CN115859882A - Temperature compensation design method and temperature compensation method based on cutting neural network - Google Patents
Temperature compensation design method and temperature compensation method based on cutting neural network Download PDFInfo
- Publication number
- CN115859882A CN115859882A CN202211426946.5A CN202211426946A CN115859882A CN 115859882 A CN115859882 A CN 115859882A CN 202211426946 A CN202211426946 A CN 202211426946A CN 115859882 A CN115859882 A CN 115859882A
- Authority
- CN
- China
- Prior art keywords
- temperature compensation
- temperature
- compensation
- training
- cutting
- 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.)
- Withdrawn
Links
- 238000013461 design Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000005520 cutting process Methods 0.000 title claims abstract description 47
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 84
- 230000007613 environmental effect Effects 0.000 claims abstract description 25
- 230000006870 function Effects 0.000 claims description 55
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 5
- 238000009966 trimming Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003245 working effect Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Images
Landscapes
- Indication And Recording Devices For Special Purposes And Tariff Metering Devices (AREA)
Abstract
The invention discloses a temperature compensation design method and a temperature compensation method based on a cutting neural network in the technical field of circuit design, and aims to solve the problems that in the prior art, a temperature compensation circuit is poor in compensation effect, not stable in compensation performance and complex in design. The method comprises the steps of obtaining compensation resistance values corresponding to a sensor circuit under different environmental temperatures, recording the environmental temperatures and the compensation resistance values, and forming a sample library; determining a grid training function, and setting basic parameters in the grid training process; substituting the sample library into a grid training function for training; cutting the trained grid training function and training again; the method is suitable for temperature compensation circuit design, applies the cutting neural network technology to the temperature compensation circuit design, solves the problems of low reliability, complex design and relatively low precision of the temperature compensation circuit design, and can meet various requirements of the circuit design.
Description
Technical Field
The invention relates to a temperature compensation design method and a temperature compensation method based on a cutting neural network, and belongs to the technical field of circuit design.
Background
Nowadays, the development of sensors has promoted the intelligent development in the fields of industrial control, automotive electronics, medical treatment, environmental monitoring and the like, but the temperature stability of the sensors has always been a non-negligible research problem. In order to obtain a sensor with more stable and reliable performance, research on temperature compensation is indispensable. The temperature compensation method can be roughly divided into hardware compensation and software compensation, and both the temperature compensation methods belong to subsequent output compensation. The hardware compensation reliability is high, but the design is complex, the labor consumption is high, and the precision is relatively low.
The existing software compensation design is usually a trial and error method, temperature compensation is carried out on a sensor circuit through a temperature compensation circuit, the compensation effect is poor, the compensation performance is not stable enough, the design is complex, and the working effect of the device is influenced.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a temperature compensation design method and a temperature compensation method based on a cutting neural network, and solves the problems that the existing temperature compensation circuit is poor in compensation effect, unstable in compensation performance, complex in design and influences the working effect of the device.
In order to solve the technical problems, the invention is realized by adopting the following technical scheme:
in a first aspect, the present invention provides a method for designing a temperature compensation based on a trimmed neural network, including:
step A: acquiring corresponding compensation resistance values of the sensor circuit at different environmental temperatures, and recording the environmental temperatures and the compensation resistance values to form a sample library;
and B: determining a grid training function, and setting basic parameters in the grid training process;
step C: substituting the sample library into a grid training function for training;
step D: and cutting the trained grid training function and retraining to complete the design of the temperature compensation circuit.
Further, obtain the compensation resistance value that sensor circuit corresponds under different ambient temperature, record ambient temperature and compensation resistance value include:
connecting the adjustable resistor into a sensor circuit needing temperature compensation;
placing the sensor circuit in a standard test environment;
adjusting the adjustable resistor to enable the output result of the sensor to be a standard test result;
recording the current resistance value of the adjustable resistor and the ambient temperature value;
acquiring the resistance values and the environmental temperature values of n groups of sensor circuits in standard test environments with different environmental temperatures to form a sample library, wherein n is a positive integer not less than 10.
Further, determining the mesh training function includes:
the network training function comprises an input layer and an output layer, the input layer is an environment temperature value, and the output layer comprises a temperature compensation circuit weighting and formula design as follows:
R1＝Re B(1/X-1/298.15)
R6＝w1X+b1
R8＝w2X+b2
in the formula: r2, R3, R4, R5, R7, R9 and R10 are fixed resistors in the temperature compensation circuit; r1 is a negative temperature coefficient thermistor in the temperature compensation circuit; r and B are negative temperature coefficient thermistor coefficients; r6 and R8 are positive temperature coefficient thermistors in the temperature compensation circuit, and w1, w2, b1 and b2 are positive temperature coefficient thermistors; and X is the ambient temperature.
Further, setting basic parameters in the grid training process includes:
setting the maximum training step number to be 1000;
setting the training time to be unlimited;
setting the range of the learning rate to be (0.01,0.8);
setting the ranges of the network weight and the threshold value to be (0,1);
the loss function is set to the sum of the squared errors.
Further, substituting the sample library into the mesh training function for training includes:
acquiring an actual temperature compensation curve according to the compensation resistance value of the sample library;
substituting the environmental temperature of the sample library into a grid training function to obtain a predicted temperature compensation curve;
and when the error of the predicted temperature compensation curve and the actual temperature compensation curve is in a set range, finishing training.
Further, cutting and retraining the trained mesh training function to complete the design of the temperature compensation circuit comprises:
comparing the obtained resistance values with preset values according to the obtained resistance values, if the resistance values are smaller than the preset values, cutting the neurons corresponding to the resistance values, repeating the step B, the step C and the step D until all the resistance values are larger than the preset values, and taking the temperature compensation circuit and the corresponding resistance values at the moment as final temperature compensation circuits and corresponding resistance values;
if the net training function after cutting reaches 1000 step length, the square sum of the difference between the predicted temperature compensation curve and the actual temperature compensation curve is smaller than a set value, namely a temperature compensation circuit and a resistance value before cutting are adopted.
In a second aspect, the present invention provides a device for designing a temperature compensation based on a trimmed neural network, including:
a sample acquisition module: acquiring corresponding compensation resistance values of the sensor circuit at different environmental temperatures, and recording the environmental temperatures and the compensation resistance values to form a sample library;
a parameter setting module: determining a grid training function, and setting basic parameters in the grid training process;
a training module: substituting the sample library into a grid training function for training;
a cutting module: and cutting the trained grid training function and retraining the trained grid training function to complete the design of the temperature compensation circuit.
In a third aspect, the present invention provides a temperature compensation method, including:
acquiring the current ambient temperature of the sensor circuit;
inputting the acquired current environment temperature of the sensor circuit into a pre-trained temperature compensation model based on the cutting neural network to acquire a required compensation resistance value; wherein the trimming neural network-based temperature compensation model is obtained by training the trimming neural network-based temperature compensation design method in the first aspect.
In a fourth aspect, the present invention provides a temperature compensation device comprising:
an acquisition module: acquiring the current ambient temperature of the sensor circuit;
the compensation module: inputting the current environment temperature of the sensor circuit into a pre-trained temperature compensation model based on a cutting neural network to obtain a required compensation resistance value; wherein the trimming neural network-based temperature compensation model is obtained by training the trimming neural network-based temperature compensation design method in the first aspect.
In a fifth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the temperature compensation method according to the third aspect.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the temperature compensation design method based on the cutting neural network, the cutting neural network technology is applied to the temperature compensation circuit design, the temperature compensation circuit is simplified, the problems of low reliability, complex design, labor consumption and relatively low precision of the temperature compensation circuit design are solved, and various requirements of the circuit design can be met;
2. the neural network fitting has better data fusion and generalization capability and strong adaptability, can accurately predict data in a given range, and realizes automatic calculation of the circuit resistance.
Drawings
FIG. 1 is a schematic flow chart of a method for designing a temperature compensation based on a pruned neural network according to an embodiment of the present invention;
FIG. 2 is a circuit diagram of a temperature compensation circuit provided in accordance with an embodiment of the present invention;
fig. 3 is a block diagram of a network training function provided in accordance with an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present invention are described in detail in the technical solutions of the present application, and are not limited to the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.
The first embodiment is as follows:
as shown in fig. 1-3, the present invention provides a method for designing a temperature compensation based on a trimmed neural network, comprising:
step A: acquiring corresponding compensation resistance values of the sensor circuit at different environmental temperatures, and recording the environmental temperatures and the compensation resistance values to form a sample library;
obtain the compensation resistance value that sensor circuit corresponds under different ambient temperature, record ambient temperature and compensation resistance value includes:
the required temperature compensation circuit was tested using adjustable resistors at different temperatures,
connecting the pluggable adjustable resistor into a sensor circuit needing temperature compensation;
placing the sensor circuit in a standard test environment;
adjusting the adjustable resistor to enable the output result of the sensor to be a standard test result;
recording the current resistance value of the adjustable resistor and the ambient temperature value;
acquiring the resistance values and the environmental temperature values of n groups of sensor circuits in standard test environments with different environmental temperatures within the required compensation temperature to form a sample library, wherein n is a positive integer not less than 10; wherein the required compensation temperature is the service temperature range of the sensor circuit.
And B, step B: determining a grid training function, and setting basic parameters in the grid training process;
determining the lattice training function includes:
the network training function comprises an input layer and an output layer, the input layer is an environment temperature value, and the output layer comprises a temperature compensation circuit weighting and formula design as follows:
R1＝Re B(1/X-1/298.15)
R6＝w1X+b1
R8＝w2X+b2
in the formula: r2, R3, R4, R5, R7, R9 and R10 are fixed resistors in the temperature compensation circuit; r1 is a negative temperature coefficient thermistor in the temperature compensation circuit; r and B are negative temperature coefficient thermistor coefficients; r6 and R8 are positive temperature coefficient thermistors in the temperature compensation circuit, and w1, w2, b1 and b2 are positive temperature coefficient thermistors; x is ambient temperature;
optionally, the selected network training function is a tensorflow2 function in a python environment.
Setting basic parameters in the grid training process comprises the following steps:
setting the maximum training step number to be 1000;
setting the training time to be unlimited;
setting the range of the learning rate to be (0.01,0.8);
setting the ranges of the network weight and the threshold value to be (0,1);
setting a loss function as a sum of squares of errors;
optionally, sigmoid is used for the activation function and Adam is used for the optimization algorithm.
Step C: substituting the sample library into a grid training function for training;
substituting the sample library into a mesh training function for training comprises:
acquiring an actual temperature compensation curve according to the compensation resistance value of the sample library;
substituting the environmental temperature of the sample library into a grid training function to obtain a predicted temperature compensation curve;
and when the predicted temperature compensation curve reaches the error square sum set target, processing the weight and the offset of the grid training function to obtain each resistance value, and introducing a judgment link of the predicted temperature compensation fitting degree, namely finishing the training when the error of the predicted temperature compensation curve and the actual temperature compensation curve is within a set range, wherein the set target and the set range are set according to the actual needs of users.
Step D: and cutting the trained grid training function and retraining to complete the design of the temperature compensation circuit.
Cutting the trained grid training function and retraining to complete the design of the temperature compensation circuit, wherein the step of cutting the trained grid training function comprises the following steps:
comparing the obtained resistance values (including the resistors R1-R10) with a preset value, if the resistance values are smaller than the preset value, locking the corresponding weight and bias to 0, namely cutting the neurons corresponding to the resistors, retraining the grid training function, repeating the steps B, C and D until all the resistance values are larger than the preset value, and taking the temperature compensation circuit and the corresponding resistance values at the moment as a final temperature compensation circuit and the corresponding resistance values; optionally, the preset value is 1 Ω;
if the network training function reaches 1000 step length after cutting, the sum of squares of the difference between the predicted temperature compensation curve and the actual temperature compensation curve is smaller than a set value, namely a temperature compensation circuit and a resistance value before cutting are adopted; the setting value can be set according to the actual needs of the user.
Compared with the prior art, the method applies the cutting neural network technology to the temperature compensation circuit design, simplifies and solves the problems of low reliability, complex design, labor consumption and relatively low precision of the temperature compensation circuit design, can meet various requirements of circuit design, trains the network training function through the sample library, designs the temperature compensation circuit through the trained network training function, and performs temperature compensation work on the sensor circuit through the temperature compensation circuit.
According to the invention, the neural network is cut, so that the accuracy of the compensation circuit can be ensured while the circuit is simplified, the automatic design of the circuit is realized, meanwhile, the neural network fitting has better data fusion and generalization capability, the adaptability is strong, the data in a given range can be accurately predicted, and the automatic calculation of the resistance value of the circuit is realized.
After the temperature compensation design method of the cutting neural network is adopted, the designed temperature compensation circuit can realize the fitting of a temperature compensation curve, the measurement relative errors of the compensated circuit in the full range are all within the qualified range, the compensation effect is good, the temperature compensation design method of the cutting neural network can more accurately design the temperature compensation circuit compared with the existing trial and error method, and the compensation performance is stable.
The second embodiment:
the invention provides a temperature compensation design device based on a cutting neural network, which comprises:
a sample acquisition module: acquiring corresponding compensation resistance values of the sensor circuit at different environmental temperatures, and recording the environmental temperatures and the compensation resistance values to form a sample library;
a parameter setting module: determining a grid training function, and setting basic parameters in the grid training process;
a training module: substituting the sample library into a grid training function for training;
a cutting module: and cutting the trained grid training function and retraining to complete the design of the temperature compensation circuit.
The specific functions of the functional modules are implemented with reference to the related contents of the first embodiment.
Example three:
the invention provides a temperature compensation method, which comprises the following steps:
acquiring the current ambient temperature of the sensor circuit;
inputting the acquired current environment temperature of the sensor circuit into a pre-trained temperature compensation model based on the cutting neural network to acquire a required compensation resistance value; the temperature compensation model based on the cutting neural network is obtained by training by using the temperature compensation design method based on the cutting neural network.
Example four:
the present invention provides a temperature compensation device, comprising:
an acquisition module: acquiring the current ambient temperature of the sensor circuit;
a compensation module: inputting the current environment temperature of the sensor circuit into a pre-trained temperature compensation model based on a cutting neural network to obtain a required compensation resistance value; the temperature compensation model based on the cutting neural network is obtained by training by using the temperature compensation design method based on the cutting neural network.
The specific functions of the functional modules are implemented with reference to the relevant contents of the first embodiment and the third embodiment.
Example five:
the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the temperature compensation method according to the third embodiment.
In summary, the present invention applies the cutting neural network technique to the temperature compensation circuit design, solves the problems of low reliability, complex design, labor consumption and relatively low precision of the temperature compensation circuit design, and can meet various requirements of the circuit design.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may 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, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A temperature compensation design method based on a cutting neural network is characterized by comprising the following steps:
step A: acquiring corresponding compensation resistance values of the sensor circuit at different environmental temperatures, and recording the environmental temperatures and the compensation resistance values to form a sample library;
and B, step B: determining a grid training function, and setting basic parameters in the grid training process;
step C: substituting the sample library into a grid training function for training;
step D: and cutting the trained grid training function and retraining to complete the design of the temperature compensation circuit.
2. The method of claim 1, wherein the obtaining of the corresponding compensation resistance values of the sensor circuit at different environmental temperatures comprises:
connecting the adjustable resistor into a sensor circuit needing temperature compensation;
placing the sensor circuit in a standard test environment;
adjusting the adjustable resistor to enable the output result of the sensor to be a standard test result;
recording the current resistance value of the adjustable resistor and the ambient temperature value;
acquiring the resistance values and the environmental temperature values of n groups of sensor circuits in standard test environments with different environmental temperatures to form a sample library, wherein n is a positive integer not less than 10.
3. The method of claim 1, wherein determining the grid training function comprises:
the network training function comprises an input layer and an output layer, the input layer is an environment temperature value, and the output layer comprises a temperature compensation circuit weighting and formula design as follows:
R1＝Re B(1/X-1/298.15)
R6＝w1X+b1
R8＝w2X+b2
in the formula: r2, R3, R4, R5, R7, R9 and R10 are fixed resistors in the temperature compensation circuit; r1 is a negative temperature coefficient thermistor in the temperature compensation circuit; r and B are negative temperature coefficient thermistor coefficients; r6 and R8 are positive temperature coefficient thermistors in the temperature compensation circuit, and w1, w2, b1 and b2 are positive temperature coefficient thermistors; and X is the ambient temperature.
4. The method as claimed in claim 3, wherein the setting of basic parameters in the mesh training process comprises:
setting the maximum training step number to be 1000;
setting the training time to be unlimited;
setting the range of the learning rate to be (0.01,0.8);
setting the ranges of the network weight and the threshold value to be (0,1);
the loss function is set to the sum of the squared errors.
5. The method of claim 4, wherein the fitting of the sample library into the mesh training function for training comprises:
acquiring an actual temperature compensation curve according to the compensation resistance value of the sample library;
substituting the environmental temperature of the sample library into a grid training function to obtain a predicted temperature compensation curve;
and when the error of the predicted temperature compensation curve and the actual temperature compensation curve is in a set range, finishing training.
6. The method of claim 5, wherein the cutting and retraining the trained mesh training function to complete the design of the temperature compensation circuit comprises:
comparing the obtained resistance values with preset values according to the obtained resistance values, if the resistance values are smaller than the preset values, cutting the neurons corresponding to the resistance values, repeating the step B, the step C and the step D until all the resistance values are larger than the preset values, and taking the temperature compensation circuit and the corresponding resistance values at the moment as final temperature compensation circuits and corresponding resistance values;
if the net training function after cutting reaches 1000 step length, the square sum of the difference between the predicted temperature compensation curve and the actual temperature compensation curve is smaller than a set value, namely a temperature compensation circuit and a resistance value before cutting are adopted.
7. A device for designing temperature compensation based on a cut neural network is characterized by comprising:
a sample acquisition module: acquiring corresponding compensation resistance values of the sensor circuit at different environmental temperatures, and recording the environmental temperatures and the compensation resistance values to form a sample library;
a parameter setting module: determining a grid training function, and setting basic parameters in the grid training process;
a training module: substituting the sample library into a grid training function for training;
a cutting module: and cutting the trained grid training function and retraining to complete the design of the temperature compensation circuit.
8. A method of temperature compensation, comprising:
acquiring the current ambient temperature of the sensor circuit;
inputting the acquired current environment temperature of the sensor circuit into a pre-trained temperature compensation model based on the cutting neural network to acquire a required compensation resistance value; wherein the tailored neural network-based temperature compensation model is trained using the tailored neural network-based temperature compensation design method of any one of claims 1-6.
9. A temperature compensation device, comprising:
an acquisition module: acquiring the current ambient temperature of the sensor circuit;
a compensation module: inputting the current environment temperature of the sensor circuit into a pre-trained temperature compensation model based on the cutting neural network to obtain a required compensation resistance value; wherein the tailored neural network-based temperature compensation model is trained using the tailored neural network-based temperature compensation design method of any one of claims 1-6.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the temperature compensation method of claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211426946.5A CN115859882A (en) | 2022-11-15 | 2022-11-15 | Temperature compensation design method and temperature compensation method based on cutting neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211426946.5A CN115859882A (en) | 2022-11-15 | 2022-11-15 | Temperature compensation design method and temperature compensation method based on cutting neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115859882A true CN115859882A (en) | 2023-03-28 |
Family
ID=85663483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211426946.5A Withdrawn CN115859882A (en) | 2022-11-15 | 2022-11-15 | Temperature compensation design method and temperature compensation method based on cutting neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115859882A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116879580A (en) * | 2023-05-30 | 2023-10-13 | 华中光电技术研究所(中国船舶集团有限公司第七一七研究所) | Accelerometer starting performance compensation method, accelerometer starting performance compensation system, electronic equipment and storage medium |
| CN117073856A (en) * | 2023-08-16 | 2023-11-17 | 深圳大学 | Temperature measurement method, device, computer equipment and storage medium |
-
2022
- 2022-11-15 CN CN202211426946.5A patent/CN115859882A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116879580A (en) * | 2023-05-30 | 2023-10-13 | 华中光电技术研究所(中国船舶集团有限公司第七一七研究所) | Accelerometer starting performance compensation method, accelerometer starting performance compensation system, electronic equipment and storage medium |
| CN116879580B (en) * | 2023-05-30 | 2024-04-26 | 华中光电技术研究所(中国船舶集团有限公司第七一七研究所) | Accelerometer starting performance compensation method, accelerometer starting performance compensation system, electronic equipment and storage medium |
| CN117073856A (en) * | 2023-08-16 | 2023-11-17 | 深圳大学 | Temperature measurement method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115859882A (en) | Temperature compensation design method and temperature compensation method based on cutting neural network | |
| CN111414977B (en) | Weighted integration temperature sensitive point combination selection method for machine tool spindle thermal error modeling | |
| CN110889091B (en) | Machine tool thermal error prediction method and system based on temperature sensitive interval segmentation | |
| CN109240204B (en) | Numerical control machine tool thermal error modeling method based on two-step method | |
| CN110736769B (en) | Automatic calibration device and method for gas alarm | |
| CN110057419B (en) | Flow signal compensation method, device, storage medium, processor and system | |
| Kothari et al. | Identification scheme for fractional Hammerstein models with the delayed Haar wavelet | |
| CN105738702B (en) | A kind of NTC thermistor test method for air conditioning for automobiles | |
| CN105571614B (en) | magnetic sensor calibration method and device | |
| CN110220945B (en) | Full-range temperature compensation method of semiconductor gas sensor | |
| JP2010277577A (en) | Real-time scheduling of linear model for control and estimation | |
| CN110716500A (en) | Method and system for determining segmented modeling points of temperature sensitive interval | |
| CN116994979B (en) | Square resistance measuring method, electronic device and storage medium | |
| CN117110362A (en) | Pipeline heat loss monitoring method, device, equipment and medium based on Internet of things | |
| CN115183884A (en) | Infrared temperature measurement compensation method and device of electric heating cooperative system | |
| CN114895724B (en) | Smart home equipment, temperature compensation method and readable storage medium | |
| CN111108738A (en) | Data processing device, data analysis device, data processing system, and method for processing data | |
| CN115790968A (en) | Pressure sensor's autonomic compensation debug system | |
| CN110705689B (en) | Continuous learning method and device capable of distinguishing features | |
| CN115102275A (en) | Self-adaptive adjustment method and device for data acquisition channel of power system | |
| CN110702256B (en) | Automatic calibration method and system based on thermistor temperature sensor acquisition equipment | |
| CN102998024B (en) | Novel temperature measuring method based on resistor-inductor (RL) circuit zero-input response | |
| Changhao et al. | Virtual Realization of Temperature Measurement of PRTD Based on Radial Basis Function Neural Network | |
| CN108594646A (en) | A kind of unstable Continuous-time System Identification method based on filtering about point-score | |
| CN113640115B (en) | Optimization method and system suitable for solving inverse problem of quasi-isentropic compression experimental data |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230328 |