CN109855763A - A kind of temperature sensor correction method based on BP neural network and PLC - Google Patents
A kind of temperature sensor correction method based on BP neural network and PLC Download PDFInfo
- Publication number
- CN109855763A CN109855763A CN201811637861.5A CN201811637861A CN109855763A CN 109855763 A CN109855763 A CN 109855763A CN 201811637861 A CN201811637861 A CN 201811637861A CN 109855763 A CN109855763 A CN 109855763A
- Authority
- CN
- China
- Prior art keywords
- neural network
- plc
- data
- weight
- temperature sensor
- 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.)
- Pending
Links
Abstract
The invention discloses a kind of temperature sensor correction method based on BP neural network and PLC, comprising: sensor to be corrected and High-precision standard sensor are placed in insulating box heating and record data at regular intervals;The data recorded are classified;Calculating correlative weight value in neural network is put into using the data of classification number;The feedforward neural network part of neural network is write in PLC;The weight being calculated is inserted neural network weight in PLC to correspond in memory block;The method of the present invention solves the linear fit result technical problem larger with actual temperature error, to realize the error correction to temperature sensor by carrying out nonlinear fitting to temperature using BP neural network algorithm.
Description
Technical field
The present invention relates to sensor field more particularly to it is a kind of based on the temperature sensor of BP neural network and PLC correct
Method.
Background technique
Existing temperature sensor correction method is that temperature sensor to be corrected and temperature sensors of high precision are put into perseverance
Incubator heating, and the defeated of two sensors is fitted using linear algorithm after the output of two sensors of record at regular intervals
Out, the updating formula of temperature sensor to be corrected is obtained with this;But due to the non-linear property of temperature sensor, use linearity correction
The resultant error that formula obtains is larger.The present invention is directed to the non-linear property of temperature sensor, using BP neural network algorithm to temperature
Degree carries out nonlinear fitting, solves the problems, such as that linear fit result is larger with actual temperature error.
Summary of the invention
The present invention provides a kind of temperature sensor correction method based on BP neural network and PLC, to solve Linear Quasi
The result technical problem larger with actual temperature error is closed, to carry out Nonlinear Quasi to temperature using BP neural network algorithm
It closes, and then realizes the error correction to temperature sensor.
In order to solve the above-mentioned technical problem, the temperature based on BP neural network and PLC that the embodiment of the invention provides a kind of
Sensor calibration method, comprising:
Sensor to be corrected and High-precision standard sensor are placed in insulating box and heats and records number at regular intervals
According to;
The data recorded are classified;
Calculating correlative weight value in neural network is put into using the data of classification number;
The feedforward neural network part of neural network is write in PLC;
The weight being calculated is inserted neural network weight in PLC to correspond in memory block.
Preferably, the data of record at regular intervals are specially data of every five minutes records.
Preferably, the data that will have been recorded are classified, and are specifically divided into training data and test data, number
It is 10:1 in amount ratio.
Preferably, the neural network correlation weight is calculated as in the pycharm software of windows platform
Using being carried out in the good neural network algorithm of python Programming with Pascal Language.
Preferably, the PLC is SIEMENS PLC.
Preferably, the feedforward neural network part is the output calculating section in neural network, does not include benefit
The part that weight is adjusted with gradient.
Preferably, the corresponding PLC memory block of the weight is DSB data store block.
Compared with the prior art, the embodiment of the present invention has the following beneficial effects:
1, by carrying out nonlinear fitting to temperature using BP neural network algorithm, linear fit result is solved with practical temperature
The larger technical problem of error is spent, to realize the error correction to temperature sensor;
2, the calculating of neural network weight carries out on computers, and the performance that can make full use of computer, which shortens, calculates the time,
And the occasion of a greater amount of training datas and test data can be applied to;
3, it has used PLC to calculate temperature, other outputs can have been set according to the temperature obtained simultaneously calculating temperature
It is standby to be controlled, and the later period is facilitated to safeguard different application situation.
Detailed description of the invention
Fig. 1: for the method step flow diagram in the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1 is please referred to, the preferred embodiment of the present invention provides a kind of temperature sensor school based on BP neural network and PLC
Correction method, comprising:
Sensor to be corrected is placed in High-precision standard sensor and heats in insulating box and record at regular intervals by S1
Data;
S2 classifies the data recorded;
S3 is put into calculating correlative weight value in neural network using the data of classification number;
S4 writes the feedforward neural network part of neural network in PLC;
The weight being calculated is inserted neural network weight in PLC and corresponded in memory block by S5.
In the present embodiment, the data of record at regular intervals are specially data of every five minutes records.
In the present embodiment, the data that will have been recorded are classified, and are specifically divided into training data and test data, number
It is 10:1 in amount ratio.
In the present embodiment, the neural network correlation weight is calculated as in the pycharm software of windows platform
Using being carried out in the good neural network algorithm of python Programming with Pascal Language.
In the present embodiment, the PLC is SIEMENS PLC.
In the present embodiment, the feedforward neural network part is the output calculating section in neural network, does not include benefit
The part that weight is adjusted with gradient.
In the present embodiment, the corresponding PLC memory block of the weight is DSB data store block.
The present invention solves linear fit result with reality by carrying out nonlinear fitting to temperature using BP neural network algorithm
The larger technical problem of border temperature error, to realize the error correction to temperature sensor.
Particular embodiments described above has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that the above is only a specific embodiment of the present invention, the protection being not intended to limit the present invention
Range.It particularly points out, to those skilled in the art, all within the spirits and principles of the present invention, that is done any repairs
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (7)
1. a kind of temperature sensor correction method based on BP neural network and PLC characterized by comprising
Sensor to be corrected and High-precision standard sensor are placed in insulating box and heats and records data at regular intervals;
The data recorded are classified;
Calculating correlative weight value in neural network is put into using the data of classification number;
The feedforward neural network part of neural network is write in PLC;
The weight being calculated is inserted neural network weight in PLC to correspond in memory block.
2. the method as described in claim 1, which is characterized in that the data of record at regular intervals are specially every five minutes
Record a data.
3. the method as described in claim 1, which is characterized in that the data that will have been recorded are classified, and instruction is specifically divided into
Practice data and test data, is 10:1 on quantitative proportion.
4. the method as described in claim 1, which is characterized in that the neural network correlation weight is calculated as in Windows
It is carried out in the neural network algorithm for using python Programming with Pascal Language good in the pycharm software of platform.
5. the method as described in claim 1, which is characterized in that the PLC is SIEMENS PLC.
6. the method as described in claim 1, which is characterized in that the feedforward neural network part is the output in neural network
Calculating section, part weight not being adjusted including the use of gradient.
7. the method as described in claim 1, which is characterized in that the corresponding PLC memory block of the weight is DSB data store block.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811637861.5A CN109855763A (en) | 2018-12-29 | 2018-12-29 | A kind of temperature sensor correction method based on BP neural network and PLC |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811637861.5A CN109855763A (en) | 2018-12-29 | 2018-12-29 | A kind of temperature sensor correction method based on BP neural network and PLC |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109855763A true CN109855763A (en) | 2019-06-07 |
Family
ID=66893240
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811637861.5A Pending CN109855763A (en) | 2018-12-29 | 2018-12-29 | A kind of temperature sensor correction method based on BP neural network and PLC |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109855763A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110702275A (en) * | 2019-11-22 | 2020-01-17 | 四川中烟工业有限责任公司 | Correction method for offset of resistance type temperature sensor |
CN111397744A (en) * | 2020-05-13 | 2020-07-10 | 金陵科技学院 | Detection early warning system for continuously and remotely monitoring body temperature and correcting body temperature by adopting BP neural network |
CN113138902A (en) * | 2021-04-27 | 2021-07-20 | 上海英众信息科技有限公司 | Computer host heat dissipation system and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1997028669A1 (en) * | 1996-01-31 | 1997-08-07 | Asm America, Inc. | Model-based predictive control of thermal processing |
CN102889944A (en) * | 2012-09-17 | 2013-01-23 | 许继集团有限公司 | Calcium carbide production furnace temperature monitoring method |
CN105987775A (en) * | 2016-07-20 | 2016-10-05 | 天津理工大学中环信息学院 | Temperature sensor nonlinearity correction method and system based on BP neural network |
CN107063509A (en) * | 2017-04-26 | 2017-08-18 | 深圳市相位科技有限公司 | A kind of thermosensitive thermometer calibration method based on neutral net |
CN107367334A (en) * | 2017-02-28 | 2017-11-21 | 淮阴师范学院 | A kind of non-linear compensation method for RTD measurement |
-
2018
- 2018-12-29 CN CN201811637861.5A patent/CN109855763A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1997028669A1 (en) * | 1996-01-31 | 1997-08-07 | Asm America, Inc. | Model-based predictive control of thermal processing |
US6373033B1 (en) * | 1996-01-31 | 2002-04-16 | Asm America, Inc. | Model-based predictive control of thermal processing |
CN102889944A (en) * | 2012-09-17 | 2013-01-23 | 许继集团有限公司 | Calcium carbide production furnace temperature monitoring method |
CN105987775A (en) * | 2016-07-20 | 2016-10-05 | 天津理工大学中环信息学院 | Temperature sensor nonlinearity correction method and system based on BP neural network |
CN107367334A (en) * | 2017-02-28 | 2017-11-21 | 淮阴师范学院 | A kind of non-linear compensation method for RTD measurement |
CN107063509A (en) * | 2017-04-26 | 2017-08-18 | 深圳市相位科技有限公司 | A kind of thermosensitive thermometer calibration method based on neutral net |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110702275A (en) * | 2019-11-22 | 2020-01-17 | 四川中烟工业有限责任公司 | Correction method for offset of resistance type temperature sensor |
CN111397744A (en) * | 2020-05-13 | 2020-07-10 | 金陵科技学院 | Detection early warning system for continuously and remotely monitoring body temperature and correcting body temperature by adopting BP neural network |
CN111397744B (en) * | 2020-05-13 | 2022-10-18 | 金陵科技学院 | Detection early warning system for continuously and remotely monitoring body temperature and correcting body temperature by adopting BP (Back propagation) neural network |
CN113138902A (en) * | 2021-04-27 | 2021-07-20 | 上海英众信息科技有限公司 | Computer host heat dissipation system and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109855763A (en) | A kind of temperature sensor correction method based on BP neural network and PLC | |
Dogan | A Galerkin finite element approach to Burgers' equation | |
Duddu et al. | A combined extended finite element and level set method for biofilm growth | |
Bugmann et al. | Scaling issues in forest succession modelling | |
CN104535223B (en) | The automatic correction algorithm of temperature curve and system of distributed optical fiber temperature sensing system | |
JPS58144918A (en) | Pressure and flow rate controlling system of water distributing pipe network | |
CN107063509A (en) | A kind of thermosensitive thermometer calibration method based on neutral net | |
CN112415635B (en) | Gamma and Gaussian distribution coupled monthly scale rainfall forecast correction method | |
CN115147012B (en) | Neural network model-based carbon emission accounting method and device | |
CN109724692A (en) | A kind of illuminance sensor bearing calibration, storage medium, calculates equipment at system | |
CN107367334A (en) | A kind of non-linear compensation method for RTD measurement | |
Bailah et al. | The Challenges of Driving School Principals in Implementing New Paradigm Learning | |
Klawe et al. | Mathematical modeling of plant cell fate transitions controlled by hormonal signals | |
Basting et al. | Optimal control for reinitialization in finite element level set methods | |
CN110852415B (en) | Vegetation index prediction method, system and equipment based on neural network algorithm | |
Chen-Charpentier et al. | Biofilm growth on medical implants with randomness | |
Schevenhoven et al. | Improving weather and climate predictions by training of supermodels | |
Nguyen et al. | Deep learning models for predicting co2 flux employing multivariate time series | |
CN114996947A (en) | Three-dimensional oil reservoir numerical simulation method | |
JP7394430B2 (en) | Greenhouse environment estimation method, greenhouse environment estimation device, and computer program | |
Stabile et al. | Bayesian identification of a projection-based reduced order model for computational fluid dynamics | |
Sheu et al. | Using the combination of GM (1, 1) and Taylor approximation method to predict the academic achievement of student | |
Tung et al. | Third-order polynomial normal transform applied to multivariate hydrologic extremes | |
CN112932745B (en) | Titanium alloy bone defect support preparation system based on 3D printing technique | |
US20210174276A1 (en) | Information processing apparatus, information processing method and non-transitory recording medium |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190607 |