CN109858144A - A kind of the discharge capacity account model building method and fugitive dust discharge capacity account method in fugitive dust source - Google Patents
A kind of the discharge capacity account model building method and fugitive dust discharge capacity account method in fugitive dust source Download PDFInfo
- Publication number
- CN109858144A CN109858144A CN201910088129.5A CN201910088129A CN109858144A CN 109858144 A CN109858144 A CN 109858144A CN 201910088129 A CN201910088129 A CN 201910088129A CN 109858144 A CN109858144 A CN 109858144A
- Authority
- CN
- China
- Prior art keywords
- fugitive dust
- discharge capacity
- data
- dust source
- source
- 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
Abstract
The invention discloses a kind of discharge capacity account model building method in fugitive dust source and fugitive dust discharge capacity account method, the discharge capacity account model building method in the fugitive dust source includes: several fugitive dust displacement datas according to predetermined period acquisition fugitive dust source；Acquire the data of several influence factors corresponding with fugitive dust displacement data；The discharge capacity account model in fugitive dust source is generated according to the training of the data of fugitive dust displacement data and its corresponding each influence factor.By according to fugitive dust displacement data, and the data training of several corresponding influence factors of fugitive dust displacement data generates the discharge capacity account model in fugitive dust source, making the parameters in the model of building is obtained on the basis of the training of a large amount of history data sets, accuracy is higher, when discharge capacity account model to make the method based on the embodiment of the present invention obtain carries out the fugitive dust discharge capacity account in fugitive dust source, the accuracy of obtained calculated result is also higher.
Description
Technical field
The present invention relates to environmental contaminants field of measuring technique more particularly to a kind of discharge capacity account model structures in fugitive dust source
Construction method and fugitive dust discharge capacity account method.
Background technique
Fugitive dust is first in one of major source for causing city Particulate Pollution and the air pollution of China most cities
The pollutant wanted.Domestic and international research and experiment shows that fugitive dust is the important sources of PM10 in urban atmosphere, and early stage, fugitive dust was to atmosphere
The contribution rate of middle PM10 is more than 50%, and by the improvement of many years, in the recent period, many urban air-qualities have great improvement, but
The contribution rate of fugitive dust PM10 is still 20% or more, in addition, it also has very important influence to the contribution rate of PM2.5, therefore,
The fugitive dust discharge amount in the main fugitive dust source effectively in the especially city of control city, the lasting improvement to ambient air quality is promoted
It has a very important significance.
Currently, the calculation method of domestic common fugitive dust discharge amount is emission factor method (USEPA), it is based on emission factor method
The calculation formula for calculating the fugitive dust total emission volumn in fugitive dust source is as follows: Wci=Eci×Ac× T, Eci=2.69 × 10-4× (1- η),
In, WciFor PMi total release in construction fugitive dust source, ton/year, EciFor the average emission coefficient of entire construction site PMi, 2.69
×10-4t/(m2Month), AC is construction area area, m2, T is that the construction in building site enlivens moon number, generally presses construction days/30
It calculates, η is removal efficiency of the pollution control technology to fugitive dust, %.The formula can be used for whole building construction area total emission volumn
Estimation, TSP, PM10 and PM2.5 discharge amount can also be calculated separately.But the average emission coefficient of the PMi in above-mentioned formula
WciIt is determined to be searched from fugitive dust discharge capacity inventory prepared in advance, and generally only includes domestic several masters in fugitive dust discharge capacity inventory
The specific particle emission factor in city (Beijing, Hong Kong etc.) and part foreign countries is wanted, it is to be calculated when not included in emission inventories
Fugitive dust source where city when, it is necessary to select emission factor of the emission factors of external or domestic other provinces and cities as this area
It participates in calculating, the error of obtained calculated result is larger.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of discharge capacity account model building method in fugitive dust source and fugitive dust discharge capacities
Calculation method, when solving to calculate the fugitive dust discharge capacity in fugitive dust source using existing calculation method, the error of obtained calculated result
Larger problem.
According in a first aspect, the embodiment of the invention provides a kind of discharge capacity account model building methods in fugitive dust source, including
Following steps: according to several fugitive dust displacement datas in predetermined period acquisition fugitive dust source；It acquires corresponding with fugitive dust displacement data
The data of several influence factors；Fugitive dust source is generated according to the training of the data of fugitive dust displacement data and its corresponding each influence factor
Discharge capacity account model.
By being given birth to according to the training of the data of fugitive dust displacement data and several corresponding influence factors of fugitive dust displacement data
At the discharge capacity account model in fugitive dust source, making the parameters in the model of building is on the basis of a large amount of history data sets training
On obtain, accuracy is higher, so that the discharge capacity account model for obtaining the method based on the embodiment of the present invention carries out fugitive dust source
Fugitive dust discharge capacity account when, the accuracy of obtained calculated result is also higher.
With reference to first aspect, in first aspect first embodiment, influence factor includes that the particulate matter in fugitive dust source is flat
Equal mass concentration.
It being set as including the particulate matter average quality concentration in fugitive dust source by will affect factor, establishing particulate matter and being averaged matter
The quantitative relationship between concentration and fugitive dust discharge capacity is measured, so that acquiring the particulate matter in fugitive dust source in real time by fugitive dust monitoring device
When average quality concentration, the fugitive dust discharge capacity in fugitive dust source is calculated in the discharge capacity account model for being able to use training generation in real time, is
The dust controlling measure effect for evaluating fugitive dust source provides quantized data basis.
With reference to first aspect, in first aspect second embodiment, influence factor includes wind speed, air in fugitive dust source
Humidity and activity intensity；Activity intensity refers to the present granule object average quality concentration in fugitive dust source relative to several history
The non-negative change rate of minimum value in grain object average quality concentration.
It is set as by will affect factor including wind speed, air humidity and activity intensity, and will be current in fugitive dust source
Particulate matter average quality concentration is made relative to the non-negative change rate of the minimum value in several history particulate matter average quality concentration
For activity intensity, the activity intensity is made to can reflect construction site construction intensity, goods yard operation intensity, road traffic wagon flow
Measure intensity and the stream of people in other places, the movable intensity of wagon flow, and these intensity have to the fugitive dust discharge capacity in fugitive dust source it is larger
It influences, accordingly, it is considered to which the discharge capacity model of the key factor of this influence fugitive dust discharge amount of activity intensity, can make to be based on the mould
The fugitive dust discharge amount that type is calculated is more acurrate.
First embodiment or first aspect second embodiment with reference to first aspect, in first aspect third embodiment
In, particulate matter average quality concentration is the particle concentration of the center position of the particulate matter diffusion height in fugitive dust source.
First embodiment or first aspect second embodiment with reference to first aspect, in the 4th embodiment of first aspect
In, the step of the discharge capacity account model in fugitive dust source is generated according to the training of the data of fugitive dust displacement data and its corresponding each influence factor
Suddenly, comprising: the fugitive dust rate of discharge data in fugitive dust source are calculated based on fugitive dust displacement data；Fugitive dust rate of discharge data refer to
The quality of the particulate matter of the unit area discharge in fugitive dust source in predetermined period；According to fugitive dust rate of discharge data and its corresponding
The data training of each influence factor generates the fugitive dust rate of discharge computation model in fugitive dust source；By fugitive dust rate of discharge computation model with
The area in fugitive dust source is multiplied, and generates the discharge capacity account model in fugitive dust source.
Second embodiment with reference to first aspect is raised in the 5th embodiment of first aspect according to predetermined period acquisition
The step of several fugitive dust displacement datas in dirt source, comprising: according to the particulate matter average quality in predetermined period acquisition fugitive dust source
Concentration data；Construct the virtual sample space for acquiring the fugitive dust displacement data in fugitive dust source；According to the body of virtual sample space
Fugitive dust displacement data is calculated in long-pending and particulate matter average quality concentration data.
The virtual sample space that the fugitive dust spread condition in fugitive dust source can be characterized by constructing keeps fugitive dust discharge amount simple
Single volume (being calculated by the parameter of the virtual sampling body itself of building) and fugitive dust source by virtual sample space
Interior particulate matter average quality concentration data (being collected by fugitive dust monitoring device) is calculated, and reduces fugitive dust discharge capacity number
According to acquisition difficulty.
5th embodiment with reference to first aspect constructs in first aspect sixth embodiment for acquiring fugitive dust source
Fugitive dust displacement data virtual sample space the step of, comprising: obtain fugitive dust source center wind speed；Wind speed is acquisition
Wind speed when particulate matter average quality concentration；It is empty that virtual sampling is constructed according to the particulate matter diffusion height in wind speed and fugitive dust source
Between.
Sixth embodiment with reference to first aspect, in the 7th embodiment of first aspect, virtual sample space is one long
Cube, a length of wind speed of cuboid and the product of predetermined period, width are a default sampling width, a height of particulate matter diffusion height.
According to second aspect, the embodiment of the invention provides a kind of fugitive dust discharge capacity account method in fugitive dust source, including it is as follows
Step: the current data of several influence factors of the fugitive dust discharge capacity in acquisition fugitive dust source；Current data is inputted according to first party
The row of the discharge capacity account model building method building in fugitive dust source described in any one of face or first aspect embodiment
It measures in computation model, obtains the calculated result of the fugitive dust discharge capacity in fugitive dust source；The collection period of current data is identical as predetermined period.
The discharge capacity constructed as the method according to any one of first aspect or first aspect embodiment
Computation model is established for the training based on a large amount of history data sets, and accuracy is higher, therefore, current data is inputted the row
The accuracy of the calculated result of the fugitive dust discharge capacity in the fugitive dust source that amount computation model obtains is also higher, can be preferably close to fugitive dust source
Practical fugitive dust discharge amount.
According to the third aspect, the embodiment of the invention provides a kind of discharge capacity account model construction devices in fugitive dust source, comprising:
First data acquisition module, for several fugitive dust displacement datas according to predetermined period acquisition fugitive dust source；The acquisition of second data
Module, for acquiring the data of several influence factors corresponding with fugitive dust displacement data；Model training module is raised for basis
The training of the data of dirt displacement data and its corresponding each influence factor generates the discharge capacity account model in fugitive dust source.
According to fourth aspect, the embodiment of the invention provides a kind of fugitive dust discharge capacity account device in fugitive dust source, feature exists
In, comprising: third data acquisition module, the current data of several influence factors of the fugitive dust discharge capacity for acquiring fugitive dust source；
Discharge capacity account module, for inputting current data according to institute in any one of first aspect or first aspect embodiment
In the discharge capacity account model of the discharge capacity account model building method building in the fugitive dust source stated, the meter of the fugitive dust discharge capacity in fugitive dust source is obtained
Calculate result；The collection period of current data is identical as predetermined period.
According to the 5th aspect, the embodiment of the invention provides a kind of electronic equipment, comprising: memory and processor, storage
Connection is communicated with each other between device and the processor, computer instruction is stored in memory, processor is by executing computer
Instruction, method described in any one embodiment or second aspect thereby executing first aspect, first aspect.
According to the 6th aspect, the embodiment of the invention provides a kind of computer readable storage medium, computer-readable storage
Medium storing computer instruction, any one implementation that computer instruction is used to that computer to be made to execute first aspect, first aspect
Method described in mode or second aspect.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow chart of the discharge capacity account model building method in fugitive dust source provided in an embodiment of the present invention；
Fig. 2 be another embodiment of the present invention provides fugitive dust source discharge capacity account model building method flow chart；
Fig. 3 is the flow chart of the fugitive dust discharge capacity account method in fugitive dust source provided in an embodiment of the present invention；
Fig. 4 is the functional block diagram of the discharge capacity account model construction device in fugitive dust source provided in an embodiment of the present invention；
Fig. 5 is the functional block diagram of the fugitive dust discharge capacity account device in fugitive dust source provided in an embodiment of the present invention；
Fig. 6 is the hardware structural diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that term " first ", " second ", " third " are used for description purposes only,
It is not understood to indicate or imply relative importance.
Embodiment 1
Fig. 1 shows the flow chart of the discharge capacity account model building method in the fugitive dust source of the embodiment of the present invention, such as Fig. 1 institute
Show, this method may include steps of:
S101, according to several fugitive dust displacement datas in predetermined period acquisition fugitive dust source.Herein, predetermined period can root
Specifically it is arranged according to the acquisition situation of fugitive dust displacement data, for example, when using according to the particulate matter in predetermined period acquisition fugitive dust source
Average quality concentration data；Construct the virtual sample space for acquiring the fugitive dust displacement data in fugitive dust source；According to virtual sampling
When the method for fugitive dust displacement data is calculated in the volume and particulate matter average quality concentration data in space, predetermined period can be with
It is arranged according to the collection period of the equipment (such as fugitive dust monitoring device) to acquire particulate matter average quality concentration data, specifically
Ground can be set to 1min, in other optional embodiments, can also set predetermined period in 1min-15min
Period needed for any, such as selection 2min, 3min, 5min or 15min.For example, the method for depositing dust (DF) measurement acquires fugitive dust
When displacement data, in order to keep the amount of dust cylinder Deposited particulate matter enough, increase the accuracy of the data of acquisition, predetermined period
The generally relatively long period can specifically set predetermined period to 1 month or the longer period.
S102 acquires the data of several influence factors corresponding with fugitive dust displacement data.Herein, influence factor can be with
Being includes particulate matter average quality concentration data in fugitive dust source, can also be include wind speed in fugitive dust source, air humidity and
Activity intensity.It is, of course, also possible to be carried out according to the material elements for the fugitive dust discharge capacity that can influence fugitive dust source in practical application scene
Adjustment.
S103 generates the discharge capacity meter in fugitive dust source according to the training of the data of fugitive dust displacement data and its corresponding each influence factor
Calculate model.Herein, the type of discharge capacity account model and design parameter are several influence factors according to above-mentioned acquisition
Data be specifically arranged, use the example above, being when influence factor includes particulate matter average quality concentration data in fugitive dust source
When, the neural network models such as CNN, RNN, CRNN can be constructed, and using the data of each influence factor as neural network model
Input, corresponding fugitive dust discharge capacity are trained it as the output of neural network model；Being when influence factor includes fugitive dust source
When interior wind speed, air humidity and activity intensity, nonlinear mathematical model can be constructed, and according to fugitive dust displacement data and its right
The data for each influence factor answered solve the coefficient that each influence factor corresponds to parameter.It should be noted that fugitive dust source herein
Discharge capacity account model is the fugitive dust discharge capacity account model in fugitive dust source in predetermined period described in S101, for example, working as predetermined period
When for 1min, fugitive dust discharge capacity account model herein is the computation model of fugitive dust discharge capacity of the fugitive dust source in 1min.
In embodiments of the present invention, by according to fugitive dust displacement data and several corresponding shadows of fugitive dust displacement data
The data training of the factor of sound generates the discharge capacity account model in fugitive dust source, and making the parameters in the model of building is largely to go through
It is obtained on the basis of the training of history data set, accuracy is higher, thus the discharge capacity for obtaining the method based on the embodiment of the present invention
When computation model carries out the fugitive dust discharge capacity account in fugitive dust source, the accuracy of obtained calculated result is also higher.
It include wind speed in fugitive dust source, air humidity with influence factor as a kind of optional embodiment of the present embodiment
With for activity intensity come describe the embodiment of the present invention fugitive dust source discharge capacity account model building method.As shown in Fig. 2, the party
Method may include steps of:
S201, according to the particulate matter average quality concentration data in predetermined period acquisition fugitive dust source.Herein, predetermined period
It can be set to 1min, in other optional embodiments, the institute that predetermined period can also be set in 1min-15min
Need period, such as selection 2min, 3min, 5min or 15min.Herein, the particulate matter average quality concentration numbers in fugitive dust source
According to can be by the way that multiple fugitive dust monitoring devices are arranged at the different location in fugitive dust source and at different height, and calculate multiple
The average value of the monitoring result of fugitive dust monitoring device obtains, and can also be the center in fugitive dust source, vertical position by horizontal position
Be set in fugitive dust source particulate matter diffusion height center fugitive dust monitoring device monitoring result directly as particle
Object average quality concentration data obtains.
S202 constructs the virtual sample space for acquiring the fugitive dust displacement data in fugitive dust source.Herein, virtual sampling is empty
Between shape and size can need to be arranged according to practical application scene, with its can characterize fugitive dust source fugitive dust spread feelings
Subject to condition.For example, cuboid can be set by virtual sample space, it is of course also possible to be set as common prism, cylindrical body
Deng.By taking virtual sample space is cuboid as an example, the length and width and height of cuboid can be adjusted according to practical application scene
Whole, e.g., length can be configured according to the fugitive dust diffusion length (horizontal distance) in fugitive dust source in application scenarios, it is wide can be according to raising
The size in dirt source is configured, and high can be spread according to the fugitive dust in fugitive dust source highly (vertical range) is configured.Other
It is that cuboid is understood that the setting of the size of the virtual sample space of shape, which is referred to virtual sample space, no longer superfluous herein
It states.
It, can be by the central point in fugitive dust source when virtual sample space is cuboid in other optional embodiments
Length of the product of predetermined period described in the wind speed and S201 at place as cuboid, a default sampling width is as cuboid
Width, the particulate matter diffusion height in fugitive dust source is as high.Herein, the wind speed of the center in fugitive dust source is acquisition in S201
When grain object average quality concentration data, the wind speed of fugitive dust source center；Default sampling width can be 30m, it is of course also possible to
It is adjusted according to the needs of practical application scene, such as can also be any value in 20m-50m；Due to research shows that raising
The suspended particulate substances such as dirt are mainly spread in the space below 5m, therefore, can set 5m for the height of cuboid, certainly, when
When particulate matter diffusion height has variation, the height of cuboid can also adjust accordingly.
Fugitive dust discharge capacity is calculated according to the volume of virtual sample space and particulate matter average quality concentration data in S203
Data.Herein, it uses the example above, when virtual sample space is cuboid, the length and width of the volume cuboid of virtual sample space
With high product, fugitive dust displacement data is the volume of cuboid and the product of particulate matter average quality concentration data.
S204 acquires the data of wind speed corresponding with fugitive dust displacement data, air humidity and activity intensity.Herein, living
Fatigue resistance refers to the present granule object average quality concentration in fugitive dust source relative to several history particulate matter average quality concentration
In minimum value non-negative change rate, specifically, can pass through formula (1) calculate activity intensity:
Wherein, TSP refers to the present granule object average quality concentration in fugitive dust source, TSPBGFor background particulate matter average quality
Concentration.Herein, when TSP is greater than the minimum value in several history particulate matter average quality concentration, TSPBGAs several
Minimum value in history particulate matter average quality concentration, when TSP is dense less than or equal to several history particulate matter average qualities
When minimum value in degree, TSPBG=TSP, i.e. activity intensity S are 0.
The fugitive dust rate of discharge data in fugitive dust source are calculated based on fugitive dust displacement data by S205.Herein, fugitive dust discharges
Speed data refers to the quality of the particulate matter of the unit area discharge in the fugitive dust source in predetermined period.
S206, according to fugitive dust rate of discharge data and its training of the data of corresponding wind speed, air humidity and activity intensity
Generate the fugitive dust rate of discharge computation model in fugitive dust source.Herein, the type setting method of fugitive dust rate of discharge computation model can
Understood with setting referring to fugitive dust discharge capacity account model in S103, details are not described herein.
Herein, to construct nonlinear mathematical model, and coefficient therein is solved to realize that fugitive dust rate of discharge calculates
For model, it specifically, can use platinum Chinese Buckingham theorem in dimensional method, establish such as drag:
EF=k μa·Mb·Sc(2),
Wherein, EF refers to that fugitive dust rate of discharge, k refer to that dimension coefficient of balance, μ refer to that wind speed, M refer to air humidity, and S is
Refer to activity intensity, a, b, c are Dimension indexes.
Herein, according to the data of several groups wind speed, air humidity and activity intensity and corresponding fugitive dust rate of discharge number
According to, constantly progress regression training, k, a, b and c in above-mentioned model are solved, to complete building for fugitive dust rate of discharge computation model
It is vertical.
In the present embodiment, the complexity calculated is reduced in order to maximize, logarithm can be taken to become above-mentioned nonlinear model
Available linear regression model (LRM) after shape, specific solution are as follows:
Take logarithm that can obtain respectively on formula (2) both sides:
Formula (3) is converted and can be obtained:
Y=β0+β1x1+β2x2+β3x3(4),
Wherein, β0=lnk, β1=a, β2=b, β3=c, x1=lnμ, x2=lnM, x3=lnS,
Then, β0, β1, β2, β3This 4 parameters are exactly index to be asked.
Since a certain dependent variable y is by k independent variable x1,x2,...,xkInfluence, n group observations be ya,x1a,
x2a,...,xka(a=1,2 ..., n) when, then the structure type of its multiple linear regression model are as follows:
ya=β0+β1x1a+β2x2a+...+βkxka (5)
In formula: β0,β1,...,βkFor undetermined parameter.
And if θ0,θ1,...,θkRespectively β0,β1,β2...,βkMatch value, then regression equation are as follows:
Wherein, θ0For constant, θ1,θ2,...,θkReferred to as partial regression coefficient.
According to principle of least square method, βiThe estimated values theta of (i=0,1,2 ..., k)i(i=0,1,2 ..., k) it should make
Loss function is minimum, it may be assumed that
Therefore, θiSpecific method for solving steps are as follows:
S1 randomly selects parameter θi-1。
S2, if θi-1Loss function cannot be made to reach minimum, then continue to adjust θi-1, obtain θi.Herein, usually there is θi=
θi-1+ Δ is still the functional value variable quantity when the variable is intended to 0 to positive variable quantity due to seeking the partial derivative of variable
The limit, and the objective function of the present embodiment is minimizing, so having: θi=θi-1+(-Δ)。
And if the excessive loss function value that will lead to of △ is shaken, therefore the factor alpha of a very little is multiplied by before gradient,
Have: θi=θi-1+ (- α Δ), to obtain:
S3, if θiValue can't make loss function value minimum, then adjust θ againi, obtain θi+1.Herein,
S4, if θi+1Value is so that loss function value is minimum, that is, converges to some value and be no longer changed, iteration stopping,
Export optimal fitting parameter θi+1.Herein, if θi+1Value cannot make loss function value minimum, then will continue to execute step
S2。
In the present embodiment, rule is updated by using the continuous iteration of the above method, β can be solved0, β1, β2, β3It is quasi-
Conjunction value θ0, θ1, θ2, θ3, so as to determine fugitive dust rate of discharge computation model.
Fugitive dust rate of discharge computation model is multiplied by S207 with the area in fugitive dust source, generates the discharge capacity account mould in fugitive dust source
Type.
Herein, it should be noted that the discharge capacity account model in fugitive dust source herein is predetermined period described in S201
The fugitive dust discharge capacity account model in interior fugitive dust source, for example, fugitive dust discharge capacity account model herein is to raise when predetermined period is 1min
The computation model of fugitive dust discharge capacity of the dirt source in 1min.
In embodiments of the present invention, it is set as by will affect factor including wind speed, air humidity and activity intensity, and
By the present granule object average quality concentration in fugitive dust source relative to the minimum in several history particulate matter average quality concentration
The non-negative change rate of value makes the activity intensity can reflect construction site construction intensity, goods yard operation as activity intensity
Intensity, the stream of people of road traffic vehicle flowrate intensity and other places, the movable intensity of wagon flow, and these intensity are to fugitive dust source
Fugitive dust discharge capacity there is larger impact, accordingly, it is considered to the discharge capacity of the key factor of this influence fugitive dust discharge amount of activity intensity
Model can make the fugitive dust discharge amount being calculated based on this model more acurrate.
In addition, the virtual sample space of the fugitive dust spread condition in fugitive dust source can be characterized by building, make fugitive dust discharge amount
Can simply by virtual sample space volume (being calculated by the parameter of the virtual sampling body itself of building) and
Particulate matter average quality concentration data (being collected by fugitive dust monitoring device) in fugitive dust source is calculated, and reduces fugitive dust
The acquisition difficulty of displacement data.Also, since the particulate matter in shorter predetermined period can be acquired by fugitive dust monitoring device
Average quality concentration data, so as to calculate the fugitive dust displacement data in shorter predetermined period, training generates week short period
The discharge capacity account model in the fugitive dust source in the phase, thus collecting the particulate matter average quality concentration data in predetermined period in real time
When, the fugitive dust discharge capacity in fugitive dust source can be calculated in the discharge capacity account model obtained using the method in the embodiment of the present invention in real time
Data.
Embodiment 2
The flow chart of the fugitive dust discharge capacity account method in the fugitive dust source of the embodiment of the present invention, as shown in figure 3, this method can wrap
Include following steps:
S301 acquires the current data of several influence factors of the fugitive dust discharge capacity in fugitive dust source.It should be noted that herein
Several influence factors be training generate S302 in discharge capacity account model influence factor.
S302 constructs current data input according to the discharge capacity account model building method in fugitive dust source described in embodiment 1
Discharge capacity account model in, obtain the calculated result of the fugitive dust discharge capacity in fugitive dust source.Herein, the collection period of current data and pre-
If the period is identical, also, the calculated result of obtained fugitive dust discharge capacity is also fugitive dust discharge capacity of the fugitive dust source in predetermined period.
The particular content of the present embodiment the method can understand that details are not described herein with reference implementation example 1.
In the present embodiment, as the row of the building of the method according to embodiment 1 or its any optional embodiment
Computation model is measured, is established for the training based on a large amount of history data sets, accuracy is higher, therefore, should by current data input
The accuracy of the calculated result of the fugitive dust discharge capacity in the fugitive dust source that discharge capacity account model obtains is also higher, can be preferably close to fugitive dust
The practical fugitive dust discharge amount in source.
Embodiment 3
Fig. 4 shows a kind of functional block diagram of the discharge capacity account model construction device in fugitive dust source of the embodiment of the present invention, should
Device can be used to implement the discharge capacity account model construction side in fugitive dust source described in embodiment 1 or its any optional embodiment
Method.As shown in figure 4, the device includes: the first data acquisition module 10, the second data acquisition module 20 and model training module
30。
First data acquisition module 10 is used for several fugitive dust displacement datas according to predetermined period acquisition fugitive dust source；In detail
Content can be found in the associated description of step S101 described in above-mentioned any means embodiment.
Second data acquisition module 20 is used to acquire the data of several influence factors corresponding with fugitive dust displacement data；In detail
Thin content can be found in the associated description of step S102 described in above-mentioned any means embodiment.
Model training module 30 is used for for according to the training of the data of fugitive dust displacement data and its corresponding each influence factor
Generate the discharge capacity account model in fugitive dust source；Detailed content can be found in the correlation of step S103 described in above-mentioned any means embodiment
Description.
The discharge capacity account model construction device in fugitive dust source provided in an embodiment of the present invention, by according to fugitive dust displacement data,
And the data training of several corresponding influence factors of fugitive dust displacement data generates the discharge capacity account model in fugitive dust source, makes to construct
Model in parameters be a large amount of history data sets training on the basis of obtain, accuracy is higher, to make base
When discharge capacity account model that the method for the embodiment of the present invention obtains carries out the fugitive dust discharge capacity account in fugitive dust source, obtained calculating knot
The accuracy of fruit is also higher.
Embodiment 4
Fig. 5 shows a kind of functional block diagram of the fugitive dust discharge capacity account device in fugitive dust source according to an embodiment of the present invention, should
Device can be used to implement the fugitive dust discharge capacity account method in fugitive dust source described in embodiment 2 or its any optional embodiment.
As shown in figure 5, the device includes: third data acquisition module 40 and discharge capacity account module 50.
Third data acquisition module 40 is used to acquire the current data of several influence factors of the fugitive dust discharge capacity in fugitive dust source；
Detailed content can be found in the associated description of step S301 described in above-mentioned any means embodiment.
Discharge capacity account module 50 is used for current data input according to embodiment 1 or its any optional embodiment
Fugitive dust source discharge capacity account model building method building discharge capacity account model in, obtain the fugitive dust discharge capacity in the fugitive dust source
Calculated result；Detailed content can be found in the associated description of step S302 described in above-mentioned any means embodiment.Herein, currently
The collection period of data is identical as the predetermined period.
The fugitive dust discharge capacity account device in fugitive dust source provided in an embodiment of the present invention, due to according to embodiment 1 or it is any
The discharge capacity account model of the building of method described in optional embodiment is established for the training based on a large amount of history data sets, quasi-
True property is higher, therefore, current data is inputted to the calculated result of the fugitive dust discharge capacity in the fugitive dust source that the discharge capacity account model obtains
Accuracy is also higher, can be preferably close to the practical fugitive dust discharge amount in fugitive dust source.
The embodiment of the invention also provides a kind of electronic equipment, as shown in fig. 6, the electronic equipment may include processor 61
With memory 62, wherein processor 61 can be connected with memory 62 by bus or other modes, to pass through bus in Fig. 6
For connection.
Processor 61 can be central processing unit (Central Processing Unit, CPU).Processor 61 can be with
For other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.
Memory 62 is used as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, non-
Transient computer executable program and module, such as the discharge capacity account model building method pair in the fugitive dust source in the embodiment of the present invention
Program instruction/the module answered is (for example, the first data acquisition module 10 shown in Fig. 4, the second data acquisition module 20 and model instruction
Practice module 30).Non-transient software program, instruction and the module that processor 61 is stored in memory 62 by operation, thus
Execute the various function application and data processing of processor, i.e. method in realization above method embodiment 1 or embodiment 2.
Memory 62 may include storing program area and storage data area, wherein storing program area can storage program area,
Application program required at least one function；It storage data area can the data etc. that are created of storage processor 61.In addition, storage
Device 62 may include high-speed random access memory, can also include non-transient memory, for example, at least a magnetic disk storage
Part, flush memory device or other non-transient solid-state memories.In some embodiments, it includes relative to place that memory 62 is optional
The remotely located memory of device 61 is managed, these remote memories can pass through network connection to processor 61.The reality of above-mentioned network
Example includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more of modules are stored in the memory 62, when being executed by the processor 61, are executed
Method as shown in Figs. 1-3.
Above-mentioned electronic equipment detail can correspond in refering to fig. 1-embodiment shown in Fig. 3 corresponding associated description and
Effect is understood that details are not described herein again.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of the process in above-described embodiment method
Computer program is crossed to instruct relevant hardware and complete, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can for magnetic disk,
CD, read-only memory (Read-Only Memory, ROM), random access memory (Random Access
Memory, RAM), flash memory (Flash Memory), hard disk (Hard Disk Drive, abbreviation: HDD) or solid state hard disk
(Solid-State Drive, SSD) etc.；The storage medium can also include the combination of the memory of mentioned kind.
Obviously, the above embodiments are merely examples for clarifying the description, and does not limit the embodiments.It is right
For those of ordinary skill in the art, can also make on the basis of the above description it is other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And it is extended from this it is obvious variation or
It changes still within the protection scope of the invention.
Claims (13)
1. a kind of discharge capacity account model building method in fugitive dust source, which comprises the steps of:
Several fugitive dust displacement datas in the fugitive dust source are acquired according to predetermined period；
Acquire the data of several influence factors corresponding with the fugitive dust displacement data；
The row in the fugitive dust source is generated according to the training of the data of the fugitive dust displacement data and its corresponding each influence factor
Measure computation model.
2. the discharge capacity account model building method in fugitive dust source according to claim 1, which is characterized in that the influence factor
Including the particulate matter average quality concentration in the fugitive dust source.
3. the discharge capacity account model building method in fugitive dust source according to claim 1, which is characterized in that the influence factor
Including wind speed, air humidity and the activity intensity in the fugitive dust source；The activity intensity refers to current in the fugitive dust source
Non-negative change rate of the particulate matter average quality concentration relative to the minimum value in several history particulate matter average quality concentration.
4. the discharge capacity account model building method in fugitive dust source according to claim 2 or 3, which is characterized in that the particle
Object average quality concentration is the particle concentration of the center position of the particulate matter diffusion height in the fugitive dust source.
5. the discharge capacity account model building method in fugitive dust source according to claim 2 or 3, which is characterized in that the basis
The training of the data of the fugitive dust displacement data and its corresponding each influence factor generates the discharge capacity account mould in the fugitive dust source
The step of type, comprising:
The fugitive dust rate of discharge data in the fugitive dust source are calculated based on the fugitive dust displacement data；The fugitive dust rate of discharge
Data refer to the quality of the particulate matter of the unit area discharge in the fugitive dust source in the predetermined period；
The fugitive dust source is generated according to the training of the data of the fugitive dust rate of discharge data and its corresponding each influence factor
Fugitive dust rate of discharge computation model；
The fugitive dust rate of discharge computation model is multiplied with the area in the fugitive dust source, generates the discharge capacity account in the fugitive dust source
Model.
6. the discharge capacity account model building method in fugitive dust source according to claim 3, which is characterized in that described according to default
Period acquires the step of several fugitive dust displacement datas in the fugitive dust source, comprising:
The particulate matter average quality concentration data in the fugitive dust source is acquired according to the predetermined period；
Construct the virtual sample space for acquiring the fugitive dust displacement data in the fugitive dust source；
The fugitive dust is calculated according to the volume of the virtual sample space and the particulate matter average quality concentration data
Displacement data.
7. the discharge capacity account model building method in fugitive dust source according to claim 6, which is characterized in that the building is used for
The step of acquiring the virtual sample space of the fugitive dust displacement data in the fugitive dust source, comprising:
Obtain the wind speed of the center in the fugitive dust source；The wind speed is wind when acquiring the particulate matter average quality concentration
Speed；
The virtual sample space is constructed according to the particulate matter diffusion height in the wind speed and the fugitive dust source.
8. the discharge capacity account model building method in fugitive dust source according to claim 7, which is characterized in that the virtual sampling
Space is a cuboid, and the product of a length of wind speed and the predetermined period of the cuboid, width is that a default sampling is wide
Degree, a height of particulate matter diffusion height.
9. a kind of fugitive dust discharge capacity account method in fugitive dust source, which comprises the steps of:
Acquire the current data of several influence factors of the fugitive dust discharge capacity in the fugitive dust source；
The current data is inputted to the discharge capacity account model building method in fugitive dust source according to claim 1-8
In the discharge capacity account model of building, the calculated result of the fugitive dust discharge capacity in the fugitive dust source is obtained；The acquisition week of the current data
Phase is identical as the predetermined period.
10. a kind of discharge capacity account model construction device in fugitive dust source characterized by comprising
First data acquisition module, for acquiring several fugitive dust displacement datas in the fugitive dust source according to predetermined period；
Second data acquisition module, for acquiring the data of several influence factors corresponding with the fugitive dust displacement data；
Model training module, for being given birth to according to the training of the data of the fugitive dust displacement data and its corresponding each influence factor
At the discharge capacity account model in the fugitive dust source.
11. a kind of fugitive dust discharge capacity account device in fugitive dust source characterized by comprising
Third data acquisition module, the current data of several influence factors of the fugitive dust discharge capacity for acquiring the fugitive dust source；
Discharge capacity account module, for the current data to be inputted to the row in fugitive dust source according to claim 1-8
In the discharge capacity account model for measuring computing model construction method building, the calculated result of the fugitive dust discharge capacity in the fugitive dust source is obtained；Institute
The collection period for stating current data is identical as the predetermined period.
12. a kind of electronic equipment characterized by comprising
Memory and processor communicate with each other connection, are stored in the memory between the memory and the processor
Computer instruction, the processor is by executing the computer instruction, thereby executing the described in any item sides of claim 1-9
Method.
13. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer to refer to
It enables, the computer instruction is for making the computer perform claim require the described in any item methods of 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910088129.5A CN109858144B (en) | 2019-01-29 | 2019-01-29 | Method for constructing emission calculation model of dust source and method for calculating emission of dust |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910088129.5A CN109858144B (en) | 2019-01-29 | 2019-01-29 | Method for constructing emission calculation model of dust source and method for calculating emission of dust |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109858144A true CN109858144A (en) | 2019-06-07 |
| CN109858144B CN109858144B (en) | 2020-06-05 |
Family
ID=66896807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910088129.5A Active CN109858144B (en) | 2019-01-29 | 2019-01-29 | Method for constructing emission calculation model of dust source and method for calculating emission of dust |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858144B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112304830A (en) * | 2020-09-27 | 2021-02-02 | 山东诺方电子科技有限公司 | Method for monitoring road dust load by using social vehicles |
| CN113281231A (en) * | 2021-06-01 | 2021-08-20 | 福建师范大学 | Dynamic monitoring and analyzing method for emission of dust particles in road network |
| TWI743980B (en) * | 2020-09-08 | 2021-10-21 | 國立宜蘭大學 | River dust prediction system |
| CN113769519A (en) * | 2021-11-15 | 2021-12-10 | 辽博信息科技(山东)有限公司 | Intelligent dust fall control method and system for construction site |
| CN117180899A (en) * | 2023-11-07 | 2023-12-08 | 米脂冀东水泥有限公司 | Cement production dust cleaning method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090055103A1 (en) * | 2007-08-06 | 2009-02-26 | Ernest Gilbert | Substance Release Estimation Using Path-Averaged Concentration Measurements |
| CN102003985A (en) * | 2009-08-31 | 2011-04-06 | 宝山钢铁股份有限公司 | Method for measuring inorganization discharge amount of dust in stock ground |
| CN107657147A (en) * | 2017-10-13 | 2018-02-02 | 东南大学 | Pollutant of vehicle exhaust Emission amount calculation method based on loop data |
| CN108152458A (en) * | 2017-12-26 | 2018-06-12 | 歌尔股份有限公司 | Gas detection method and device |
-
2019
- 2019-01-29 CN CN201910088129.5A patent/CN109858144B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090055103A1 (en) * | 2007-08-06 | 2009-02-26 | Ernest Gilbert | Substance Release Estimation Using Path-Averaged Concentration Measurements |
| CN102003985A (en) * | 2009-08-31 | 2011-04-06 | 宝山钢铁股份有限公司 | Method for measuring inorganization discharge amount of dust in stock ground |
| CN107657147A (en) * | 2017-10-13 | 2018-02-02 | 东南大学 | Pollutant of vehicle exhaust Emission amount calculation method based on loop data |
| CN108152458A (en) * | 2017-12-26 | 2018-06-12 | 歌尔股份有限公司 | Gas detection method and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI743980B (en) * | 2020-09-08 | 2021-10-21 | 國立宜蘭大學 | River dust prediction system |
| CN112304830A (en) * | 2020-09-27 | 2021-02-02 | 山东诺方电子科技有限公司 | Method for monitoring road dust load by using social vehicles |
| CN113281231A (en) * | 2021-06-01 | 2021-08-20 | 福建师范大学 | Dynamic monitoring and analyzing method for emission of dust particles in road network |
| CN113769519A (en) * | 2021-11-15 | 2021-12-10 | 辽博信息科技(山东)有限公司 | Intelligent dust fall control method and system for construction site |
| CN113769519B (en) * | 2021-11-15 | 2022-04-08 | 辽博信息科技(山东)有限公司 | Intelligent dust fall control method and system for construction site |
| CN117180899A (en) * | 2023-11-07 | 2023-12-08 | 米脂冀东水泥有限公司 | Cement production dust cleaning method and system |
| CN117180899B (en) * | 2023-11-07 | 2024-02-02 | 米脂冀东水泥有限公司 | Cement production dust cleaning method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109858144B (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858144A (en) | A kind of the discharge capacity account model building method and fugitive dust discharge capacity account method in fugitive dust source | |
| Deng et al. | Simulation of land use/land cover change and its effects on the hydrological characteristics of the upper reaches of the Hanjiang Basin | |
| WO2016155372A1 (en) | Method and device for predicting air quality index | |
| Ramedani et al. | Modeling solar energy potential in a Tehran province using artificial neural networks | |
| JP6679086B2 (en) | Learning device, prediction device, learning method, prediction method, and program | |
| Frnda et al. | ECMWF short-term prediction accuracy improvement by deep learning | |
| Sfetsos et al. | A new methodology development for the regulatory forecasting of PM10. Application in the Greater Athens Area, Greece | |
| CN105023043A (en) | AOD-based PM2.5 inversion model for Hangzhou region | |
| CN110232471A (en) | A kind of precipitation sensing net node layout optimization method and device | |
| CN112986492A (en) | Method and device for establishing gas concentration prediction model | |
| Wang et al. | Development and application of a simulation model for changes in land-use patterns under drought scenarios | |
| CN113155498B (en) | High-resolution building operation energy consumption carbon emission measuring method, system and equipment | |
| Wu et al. | Evaluation of global climate model on performances of precipitation simulation and prediction in the Huaihe River basin | |
| CN111428917B (en) | Soil pollution prediction method and system for heavy metal stable pollution source | |
| CN112329997A (en) | Power demand load prediction method and system, electronic device, and storage medium | |
| Shah et al. | Analytical equations based prediction approach for PM2. 5 using artificial neural network | |
| CN117252436B (en) | Method and system for land utilization change ecological risk partition | |
| Vallam et al. | Multi‐site rainfall simulation at tropical regions: a comparison of three types of generators | |
| CN107944205B (en) | Water area characteristic model establishing method based on Gaussian smoke plume model | |
| Sørup et al. | Evaluating catchment response to artificial rainfall from four weather generators for present and future climate | |
| Cui et al. | Parallelisation of a distributed hydrologic model | |
| CN114529035A (en) | CART-based wind speed forecasting method of multi-mode integrated model | |
| Zhang et al. | Parallelization of the flow-path network model using a particle-set strategy | |
| Navarro et al. | On the application of big data techniques to noise monitoring of smart cities | |
| CN109948108B (en) | The verification method of the selection of fugitive dust discharge capacity account model, discharge capacity account and displacement data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221229 Address after: No. 788, Shuangying Road, Wuyi Park, Wuyi Town, Nanqiao District, Chuzhou City, Anhui Province 239050 Patentee after: Anhui Sumeng electric complete equipment Co.,Ltd. Address before: 211100 No. 12, mozhou East Road, moling street, Nanjing, Jiangsu Patentee before: JIANGSU XIAOFENG ENVIRONMENTAL PROTECTION TECHNOLOGY CO.,LTD. |
|
| TR01 | Transfer of patent right |