CN109724692A - A kind of illuminance sensor bearing calibration, storage medium, calculates equipment at system - Google Patents
A kind of illuminance sensor bearing calibration, storage medium, calculates equipment at system Download PDFInfo
- Publication number
- CN109724692A CN109724692A CN201811630075.2A CN201811630075A CN109724692A CN 109724692 A CN109724692 A CN 109724692A CN 201811630075 A CN201811630075 A CN 201811630075A CN 109724692 A CN109724692 A CN 109724692A
- Authority
- CN
- China
- Prior art keywords
- illuminance sensor
- output data
- training set
- sensor
- calibration model
- 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
Landscapes
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
The invention discloses a kind of illuminance sensor bearing calibration, system, storage medium, equipment is calculated, described method includes following steps: data collection: obtaining the output data of illuminance sensor;Data prediction: training set and test set are divided into output data according to the illumination moment;Training set weight computing: training set is sent into RBF neural, calculates training set correlation weight;It generates calibration model: obtaining the feedforward neural network part for the RBF neural that PLC writes;The weight being calculated is inserted in database, illuminance sensor calibration model is obtained;It tests calibration model: output data test set is sent into illuminance calibration model, test calibration model accuracy rate.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 RBF neural network algorithm.
Description
Technical field
The invention belongs to sensor field, in particular to a kind of illuminance sensor school based on RBF neural and PLC
Correction method, storage medium, calculates equipment at system.
Background technique
Illuminance sensor is a kind of common detecting instrument, measures intensity of illumination, is that agricultural planting etc. is strong to illumination
It spends more demanding production field and provides data support.Illuminance sensor can be influenced due to environment in use, be set
The reasons such as standby aging influence its measurement accuracy and then influence measurement result.
Existing illuminance sensor accuracy correcting method is by comparing illuminance sensor and normal precision to be corrected
Illuminance sensor is placed in open air and receives the output data after illumination, and the output of two sensors is fitted by linear algorithm, into
And the updating formula of illuminance sensor to be corrected is obtained, but the output result of illuminance sensor has non-linear property, it uses
The resultant error that linear correction equation obtains is larger.
Therefore a kind of bearing calibration for adapting to illuminance sensor nonlinear characteristic is needed.
Summary of the invention
The shortcomings that it is a primary object of the present invention to overcome the prior art and deficiency provide a kind of illuminance sensor correction
Method solves linear fit result with actual temperature by carrying out nonlinear fitting to temperature using RBF neural network algorithm
The larger technical problem of error, to realize the error correction to temperature sensor.
Second object of the present invention is to provide a kind of illuminance sensor correction system.
Third object of the present invention is to provide a kind of storage medium.
Fourth object of the present invention is to provide a kind of calculating equipment.
The first purpose of this invention is realized by the following technical solution: a kind of illuminance sensor bearing calibration, packet
Include following steps:
Data collection: the output data of illuminance sensor is obtained;Wherein, the illuminance sensor is placed in outdoor receiving
Illumination, including sensor to be corrected and normal precision sensor;
Data prediction: training set and test set are divided output data into according to the illumination moment;
Training set weight computing: training set is sent into RBF neural, calculates training set correlation weight;
It generates calibration model: obtaining the feedforward neural network part for the RBF neural that PLC writes;By what is be calculated
Weight is inserted in database, and illuminance sensor calibration model is obtained;
It tests calibration model: output data test set is sent into illuminance calibration model, test calibration model accuracy rate.
Preferably, it is described by sensor be placed in open air receive light application time be from high noon to complete sunset, at preset timed intervals
Period obtains output data.
Preferably, the training data and test data quantitative proportion are 10:1.
Preferably, the feedforward neural network part of the RBF neural, storage sensor output data, be calculated
Output data weight be stored in PLC.
Further, the PLC is SIEMENS PLC.
Second object of the present invention is realized by the following technical solution: a kind of illuminance sensor correction system, packet
It includes:
Data collection module, for obtaining sensor output data;
Data preprocessing module, for sensor output data to be classified as training set and test set;
RBF neural module;
The RBF neural module specifically includes:
Calculating section, i.e. feedforward neural network, for calculating training set correlation weight;
Model generating portion is worth for obtaining feedforward neural network some numerical results, and according to training set correlative weight
To calibration model;
Model measurement part, for test set to be sent into calibration model and tests calibration model accuracy rate.
Preferably, the neural network module is using python Programming with Pascal Language and to run on the nerve of windows platform
Network algorithm.
Third object of the present invention is realized by the following technical solution: a kind of storage medium is stored with program, described
When program is executed by processor, above-mentioned illuminance sensor bearing calibration is realized.
Fourth object of the present invention is realized by the following technical solution: a kind of calculating equipment, including processor and
For the memory of storage processor executable program, when the processor executes the program of memory storage, realize above-mentioned
Illuminance sensor bearing calibration.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1, the present invention is by the way that using RBF neural network algorithm, to illuminance progress nonlinear fitting, RBF neural can be with
Corresponding network topology structure is determined according to particular problem, there is self study, self-organizing, adaptation function, it is to non-linear company
Continuous function has Uniform Approximation, can with parallel high-speed handle data, solves linear fit result with practical illuminance error
Larger technical problem, to realize the error correction to illuminance sensor;
2, the calculating of neural network weight of the present invention carries out on windows platform, can make full use of the performance of computer
Shorten and calculate the time, and the occasion of a greater amount of training datas and test data can be applied to;
3, present invention uses PLC calculates illuminance, can calculate illuminance simultaneously according to the illuminance obtained
Other output equipments are controlled, and the later period is facilitated to safeguard different application situation.
Detailed description of the invention
Fig. 1 is a kind of illuminance sensor bearing calibration flow chart of the present invention;
Fig. 2 is a kind of illuminance sensor correction system structure diagram of the present invention.
Specific embodiment
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
Embodiment
As shown in Figure 1, a kind of illuminance sensor bearing calibration, includes the following steps:
Data collection: sensor to be corrected and normal precision sensor are placed in open air, received from high noon to complete sunset
Illumination and every the output data of five minutes acquisition sensors;
Data prediction: training set and test set are divided into output data according to the illumination moment, data bulk ratio is 10:
1;
Training set weight computing: training set is sent into RBF neural, calculates training set correlation weight;
RBF neural, that is, radial basis function neural network (Radical Basis Function).RBF neural is hidden
The transfer function of layer unit is about centrosymmetric RBF (such as Gaussian function).RBF neural is three layers of static feed forward neural
The structure of network, Hidden unit number i.e. network can be adaptively adjusted according to the particular problem of research in the training stage,
Currently, the training algorithm of many RBF neurals supports online and offline training, network structure and hidden layer list can be dynamically determined
The data center of member and extension constant, pace of learning are fast.RBF neural can then make the influence between each task drop to compared with
Low level, so that each task is attained by preferable effect, this parallel multitask system can make RBF neural
Using more and more extensive.In short, RBF neural can determine corresponding network topology structure according to particular problem, have certainly
Study, self-organizing, adaptation function, it has Uniform Approximation to non-linear continuous function, and pace of learning is fast, can carry out big
The data fusion of range can with parallel high-speed handle data.
It generates calibration model: obtaining the feedforward neural network part for the RBF neural that PLC writes;By what is be calculated
Weight is inserted in database, and illuminance sensor calibration model is obtained;
It tests calibration model: output data test set is sent into illuminance calibration model, test calibration model accuracy rate.
The feedforward neural network part of the RBF neural, storage sensor output data, the output number being calculated
It is stored in SIEMENS PLC according to weight.
As shown in Fig. 2, a kind of illuminance sensor corrects system, comprising:
Data collection module, for obtaining sensor output data;
Data preprocessing module, for sensor output data to be classified as training set and test set;
RBF neural module is calculated to use python Programming with Pascal Language and running on the neural network of windows platform
Method;
The RBF neural module specifically includes:
Calculating section, i.e. feedforward neural network, for calculating training set correlation weight;
Model generating portion is worth for obtaining feedforward neural network some numerical results, and according to training set correlative weight
To calibration model;
Model measurement part, for test set to be sent into calibration model and tests calibration model accuracy rate.
A kind of storage medium is stored with program, when described program is executed by processor, realizes above-mentioned illuminance sensor
Bearing calibration.
A kind of calculating equipment, including processor and for the memory of storage processor executable program, the processing
When device executes the program of memory storage, above-mentioned illuminance sensor bearing calibration is realized.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (9)
1. a kind of illuminance sensor bearing calibration, which comprises the steps of:
Data collection: the output data of illuminance sensor is obtained;Wherein, the illuminance sensor is placed in open air and receives light
According to, including sensor to be corrected and normal precision sensor;
Data prediction: training set and test set are divided output data into according to the illumination moment;
Training set weight computing: training set is sent into RBF neural, calculates training set correlation weight;
It generates calibration model: obtaining the feedforward neural network part for the RBF neural that PLC writes;The weight that will be calculated
It inserts in database, obtains illuminance sensor calibration model;
It tests calibration model: output data test set is sent into illuminance calibration model, test calibration model accuracy rate.
2. illuminance sensor bearing calibration according to claim 1, which is characterized in that described that sensor is placed in open air
Receiving light application time is from high noon to complete sunset, and the period obtains output data at preset timed intervals.
3. illuminance sensor bearing calibration according to claim 1, which is characterized in that the training data and test number
Data bulk ratio is 10:1.
4. illuminance sensor bearing calibration according to claim 1, which is characterized in that before the RBF neural
It is stored in PLC to part of neural network, storage sensor output data, the output data weight being calculated.
5. illuminance sensor bearing calibration according to claim 4, which is characterized in that the PLC is SIEMENS PLC.
6. a kind of illuminance sensor corrects system characterized by comprising
Data collection module, for obtaining sensor output data;
Data preprocessing module, for sensor output data to be classified as training set and test set;
RBF neural module;
The RBF neural module specifically includes:
Calculating section, i.e. feedforward neural network, for calculating training set correlation weight;
Model generating portion obtains school for obtaining feedforward neural network some numerical results, and according to training set correlative weight value
Positive model;
Model measurement part, for test set to be sent into calibration model and tests calibration model accuracy rate.
7. illuminance sensor according to claim 6 corrects system, which is characterized in that the neural network module is to make
With python Programming with Pascal Language and run on the neural network algorithm of windows platform.
8. a kind of storage medium, is stored with program, which is characterized in that when described program is executed by processor, realize above-mentioned light
Illuminance transducer bearing calibration.
9. a kind of calculating equipment, which is characterized in that including processor and for the memory of storage processor executable program,
When the processor executes the program of memory storage, above-mentioned illuminance sensor bearing calibration is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811630075.2A CN109724692A (en) | 2018-12-29 | 2018-12-29 | A kind of illuminance sensor bearing calibration, storage medium, calculates equipment at system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811630075.2A CN109724692A (en) | 2018-12-29 | 2018-12-29 | A kind of illuminance sensor bearing calibration, storage medium, calculates equipment at system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109724692A true CN109724692A (en) | 2019-05-07 |
Family
ID=66296629
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811630075.2A Pending CN109724692A (en) | 2018-12-29 | 2018-12-29 | A kind of illuminance sensor bearing calibration, storage medium, calculates equipment at system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109724692A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110196069A (en) * | 2019-05-28 | 2019-09-03 | 北京航空航天大学 | A kind of sensor compensation system and its compensation method |
CN111076758A (en) * | 2019-11-26 | 2020-04-28 | 北京工业大学 | Automatic calibration method for high-altitude detection sensor based on Internet of things |
CN111272277A (en) * | 2020-01-21 | 2020-06-12 | 中国工程物理研究院激光聚变研究中心 | Laser pulse waveform measurement distortion correction method and system based on neural network |
CN111811786A (en) * | 2020-08-20 | 2020-10-23 | 深圳市路美康尔医疗科技有限公司 | Exposure intensity calibration method for ultraviolet disinfection cabinet |
CN112903093A (en) * | 2021-02-01 | 2021-06-04 | 清华大学 | Near field distribution photometry measuring method and device based on deep learning |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107121924A (en) * | 2017-03-03 | 2017-09-01 | 中国农业大学 | A kind of Visual Environment regulator control system and method based on RBF neural |
-
2018
- 2018-12-29 CN CN201811630075.2A patent/CN109724692A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107121924A (en) * | 2017-03-03 | 2017-09-01 | 中国农业大学 | A kind of Visual Environment regulator control system and method based on RBF neural |
Non-Patent Citations (3)
Title |
---|
侯立群等: "基于RBF神经网络的传感器非线性误差校正方法", 《传感器技术》 * |
樊润洁 等: "基于神经网络的传感器非线性误差校正方法", 《电子设计工程》 * |
陈丽华等: "《人工神经网络及其在水质信息检测中的应用》", 30 April 2011 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110196069A (en) * | 2019-05-28 | 2019-09-03 | 北京航空航天大学 | A kind of sensor compensation system and its compensation method |
CN111076758A (en) * | 2019-11-26 | 2020-04-28 | 北京工业大学 | Automatic calibration method for high-altitude detection sensor based on Internet of things |
CN111272277A (en) * | 2020-01-21 | 2020-06-12 | 中国工程物理研究院激光聚变研究中心 | Laser pulse waveform measurement distortion correction method and system based on neural network |
CN111811786A (en) * | 2020-08-20 | 2020-10-23 | 深圳市路美康尔医疗科技有限公司 | Exposure intensity calibration method for ultraviolet disinfection cabinet |
CN112903093A (en) * | 2021-02-01 | 2021-06-04 | 清华大学 | Near field distribution photometry measuring method and device based on deep learning |
CN112903093B (en) * | 2021-02-01 | 2022-04-08 | 清华大学 | Near field distribution photometry measuring method and device based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109724692A (en) | A kind of illuminance sensor bearing calibration, storage medium, calculates equipment at system | |
Wu et al. | Simulating daily field crop canopy photosynthesis: an integrated software package | |
CN105913079B (en) | Electronic nose isomeric data recognition methods based on the study of the target domain migration limit | |
Hongkang et al. | Recurrent neural network model for prediction of microclimate in solar greenhouse | |
US20190072075A1 (en) | Method and device for detecting equivalent load of wind turbine | |
CN110441374B (en) | Dissolved oxygen sensor compensation method based on SA-BP neural network | |
CN110795780A (en) | XGboost algorithm-based cable-stayed bridge finite element correction method | |
CN108872508A (en) | A kind of eutrophy quality evaluation method of GA-BP optimization TSFNN | |
CN114154401B (en) | Soil erosion modulus calculation method and system based on machine learning and observation data | |
CN112713881B (en) | Synchronous clock maintaining system and method based on edge calculation | |
US20220309393A1 (en) | Cloud-edge collaboration forecasting system and method for aluminum oxide production indexes | |
CN111832790A (en) | Method and system for predicting medium and long-term water demand of water supply pipe network | |
CN108595892A (en) | Soft-measuring modeling method based on time difference model | |
CN112365056A (en) | Electrical load joint prediction method and device, terminal and storage medium | |
CN113393057A (en) | Wheat yield integrated prediction method based on deep fusion machine learning model | |
CN112949930A (en) | PA-LSTM network-based road motor vehicle exhaust high-emission early warning method | |
CN111596006A (en) | Calibration method of atmosphere online monitor and monitor | |
CN115034361A (en) | Sensor physical quantity regression method based on ICS-BP neural network | |
CN114971090A (en) | Electric heating load prediction method, system, equipment and medium | |
CN114599127A (en) | Intelligent control method for urban lighting system | |
CN111461297A (en) | Solar irradiation quantity optimization prediction algorithm based on MPC and E L M neural network | |
CN109187898B (en) | Soft measurement method and device for ammonia nitrogen content of water in aquaculture environment | |
CN115907204A (en) | Forest transpiration water consumption prediction method for optimizing BP neural network by sparrow search algorithm | |
Ahuja et al. | A synthesis of current parameterization approaches and needs for further improvements | |
CN115017799B (en) | EM-DBN fusion-based solar radiation estimation method for quantitative region |
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: 20190507 |