing capacitance tomography based on graph convolution network | |
CN116224070A (en) | OCV (open circuit voltage) -SOC (system on a chip) model-based full-temperature lithium ion battery OCV (open circuit voltage) evaluation method and system | |
CN115659750A (en) | Physical structure system numerical modeling parameter identification method based on SMA-aSCE | |
CN115327385A (en) | Power battery SOC value estimation method and system | |
CN112001035B (en) | Wing structure deformation reconstruction method based on feature engineering and ridge regression | |
CN111914402B (en) | Dynamic topology estimation system and method based on signal characteristics and topology change priori | |
CN113343431B (en) | Structural system reliability analysis method based on differential evolution and equivalent plane method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |