A method and system for predicting dust concentration at construction sites

Abstract

The present invention discloses a method for predicting dust concentration at a construction site, comprising the following steps: setting a plurality of detection points in the construction site, obtaining dust concentration data and environmental information at any time of the detection points; using a neural network model to construct an initial model for predicting dust concentration at the construction site; obtaining dust concentration data and environmental information at a plurality of different times of each detection point, correcting the dust concentration data of each detection point, and obtaining dust concentration correction data of each detection point; obtaining a dust concentration prediction model at the construction site; inputting the real-time environmental information of the detection point to be predicted into the dust concentration prediction model, and obtaining the real-time dust concentration correction data of the detection point; and then processing the dust concentration correction data, and obtaining the dust concentration prediction data of the detection point to be predicted. The present invention provides a method and system for predicting dust concentration at a construction site, and predicts the dust concentration at the construction site according to the real-time environmental information of the construction site.

Description

Technical Field

[0001] The present invention relates to the field of construction site management, and more specifically, to a method and system for predicting dust concentration at a construction site. Background Art

[0002] Dust is an open pollution source that enters the atmosphere due to dust on the ground being blown up by wind, human factors, or other factors. It is an important component of the total suspended particulate matter in the ambient air. In construction sites, dust is mainly controlled by watering when the dust is heavy. At present, there are dust concentration detection devices for construction sites on the market, but there is no prediction of dust concentration for construction sites, and it is impossible to prepare in advance when the environment changes. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for predicting dust concentration at a construction site, which predicts the dust concentration at a construction site based on real-time temperature data, humidity data, air pressure data, wind speed data and rainfall data of the construction site.

[0004] In order to achieve these purposes and other advantages according to the present invention, a method for predicting dust concentration at a construction site is provided, comprising the following steps:

[0005] Setting up multiple detection points in the construction site, obtaining dust concentration data and environmental information at any time at the detection points, wherein the environmental information at least includes temperature data, humidity data, air pressure data, wind speed data and rainfall data at the corresponding detection points;

[0006] The neural network model is used to construct an initial model for predicting dust concentration at construction sites;

[0007] Acquire the dust concentration data and the environmental information of each detection point at a plurality of different times, correct the dust concentration data of each detection point, and obtain dust concentration correction data of each detection point;

[0008] The dust concentration correction data of each detection point is used as the expected output, and the environmental information is used as the input sample to train the initial model for predicting dust concentration, so as to obtain a dust concentration prediction model for the construction site;

[0009] Input the real-time environmental information of the detection point to be predicted into the dust concentration prediction model to obtain the real-time dust concentration correction data of the detection point, and then process the dust concentration correction data to obtain the dust concentration prediction data of the detection point to be predicted;

[0010] In the construction site dust concentration prediction method, when the dust concentration data of each detection point is corrected, the following steps are included:

[0011] According to the main source of dust at the detection point, the dust concentration data is processed for the first time:

[0012] W1= A W0

[0013] In the above formula, W1 is the data obtained after the dust concentration data is processed for the first time; W0 is the dust concentration data; A is the first correction coefficient;

[0014] According to the construction stage of the detection point, W1 is modified:

[0015] W2= B W1

[0016] In the above formula, W2 is the corrected data of the detection point; B is the second correction coefficient;

[0017] In the construction site dust concentration prediction method, the calculation method of the first correction coefficient is as follows:

[0018] Take the dust concentration data of each detection point at multiple different times in the same period of time and calculate its average value , select multiple The smallest value is ,but

[0019] A =

[0020] In the construction site dust concentration prediction method, the second correction coefficient is calculated as follows:

[0021] Take the dust concentration data at each detection point at each construction stage at multiple different times and calculate the average value , select multiple The smallest value is ,but

[0022] B = .

[0023] Preferably, in the method for predicting dust concentration at a construction site, the neural network model is a BP neural network model.

[0024] The present invention also provides an intelligent pipeline defect detection system, which adopts any of the methods described above, including multiple data detection devices and processors, the detection points are all equipped with the data detection devices, and the dust concentration data and environmental information of the detection points at any time are obtained through the data detection devices, and the data detection devices are electrically connected to the processor.

[0025] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described above when executing the program.

[0026] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above-described methods when executed by a processor.

[0027] The construction site dust concentration prediction method and system of the present invention are based on historical data modeling of the construction site, and predict the dust concentration of the construction site according to the real-time temperature data, humidity data, air pressure data, wind speed data and rainfall data of the construction site.

[0028] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a flow chart of the present invention. DETAILED DESCRIPTION

[0030] The present invention is further described in detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.

[0031] It should be noted that, in the description of the present invention, the terms "lateral", "longitudinal", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" etc. indicating orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0032] like Figure 1 As shown, an embodiment of the present invention provides a method for predicting dust concentration at a construction site, comprising the following steps:

[0033] Setting up multiple detection points in the construction site, obtaining dust concentration data and environmental information at any time at the detection points, wherein the environmental information at least includes temperature data, humidity data, air pressure data, wind speed data and rainfall data at the corresponding detection points;

[0034] A neural network model is used to construct an initial model for predicting dust concentration at a construction site; the neural network model is a BP neural network model;

[0035] Acquire the dust concentration data and the environmental information of each detection point at a plurality of different times, correct the dust concentration data of each detection point, and obtain dust concentration correction data of each detection point;

[0036] The dust concentration correction data of each detection point is used as the expected output, and the environmental information is used as the input sample to train the initial model for predicting dust concentration, so as to obtain a dust concentration prediction model for the construction site;

[0037] By inputting the real-time environmental information of the detection point that needs to be predicted into the dust concentration prediction model, the real-time dust concentration correction data of the detection point can be obtained, and then the dust concentration prediction data of the detection point that needs to be predicted can be obtained by processing the dust concentration correction data.

[0038] In this embodiment, the BP neural network model is a multi-layer network that performs weight training on nonlinear differentiable functions. Its greatest feature is that it can realize a highly nonlinear mapping of the system from the pm space composed of the pattern vectors p of m input neurons to the yn space n (the number of output nodes) with the help of sample data alone, without the need to establish a mathematical model of the system. The BP neural network model is proposed to solve the weight coefficient optimization of the multi-layer forward neural network; therefore, the BP neural network model also implies that the topological structure of the neural network is a multi-layer forward network without feedback. Therefore, the multi-layer forward network without feedback is sometimes called the BP neural network model. In the actual application of artificial neural networks, 80% to 90% of the neural network models use the BP neural network model or its variations. The BP neural network model is a learning algorithm for feedforward multi-layer networks.

[0039] Preferably, as another embodiment of the present invention, when the dust concentration data of each detection point is corrected, the following steps are included:

[0040] According to the main source of dust at the detection point, the dust concentration data is processed for the first time:

[0041] W1= A W0

[0042] In the above formula, W1 is the data obtained after the dust concentration data is processed for the first time; W0 is the dust concentration data; A is the first correction coefficient;

[0043] According to the construction stage of the detection point, W1 is modified:

[0044] W2= B W1

[0045] In the above formula, W2 is the corrected data of the detection point; B is the second correction coefficient.

[0046] Preferably, as another embodiment of the present invention, the calculation method of the first correction coefficient is as follows:

[0047] Take the dust concentration data of each detection point at multiple different times in the same period of time and calculate its average value , select multiple The smallest value is ,but

[0048] A =

[0049] Preferably, as another embodiment of the present invention, the calculation method of the second correction coefficient is as follows:

[0050] Take the dust concentration data at each detection point at each construction stage at multiple different times and calculate the average value , select multiple The smallest value is ,but

[0051] B =

[0052] Preferably, as another embodiment of the present invention, the neural network model is a BP neural network model.

[0053] The present invention also provides an intelligent pipeline defect detection system, which adopts any of the methods described above, including multiple data detection devices and processors, the detection points are all equipped with the data detection devices, and the dust concentration data and environmental information of the detection points at any time are obtained through the data detection devices, and the data detection devices are electrically connected to the processor.

[0054] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described above when executing the program.

[0055] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above-described methods when executed by a processor.

[0056] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the embodiments shown and described herein.

Claims

1. A method for predicting dust concentration at a construction site, characterized in that: The following steps are involved: Setting up multiple detection points in the construction site, obtaining dust concentration data and environmental information at any time at the detection points, wherein the environmental information at least includes temperature data, humidity data, air pressure data, wind speed data and rainfall data at the corresponding detection points; The neural network model is used to construct an initial model for predicting dust concentration at construction sites; Acquire the dust concentration data and the environmental information of each detection point at a plurality of different times, correct the dust concentration data of each detection point, and obtain dust concentration correction data of each detection point; The dust concentration correction data of each detection point is used as the expected output, and the environmental information is used as the input sample to train the initial model for predicting dust concentration, so as to obtain a dust concentration prediction model for the construction site; Input the real-time environmental information of the detection point to be predicted into the dust concentration prediction model to obtain the real-time dust concentration correction data of the detection point, and then process the dust concentration correction data to obtain the dust concentration prediction data of the detection point to be predicted; When the dust concentration data of each detection point is corrected, the following steps are included: According to the main source of dust at the detection point, the dust concentration data is processed for the first time: W1= A W0 In the above formula, W1 is the data obtained after the dust concentration data is processed for the first time; W0 is the dust concentration data; A is the first correction coefficient; According to the construction stage of the detection point, W1 is modified: W2= B W1 In the above formula, W2 is the corrected data of the detection point; B is the second correction coefficient; The calculation method of the first correction coefficient is as follows: Take the dust concentration data of each detection point at multiple different times in the same period of time and calculate its average value , select multiple The smallest value is ,but A = The calculation method of the second correction coefficient is as follows: Take the dust concentration data at each detection point at each construction stage at multiple different times and calculate the average value , select multiple The smallest value is ,but B = 。 2. A method for predicting dust concentration at a construction site as claimed in claim 1, characterized in that: The neural network model is a BP neural network model.

3. An intelligent pipeline defect detection system, using the method according to any one of claims 1 to 2, characterized in that: It includes multiple data detection devices and processors. The detection points are all equipped with the data detection devices, and the dust concentration data and environmental information of the detection points at any time are obtained through the data detection devices. The data detection devices are electrically connected to the processor.

4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 2 are implemented.

5. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Images