CN114492984A - Method, device, equipment and storage medium for predicting time-space distribution of dust concentration - Google Patents
Method, device, equipment and storage medium for predicting time-space distribution of dust concentration Download PDFInfo
- Publication number
- CN114492984A CN114492984A CN202210079569.6A CN202210079569A CN114492984A CN 114492984 A CN114492984 A CN 114492984A CN 202210079569 A CN202210079569 A CN 202210079569A CN 114492984 A CN114492984 A CN 114492984A
- Authority
- CN
- China
- Prior art keywords
- prediction
- time period
- prediction model
- dust concentration
- environment parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000428 dust Substances 0.000 title claims abstract description 129
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000009826 distribution Methods 0.000 title claims abstract description 31
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 230000007613 environmental effect Effects 0.000 claims abstract description 123
- 238000005070 sampling Methods 0.000 claims description 69
- 238000003062 neural network model Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 5
- 230000002123 temporal effect Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 description 28
- 238000004364 calculation method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 238000009792 diffusion process Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000007774 longterm Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- PWHULOQIROXLJO-UHFFFAOYSA-N Manganese Chemical compound [Mn] PWHULOQIROXLJO-UHFFFAOYSA-N 0.000 description 2
- ATBAMAFKBVZNFJ-UHFFFAOYSA-N beryllium atom Chemical compound [Be] ATBAMAFKBVZNFJ-UHFFFAOYSA-N 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000012895 dilution Substances 0.000 description 2
- 238000010790 dilution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000004072 lung Anatomy 0.000 description 2
- 229910052748 manganese Inorganic materials 0.000 description 2
- 239000011572 manganese Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 206010035653 pneumoconiosis Diseases 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 206010010741 Conjunctivitis Diseases 0.000 description 1
- 201000004624 Dermatitis Diseases 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 201000010001 Silicosis Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000003915 air pollution Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013618 particulate matter Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present disclosure provides a method, an apparatus, a device and a storage medium for predicting the spatial-temporal distribution of dust concentration, wherein the method comprises: obtaining an environmental parameter prediction value of a point to be predicted in a prediction time period by adopting a pre-established environmental parameter gray prediction model; according to the method, the dust concentration prediction value of the point to be predicted in the prediction time period is obtained by using a pre-constructed dust concentration prediction model according to the position information and the environmental parameter prediction value of the point to be predicted.
Description
Technical Field
The disclosure relates to the technical field of air quality detection, and in particular relates to a method, a device, equipment and a storage medium for predicting the time-space distribution of dust concentration.
Background
The accumulation of dust in the lungs increases gradually due to the long-term inhalation of dust by workers who have been in contact with productive dust for a long time, and pneumoconiosis can be caused when a certain amount of dust is reached. Pneumoconiosis is one of the most important hazards of productive dust to human body, and long-term inhalation of free silica dust can cause silicosis, long-term inhalation of metallic dust such as manganese dust, beryllium dust and the like can cause various metal lungs such as manganese dust, beryllium dust and the like. When the asphalt smoke dust is contacted with the sunlight, light dermatitis, eye conjunctivitis and the like can be caused, other harmful substances can be attached to the dust floating in the air to form serious air pollution, and various diseases can be caused by the inhalation of organisms. In addition, a large amount of dust is suspended in the air, which can reduce the visibility of the atmosphere, promote the formation of smoke, and affect the heat radiation of the sun. Dust is very common in the nuclear power construction production process, and dust is generated in a plurality of links such as an excavator, a bulldozer, a road roller, transportation and the like. In order to reduce the harm of dust to human bodies and the influence on the progress of construction, the dust concentration is necessary to be predicted. However, the sources of dust in nuclear power construction are numerous, the influencing factors are numerous, and the variables have a million-strand relationship, so that the dust concentration in a construction site is difficult to accurately predict.
Disclosure of Invention
In view of the above, the present disclosure provides a method, an apparatus, a device, and a storage medium for predicting the time-space distribution of dust concentration, which can accurately predict the dust concentration at a construction site.
According to a first aspect of the present disclosure, there is provided a method for predicting a temporal and spatial distribution of dust concentration, comprising:
obtaining an environmental parameter prediction value of a point to be predicted in a prediction time period by adopting a pre-established environmental parameter gray prediction model;
obtaining a dust concentration predicted value of the point to be predicted in the prediction time period by using a pre-constructed dust concentration prediction model according to the position information of the point to be predicted and the environmental parameter predicted value;
wherein the environment parameter gray prediction model comprises at least one of an air pressure gray prediction model, a temperature gray prediction model, a wind speed gray prediction model, a wind direction gray prediction model and a humidity gray prediction model.
In a possible implementation manner, the environment parameter gray prediction model is constructed based on environment parameter actual values acquired by sampling points in n preceding time periods of the prediction time period, wherein a value of n is a positive number.
In a possible implementation manner, when the environment parameter gray prediction model is constructed based on the environment parameter actual values acquired by the sampling points in the first n time periods of the prediction time period, the method includes:
acquiring the actual values of the environmental parameters of the sampling points acquired in the first n time periods of the prediction time period, and constructing an actual value sequence of the environmental parameters;
sequentially accumulating the acquired environmental parameter actual values of each time period respectively to obtain an environmental parameter accumulated value corresponding to each time period, and constructing an environmental parameter accumulated value sequence based on the obtained environmental parameter accumulated values;
and constructing and obtaining the environment parameter gray prediction model based on the environment parameter actual value sequence and the environment parameter accumulated value sequence.
In a possible implementation manner, after obtaining the environment parameter gray prediction model, the method further includes:
carrying out posterior difference inspection on the environment parameter gray prediction model to obtain a posterior difference ratio and a small error probability;
and judging whether the environment parameter gray prediction model meets a preset precision grade or not based on the posterior difference ratio and the small error probability, and under the condition that the set precision grade is not met, correcting the environment parameter gray prediction model by adopting a residual error correction method until the environment parameter gray prediction model meets the preset precision grade.
In a possible implementation manner, when an environmental parameter grey prediction model which is set up in advance is adopted to obtain an environmental parameter prediction value of a point to be predicted in a prediction time period, the method includes the following steps:
determining a first neighboring time period and a second neighboring time period based on the predicted time period; the second adjacent time period, the first adjacent time period and the predicted time period are time periods sequentially connected in time sequence;
inputting the first adjacent time period into the environment parameter grey prediction model to obtain a prediction accumulated value under the prediction time period;
inputting the second adjacent time period into the environment parameter gray prediction model to obtain a prediction accumulated value under the first adjacent time period;
and obtaining the environmental parameter predicted value in the prediction time period according to the prediction accumulated value in the prediction time period and the prediction accumulated value in the first adjacent time period.
In a possible implementation manner, after the environmental parameter prediction value under the prediction time period is obtained, a step of preprocessing the environmental parameter prediction value is further included.
In one possible implementation, constructing the dust concentration prediction model includes:
respectively acquiring sample data of k sampling points; the sample data includes: position information of sampling points, historical data of environmental parameters and historical data of dust concentration;
and training model parameters of a neural network model by taking the position information and the environmental parameter historical data of each sampling point as input data and taking the dust concentration historical data of each sampling point as output data to obtain the dust concentration prediction model.
According to a second aspect of the present disclosure, there is provided a dust concentration spatiotemporal distribution prediction apparatus comprising:
the environment parameter prediction module is used for obtaining an environment parameter prediction value of a point to be predicted in a prediction time period by adopting a pre-established environment parameter gray prediction model;
the dust concentration prediction module is used for obtaining a dust concentration prediction value of the point to be predicted in the prediction time period by using a pre-constructed dust concentration prediction model according to the position information of the point to be predicted and the environmental parameter prediction value;
the environment parameter gray prediction model comprises at least one of an air pressure gray prediction model, a temperature gray prediction model, a wind speed gray prediction model, a wind direction gray prediction model and a humidity gray prediction model.
According to a third aspect of the present disclosure, there is provided a dust concentration spatiotemporal distribution prediction apparatus including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the executable instructions.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the above-described method.
In the method, a pre-established environment parameter gray prediction model is adopted to obtain an environment parameter prediction value of a point to be predicted in a prediction time period; and then according to the position information of the point to be predicted and the predicted value of the environmental parameter, obtaining a predicted value of the dust concentration of the point to be predicted in a prediction time period by using a pre-constructed dust concentration prediction model. According to the method, the dust concentration is accurately predicted in a mode of combining the environment parameter gray prediction model and the dust concentration prediction model.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.
FIG. 1 shows a schematic flow diagram of a method of spatio-temporal distribution prediction of dust concentration according to an embodiment of the present disclosure;
FIG. 2 shows a schematic block diagram of a dust concentration spatiotemporal distribution prediction apparatus according to an embodiment of the present disclosure;
fig. 3 shows a schematic block diagram of a temporal spatial distribution prediction apparatus of dust concentration according to an embodiment of the present disclosure.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.
< method examples >
FIG. 1 shows a schematic flow diagram of a method of spatiotemporal distribution prediction of dust concentration according to an embodiment of the present disclosure. As shown in FIG. 1, the method for predicting the spatiotemporal distribution of dust concentration includes steps S110 to S120.
And S110, obtaining an environmental parameter predicted value of the point to be predicted in a prediction time period by adopting a pre-established environmental parameter gray prediction model.
The environment parameter gray prediction model is a gray differential prediction model constructed by using the actual value of the environment parameter of the construction site, and can be used for predicting the environment parameter of the construction site. The point to be predicted is a position point which is selected in a construction site and any one of which needs to be subjected to dust concentration prediction.
It should be noted that before predicting the dust concentration of a point to be predicted, sampling points need to be laid on a construction site, and then an environmental parameter gray prediction model is constructed based on an environmental parameter actual value obtained from the sampling points.
The principle of laying sampling points on a construction site is as follows: and (3) taking the construction site as a unit, and laying sampling points according to the personnel distribution characteristics, the dust source distribution characteristics and the environmental characteristics of the construction site so that the sampling points can represent the distribution condition of the dust concentration of the construction site. For example, the sampling points are distributed in a representative area capable of reflecting the area environment quality, the sampling points are distributed in an encrypted manner in an area with a dust source, and the sampling points are distributed in a respiratory belt area in an area with personnel working.
The method for laying sampling points on a construction site comprises the following steps: when the sampling points are distributed in the corresponding sampling units, if the environmental factors in the sampling units are consistent, the sampling points are distributed by adopting a grid method, an S-shaped method, a diagonal method, a checkerboard method or a quincunx method; if the distribution of the environmental factors in the sampling unit is complex, the sampling points are distributed in a random mode.
After the sampling points are arranged based on the principle and the method, firstly, a space rectangular coordinate system is established by taking a certain point of a construction site as a coordinate origin, and the coordinate values of the sampling points are obtained by a laser distance meter and are used as the position information of the sampling points. And secondly, arranging an environment monitor and a dust concentration measuring instrument at the sampling point to obtain the environment parameter influencing the dust concentration of the construction site at the sampling point through the environment monitor and obtain the dust concentration of the sampling point under the current environment parameter through the dust concentration measuring instrument. Thirdly, recording the environmental parameters and the dust concentration at the sampling point according to the set time interval.
The time interval of recording may be determined according to specific requirements and/or performance of the instrument. For example, the determined time interval may be 15min, depending on the need for short time sampling. As another example, the determined time interval may be 60min according to the requirement of long time sampling. The recorded time interval can also be determined according to the dust monitoring regulations of the application industry, for example, the time interval can be determined according to the dust measurement in air of workplaces (GBZ 192.1.1-2007). In one possible implementation, the value range of the time interval may be: 30-60 min.
In the present disclosure, the environmental parameter refers to an environmental parameter that affects dust concentration at a construction site, and the environmental parameter may include at least one of air pressure, temperature, wind speed, wind direction, and humidity.
For air pressure, when the ground is controlled by low pressure, high-pressure air mass on the periphery flows to the center, so that ascending air flow is formed in the center, strong wind is formed, upward diffusion of dust is facilitated, and the dust concentration is low; and when the ground surface is controlled by high pressure, the sinking inverse temperature is easy to form, the upward diffusion of pollutants is inhibited, and the dust concentration is increased under the stable high-pressure control.
The concentration of the dust is influenced mainly by two aspects as for the temperature, on one hand, the higher the temperature is, the faster the diffusion speed of the gas is, and the larger the influence on the concentration of the dust is; on the other hand, the temperature difference is large and is a necessary thermal condition for gas convection, and the larger the temperature difference is, the stronger the rising movement is, the more easily the convection is caused, thereby accelerating the dilution of dust.
For wind speed, the wind speed and the dust concentration have obvious negative correlation, namely the larger the wind speed, the smaller the dust concentration, the better the air quality, and the more favorable the dilution and diffusion of dust in the air.
For wind direction, when the wind direction makes the dust diffuse to the monitoring point, the position dust concentration of monitoring point becomes big, otherwise the dust concentration of monitoring point becomes little.
As for humidity, relative humidity plays an important role in the monitoring and prediction of fine particulate matter thereof. When the relative humidity of the rainfall-free air is below 60% -80%, the secondary generation effect of the particulate matters is strong, and the dust concentration and the relative humidity are in a direct proportion relation. When the relative humidity of air is more than 80%, rainfall is easy to form, the particles in the air are washed, the concentration of the particles is inversely proportional to the relative humidity, and some dust can be dissolved in water molecules in the air.
And the data acquisition can be carried out on the environmental parameters by setting the corresponding environmental monitor. For example, the actual values of air pressure may be obtained by a digital barometer, and the actual values of temperature, wind speed, wind direction and humidity may be obtained by an ultrasonic anemometer. The wind direction can be represented by an angle, the circumference is divided into 360 degrees, the north wind is 0 degrees (namely 360 degrees), the east wind is 90 degrees, the south wind is 180 degrees, the west wind is 270 degrees, and the other wind directions can be calculated according to the wind direction.
Because the environmental parameters of the construction site are basically consistent, a target sampling point can be selected from a plurality of sampling points according to the actual condition of the construction site, an environmental parameter gray prediction model is constructed based on the actual values of the environmental parameters collected by the target sampling point, and the environmental parameters of any point to be measured of the construction site are predicted through the environmental parameter gray prediction model.
According to the method, at least one of an air pressure gray prediction model, a temperature gray prediction model, a wind speed gray prediction model, a wind direction gray prediction model and a humidity gray prediction model can be constructed according to at least one of the air pressure, the temperature, the wind speed, the wind direction and the humidity acquired by a target sampling point, so that the corresponding environmental parameters of a construction site can be predicted through the at least one environmental parameter gray prediction model. For example, an air pressure grey prediction model is constructed based on the acquired air pressure value of the target sampling point so as to predict the air pressure of a construction site; constructing a temperature gray prediction model based on the temperature values acquired by the target sampling points so as to predict the temperature of the construction site; constructing a wind speed grey prediction model based on the wind speed value obtained by the target sampling point so as to predict the wind speed of the construction site; constructing a wind direction grey prediction model based on the wind direction value obtained by the target sampling point so as to predict the wind direction of the construction site; and constructing a humidity gray prediction model based on the humidity value obtained by the target sampling point, and predicting the humidity of the construction site.
In a possible implementation manner, an environmental parameter gray prediction model of a construction site may be further constructed based on environmental parameters obtained by a plurality of sampling points, which is not specifically limited herein.
In a possible implementation manner, the environment parameter gray prediction model is constructed based on environment parameter actual values acquired by sampling points in n preceding time periods of the prediction time period, where n is the number of data selected according to an actual situation, and a value of n is a positive number, for example, a value of n may be 8.
In one possible implementation, in order to determine the optimal value of n, different values of n may be selected to establish a plurality of environment parameter gray prediction models, for example, when n is 8, n is 9, … …, and n is 15, the environment parameter gray prediction models may be respectively established; predicting the predicted value of the grey prediction model of the later time intervals based on each environment parameter grey prediction model, then comparing the predicted value with the actual value, and taking the value of n of the environment parameter grey prediction model with the minimum deviation between the predicted value and the actual value as the value of n when the environment parameter grey prediction model is constructed.
In a possible implementation manner, when an environment parameter gray prediction model is constructed based on environment parameter actual values acquired by sampling points in the first n time periods of a prediction time period, the method includes:
step 1, acquiring the actual values of the environmental parameters of the sampling points acquired in the first n time periods of the prediction time period, and constructing an actual value sequence of the environmental parameters.
For example, the actual values of the environmental parameters obtained in the first n time segments of the prediction time segment are respectively
The constructed sequence of actual values of the environmental parameter is
And 2, sequentially accumulating the acquired environmental parameter actual values in each time period to obtain an environmental parameter accumulated value corresponding to each time period, and constructing an environmental parameter accumulated value sequence based on the obtained environmental parameter accumulated values.
Accumulated value of environmental parameter corresponding to k-th time period
Is calculated as follows:
wherein,
the actual values of the environmental parameters collected for the j time periods.
The first n time segments of the prediction time segment are sequentially marked as the 1 st time segment, the 2 nd time segment, … … and the nth time segment in time sequence.
For the 1 st time period, namely when k is 1, the corresponding environment parameter accumulated value is
Wherein,
for the 2 nd time period, i.e. when k is 2, the corresponding accumulated value of the environmental parameters is
Wherein,
for the 3 rd time period, namely when k is 3, the corresponding environment parameter accumulated value is
Wherein,
and so on, obtaining the environment parameter accumulated values corresponding to the n time periods as follows:
the constructed environmental parameter accumulated value sequence is
And 3, constructing and obtaining an environment parameter gray prediction model based on the environment parameter actual value sequence and the environment parameter accumulated value sequence, wherein the method specifically comprises the following steps:
3.1, using the accumulated value sequence of the environmental parameters as
Establishing a gray prediction model of a first environmental parameter as shown in formula (1) as a basis:
in the formula, a and u are parameters to be distinguished.
3.2, solving the formula (1) to obtain a second environment parameter gray prediction model shown as the formula (2):
in the formula,
is the prediction accumulated value in the k +1 th prediction period.
And 3.3, constructing an equation set shown as a formula (3) based on the actual value sequence of the environmental parameters and the accumulated value sequence of the environmental parameters, and solving a mode set through a least square method to obtain two parameters a and u to be distinguished.
Order:
namely:
then, the following formula is used to obtain
Least squares solution of (c):
and 3.4, substituting the two parameters to be distinguished of a and u into the formula (2) to obtain an environment parameter gray prediction model.
An environment parameter gray prediction model is constructed on the basis of the environment parameter actual values acquired by the sampling points in the first n time periods of the prediction time periods, and environment parameter prediction is carried out on the basis of the environment parameter gray prediction model, so that the accuracy of the environment parameter prediction value can be improved.
In a possible implementation manner, after obtaining the environment parameter gray prediction model, the method further includes a step 4 of correcting the environment parameter gray prediction model, where the step 4 specifically includes:
4.1, carrying out posterior difference inspection on the environment parameter gray prediction model to obtain a posterior difference ratio and a small error probability.
4.1.1, calculating a 0-order residual corresponding to each time interval, wherein the calculation formula of the 0-order residual is shown as formula (7):
in the formula:
in order to obtain the predicted value of the environmental parameter in the kth time period through the grey prediction model of the environmental parameter,
is the actual value of the environmental parameter at the kth time period,
is the 0 th order residual error corresponding to the k-th time interval.
4.1.2, calculating the residual average value of the n time intervals, wherein the calculation formula of the residual average value is shown as formula (8):
4.1.3, calculating residual variance of n time intervals, wherein the calculation formula of the residual variance is shown as formula (9):
4.1.4, calculating the average value of the actual values of the environmental parameters of the n time intervals, wherein the average value calculation formula is shown as the formula (10):
4.1.5, calculating the variance of the actual values of the environmental parameters in the n time intervals, wherein the variance calculation formula of the actual values of the environmental parameters is shown as the formula (11):
4.1.6, calculating the posterior difference ratio according to the formula (12), and calculating the small error difference value according to the formula (13):
and 4.2, judging whether the environment parameter gray prediction model meets a preset precision grade or not based on the posterior difference ratio and the small error probability, and under the condition that the set precision grade is not met, correcting the environment parameter gray prediction model by adopting a residual error correction method until the environment parameter gray prediction model meets the preset precision grade.
In one possible implementation, the accuracy levels of the environmental parameter gray prediction model may be divided as shown in Table 1.
TABLE 1
In a possible implementation manner, the preset precision level may be qualified, and when the posterior difference ratio and the small error probability do not satisfy the qualified precision level, the environment parameter gray prediction model is corrected by using a residual error correction method until the environment parameter gray prediction model satisfies the requirement of the qualified precision level, that is, the posterior difference ratio is less than 0.50 and the small error probability is greater than 0.80. The prediction accuracy of the environment parameter gray prediction model can be further improved by correcting the environment parameter gray prediction model.
In a possible implementation manner, when an environmental parameter grey prediction model which is set up in advance is adopted to obtain an environmental parameter prediction value of a point to be predicted in a prediction time period, the method includes the following steps:
step 1, determining a first adjacent time period and a second adjacent time period based on a predicted time period; the second adjacent time period, the first adjacent time period and the predicted time period are time periods sequentially connected in chronological order.
For example, if the predicted time interval is the (k + 1) th time interval, the first adjacent time interval is the (k) th time interval, and the second adjacent time interval is the (k-1) th time interval.
And 2, inputting the first adjacent time period into an environment parameter gray prediction model to obtain a prediction accumulated value in the prediction time period.
For example, k is input to equation (2) to obtain a prediction accumulated value in a prediction time period k +1
And 3, inputting the second adjacent time period into an environment parameter gray prediction model to obtain a prediction accumulated value under the first adjacent time period.
For example, k-1 is input into the formula (2) to obtain the predicted accumulated value in the first adjacent time period k
And 4, obtaining the environmental parameter predicted value in the prediction time period according to the prediction accumulated value in the prediction time period and the prediction accumulated value in the first adjacent time period.
In a possible implementation manner, the environmental parameter predicted value in the prediction time period may be obtained by subtracting the prediction accumulated value in the prediction time period from the prediction accumulated value in the first adjacent time period, that is, the calculation formula of the environmental parameter predicted value in the prediction time period is as shown in formula (14):
in the formula,
the predicted value of the environmental parameter in the (k + 1) th prediction time period is obtained.
In a possible implementation manner, after the environmental parameter predicted value under the prediction time period is obtained, the method further comprises the step of preprocessing the environmental parameter predicted value so as to convert the environmental parameter predicted value into the range between [ -1,1] through preprocessing. Wherein, the calculation formula of the preprocessing is shown as formula (15):
in the formula: x is the number ofiAs input variables, xminIs the minimum value of the input variable, xmaxIs the maximum value of the input variable, niAs an input variable xiThe result of the pretreatment of (1).
And S120, obtaining a dust concentration predicted value of the point to be predicted in a predicted time period by using a pre-constructed dust concentration prediction model according to the position information of the point to be predicted and the environmental parameter predicted value.
The dust concentration prediction model is a neural network model reflecting the mapping relation between the position information and the environmental parameter prediction value of the point to be predicted and the dust concentration of the point to be predicted. And inputting the obtained position information of the point to be predicted and the predicted value of the environmental parameter into a dust concentration prediction model, so that the predicted value of the dust concentration of the point to be predicted in a prediction time period can be obtained.
Before the dust concentration is predicted, the dust concentration prediction model needs to be constructed according to the environmental parameter value historical data and the dust concentration historical data acquired by the sampling points arranged in step S110.
In one possible implementation, constructing the dust concentration prediction model includes:
step 1, respectively acquiring sample data of k sampling points; the sample data includes: the position information of the sampling point, the historical data of the environmental parameters and the historical data of the dust concentration.
And for each sampling point, recording the position information, the environmental parameter historical data and the dust concentration historical data of the sampling point according to a set time interval. Wherein the historical data of the environmental parameters comprises historical data of at least one environmental parameter of air pressure, temperature, wind speed, wind direction and humidity.
And 2, training model parameters of the neural network model by taking the position information and the environmental parameter historical data of each sampling point as input data and taking the dust concentration historical data of each sampling point as output data to obtain a dust concentration prediction model.
When training the model parameters of the neural network model through k groups of sample data, the k groups of sample data can be uniformly divided into 2 groups: i.e., training samples and test samples, which account for 2/3 and 1/3, respectively, of the total number of sample data. The training sample is used for training the neural network model, and the weight and the threshold value of the network are continuously updated by calculating the gradient of the performance function, so that the performance function is continuously reduced; the test sample is used for testing the training result of the neural network model and verifying the quality of the network generalization capability. And substituting the 2 groups of samples into a neural network model for training, testing generalization capability, continuously adjusting each attribute value of the network according to the difference between the training result and the actual value until the final satisfaction, if the trained neural network model can stably predict the dust concentration of each sampling point according to the position information and the environmental parameters of the sampling point and the error between the trained neural network model and the actual value is very small, the neural network model passes the inspection, and the validated neural network model is used as a dust concentration prediction model.
In the embodiment of preprocessing the predicted value of the obtained environmental parameter, when a dust concentration prediction model is constructed, the same preprocessing step needs to be carried out on sample data, and then the parameters of the neural network model are trained through the preprocessed sample data, so that the training effect and the generalization capability of the neural network model can be enhanced. For example, the coordinate values of K sampling points-X, Y, Z, wind speed, wind direction, air pressure, temperature, humidity and dust concentration are respectively substituted into formula (15) to carry out pretreatment.
The neural network model generally comprises an input layer, a hidden layer and an output layer, wherein data of the input layer is transmitted to the hidden layer, and then the data of the hidden layer is transmitted to the output layer,thereby realizing the forward propagation of the neural network. Output result z with hidden layer nodes and output layer nodesk、yjRespectively as follows:
in the formula (f)1(·)、f2() transfer function of input layer to hidden layer and hidden layer to output layer, respectively; n, q and m are the node numbers of the input layer, the hidden layer and the output layer respectively; v. ofkj、wjkThe weights of the input layer and the hidden layer, and the hidden layer and the output layer are respectively.
The step of determining the back propagation of the neural network model comprises:
step 1, defining an error function
Inputting P learning samples by x1，x2，x3，……，xpTo express that the p-th sample is input into the network to obtain the output
Using a square error function, the error E of the p-th sample is obtainedp：
In the formula:
is the desired output.
For P samples, the global error is:
step 2, determining the change of the weight value of the output layer
Adjusting w using accumulated error BP algorithmjkMake the global error E smaller, i.e.
In the formula: eta is learning rate
The error signal is defined as:
wherein the first term:
the second term is:
is the partial differential of the output layer transfer function.
Thus:
by the chain theorem:
then, the weight adjustment formula of each neuron in the output layer is:
step 3, determining the change of the hidden layer weight value
The error signal is defined as:
the first item of
According to the chain theorem, the method comprises the following steps:
the second term is:
is the partial differential of the implicit layer transfer function.
Thus:
from the chain theorem:
thus, the weight value adjustment formula of each neuron of the hidden layer is obtained as follows:
after the forward propagation and backward propagation functions of the neural network model are determined, the training samples can be used to train the neural network model repeatedly in the forward propagation and backward propagation. During the repeated training, the error is smaller and smaller, the preset training times are finally reached or the error is reduced to a specified acceptable degree, and the training is finished.
In a possible implementation manner, after the dust concentration prediction model is obtained, the method further comprises the step of evaluating the accuracy of the dust concentration prediction model.
And comparing and analyzing the predicted value and the actual measured value of the verification sample by using the average absolute error (MAE), the average relative error (MRE), the Root Mean Square Error (RMSE) and the goodness of fit (R2) to obtain the precision evaluation results of different models.
In the formula: y isact(i)Represents the measured value of the ith sample; y ispre(i)Is the predicted value for the ith sample;
the average value of measured values of the samples is shown, and n is the number of data.
In the method, a pre-established environment parameter gray prediction model is adopted to obtain an environment parameter prediction value of a point to be predicted in a prediction time period; and then according to the position information of the point to be predicted and the predicted value of the environmental parameter, obtaining a predicted value of the dust concentration of the point to be predicted in a prediction time period by using a pre-constructed dust concentration prediction model. According to the method, the dust concentration is accurately predicted in a mode of combining the environment parameter gray prediction model and the dust concentration prediction model.
< apparatus embodiment >
Fig. 2 shows a schematic block diagram of a spatial-temporal distribution prediction apparatus of dust concentration according to an embodiment of the present disclosure. As shown in fig. 2, the dust concentration spatio-temporal distribution prediction apparatus 2000 includes:
the environment parameter prediction module 2100 is used for obtaining an environment parameter prediction value of a point to be predicted in a prediction time period by adopting a pre-established environment parameter grey prediction model;
the dust concentration prediction module 2200 is used for obtaining a dust concentration prediction value of the point to be predicted in a prediction time period by using a pre-constructed dust concentration prediction model according to the position information of the point to be predicted and the environmental parameter prediction value;
the environment parameter gray prediction model comprises at least one of an air pressure gray prediction model, a temperature gray prediction model, a wind speed gray prediction model, a wind direction gray prediction model and a humidity gray prediction model.
In a possible implementation manner, the environment parameter gray prediction model is constructed based on environment parameter actual values acquired by sampling points in the first n time periods of the prediction time period, wherein the value of n is a positive number.
In a possible implementation manner, the dust concentration space-time distribution prediction apparatus 2000 further includes a first model building module, where the first model building module is configured to build an environmental parameter gray prediction model, and when the environmental parameter gray prediction model is built based on the environmental parameter actual values collected by the sampling points in the first n time periods of the prediction time period, the first model building module is specifically configured to: acquiring the actual values of the environmental parameters of the sampling points acquired in the first n time periods of the prediction time period, and constructing an actual value sequence of the environmental parameters; sequentially accumulating the acquired environmental parameter actual values of each time period respectively to obtain an environmental parameter accumulated value corresponding to each time period, and constructing an environmental parameter accumulated value sequence based on the obtained environmental parameter accumulated values; and constructing and obtaining an environment parameter gray prediction model based on the environment parameter actual value sequence and the environment parameter accumulated value sequence.
In a possible implementation, after obtaining the environment parameter gray prediction model, the first model construction module is further configured to: carrying out posterior difference inspection on the environment parameter gray prediction model to obtain a posterior difference ratio; and judging whether the posterior difference ratio meets the set precision grade, and under the condition that the posterior difference ratio does not meet the set precision grade, correcting the environment parameter gray prediction model by adopting a residual error correction method until the posterior difference ratio meets the set precision grade.
In a possible implementation manner, when the environmental parameter prediction module 2100 obtains an environmental parameter prediction value of a point to be predicted in a prediction time period by using a pre-established environmental parameter gray prediction model, the environmental parameter prediction module is specifically configured to: determining a first neighboring time period and a second neighboring time period based on the predicted time period; the second adjacent time period, the first adjacent time period and the predicted time period are time periods which are sequentially connected according to time sequence; inputting the first adjacent time period into an environment parameter gray prediction model to obtain a prediction accumulated value under the prediction time period; inputting the second adjacent time period into an environment parameter gray prediction model to obtain a prediction accumulated value under the first adjacent time period; and obtaining the environmental parameter predicted value under the prediction time period according to the prediction accumulated value under the prediction time period and the prediction accumulated value under the first adjacent time period.
In a possible implementation manner, the environmental parameter prediction module 2100 is further configured to pre-process the environmental parameter prediction value after obtaining the environmental parameter prediction value in the prediction time period.
In a possible implementation manner, the dust concentration space-time distribution prediction apparatus 2000 further includes a second model building module, where the second model building module is configured to build a dust concentration prediction model, and when the second model building module builds the dust concentration prediction model, the second model building module is specifically configured to: respectively acquiring sample data of k sampling points; the sample data includes: position information of sampling points, historical data of environmental parameters and historical data of dust concentration; and training model parameters of the neural network model by taking the position information, the environmental parameter historical data and the dust concentration historical data of each sampling point as input data and taking the dust concentration historical data of each sampling point as output data to obtain a dust concentration prediction model.
< apparatus embodiment >
Fig. 3 shows a schematic block diagram of a temporal spatial distribution prediction apparatus of dust concentration according to an embodiment of the present disclosure. As shown in fig. 3, the dust concentration spatiotemporal distribution prediction apparatus 3000 includes a processor 3100 and a memory 3200 for storing executable instructions of the processor 3100. Wherein the processor 3100 is configured to implement the method for spatio-temporal distribution prediction of dust concentration of any of the preceding when executing the executable instructions.
Here, it should be noted that the number of the processors 3100 may be one or more. Meanwhile, in the spatial-temporal distribution prediction apparatus 3000 of dust concentration of the embodiment of the present disclosure, an input device 3300 and an output device 2400 may be further included. The processor 3100, the memory 3200, the input device 3300, and the output device 2400 may be connected by a bus, or may be connected by another method, which is not particularly limited herein.
The memory 3200, which is a computer-readable storage medium, may be used to store software programs, computer-executable programs, and various modules, such as: the disclosed embodiment relates to a program or a module corresponding to a method for predicting the spatial-temporal distribution of dust concentration. The processor 3100 executes various functional applications and data processing of the dust concentration spatiotemporal distribution prediction apparatus 3000 by running software programs or modules stored in the memory 3200.
The input device 3300 may be used to receive input numbers or signals. Wherein the signal may be a key signal generated in connection with user settings and function control of the device/terminal/server. The output device 2400 may include a display device such as a display screen.
< computer-readable storage Medium embodiment >
According to another aspect of the present disclosure, there is also provided a non-transitory computer readable storage medium having stored thereon computer program instructions which, when executed by the processor 3100, implement the spatio-temporal distribution prediction method of dust concentration of any of the foregoing.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A method for predicting the spatial-temporal distribution of dust concentration is characterized by comprising the following steps:
obtaining an environmental parameter prediction value of a point to be predicted in a prediction time period by adopting a pre-established environmental parameter gray prediction model;
obtaining a dust concentration predicted value of the point to be predicted in the prediction time period by using a pre-constructed dust concentration prediction model according to the position information of the point to be predicted and the environmental parameter predicted value;
wherein the environment parameter gray prediction model comprises at least one of an air pressure gray prediction model, a temperature gray prediction model, a wind speed gray prediction model, a wind direction gray prediction model and a humidity gray prediction model.
2. The method according to claim 1, wherein the environment parameter gray prediction model is constructed based on environment parameter actual values collected at sampling points in n preceding time periods of the prediction time period, wherein the value of n is a positive number.
3. The method of claim 2, wherein when the environment parameter gray prediction model is constructed based on the environment parameter actual values collected by the sampling points in the first n time periods of the prediction time period, the method comprises:
acquiring the actual values of the environmental parameters of the sampling points acquired in the first n time periods of the prediction time period, and constructing an actual value sequence of the environmental parameters;
sequentially accumulating the acquired environmental parameter actual values of each time period respectively to obtain an environmental parameter accumulated value corresponding to each time period, and constructing an environmental parameter accumulated value sequence based on the obtained environmental parameter accumulated values;
and constructing and obtaining the environment parameter gray prediction model based on the environment parameter actual value sequence and the environment parameter accumulated value sequence.
4. The method of claim 2, further comprising, after obtaining the environmental parameter gray prediction model:
carrying out posterior difference inspection on the environment parameter gray prediction model to obtain a posterior difference ratio and a small error probability;
and judging whether the environment parameter gray prediction model meets a preset precision grade or not based on the posterior difference ratio and the small error probability, and under the condition that the set precision grade is not met, correcting the environment parameter gray prediction model by adopting a residual error correction method until the environment parameter gray prediction model meets the preset precision grade.
5. The method according to any one of claims 1 to 4, wherein when a pre-built environment parameter grey prediction model is adopted to obtain an environment parameter prediction value of a point to be predicted in a prediction time period, the method comprises the following steps:
determining a first neighboring time period and a second neighboring time period based on the predicted time period; the second adjacent time period, the first adjacent time period and the predicted time period are time periods sequentially connected in time sequence;
inputting the first adjacent time period into the environment parameter gray prediction model to obtain a prediction accumulated value under the prediction time period;
inputting the second adjacent time period into the environment parameter gray prediction model to obtain a prediction accumulated value under the first adjacent time period;
and obtaining the environmental parameter predicted value in the prediction time period according to the prediction accumulated value in the prediction time period and the prediction accumulated value in the first adjacent time period.
6. The method according to any one of claims 1 to 4, wherein after obtaining the predicted value of the environmental parameter at the prediction time period, the method further comprises the step of preprocessing the predicted value of the environmental parameter.
7. The method of any of claims 1 to 4, wherein constructing the dust concentration prediction model comprises:
respectively acquiring sample data of k sampling points; the sample data includes: position information of sampling points, historical data of environmental parameters and historical data of dust concentration;
and training model parameters of a neural network model by taking the position information and the environmental parameter historical data of each sampling point as input data and taking the dust concentration historical data of each sampling point as output data to obtain the dust concentration prediction model.
8. An apparatus for predicting a temporal and spatial distribution of dust concentration, comprising:
the environment parameter prediction module is used for obtaining an environment parameter prediction value of a point to be predicted in a prediction time period by adopting a pre-established environment parameter gray prediction model;
the dust concentration prediction module is used for obtaining a dust concentration prediction value of the point to be predicted in the prediction time period by using a pre-constructed dust concentration prediction model according to the position information of the point to be predicted and the environmental parameter prediction value;
the environment parameter gray prediction model comprises at least one of an air pressure gray prediction model, a temperature gray prediction model, a wind speed gray prediction model, a wind direction gray prediction model and a humidity gray prediction model.
9. An apparatus for predicting a temporal spatial distribution of dust concentration, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to carry out the executable instructions when implementing the method of any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210079569.6A CN114492984A (en) | 2022-01-24 | 2022-01-24 | Method, device, equipment and storage medium for predicting time-space distribution of dust concentration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210079569.6A CN114492984A (en) | 2022-01-24 | 2022-01-24 | Method, device, equipment and storage medium for predicting time-space distribution of dust concentration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114492984A true CN114492984A (en) | 2022-05-13 |
Family
ID=81475050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210079569.6A Pending CN114492984A (en) | 2022-01-24 | 2022-01-24 | Method, device, equipment and storage medium for predicting time-space distribution of dust concentration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114492984A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117139317A (en) * | 2023-10-31 | 2023-12-01 | 米脂冀东水泥有限公司 | Cement solid waste processing system dust treatment device |
| CN117196109A (en) * | 2023-09-15 | 2023-12-08 | 中煤科工集团重庆研究院有限公司 | Underground coal mine dust concentration prediction correction method based on multi-source information fusion |
-
2022
- 2022-01-24 CN CN202210079569.6A patent/CN114492984A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196109A (en) * | 2023-09-15 | 2023-12-08 | 中煤科工集团重庆研究院有限公司 | Underground coal mine dust concentration prediction correction method based on multi-source information fusion |
| CN117196109B (en) * | 2023-09-15 | 2024-04-05 | 中煤科工集团重庆研究院有限公司 | Underground coal mine dust concentration prediction correction method based on multi-source information fusion |
| CN117139317A (en) * | 2023-10-31 | 2023-12-01 | 米脂冀东水泥有限公司 | Cement solid waste processing system dust treatment device |
| CN117139317B (en) * | 2023-10-31 | 2024-02-13 | 米脂冀东水泥有限公司 | Cement solid waste processing system dust treatment device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Formetta et al. | Evaluating performance of simplified physically based models for shallow landslide susceptibility | |
| CN110232471B (en) | Rainfall sensor network node layout optimization method and device | |
| CN105740991A (en) | Climate change prediction method and system for fitting various climate modes based on modified BP neural network | |
| CN114492984A (en) | Method, device, equipment and storage medium for predicting time-space distribution of dust concentration | |
| CN106404620A (en) | Method and system for inverting ground PM 2.5 through combination of geostatistical interpolation and satellite remote sensing | |
| CN111625988A (en) | Bridge health management analysis and prediction system and method based on deep learning | |
| CN113610301B (en) | Prediction algorithm for representing ground settlement time sequence evolution | |
| CN112163375A (en) | Long-time sequence near-surface ozone inversion method based on neural network | |
| CN110595960B (en) | PM2.5 concentration remote sensing estimation method based on machine learning | |
| JP2019085712A (en) | Slope stability determination assistance system | |
| CN107480781A (en) | The nuclear accident Source Term Inversion method of neutral net adaptive Kalman filter | |
| CN115438848A (en) | PM based on deep mixed graph neural network 2.5 Long-term concentration prediction method | |
| CN105678417A (en) | Prediction method and device for tunnel face water inflow of construction tunnel | |
| CN115471679A (en) | Method and intelligent system for synchronously assimilating water level and flow of natural river | |
| CN116402369A (en) | Smart city traffic operation safety monitoring data evaluation system and method | |
| CN116777079A (en) | Desertification intrusion disaster prediction method based on Bayesian interlayer structure model | |
| CN117077554B (en) | Three-dimensional salty tide forecasting method based on ConvGRU | |
| KR102454007B1 (en) | Apparatus and method for calculating solar insolation quantity based on artificial intelligence using artificial satellite observation data | |
| CN116415481A (en) | Regional landslide hazard risk prediction method and device, computer equipment and storage medium | |
| CN113640712B (en) | Prediction method for vertical component of vertical induction magnetic field of ship | |
| Zheng et al. | An ensemble Kalman filter for atmospheric data assimilation: Application to wind tunnel data | |
| CN116110210B (en) | Data-driven landslide hazard auxiliary decision-making method in complex environment | |
| CN115840908B (en) | Method for constructing PM2.5 three-dimensional dynamic monitoring field based on microwave link of LSTM model | |
| CN113408916B (en) | Fire-fighting facility detection and field acceptance assessment system based on intelligent AI and mobile APP | |
| CN113706217A (en) | Heterogeneity-based land overall price measuring and calculating method |
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 | ||
| CB02 | Change of applicant information |
Address after: 518120 rooms 204 and 205, 2 / F, building 1, 23 South Science and Technology Park, No.1, Xihuan South Road, Dapeng street, Dapeng New District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Puda Nuclear Industry Digital Measurement and Control Co.,Ltd. Address before: 518120 rooms 204 and 205, 2 / F, building 1, 23 South Science and Technology Park, No.1, Xihuan South Road, Dapeng street, Dapeng New District, Shenzhen City, Guangdong Province Applicant before: Shenzhen Zhonghe Puda Measurement Technology Co.,Ltd. |
|
| CB02 | Change of applicant information |