CN114881168A - Photoionization detector calibration method, photoionization detector calibration system, electronic device and storage medium - Google Patents
Photoionization detector calibration method, photoionization detector calibration system, electronic device and storage medium Download PDFInfo
- Publication number
- CN114881168A CN114881168A CN202210579387.5A CN202210579387A CN114881168A CN 114881168 A CN114881168 A CN 114881168A CN 202210579387 A CN202210579387 A CN 202210579387A CN 114881168 A CN114881168 A CN 114881168A
- Authority
- CN
- China
- Prior art keywords
- photoionization
- calibrated
- photoionization detector
- sample data
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The invention discloses a method for calibrating a photoionization detector, which comprises the following steps: acquiring sample data and carrying out clustering treatment, wherein the sample data comprises the total volatile organic compound concentration of the photoionization detector to be calibrated, the temperature and the relative humidity in the photoionization detector to be calibrated and the average value of the total volatile organic compound concentrations of a plurality of reference photoionization detectors; constructing a calibration model based on a radial basis function, wherein the calibration model comprises a hidden layer and an output layer; iteratively training the calibration model by using the sample data after clustering according to a preset target function and a preset minimum error to obtain a trained calibration model; and calibrating the photoionization detector to be calibrated by using the trained calibration model. The invention also discloses a photoionization detector calibration system, electronic equipment and a storage medium.
Description
Technical Field
The invention relates to the field of instrument calibration, in particular to a method and a system for calibrating a photoionization detector, electronic equipment and a storage medium.
Background
A photoionization Detector (PID for short) is a Detector with extremely high sensitivity and wide application, and is mainly used for detecting volatile organic compounds with the concentration within the range of 1 ppb-10000 ppm. The detector has the advantages of high precision (ppb level), quick response, continuous test and the like, and can be widely applied to detecting aromatic hydrocarbons, ketones, aldehydes, amines, amine compounds, chlorinated hydrocarbons, unsaturated hydrocarbons and the like. In order to meet the use requirement, the PID monitor needs to be calibrated in a timing mode, and the zero point and the sensitivity are corrected.
Ozone pollution, especially in summer, is an important factor affecting air quality. TVOC (Total Volatile Organic Compounds) is used as one of precursor substances of O3, and sensor equipment is arranged to carry out high-density monitoring on the TVOC, so that the TVOC has important significance for prevention and treatment of O3. In the prior art, the TVOC sensor is nonlinear in both the concentration dimension and the temperature dimension, and many instruments on the market adjust the sensitivity and the zero point of the sensor through a potentiometer at present, but the nonlinear compensation problem of the sensor cannot be solved through the potentiometer adjustment. If zero setting is close to equipment, PID sensor equipment volume is big, wastes time and energy.
Disclosure of Invention
In view of the above problems, the present invention provides a method, a system and an electronic device for calibrating a photoionization detector, so as to solve at least one of the above problems.
According to a first aspect of the present invention, there is provided a method of calibrating a photoionization detector, comprising:
acquiring sample data and carrying out clustering treatment, wherein the sample data comprises the total volatile organic compound concentration of the photoionization detector to be calibrated, the temperature and the relative humidity in the photoionization detector to be calibrated and the average value of the total volatile organic compound concentrations of a plurality of reference photoionization detectors;
constructing a calibration model based on a radial basis function, wherein the calibration model comprises a hidden layer and an output layer;
iteratively training the calibration model by using the sample data after clustering according to a preset target function and a preset minimum error to obtain a trained calibration model;
and calibrating the photoionization detector to be calibrated by using the trained calibration model.
According to an embodiment of the present invention, the acquiring sample data includes:
regularly introducing standard gas into a plurality of reference photoionization detectors, wherein each reference photoionization detector is provided with a GPS module and a data uploading module;
carrying a plurality of reference photoionization detectors to cruise according to a cruising line in a region according to preset time, wherein the cruising line is provided with a plurality of photoionization detectors to be calibrated, and each photoionization detector to be calibrated comprises a GPS module, a data uploading module, a temperature sensor and a humidity sensor;
and automatically matching the reference photoionization detector and the photoionization detector to be calibrated by utilizing longitude and latitude information to obtain the total volatile organic compound concentration of the photoionization detector to be calibrated at a plurality of time points, the temperature and the relative humidity in the photoionization detector to be calibrated and the average value of the total volatile organic compound concentrations of the plurality of reference photoionization detectors.
According to an embodiment of the present invention, the standard gas includes standard gases having concentrations of 20%, 50%, and 80%;
wherein, it includes to the gaseous standard of many benchmark photoionization detectors lets in:
the flow rate of the introduced standard gas is controlled between 150mL/min and 250 mL/min.
According to an embodiment of the present invention, the clustering process includes:
randomly dividing sample data into a training set and a test set;
constructing a clustering processing model based on a K-means algorithm, taking the total volatile organic compound concentration of the photoionization detector to be calibrated, the temperature and the relative humidity in the photoionization detector to be calibrated as the input of the clustering processing model, and taking the average value of the total volatile organic compound concentrations of a plurality of reference photoionization detectors as the output of the clustering processing model;
randomly selecting a plurality of sample data in the test set as a clustering center of the sample data;
calculating the grouping of the sample data by using a clustering processing model and acquiring a new clustering center of the sample data;
and (4) iteratively calculating sample grouping and obtaining a new clustering center until the new clustering center is not changed any more, and finishing the clustering processing of the sample data.
According to an embodiment of the present invention, the above hidden layer is determined by equation (1):
wherein, c i Is the center of the ith hidden node, k is the number of hidden nodes, r i The width of the layer neuron basis functions is implied for the neurons.
According to an embodiment of the present invention, the above output layer is determined by equation (2):
wherein, w i Is the connection authority of the ith hidden node to the output layer.
According to an embodiment of the present invention, the preset objective function is determined by equation (3):
wherein, C oi Represents the average value of the total volatile organic compound concentration f (x) of a plurality of reference photoionization detectors i ) The output layer is represented.
According to a second aspect of the present invention there is provided a calibration system for a photoionization detector, comprising:
the data acquisition and processing module is used for acquiring sample data and performing clustering processing, wherein the sample data comprises the total volatile organic compound concentration of the photoionization detector to be calibrated, the temperature and the relative humidity in the photoionization detector to be calibrated and the average value of the total volatile organic compound concentrations of the plurality of reference photoionization detectors;
the model building module is used for building a calibration model based on the radial basis function, wherein the calibration model comprises a hidden layer and an output layer;
the model iterative training module is used for iteratively training the calibration model by using the sample data after the clustering processing according to a preset target function and a preset minimum error to obtain a trained calibration model;
and the calibration module is used for calibrating the photoionization detector to be calibrated by utilizing the trained calibration model.
According to a third aspect of the present invention, there is provided an electronic apparatus comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method for calibrating a photoionization detector.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of calibration of a photoionization detector described above.
According to the calibration method provided by the invention, the data of the device to be calibrated and the data of the reference device are taken as sample data and are preprocessed, the calibration model based on the Radial Basis Function (RBF) is constructed, the preset target Function and the preset minimum error are used for repeatedly training the calibration model, and the trained calibration model is further used for calibrating the photoionization detector to be calibrated, so that the precision of the photoionization detector to be calibrated can be improved.
Drawings
FIG. 1 is a flow chart of a method for calibrating a photoionization detector according to an embodiment of the invention;
FIG. 2 is a flow diagram of obtaining sample data according to an embodiment of the invention;
FIG. 3 is a flow diagram of a clustering process according to an embodiment of the invention;
FIG. 4 is a block diagram of a calibration system for a photoionization detector according to an embodiment of the invention;
figure 5 schematically illustrates a block diagram of electronics suitable for implementing a method for calibration of a photoionization detector, in accordance with an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the accompanying drawings in combination with the embodiments.
Air pollution, in particular to pollution problems such as atmospheric haze and the like, which affect the health of residents, fine particle pollutants are included in the atmospheric haze, so that the detection precision of the fine particle pollutants in the air is necessary to be improved. At the same time, ozone (O) 3 ) Pollution is also an important factor affecting air quality, and TVOC as one of the precursor substances of ozone is also the key point of detection.
In the prior art, a photoionization detector is generally used for detecting the pollutants, so that the precision of the photoionization detector is improved, and the pollutants can be effectively detected. At present, problems such as low calibration precision, time consumption, high calibration cost and the like exist in a calibration method for a photoionization detector.
In order to solve various problems of a photoionization detector calibration method in the prior art, the invention provides a photoionization detector calibration method and system based on a radial basis function neural network, electronic equipment and a storage medium.
The sample data and the sample data acquisition process related to the embodiment of the invention both accord with the regulations of related laws and regulations, necessary security measures are taken, and the common customs of public sequences is not violated.
FIG. 1 is a flow chart of a method for calibrating a photoionization detector according to an embodiment of the invention.
As shown in fig. 1, the method for calibrating the photoionization detector includes operation S110 to operation S140.
In operation S110, sample data is obtained and clustered, where the sample data includes a total volatile organic compound concentration of the photoionization detector to be calibrated, a temperature and a relative humidity in the photoionization detector to be calibrated, and a mean value of the total volatile organic compound concentrations of the plurality of reference photoionization detectors.
In operation S120, a calibration model based on a radial basis function is constructed, wherein the calibration model includes a hidden layer and an output layer.
In operation S130, the calibration model is iteratively trained by using the sample data after the clustering process according to a preset objective function and a preset minimum error, so as to obtain a trained calibration model.
In operation S140, the photo-ionization detector to be calibrated is calibrated by using the trained calibration model.
According to the calibration method provided by the invention, the data of the device to be calibrated and the data of the reference device are taken as sample data and are preprocessed, the calibration model based on the Radial Basis Function (RBF) is constructed, the preset target Function and the preset minimum error are used for repeatedly training the calibration model, and the trained calibration model is further used for calibrating the photoionization detector to be calibrated, so that the precision of the photoionization detector to be calibrated can be improved.
Fig. 2 is a flowchart of acquiring sample data according to an embodiment of the present invention.
As shown in fig. 2, operations S210 to S230 are included.
In operation S210, a standard gas is periodically supplied to a plurality of reference photoionization detectors, wherein each of the reference photoionization detectors is provided with a GPS module and a data upload module.
The periodicity may be a fixed date or a fixed time interval per month, where the standard gas is a gas with uniform concentration, good stability, and accurate magnitude as understood by those skilled in the art, and may include one or more gases.
In operation S220, a plurality of reference photoionization detectors are carried to cruise according to a cruising route in an area according to preset time, wherein a plurality of photoionization detectors to be calibrated are arranged on the cruising route, and each photoionization detector to be calibrated includes a GPS module, a data uploading module, a temperature sensor and a humidity sensor.
For example, two reference photoionization detectors are used on a motor vehicle (e.g., an electric vehicle) to complete cruising with equipment deployed in an area (e.g., a certain urban area) on the first three (variable) days of each month. Wherein, a plurality of point positions are arranged on the route patrol road, and a photoionization detector to be calibrated is arranged on each point position.
In operation S230, the longitude and latitude information is used to automatically match the reference photoionization detector and the photoionization detector to be calibrated, so as to obtain the total volatile organic compound concentration of the photoionization detector to be calibrated at a plurality of time points, the temperature and the relative humidity in the photoionization detector to be calibrated, and the average value of the total volatile organic compound concentrations of the plurality of reference photoionization detectors.
The library stores the values of a reference photoionization detector (reference device) and a photoionization detector to be calibrated (device to be calibrated),automatically matching according to the longitude and latitude to obtain a time point (t is 1,2,.., n) at which the distance between the reference equipment and each equipment to be calibrated is closest (the longitude and latitude are approximately coincident and the distance is ensured to be less than 100m) each time, and obtaining the TVOC concentration (C) of the equipment to be calibrated at the time point si ) Temperature (T) in the device to be calibrated si ) Relative Humidity (RH) in the device to be calibrated si ) Mean value (C) of TVOC concentrations of two reference photoionization detectors (reference devices) oi ) The above data are taken as a group.
Through regular cruising, automatic longitude and latitude matching is carried out on equipment to be calibrated and reference equipment which are arranged on a cruising route, sample data under multiple time points are obtained, and a large amount of high-quality and high-reliability data are provided for training of a subsequent calibration model.
According to an embodiment of the present invention, the standard gas includes standard gases having concentrations of 20%, 50%, and 80%;
wherein, it includes to the gaseous standard of many benchmark photoionization detectors lets in:
the flow rate of the introduced standard gas is controlled between 150mL/min and 250 mL/min.
By introducing standard gases with different concentrations into the reference photoionization detector, the detection precision of reference equipment can be effectively improved, and the reliability of detection data is ensured.
Fig. 3 is a flow diagram of a clustering process according to an embodiment of the invention.
As shown in fig. 3, operation S310 to operation S350 are included.
In operation S310, sample data is randomly divided into a training set and a test set.
Randomly selecting 70% of the data group as a training set and the rest 30% as a test set from sample data in a period of time.
In operation S320, a clustering model based on the K-means algorithm is constructed, the total volatile organic compound concentration of the photoionization detector to be calibrated, the temperature and the relative humidity in the photoionization detector to be calibrated are used as input of the clustering model, and the average value of the total volatile organic compound concentrations of the plurality of reference photoionization detectors is used as output of the clustering model.
In operation S330, a plurality of sample data is randomly selected as a cluster center of the sample data in the test set.
In operation S340, a grouping of sample data is calculated using a clustering process model and a new clustering center of the sample data is acquired.
In operation S350, the sample grouping is iteratively calculated and a new clustering center is obtained until the new clustering center is not changed any more, and the clustering process on the sample data is completed.
The clustering method comprises subjecting RH si 、T si And C si (the data sets are collectively referred to as x) i ) Input the models together, and C oi As the desired output. The center point is obtained using the K-means algorithm. The method comprises the steps of randomly finding k training samples in a test set to serve as clustering centers, calculating grouping of input samples, and calculating an average value of the clustering samples to obtain a new clustering center. The steps of computing groupings and computing new cluster centers are repeated until the cluster centers do not change.
According to an embodiment of the present invention, the above hidden layer is determined by equation (1):
wherein, c i Is the center of the ith hidden node, k is the number of hidden nodes, r i The width of the layer neuron basis functions is implied for the neurons.
Through the hidden layer determined by the formula (1), a sample data processing task can be well completed, the reliability of the calibration model is improved, and meanwhile, the application scene of the calibration model can be expanded.
According to an embodiment of the present invention, the above output layer is determined by equation (2):
wherein, w i From the ith hidden node to the output layerAnd (4) connecting the rights.
Through the output layer determined by the formula (2), calibration data conforming to an actual scene can be output.
According to an embodiment of the present invention, the preset objective function is determined by equation (3):
wherein, C oi Represents the average value of the total volatile organic compound concentration f (x) of a plurality of reference photoionization detectors i ) The output layer is represented.
The target function determined by the formula (3) can be better used for training the calibration model, so that the efficiency of model training is improved, and the accuracy of the training process of the calibration model is facilitated.
Figure 4 is a block diagram of a calibration system for a photoionization detector according to an embodiment of the invention.
As shown in FIG. 4, the calibration system 400 includes a data acquisition and processing module 410, a model building module 420, a model iterative training module 430, and a calibration module 440.
The data obtaining and processing module 410 is configured to obtain sample data and perform clustering processing, where the sample data includes a total volatile organic compound concentration of the photoionization detector to be calibrated, a temperature and a relative humidity in the photoionization detector to be calibrated, and a mean value of the total volatile organic compound concentrations of the plurality of reference photoionization detectors;
a model construction module 420 configured to construct a calibration model based on a radial basis function, wherein the calibration model includes a hidden layer and an output layer;
the model iterative training module 430 is configured to iteratively train a calibration model by using the sample data after the clustering process according to a preset objective function and a preset minimum error, and obtain a trained calibration model;
and the calibration module 440 is configured to calibrate the photoionization detector to be calibrated by using the trained calibration model.
The calibration system can improve the calibration precision of the equipment to be calibrated, and meanwhile, due to the utilization of the neural network model based on the radial basis function, the generalization of the system is improved, and the application of the system in a plurality of scenes is facilitated.
According to the embodiment of the present invention, any of the data acquisition and processing module 410, the model construction module 420, the model iteration training module 430, and the calibration module 440 may be combined and implemented in one module, or any one of them may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present invention, at least one of the data acquisition and processing module 410, the model building module 420, the model iteration training module 430 and the calibration module 440 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or in any one of three implementations of software, hardware and firmware, or in any suitable combination of any of them. Alternatively, at least one of the data acquisition and processing module 410, the model building module 420, the model iterative training module 430 and the calibration module 440 may be at least partially implemented as a computer program module that, when executed, may perform corresponding functions.
FIG. 5 schematically illustrates a block diagram of an electronic device suitable for implementing a method for calibration of a photoionization detector, in accordance with an embodiment of the invention.
As shown in fig. 5, an electronic device 500 according to an embodiment of the present invention includes a processor 501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. The processor 501 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 501 may also include onboard memory for caching purposes. Processor 501 may include a single processing unit or multiple processing units for performing the different actions of the method flows according to embodiments of the present invention.
In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are stored. The processor 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. The processor 501 performs various operations of the method flow according to the embodiments of the present invention by executing programs in the ROM 502 and/or the RAM 503. Note that the programs may also be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 may also perform various operations of method flows according to embodiments of the present invention by executing programs stored in the one or more memories.
According to an embodiment of the present invention, electronic device 500 may also include an input/output (I/O) interface 505, input/output (I/O) interface 505 also being connected to bus 504. The electronic device 500 may also include one or more of the following components connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
The present invention also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the present invention.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for calibrating a photoionization detector comprises the following steps:
acquiring sample data and carrying out clustering treatment, wherein the sample data comprises the total volatile organic compound concentration of the photoionization detector to be calibrated, the temperature and the relative humidity in the photoionization detector to be calibrated and the average value of the total volatile organic compound concentrations of a plurality of reference photoionization detectors;
constructing a calibration model based on a radial basis function, wherein the calibration model comprises a hidden layer and an output layer;
iteratively training the calibration model by using the sample data after the clustering process according to a preset target function and a preset minimum error to obtain a trained calibration model;
and calibrating the photoionization detector to be calibrated by using the trained calibration model.
2. The method of claim 1, wherein said obtaining sample data comprises:
regularly introducing standard gas into the plurality of reference photoionization detectors, wherein the reference photoionization detectors are provided with a GPS module and a data uploading module;
carrying the plurality of reference photoionization detectors to cruise according to a cruising line in an area according to preset time, wherein the cruising line is provided with a plurality of photoionization detectors to be calibrated, and each photoionization detector to be calibrated comprises a GPS (global positioning system) module, a data uploading module, a temperature sensor and a humidity sensor;
and automatically matching the reference photoionization detector and the photoionization detector to be calibrated by utilizing longitude and latitude information to obtain the total volatile organic compound concentration of the photoionization detector to be calibrated, the temperature and the relative humidity in the photoionization detector to be calibrated and the average value of the total volatile organic compound concentrations of the plurality of reference photoionization detectors at a plurality of time points.
3. The method of claim 2, wherein the standard gas comprises standard gases at concentrations of 20%, 50%, and 80%;
wherein, the step of introducing standard gas into the plurality of reference photoionization detectors comprises the following steps:
the flow rate of the introduced standard gas is controlled between 150mL/min and 250 mL/min.
4. The method of claim 1, wherein the clustering process comprises:
randomly dividing the sample data into a training set and a testing set;
constructing a clustering processing model based on a K-means algorithm, taking the total volatile organic compound concentration of the photoionization detector to be calibrated, the temperature and the relative humidity in the photoionization detector to be calibrated as the input of the clustering processing model, and taking the average value of the total volatile organic compound concentrations of the plurality of reference photoionization detectors as the output of the clustering processing model;
randomly selecting a plurality of sample data in the test set as a clustering center of the sample data;
calculating the grouping of the sample data by using the clustering processing model and acquiring a new clustering center of the sample data;
and iteratively calculating sample grouping and obtaining the new clustering center until the new clustering center is not changed any more, and finishing the clustering processing of the sample data.
5. The method of claim 1, wherein the hidden layer is determined by equation (1):
wherein, c i Is the center of the ith hidden node, k is the number of hidden nodes, r i The width of the layer neuron basis functions is implied for the neurons.
6. The method of claim 1, wherein the output layer is determined by equation (2):
wherein, w i Is the connection authority of the ith hidden node to the output layer.
7. The method of claim 1, wherein the preset objective function is determined by equation (3):
wherein, C oi Represents the mean value of the total volatile organic compound concentration of the plurality of reference photoionization detectors, f (x) i ) Representing the output layer.
8. A calibration system for a photoionization detector, comprising:
the data acquisition and processing module is used for acquiring sample data and performing clustering processing, wherein the sample data comprises the total volatile organic compound concentration of the photoionization detector to be calibrated, the temperature and the relative humidity in the photoionization detector to be calibrated and the average value of the total volatile organic compound concentrations of a plurality of reference photoionization detectors;
the model building module is used for building a calibration model based on a radial basis function, wherein the calibration model comprises a hidden layer and an output layer;
the model iterative training module is used for iteratively training the calibration model by using the sample data after the clustering processing according to a preset target function and a preset minimum error to obtain a trained calibration model;
and the calibration module is used for calibrating the photoionization detector to be calibrated by utilizing the trained calibration model.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-7.
10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210579387.5A CN114881168B (en) | 2022-05-25 | 2022-05-25 | Method and system for calibrating photoionization detector, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210579387.5A CN114881168B (en) | 2022-05-25 | 2022-05-25 | Method and system for calibrating photoionization detector, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114881168A true CN114881168A (en) | 2022-08-09 |
| CN114881168B CN114881168B (en) | 2023-04-07 |
Family
ID=82677371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210579387.5A Active CN114881168B (en) | 2022-05-25 | 2022-05-25 | Method and system for calibrating photoionization detector, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114881168B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393882A (en) * | 2011-09-21 | 2012-03-28 | 济中节能技术（苏州）有限公司 | Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line |
| CN107121463A (en) * | 2017-04-27 | 2017-09-01 | 浙江清华长三角研究院 | A kind of multi-channel electronic nose detecting system and its measuring method |
| CN107966490A (en) * | 2016-11-18 | 2018-04-27 | 南京清元景和环境科技有限公司 | A kind of photo-ionization gas detector On-line Control case |
| US10101298B1 (en) * | 2017-04-18 | 2018-10-16 | Broadsens Corp. | Photo ionization detector with self-calibration |
| CN111596006A (en) * | 2020-04-29 | 2020-08-28 | 北京雪迪龙科技股份有限公司 | Calibration method of atmosphere online monitor and monitor |
| CN111936825A (en) * | 2018-03-21 | 2020-11-13 | 祖克斯有限公司 | Sensor calibration |
| CN113408699A (en) * | 2021-06-16 | 2021-09-17 | 中国地质科学院 | Lithology identification method and system based on improved radial basis function neural network |
-
2022
- 2022-05-25 CN CN202210579387.5A patent/CN114881168B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393882A (en) * | 2011-09-21 | 2012-03-28 | 济中节能技术（苏州）有限公司 | Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line |
| CN107966490A (en) * | 2016-11-18 | 2018-04-27 | 南京清元景和环境科技有限公司 | A kind of photo-ionization gas detector On-line Control case |
| US10101298B1 (en) * | 2017-04-18 | 2018-10-16 | Broadsens Corp. | Photo ionization detector with self-calibration |
| CN107121463A (en) * | 2017-04-27 | 2017-09-01 | 浙江清华长三角研究院 | A kind of multi-channel electronic nose detecting system and its measuring method |
| CN111936825A (en) * | 2018-03-21 | 2020-11-13 | 祖克斯有限公司 | Sensor calibration |
| CN111596006A (en) * | 2020-04-29 | 2020-08-28 | 北京雪迪龙科技股份有限公司 | Calibration method of atmosphere online monitor and monitor |
| CN113408699A (en) * | 2021-06-16 | 2021-09-17 | 中国地质科学院 | Lithology identification method and system based on improved radial basis function neural network |
Non-Patent Citations (4)
| Title |
|---|
| MORTAZA AGHBASHLO ET AL.: "Multi-objective exergetic optimization of continuous photo-biohydrogen production process using a novel hybrid fuzzy clustering-ranking approach coupled with Radial Basis Function (RBF) neural network", 《SCIENCEDIRECT》 * |
| 杨子宾 等: "基于径向基函数神经网络的探空仪湿度传感器曲线拟合", 《气象科技》 * |
| 肖清湄: "基于LM改进的RBF神经网络算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 菅傲群: "光离子化气体传感器的基础研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114881168B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Malings et al. | Development of a general calibration model and long-term performance evaluation of low-cost sensors for air pollutant gas monitoring | |
| CN112880751B (en) | Air pollution condition obtaining method based on navigation monitoring | |
| CN106446307B (en) | Aerosol foundation data-based AOD (automated optical inspection) vertical correction effect evaluation method and system | |
| CN110426493B (en) | Air quality monitoring data calibration method, device, equipment and storage medium | |
| CN108614071B (en) | Distributed outdoor air quality monitoring precision correction system and parameter updating method | |
| CN116297068A (en) | Aerosol optical thickness inversion method and system based on earth surface reflectivity optimization | |
| CN115235560B (en) | Method, device, equipment and storage medium for evaluating carbon sink capacity of ecosystem | |
| CN113344149B (en) | PM2.5 hourly prediction method based on neural network | |
| Lee et al. | Spatial cluster detection of regression coefficients in a mixed‐effects model | |
| CN115825338A (en) | Ozone monitoring downscaling method, device, equipment and computer readable storage medium | |
| CN113341434B (en) | Infrared band on-orbit transfer calibration method and device | |
| Kim et al. | Long-term behavior and stability of calibration models for NO and NO 2 low-cost sensors | |
| Murray et al. | Combining satellite imagery and numerical model simulation to estimate ambient air pollution: An ensemble averaging approach | |
| CN110168347A (en) | Measurement device and measuring method | |
| CN114881168B (en) | Method and system for calibrating photoionization detector, electronic device and storage medium | |
| CN112326882B (en) | Air quality sensor processing method and device | |
| CN116189796A (en) | Machine learning-based satellite-borne short wave infrared CO 2 Column concentration estimation method | |
| CN114487300A (en) | Scattered point source carbon emission intensity monitoring method and system based on vehicle-mounted measurement system | |
| CN115859026A (en) | High-resolution near-surface PM2.5 concentration remote sensing inversion method and device | |
| Leroy et al. | The application of COSMIC data to global change research | |
| Srishti et al. | Multiple PM low-cost sensors, multiple seasons’ data, and multiple calibration models | |
| Esatbeyoglu et al. | Data driven concept for sensor data adaptation of electrochemical sensors for mobile air quality measurements | |
| US20200178459A1 (en) | Scanning mode application of neutron gamma analysis for soil carbon mapping | |
| CN112529307B (en) | Atmospheric pollution prediction method and device, electronic equipment and storage medium | |
| US11553318B2 (en) | Routing method for mobile sensor platforms |
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 |