CN111896050B - Type limiting method of smoke measuring instrument - Google Patents
Type limiting method of smoke measuring instrument Download PDFInfo
- Publication number
- CN111896050B CN111896050B CN202010673675.8A CN202010673675A CN111896050B CN 111896050 B CN111896050 B CN 111896050B CN 202010673675 A CN202010673675 A CN 202010673675A CN 111896050 B CN111896050 B CN 111896050B
- Authority
- CN
- China
- Prior art keywords
- smoke
- flue gas
- monitoring module
- measuring instrument
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000000779 smoke Substances 0.000 title claims abstract description 167
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012544 monitoring process Methods 0.000 claims abstract description 117
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims abstract description 103
- 239000003546 flue gas Substances 0.000 claims abstract description 103
- 239000000428 dust Substances 0.000 claims abstract description 57
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 49
- 231100000719 pollutant Toxicity 0.000 claims abstract description 49
- 238000004891 communication Methods 0.000 claims abstract description 9
- 239000000523 sample Substances 0.000 claims description 51
- 239000011159 matrix material Substances 0.000 claims description 42
- 238000005259 measurement Methods 0.000 claims description 42
- 238000003062 neural network model Methods 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 28
- 230000007797 corrosion Effects 0.000 claims description 22
- 238000005260 corrosion Methods 0.000 claims description 22
- 238000005070 sampling Methods 0.000 claims description 19
- 239000004071 soot Substances 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000013145 classification model Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 239000007789 gas Substances 0.000 abstract description 9
- 238000012216 screening Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 abstract description 2
- 238000003860 storage Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000007664 blowing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000011010 flushing procedure Methods 0.000 description 2
- 238000010408 sweeping Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000003915 air pollution Methods 0.000 description 1
- 238000000738 capillary electrophoresis-mass spectrometry Methods 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000002912 waste gas Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Sampling And Sample Adjustment (AREA)
Abstract
The invention discloses a flue gas online monitoring control system and a control method thereof, wherein the flue gas online monitoring control system does not have the functions of information sharing and cloud storage, so that information cannot be disclosed in time, and data loss occurs, so that the whole system has serious control defects. The invention can carry out preliminary screening on sample smoke, divide the sample smoke into smoke dust, smoke gas and gaseous pollutants, then sequentially introduce the classified sample smoke into the smoke dust monitoring module, the smoke gas parameter monitoring module and the gaseous pollutant monitoring module, firstly sample the smoke gas, then monitor, avoid the influence of dust on the monitoring result, and secondly transmit digital and image signals to the mobile equipment and the shared cloud end through a remote communication interface or an AO/DO interface, on one hand, the information can be disclosed, and on the other hand, the information can be stored.
Description
Technical Field
The invention relates to the technical field of environment monitoring equipment, in particular to a kind limiting method of a smoke dust measuring instrument.
Background
A flue gas automatic monitoring system (CEMS) is a device for continuously monitoring the concentration and the total emission amount of gaseous pollutants and particulate matters emitted by an air pollution source and transmitting information to a competent department in real time, and is also called as a flue gas emission continuous monitoring system or a flue gas on-line monitoring system, the waste gas pollution monitored by the flue gas automatic monitoring system comprises SO2, NQX, HCL, CO2 and particulate matters, one of the most important parts in the flue gas automatic monitoring system is an analysis instrument for measuring flue gas components, and because the analysis instrument for measuring the flue gas components has certain requirements on the cleanliness of the flue gas, the flue gas emitted in industrial production must be filtered by a flue gas filter in a flue gas sampler to detect the flue gas components, SO the particulate matters in the flue gas are easily gathered in the flue gas filter and a nearby flue, if the time is long, even the flue and the flue gas filter are blocked, in order to recover the filtering function of the flue gas filter, compressed air is used as an air source within a certain time, a back flushing function is started, namely the compressed air with the opposite flue gas flowing direction is used for back flushing to the flue gas filter and the adjacent flue, particles, dust and the like in the flue gas filter and the front end flue are taken away, and the filtering function of the flue gas filter is recovered.
The current online monitoring and control system for the flue gas does not have the information sharing and cloud storage functions, so that information cannot be published in time, data loss occurs, and the whole system has serious control defects.
Aiming at the problems, the existing device is improved, and the flue gas online monitoring control system and the control method thereof are provided.
Disclosure of Invention
The invention aims to provide a flue gas on-line monitoring control system and a control method thereof, wherein a sampler is used for sampling flue gas at fixed points and quantitatively, the sample flue gas is primarily screened, the sample flue gas is divided into smoke dust, flue gas and gaseous pollutants, the classified sample flue gas is sequentially introduced into a smoke dust monitoring module, a flue gas parameter monitoring module and a gaseous pollutant monitoring module, the flue gas is sampled and then monitored, the influence of dust on a monitoring result is avoided, meanwhile, a blower is arranged on the outer surface of the sampler, the blower is connected with an external air pump, a dust sensor is arranged in the blower, the dust sensor is electrically connected with the blower, the blower can blow the sampler to prevent the dust from blocking the sampler, and then a data acquisition control processing output subsystem is used for converting transmitted electric signals into digital signals or image signals, secondly, the digital and image signals are transmitted to the mobile device and the sharing cloud end through the remote communication interface or the AO/DO interface, information can be registered in the cloud end, on one hand, the information can be disclosed, on the other hand, the information can be stored, and the problem in the background technology is solved.
In order to achieve the purpose, the invention provides the following technical scheme: the utility model provides a flue gas on-line monitoring control system, includes smoke and dust monitoring module, flue gas parameter monitoring module, gaseous pollutant monitoring module and data acquisition control processing output subsystem, smoke and dust monitoring module, flue gas parameter monitoring module and gaseous pollutant monitoring module all handle output subsystem interactive data, its characterized in that through wireless mode and data acquisition control processing: the smoke monitoring module is internally provided with a smoke measuring instrument, and the smoke measuring instrument processes the monitored smoke parameters into a chart or other signals and then reflects the chart or other signals by using the display module.
Furthermore, the smoke parameter monitoring module comprises a smoke flow velocity transmitter, a smoke temperature transmitter, a smoke pressure transmitter and a smoke humidity transmitter, and the smoke flow velocity transmitter, the smoke temperature transmitter, the smoke pressure transmitter and the smoke humidity transmitter all interact data with the smoke parameter monitoring module in a wireless mode.
Further, a flow velocity tester is arranged in the flue gas flow velocity transmitter, a temperature monitor is arranged in the flue gas temperature transmitter, a pressure monitor is arranged in the flue gas pressure transmitter, a moisture monitor is arranged in the flue gas humidity transmitter, and the flow velocity tester, the temperature monitor, the pressure monitor and the moisture monitor are all in signal connection with the flue gas parameter monitoring module.
Further, gaseous pollutant monitoring module includes flue gas gaseous pollutant sampling probe and flue gas pretreatment systems, and flue gas gaseous pollutant sampling probe is linked together with external flue gas, is provided with gaseous pollutant analysis appearance in the flue gas pretreatment systems, and gaseous pollutant analysis appearance and flue gas gaseous pollutant sampling probe intercommunication each other, and gaseous pollutant analysis appearance is reflected to utilize display module after handling into chart or other signals with the pollution parameter who monitors.
Furthermore, the data acquisition control processing output subsystem is in signal connection with the smoke dust monitoring module, the smoke parameter monitoring module and the gaseous pollutant monitoring module through a data acquisition device and a system control interface, the data acquisition device and the system control interface are in signal connection with the system control processing device through a remote communication interface or an AO/DO interface, and the system control processing device converts parameter signals into image signals.
The invention provides another technical scheme that: the control method of the flue gas on-line monitoring control system comprises the following steps:
s1: the method comprises the following steps of carrying out fixed-point quantitative sampling on smoke by using a sampler, carrying out primary screening on the sample smoke, dividing the sample smoke into smoke, smoke and gaseous pollutants, and then sequentially introducing the classified sample smoke into a smoke monitoring module, a smoke parameter monitoring module and a gaseous pollutant monitoring module;
s2: the classified sample smoke is subjected to data analysis through a smoke monitoring module, a smoke parameter monitoring module and a gaseous pollutant monitoring module, and data monitored by each module is transmitted to a data acquisition control processing output subsystem through electric signals;
s3: the transmitted electric signals are converted into digital signals or image signals through a data acquisition control processing output subsystem, and then the digital and image signals are transmitted to the mobile equipment and the shared cloud end through a remote communication interface or an AO/DO interface;
s4: the electric signals transmitted to the mobile equipment and the sharing cloud are converted into image signals through a system control processing device, firstly, the signals of the sharing cloud can be provided for all authorized people to watch, and secondly, the converted image signals are converted again through a signal output device;
s5: the converted image signal is stored by a printer or a copying machine, so that the later loss is prevented.
Further, be provided with on the surface of sampler and sweep the ware, sweep the ware and be connected with external air pump, sweep the inside dust inductor that is provided with of ware, dust inductor and sweep ware electric connection, when the dust inductor senses the sampler and has the dust on the surface, the blowing head begins the operation to encircle the sampler surface and sweep a week, otherwise the contrary.
Further, a smoke and dust measuring instrument is arranged in the smoke and dust monitoring module, and the specific steps for limiting the types of the smoke and dust measuring instruments are as follows:
step A1, constructing sample data according to the following formula:
wherein, X1Representing a sample data matrix formed by recording the corrosion resistance, the measurement precision and the measurement resolution of the LB-70C type smoke dust measuring instrument for n times, X2Representing a sample data matrix formed by recording the corrosion resistance, the measurement precision and the measurement resolution of the LB-70D type smoke dust measuring instrument for n times, X3Representing a sample data matrix formed by recording the corrosion resistance, the measurement precision and the measurement resolution of an LB-1080 type smoke measuring instrument for n times, wherein the matrix X is1,X2,X3In which there are n rows and 3 columns, matrix X1,X2,X3The first column in the drawing represents the corrosion resistance data of three different types of smoke measuring instruments in n records, and a matrix X1,X2,X3In x11Representing corrosion resistance data of three different types of soot gauges in a first recording, matrix X1,X2,X3The second column represents the measurement accuracy data of three different types of smoke measuring instruments in n records, and the matrix X1,X2,X3In x21Representing measurement accuracy data of three different types of smoke meters in a first recording, matrix X1,X2,X3The third column represents the measurement resolution data of three different types of smoke measuring instruments in n records, and the matrix X1,X2,X3In x31Representing the measurement resolution data of three different types of smoke measuring instruments in the first recording;
step A2, neural network model x according to the following formulaiW + b advances the sample data in step a1Prediction of line type:
wherein,
the type of the sample data in step a1 is predicted on behalf of the neural network classification model, and is in the form of matrix, when i is 1,
the type of the smoke measuring instrument of the LB-70C type is predicted, when i is 2,
the type of the smoke measuring instrument of LB-70D type is predicted, when i is 3,
the type of the smoke measuring instrument is predicted for LB-1080 type smoke measuring instruments, each record can predict a class value, n records and n predicted values form a matrix with 1 column and n rows, 3 matrixes are formed in total, and X isiRepresenting the corrosion resistance, the measurement precision and the measurement resolution of different types of smoke measuring instruments, and recording n times to form a sample data matrix, wherein i is 1,2 and 3, w represents the weight value of the initialization of the neural network model, the initialization value is 0, b represents the bias value of the initialization of the neural network model, the initialization value is 0, and e represents a natural constant;
step A3, optimizing the weight value and the bias value in the neural network model according to the following formulas:
wherein,
represents the weight value after the optimization, and the weight value,
represents the optimized offset value, XiRepresenting a sample data matrix formed by recording n times of corrosion resistance, measurement precision and measurement resolution of different types of smoke measuring instruments (101), wherein i is 1,2,3, and e represents a natural constant;
and A4, substituting the optimized weight value and the optimized bias value in the step A3 into the step A3 to predict a neural network model, wherein the neural network model is the optimized neural network model, the neural network model learns the characteristics of 3 types of smoke measuring instruments, and the neural network model limits the types of the smoke measuring instruments according to different selected characteristics.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention provides a flue gas on-line monitoring control system and a control method thereof, wherein a sampler is used for sampling flue gas at fixed points and quantitatively, the sample flue gas is primarily screened, the sample flue gas is divided into smoke dust, flue gas and gaseous pollutants, the classified sample flue gas is sequentially introduced into a smoke dust monitoring module, a flue gas parameter monitoring module and a gaseous pollutant monitoring module, the flue gas is sampled and then monitored, the influence of dust on a monitoring result is avoided, meanwhile, a blower is arranged on the outer surface of the sampler, the blower is connected with an external air pump, a dust sensor is arranged in the blower, the dust sensor is electrically connected with the blower, when the dust sensor senses that dust exists on the surface of the sampler, a blowing head starts to operate and blows around the surface of the sampler for a circle, when no dust exists on the surface of the sampler, the sweeping head idles for a week around the surface of the sampler, so that the phenomenon that the sampler is blocked by dust in smoke in the sampling process is avoided, and the sampling progress and quality are influenced.
2. According to the on-line smoke monitoring control system and the control method thereof, the transmitted electric signals are converted into digital signals or image signals through the data acquisition control processing output subsystem, then the digital and image signals are transmitted to the mobile equipment and the shared cloud end through the remote communication interface or the AO/DO interface, all disclosed information can be displayed through the cloud end, certain timeliness and universality are achieved, meanwhile, the cloud end can store the uploaded information, accidental data loss is prevented, meanwhile, the information can be conveniently and quickly retrieved when needed next time, and the integrity and the convenience of data are improved.
3. According to the on-line smoke monitoring and controlling system and the controlling method thereof, the electric signals transmitted to the mobile equipment and the shared cloud end are converted into image signals through the system control processing device, and then the converted image signals are printed out through the printer or the copying machine, so that the staff can conveniently read each other, and the monitored information has flexibility.
Drawings
FIG. 1 is a block diagram of the smoke on-line monitoring control system of the present invention;
FIG. 2 is a block diagram of the smoke monitoring module of the online smoke monitoring and controlling system;
FIG. 3 is a block diagram of a smoke parameter monitoring module of the online smoke monitoring and controlling system;
FIG. 4 is a block diagram of the gaseous pollutant monitoring module of the flue gas on-line monitoring control system of the present invention;
FIG. 5 is a block diagram of a data acquisition control processing output subsystem of the flue gas on-line monitoring control system of the present invention;
FIG. 6 is a diagram of the overall steps of the flue gas on-line monitoring control system of the present invention;
FIG. 7 is a structural diagram of the working principle of the blower of the online flue gas monitoring and controlling system of the present invention.
In the figure: 10. a smoke monitoring module; 101. a smoke dust measuring instrument; 20. a smoke parameter monitoring module; 201. a flue gas flow velocity transmitter; 2011. a flow rate tester; 202. a flue gas temperature transmitter; 2021. a temperature monitor; 203. a flue gas pressure transmitter; 2031. a pressure monitor; 204. a flue gas humidity transmitter; 2041. a moisture monitor; 30. a gaseous pollutant monitoring module; 40. and the data acquisition control processing output subsystem.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Referring to fig. 1-4, an online monitoring and controlling system for flue gas comprises a smoke monitoring module 10, a flue gas parameter monitoring module 20, a gaseous pollutant monitoring module 30 and a data acquisition control processing output subsystem 40, wherein the smoke monitoring module 10, the flue gas parameter monitoring module 20 and the gaseous pollutant monitoring module 30 interact data with the data acquisition control processing output subsystem 40 in a wireless manner, a smoke measuring instrument 101 is arranged in the smoke monitoring module 10, the smoke measuring instrument 101 processes monitored smoke parameters into a chart or other signals and reflects the signals by using a display module, the flue gas parameter monitoring module 20 comprises a flue gas flow rate transmitter 201, a flue gas temperature transmitter 202, a flue gas pressure transmitter 203 and a flue gas humidity transmitter 204, the flue gas flow rate transmitter 201, the flue gas temperature transmitter 202, the flue gas pressure transmitter 203 and the flue gas humidity transmitter 204 interact data with the flue gas parameter monitoring module 20 in a wireless manner, be provided with velocity of flow tester 2011 in flue gas velocity of flow transmitter 201, be provided with temperature monitor 2021 in the flue gas temperature transmitter 202, be provided with pressure monitor 2031 in the flue gas pressure transmitter 203, be provided with moisture monitor 2041 in the flue gas humidity transmitter 204, velocity of flow tester 2011, temperature monitor 2021, pressure monitor 2031 and moisture monitor 2041 all with flue gas parameter monitoring module 20 signal connection, gaseous state pollutant monitoring module 30 includes flue gas gaseous state pollutant sampling probe and flue gas pretreatment systems, flue gas gaseous state pollutant sampling probe is linked together with external flue gas, be provided with gaseous pollutant analyzer in the flue gas pretreatment systems, gaseous pollutant analyzer and flue gas gaseous state pollutant sampling probe communicate each other, gaseous pollutant analyzer utilizes the display module to embody after handling into diagram or other signals the pollution parameter of monitoring.
Example two
Referring to fig. 5 and 6, the data acquisition control processing output subsystem 40 is in signal connection with the smoke monitoring module 10, the flue gas parameter monitoring module 20 and the gaseous pollutant monitoring module 30 through a data acquisition device and a system control interface, the data acquisition device and the system control interface are in signal connection with a system control processing device through a remote communication interface or an AO/DO interface, and the system control processing device converts parameter signals into image signals.
EXAMPLE III
Referring to fig. 7, be provided with on the surface of sampler and sweep the ware, it is connected with external air pump to sweep the ware, sweep the inside dust inductor that is provided with of ware, dust inductor and sweep ware electric connection, when the dust inductor senses the sampler and has the dust on the surface, the sweep head begins the operation, and sweep a week around the sampler surface, when the sampler does not have the dust on the surface, the sweep head encircles sampler surface idle running a week, avoid in the sampling process, the dust in the flue gas has produced blocking phenomenon to the sampler, sample progress and quality have been influenced.
In order to better show the online flue gas monitoring and controlling system and the controlling method thereof, the embodiment provides a controlling method of the online flue gas monitoring and controlling system, which includes the following steps:
the method comprises the following steps: the method comprises the steps of utilizing a sampler to perform fixed-point quantitative sampling on smoke, performing primary screening on the sample smoke, dividing the sample smoke into smoke, smoke and gaseous pollutants, and then sequentially introducing the classified sample smoke into a smoke monitoring module 10, a smoke parameter monitoring module 20 and a gaseous pollutant monitoring module 30;
step two: the classified sample smoke is subjected to data analysis through the smoke monitoring module 10, the smoke parameter monitoring module 20 and the gaseous pollutant monitoring module 30, and data monitored by each module is transmitted to the data acquisition control processing output subsystem 40 through electric signals;
step three: the transmitted electric signals are converted into digital signals or image signals through the data acquisition control processing output subsystem 40, and then the digital and image signals are transmitted to the mobile equipment and the shared cloud end through a remote communication interface or an AO/DO interface;
step four: the electric signals transmitted to the mobile equipment and the sharing cloud are converted into image signals through a system control processing device, firstly, the signals of the sharing cloud can be provided for all authorized people to watch, and secondly, the converted image signals are converted again through a signal output device;
step five: the converted image signal is stored by a printer or a copying machine, so that the later loss is prevented.
In summary, the following steps: the smoke on-line monitoring control system comprises a smoke monitoring module 10, a smoke parameter monitoring module 20 and a gaseous pollutant monitoring module 30, wherein the smoke monitoring module 10, the smoke parameter monitoring module 20 and the gaseous pollutant monitoring module 30 interact data with a data acquisition control processing output subsystem 40 in a wireless mode, the transmitted electric signals are converted into digital signals or image signals through the data acquisition control processing output subsystem 40, the digital signals and the image signals are transmitted to mobile equipment and a shared cloud end through a remote communication interface or an AO/DO interface, all disclosed information can be displayed through the cloud end, certain timeliness and universality are achieved, meanwhile, the uploaded information can be stored by the cloud end, accidental loss of the data is prevented, meanwhile, when the next time is needed, the data can be conveniently and quickly searched out, the integrity and the convenience of the data are improved, and a smoke measuring instrument 101 is arranged in the smoke monitoring module 10, the smoke and dust measuring instrument 101 processes the monitored smoke and dust parameters into a chart or other signals, then displays the chart or other signals by using a display module, performs fixed-point quantitative sampling on smoke and gas by using a sampler, performs primary screening on the sample smoke and gas, divides the sample smoke into smoke and dust, smoke and gas and gaseous pollutants, then sequentially introduces the classified sample smoke into the smoke and dust monitoring module 10, the smoke and gas parameter monitoring module 20 and the gaseous pollutant monitoring module 30, samples the smoke and gas firstly, monitors the smoke and gas, avoids the influence of dust on the monitoring result, meanwhile, a blower is arranged on the outer surface of the sampler, the blower is connected with an external air pump, a dust sensor is arranged in the blower, the dust sensor is electrically connected with the blower, when the dust sensor senses that dust exists on the surface of the sampler, the blowing head starts to operate and blows around the surface of the sampler for a circle, when the sampler does not have the dust on the surface, the sweeping head idles for a week around the surface of the sampler, so that the phenomenon that the dust in the flue gas blocks the sampler during sampling is avoided, and the sampling progress and quality are influenced.
A smoke measuring instrument 101 is arranged in the smoke monitoring module 10, and the specific steps for limiting the types of the smoke measuring instruments 101 are as follows:
step A1, constructing sample data according to the following formula:
wherein, X1Representing a sample data matrix formed by n times of recording the corrosion resistance, the measurement precision and the measurement resolution of the LB-70C type smoke measuring instrument 101, X2Representing a sample data matrix formed by n times of recording the corrosion resistance, the measurement precision and the measurement resolution of the LB-70D type smoke measuring instrument 101, X3Representing a sample data matrix formed by recording the corrosion resistance, the measurement precision and the measurement resolution of the LB-1080 type smoke measuring instrument 101 for n times, wherein the matrix X is1,X2,X3In which there are n rows and 3 columns, matrix X1,X2,X3The first column in the drawing represents the corrosion resistance data of three different types of soot gauges 101 recorded n times, matrix X1,X2,X3In x11Representing the corrosion resistance data of three different types of soot gauges 101 in the first recording, matrix X1,X2,X3The second column represents the measurement accuracy data of three different types of smoke measuring instruments in n records, and the matrix X1,X2,X3In x21Representing measurement accuracy data of three different types of smoke meters 101 in a first recording, matrix X1,X2,X3The third column represents the measurement resolution data of three different types of smoke meters 101 in n records, matrix X1,X2,X3In x31Representing the measurement resolution data of three different types of smoke measuring instruments 101 in the first recording;
step A2, fitting the neural network model x according to the following formulaiW + b makes a prediction of the type of sample data in step a 1:
wherein,
the type of prediction performed on the sample data in step a1 on behalf of the neural network model is in the form of a matrix, and when i is 1,
a type prediction is made for a soot gauge 101 of the LB-70C type, when i is 2,
a type prediction is made for a soot gauge 101 of the LB-70D type, when i is 3,
the type of the LB-1080 type smoke measuring instrument 101 is predicted, each record can predict a class value, n records and n predicted values form a matrix with 1 column and n rows, 3 matrixes are formed, and XiRepresenting the sample data matrix formed by recording the dust measuring instrument 101 with different types for n times, i is 1,2 and 3, w represents the weight value of the neural network model initialization, the initialization value is 0, and b is generationThe bias value of the initialization of the table neural network model is 0, and e represents a natural constant;
step A3, optimizing the weight value and the bias value in the neural network model according to the following formulas:
wherein,
represents the weight value of the optimization, and represents the weight value of the optimization,
represents the optimum offset value, XiRepresenting a sample data matrix formed by recording the corrosion resistance, the measurement precision and the measurement resolution of different types of smoke measuring instruments 101 for n times, wherein i is 1,2,3, and e represents a natural constant;
and step A4, substituting the optimized weight value and the optimized bias value in the step A3 into the step A3 to predict a neural network model, wherein the neural network model is the optimized neural network model, the neural network model learns the characteristics of the 3 types of smoke measuring instruments 101, and the neural network model limits the types of the smoke measuring instruments 101 according to different selected characteristics.
In this embodiment, 3 different types of soot measuring instruments 101 are selected in total, the types are LB-70C type, LB-70D type and LB-1080 type, and it is more suitable to measure 3 types of soot measuring instruments 101 according to 3 different characteristics in practical application, the 3 different characteristics are corrosion resistance, measurement accuracy and measurement resolution, 3 characteristics in practical application are selected manually to reach a certain value, and then a characteristic value which is more suitable for being set manually is automatically selected according to the model, for example, the corrosion resistance is selected manually to be 100 degrees, the measurement resolution is selected to be 0.5, and the measurement accuracy is up to 97.5%, so that the soot measuring instrument 101 which is most suitable for being selected manually in the 3 characteristics can be selected through the model.
The beneficial effects of the above technical scheme are: the algorithm selects a deep learning technology, the neural network classification model fitting is carried out on data, the neural network model parameters are optimized, the neural network model is the optimized model at the moment, the characteristic data of different types of smoke and dust measuring instruments 101 are artificially collected, the neural network classification model learns the characteristic data of the different types of smoke and dust measuring instruments 101 to carry out parameter training, the neural network model recognizes the different types of smoke and dust measuring instruments 101, the type limitation is carried out through the neural network model according to the selected characteristic data during working, the speed is greatly improved, the neural network model parameters are finally optimized through a large number of iteration training models, the neural network model parameters are predicted by using the optimal neural network model parameters, the accuracy of the neural network model prediction is improved, and the working efficiency is improved.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (5)
1. A kind limiting method of a smoke measuring instrument, which is applied to a smoke on-line monitoring control system, the smoke on-line monitoring control system comprises a smoke monitoring module (10), a smoke parameter monitoring module (20), a gaseous pollutant monitoring module (30) and a data acquisition control processing output subsystem (40), wherein the smoke monitoring module (10), the smoke parameter monitoring module (20) and the gaseous pollutant monitoring module (30) interact data with the data acquisition control processing output subsystem (40) in a wireless mode, a smoke measuring instrument (101) is arranged in the smoke monitoring module (10), the smoke measuring instrument (101) processes monitored smoke parameters into graphs or other signals and then reflects the graphs or other signals by using a display module, be provided with smoke and dust measuring apparatu (101) in smoke and dust monitoring module (10), its characterized in that includes the following step:
step A1, constructing sample data according to the following formula:
wherein, X1Representing a sample data matrix formed by n times of recording the corrosion resistance, the measurement precision and the measurement resolution of an LB-70C type smoke measuring instrument (101), X2Representing a sample data matrix formed by n times of recording the corrosion resistance, the measurement precision and the measurement resolution of an LB-70D type smoke measuring instrument (101), X3Representing a sample data matrix formed by n times of recording the corrosion resistance, the measurement precision and the measurement resolution of an LB-1080 type smoke measuring instrument (101), and a matrix X1,X2,X3In which there are n rows and 3 columns, matrix X1,X2,X3The first column in the drawing represents corrosion resistance data of three different types of smoke measuring instruments (101) in n records, and a matrix X1,X2,X3In x11Representing corrosion resistance data of three different types of soot gauges (101) in a first recording, matrix X1,X2,X3The second column represents the measurement accuracy data of three different types of smoke measuring instruments (101) in n records, and the matrix X1,X2,X3In x21Representing measurement accuracy data of three different types of smoke meters (101) in a first recording, matrix X1,X2,X3The third column represents the measurement resolution data of three different types of smoke meters (101) in n records, and the matrix X1,X2,X3In x31Data representing the measurement resolution of three different types of smoke measuring instruments (101) in the first recording;
step A2, neural network model x according to the following formulaiW + b makes a prediction of the type of sample data in step a 1:
wherein,
the type of the sample data in step a1 is predicted on behalf of the neural network classification model, and is in the form of matrix, when i is 1,
the type of the LB-70C type smoke measuring instrument (101) is predicted, when i is 2,
the type of the soot measuring instrument (101) of the LB-70D type is predicted, when i is 3,
the type of the LB-1080 type smoke measuring instrument (101) is predicted, each record can predict a class value, n records and n predicted values form a matrix with 1 column and n rows, 3 matrixes are formed, and XiRepresenting a sample data matrix formed by recording different types of smoke measuring instruments (101) for n times according to corrosion resistance, measuring precision and measuring resolution, wherein i is 1,2 and 3, w represents a weight value of initialization of a neural network model, an initialization value is 0, b represents a bias value of the initialization of the neural network model, the initialization value is 0, and e represents a natural constant;
step A3, optimizing the weight value and the bias value in the neural network model according to the following formulas:
wherein,
represents the weight value after the optimization, and the weight value,
represents the optimized offset value, XiRepresenting a sample data matrix formed by recording n times of corrosion resistance, measurement precision and measurement resolution of different types of smoke measuring instruments (101), wherein i is 1,2,3, and e represents a natural constant;
and A4, substituting the optimized weight value and the optimized bias value in the step A3 into the step A3 to predict a neural network model, wherein the neural network model is the optimized neural network model, the neural network model learns the characteristics of 3 types of smoke measuring instruments (101), and the neural network model limits the types of the smoke measuring instruments (101) according to different selected characteristics.
2. The kind limiting method of a soot measuring instrument as defined in claim 1, wherein: the smoke parameter monitoring module (20) comprises a smoke flow velocity transmitter (201), a smoke temperature transmitter (202), a smoke pressure transmitter (203) and a smoke humidity transmitter (204), and the smoke flow velocity transmitter (201), the smoke temperature transmitter (202), the smoke pressure transmitter (203) and the smoke humidity transmitter (204) interact with the smoke parameter monitoring module (20) in a wireless mode.
3. The kind limiting method of a soot measuring instrument as defined in claim 2, wherein: a flow velocity tester (2011) is arranged in the flue gas flow velocity transmitter (201), a temperature monitor (2021) is arranged in the flue gas temperature transmitter (202), a pressure monitor (2031) is arranged in the flue gas pressure transmitter (203), a moisture monitor (2041) is arranged in the flue gas humidity transmitter (204), and the flow velocity tester (2011), the temperature monitor (2021), the pressure monitor (2031) and the moisture monitor (2041) are all in signal connection with the flue gas parameter monitoring module (20).
4. The kind limiting method of a soot measuring instrument as defined in claim 1, wherein: the gaseous pollutant monitoring module (30) comprises a flue gas gaseous pollutant sampling probe and a flue gas pretreatment system, the flue gas gaseous pollutant sampling probe is communicated with external flue gas, a gaseous pollutant analyzer is arranged in the flue gas pretreatment system, the gaseous pollutant analyzer is communicated with the flue gas gaseous pollutant sampling probe, and the gaseous pollutant analyzer processes monitored pollution parameters into a graph or other signals and then reflects the graph or other signals by using the display module.
5. The kind limiting method of a soot measuring instrument as defined in claim 1, wherein: the data acquisition control processing output subsystem (40) is in signal connection with the smoke dust monitoring module (10), the smoke parameter monitoring module (20) and the gaseous pollutant monitoring module (30) through a data acquisition device and a system control interface, the data acquisition device and the system control interface are in signal connection with the system control processing device through a remote communication interface or an AO/DO interface, and the system control processing device converts parameter signals into image signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010673675.8A CN111896050B (en) | 2020-07-14 | 2020-07-14 | Type limiting method of smoke measuring instrument |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010673675.8A CN111896050B (en) | 2020-07-14 | 2020-07-14 | Type limiting method of smoke measuring instrument |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111896050A CN111896050A (en) | 2020-11-06 |
| CN111896050B true CN111896050B (en) | 2021-04-06 |
Family
ID=73192608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010673675.8A Active CN111896050B (en) | 2020-07-14 | 2020-07-14 | Type limiting method of smoke measuring instrument |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111896050B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114543543A (en) * | 2022-03-01 | 2022-05-27 | 景德镇市市场监督管理综合检验检测中心 | Online measuring method and system for components of kiln smoke |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1936995A (en) * | 2006-10-10 | 2007-03-28 | 江南大学 | Control for industrial smoke on-line monitoring system and data transmission system and method |
| CN103645127A (en) * | 2013-12-12 | 2014-03-19 | 天津勃名能源科技发展有限公司 | Back flushing type real-time online monitoring system for smoke pollutants |
| CN105675801A (en) * | 2014-11-18 | 2016-06-15 | 姚秋丽 | Continuous flue gas emission monitoring system |
| CN106840264A (en) * | 2017-02-21 | 2017-06-13 | 上海宝英光电科技有限公司 | A kind of continuous on-line monitoring system of flue gas |
| CN109145516A (en) * | 2018-10-08 | 2019-01-04 | 电子科技大学 | A kind of analog circuit fault recognition methods based on modified extreme learning machine |
| KR102016262B1 (en) * | 2018-05-30 | 2019-08-29 | 세종대학교산학협력단 | Image processing method and system for smoky environment |
| CN110361176A (en) * | 2019-06-05 | 2019-10-22 | 华南理工大学 | A kind of intelligent failure diagnosis method for sharing neural network based on multitask feature |
-
2020
- 2020-07-14 CN CN202010673675.8A patent/CN111896050B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1936995A (en) * | 2006-10-10 | 2007-03-28 | 江南大学 | Control for industrial smoke on-line monitoring system and data transmission system and method |
| CN103645127A (en) * | 2013-12-12 | 2014-03-19 | 天津勃名能源科技发展有限公司 | Back flushing type real-time online monitoring system for smoke pollutants |
| CN105675801A (en) * | 2014-11-18 | 2016-06-15 | 姚秋丽 | Continuous flue gas emission monitoring system |
| CN106840264A (en) * | 2017-02-21 | 2017-06-13 | 上海宝英光电科技有限公司 | A kind of continuous on-line monitoring system of flue gas |
| KR102016262B1 (en) * | 2018-05-30 | 2019-08-29 | 세종대학교산학협력단 | Image processing method and system for smoky environment |
| CN109145516A (en) * | 2018-10-08 | 2019-01-04 | 电子科技大学 | A kind of analog circuit fault recognition methods based on modified extreme learning machine |
| CN110361176A (en) * | 2019-06-05 | 2019-10-22 | 华南理工大学 | A kind of intelligent failure diagnosis method for sharing neural network based on multitask feature |
Non-Patent Citations (1)
| Title |
|---|
| 基于深度卷积网络的糖尿病并发症分类;白旭飞;《电子技术与软件工程》;20190331;第155-158页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111896050A (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN201233390Y (en) | Flue gas on-line continuous monitoring apparatus | |
| CN104360667B (en) | A kind of polluter on-line monitoring platform and the anti-counterfeiting method of pollution source monitoring data | |
| CN1936995A (en) | Control for industrial smoke on-line monitoring system and data transmission system and method | |
| CN206756778U (en) | A kind of gas monitors long-range quality control system on-line | |
| CN101299031B (en) | Method for detecting automobile tail gas based on gas sensor array | |
| CN108956876A (en) | A kind of measurement time delay correcting method of flue gas on-line continuous monitoring system | |
| CN107607450A (en) | A kind of air quality surveillance method and relevant device | |
| CN107132318A (en) | A kind of stationary source VOC on-line monitoring systems | |
| CN204008588U (en) | The continuous on-line monitoring system of a kind of flue gas | |
| CN115876655B (en) | System and method for monitoring whole process of explosion-related dust in limited space | |
| CN104297020A (en) | Flue gas pollution collection device and method | |
| CN113280909A (en) | Coal preparation plant vibrating screen intelligent detection system and method based on vibration signal analysis | |
| CN111896050B (en) | Type limiting method of smoke measuring instrument | |
| CN202994770U (en) | System for monitoring smoke continuously | |
| CN108614071A (en) | Distributed outside atmosphere quality-monitoring accuracy correction system and parameter updating method | |
| CN108803466B (en) | A kind of Industrial Boiler efficiency on-line detecting system and method | |
| CN110610295B (en) | Universal integrated acquisition system and method for resource environment load data | |
| CN203909009U (en) | Continuous online monitoring system for flue gas | |
| CN113917093B (en) | Air quality monitoring system based on wireless network | |
| CN202330277U (en) | Portable ultraviolet spectrum flue gas analyzer | |
| CN2692660Y (en) | Laser dust meter | |
| CN207407924U (en) | Industrial park ambient air quality supervisory systems | |
| CN109682731A (en) | A kind of thermal power plant dust concentration on-line monitoring system and method | |
| CN118446530A (en) | Municipal construction engineering construction management system | |
| CN117054616B (en) | Remote middle station atmosphere pollution tracing system based on artificial intelligence |
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 |