A wind speed prediction method and system based on big data

Abstract

This invention discloses a wind speed prediction method and system based on big data, comprising: collecting historical wind speed data of a target area; obtaining a first information relationship between wind speed information and wind direction information, temperature information, and air pressure information based on time information; obtaining a second information relationship between historical wind speed data and location information based on the location information of the target area; and processing the first and second information relationships using a linear fitting method to construct a wind speed prediction model for the target area. The wind speed prediction model is used to predict the locational distribution and trend of wind speed by acquiring current wind speed data of the target area. This invention considers not only wind speed changes over time but also wind speed changes in space. By combining these considerations with a linear regression method, the prediction performance is significantly improved, providing data support for wind-resistant design in building construction.

Description

Technical Field

[0001] This invention relates to the field of structural wind engineering, and in particular to a wind speed prediction method and system based on big data. Background Technology

[0002] Structural wind engineering is based on the theories of meteorology, bluff body aerodynamics, and random vibration of structures. It uses one or more methods, such as wind tunnel testing, field measurement, or numerical simulation, to analyze and evaluate the structural response, such as displacement and acceleration, under wind loads, as well as the wind environment around the building, in order to ensure the safety and comfort of the structure.

[0003] The wind environment surrounding a building directly affects its safety, necessitating wind-resistant design. Structural wind-resistant design primarily comprises two aspects: wind-resistant design of the building's surface cladding and wind-resistant design of the main structure. The key reference factor for wind-resistant design is the wind speed at the building's location. This requires considering not only current wind speeds but also historical data and forecasting future wind speeds to ensure the building meets wind-resistant design requirements. Therefore, a big data-based wind speed prediction method and system are urgently needed to predict wind speeds in the building's area, providing data support for the building's design and construction. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide a wind speed prediction method and system based on big data. This method uses big data prediction to perform time-based and space-based wind speed predictions based on data such as time, wind direction, wind speed, temperature, and air pressure. Furthermore, by combining these prediction results using linear regression, the final wind speed prediction result is obtained, providing data support for building design and construction.

[0005] To achieve the above technical objectives, this invention provides a wind speed prediction method based on big data, comprising the following steps:

[0006] Collect historical wind speed data for the target area, including time information, wind direction information, wind speed information, temperature information, and air pressure information.

[0007] Based on time information, the first information relationship between wind speed information and wind direction information, temperature information, and air pressure information is obtained;

[0008] Based on the location information of the target area, a second information relationship between historical wind speed data and location information is obtained, where the location information is used to represent the geographical location information of the target area;

[0009] Based on the linear fitting method, the first information relationship and the second information relationship are processed to construct a wind speed prediction model for the target area. The wind speed prediction model is used to predict the location distribution and trend of wind speed by acquiring the current wind speed data of the target area.

[0010] Preferably, during the process of acquiring historical wind speed data, wind direction information, wind speed information, temperature information, and air pressure information are acquired based on time information;

[0011] Based on the distribution characteristics of time information, wind direction information, wind speed information, temperature information, and air pressure information are classified to construct historical wind speed data.

[0012] Preferably, in the process of generating the first information relationship, based on the correlation function model, the first relationship between wind direction information and wind speed information, the second relationship between temperature information and wind speed information, and the third relationship between air pressure information and wind speed information are obtained respectively.

[0013] Generate the first information relation based on the first relation, the second relation, and the third relation.

[0014] Preferably, in the process of generating the first information relationship, a first wind speed prediction sub-model based on time information is constructed using a linear regression method through the first relationship, the second relationship, and the third relationship, and is used to generate the first information relationship.

[0015] Preferably, in the process of generating the second information relationship, without considering time information, a fourth relationship between historical wind speed data and location information is obtained to generate the second information relationship based on location information.

[0016] Preferably, in the process of obtaining the second information relationship, based on the ANN model with a single hidden layer, and according to the obtained fourth and fifth relationships, a second wind speed prediction sub-model for wind speed spatial prediction is constructed to generate the second information relationship.

[0017] Preferably, in the process of constructing the wind speed prediction model, a wind speed prediction model is constructed based on the first wind speed prediction sub-model and the second wind speed prediction sub-model by using a linear fitting method. The wind speed prediction model is used to predict the wind speed based on the time information and location information by acquiring wind direction information, temperature information, and air pressure information.

[0018] This invention discloses a wind speed prediction system based on big data, comprising:

[0019] The data acquisition module is used to collect historical wind speed data of the target area. The historical wind speed data includes time information, wind direction information, wind speed information, temperature information, and air pressure information.

[0020] The first data processing module is used to obtain the first information relationship between wind speed information and wind direction information, temperature information, and air pressure information based on time information;

[0021] The second data processing module is used to obtain the second information relationship between wind speed information, location information, and time information based on the location information of the target area. The location information is used to represent the geographical location information of the target area.

[0022] The wind speed prediction module is used to process the first information relationship and the second information relationship based on the linear fitting method to construct a wind speed prediction model for the target area. The wind speed prediction model is used to predict the location distribution and trend of wind speed by acquiring the current wind speed data of the target area.

[0023] The present invention discloses the following technical effects:

[0024] This invention considers not only wind speed variations over time but also wind speed variations in space. By combining these considerations with linear regression, the predictive performance is significantly improved, providing data support for wind-resistant design in building construction. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart illustrating the method described in an embodiment of the present invention;

[0027] Figure 2 This is a system structure diagram according to an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0029] Example 1: As an example, such as Figure 1 As shown, this invention provides a wind speed prediction method based on big data, including the following steps:

[0030] Collect historical wind speed data for the target area, including time information, wind direction information, wind speed information, temperature information, and air pressure information.

[0031] Based on time information, the first information relationship between wind speed information and wind direction information, temperature information, and air pressure information is obtained;

[0032] Based on the location information of the target area, a second information relationship between historical wind speed data and location information is obtained, where the location information is used to represent the geographical location information of the target area;

[0033] Based on the linear fitting method, the first information relationship and the second information relationship are processed to construct a wind speed prediction model for the target area. The wind speed prediction model is used to predict the location distribution and trend of wind speed by acquiring the current wind speed data of the target area.

[0034] More preferably, in the process of acquiring historical wind speed data, the present invention acquires wind direction information, wind speed information, temperature information, and air pressure information based on time information;

[0035] Based on the distribution characteristics of time information, wind direction information, wind speed information, temperature information, and air pressure information are classified to construct historical wind speed data.

[0036] More preferably, in the process of generating the first information relationship, based on the correlation function model, the present invention obtains the first relationship between wind direction information and wind speed information, the second relationship between temperature information and wind speed information, and the third relationship between air pressure information and wind speed information.

[0037] Generate the first information relation based on the first relation, the second relation, and the third relation.

[0038] More preferably, in the process of generating the first information relationship, the present invention uses a linear regression method to construct a first wind speed prediction sub-model based on time information through the first relationship, the second relationship, and the third relationship, which is used to generate the first information relationship.

[0039] More preferably, in the process of generating the second information relationship, the present invention obtains the fourth relationship between historical wind speed data and location information without considering time information, and generates the second information relationship based on location information.

[0040] More preferably, in the process of obtaining the second information relationship, the present invention, based on an ANN model with a single hidden layer, constructs a second wind speed prediction sub-model for wind speed spatial prediction based on the obtained fourth and fifth relationships, which is used to generate the second information relationship.

[0041] More preferably, in the process of constructing the wind speed prediction model, based on the first wind speed prediction sub-model and the second wind speed prediction sub-model, the present invention constructs the wind speed prediction model through a linear fitting method. The wind speed prediction model is used to predict the wind speed based on the time information and location information by acquiring wind direction information, temperature information and air pressure information.

[0042] The wind speed prediction method mentioned in this invention mainly relies on big data prediction based on spatiotemporal data. Spatiotemporal data is represented by spatial data and temporal data. Spatial data can be understood as data on different regional locations at a specific moment, without considering temporal data. This data can represent different target locations or different spatial locations of the same target location. Temporal data can be understood as the current and historical data of the target location without considering spatial data. From the perspective of the characteristics of spatiotemporal data, these data include time, wind direction, wind speed, temperature, air pressure, etc.

[0043] Taking wind direction data as an example, in the process of acquiring wind direction data, we can obtain wind direction data in different spatial features based on spatial data to analyze the influence of space on direction. We can also obtain wind direction data in different time periods based on temporal data. These different time periods can be understood as daytime, nighttime, or time periods based on solar terms or months. By analyzing and summarizing historical data corresponding to different times, we can obtain the changing patterns of wind direction over time, and then obtain step-by-step trend charts for two different phenomena. Then, by obtaining the trend charts corresponding to different data separately and merging them into a single trend chart, we can see the mutual influence between each type of data, and further analyze the distribution characteristics and trends of wind speed in a certain spatiotemporal region. This analysis process is implemented through a big data analysis model. Therefore, when considering the wind speed trend at a certain spatiotemporal feature point in a target area, only the current wind speed data needs to be measured to predict the future trend, thus providing corresponding data support for building design and construction.

[0044] When analyzing time-based data, we can see that the data are linearly distributed, and the analysis process can be achieved through linear analysis methods. However, when analyzing spatial data, the data distribution is non-linear. In this case, deep learning methods are needed for identification and analysis. Here, we choose an ANN deep learning network to achieve wind speed prediction based on spatial data.

[0045] Example 2: As an example, such as Figure 2 As shown, this invention discloses a wind speed prediction system based on big data, used to implement the wind speed prediction method mentioned in Example 1, including:

[0046] The data acquisition module is used to collect historical wind speed data of the target area. The historical wind speed data includes time information, wind direction information, wind speed information, temperature information, and air pressure information.

[0047] The first data processing module is used to obtain the first information relationship between wind speed information and wind direction information, temperature information, and air pressure information based on time information;

[0048] The second data processing module is used to obtain the second information relationship between wind speed information, location information, and time information based on the location information of the target area. The location information is used to represent the geographical location information of the target area.

[0049] The wind speed prediction module is used to process the first information relationship and the second information relationship based on the linear fitting method to construct a wind speed prediction model for the target area. The wind speed prediction model is used to predict the location distribution and trend of wind speed by acquiring the current wind speed data of the target area.

[0050] Example 3: As an example, the present invention also discloses a computer program for implementing a wind speed prediction method according to the big data analysis method mentioned in Example 1, forming an executable program, embedding it into a data terminal, and predicting the wind speed of the target area by collecting wind speed data of the target area.

[0051] Example 4: As an example, the present invention also discloses a portable storage device for carrying a runnable program as mentioned in Example 3, which, after being connected to a data terminal, acquires wind speed data and makes predictions to obtain wind speed data of a target area.

[0052] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

[0053] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0054] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A wind speed prediction method based on big data, characterized in that, Includes the following steps: Collect historical wind speed data for the target area, wherein the historical wind speed data includes time information, wind direction information, wind speed information, temperature information, and air pressure information; Based on the time information, a first information relationship is obtained between the wind speed information and the wind direction information, the temperature information, and the air pressure information; Based on the location information of the target area, a second information relationship between the historical wind speed data and the location information is obtained, wherein the location information is used to represent the geographical location information of the target area; Based on the linear fitting method, the first information relationship and the second information relationship are processed to construct a wind speed prediction model for the target area. The wind speed prediction model is used to predict the location distribution and trend of wind speed by acquiring the current wind speed data of the target area. In the process of acquiring historical wind speed data, based on the time information, the wind direction information, the wind speed information, the temperature information, and the air pressure information are acquired; Based on the distribution characteristics of the time information, the wind direction information, wind speed information, temperature information, and air pressure information are classified to construct the historical wind speed data; In the process of generating the first information relationship, based on the relevant function model, the first relationship between the wind direction information and the wind speed information, the second relationship between the temperature information and the wind speed information, and the third relationship between the air pressure information and the wind speed information are obtained respectively. The first information relationship is generated based on the first relationship, the second relationship, and the third relationship; In the process of generating the first information relationship, a first wind speed prediction sub-model based on time information is constructed using the first relationship, the second relationship, and the third relationship, based on the linear regression method, to generate the first information relationship; In the process of generating the second information relationship, without considering the time information, a fourth relationship between the historical wind speed data and the location information is obtained, and the second information relationship based on the location information is generated. In the process of obtaining the second information relationship, based on the ANN model with a single hidden layer and according to the obtained fourth relationship, a second wind speed prediction sub-model for wind speed spatial prediction is constructed to generate the second information relationship. In the process of constructing the wind speed prediction model, the wind speed prediction model is constructed based on the first wind speed prediction sub-model and the second wind speed prediction sub-model by using a linear fitting method. The wind speed prediction model is used to predict the wind speed based on the time information and the location information by obtaining the wind direction information, the temperature information, and the air pressure information.

2. A wind speed prediction system based on big data, used to implement the wind speed prediction method based on big data as described in claim 1, characterized in that, include: The data acquisition module is used to collect historical wind speed data of the target area, wherein the historical wind speed data includes time information, wind direction information, wind speed information, temperature information, and air pressure information; The first data processing module is used to obtain a first information relationship between the wind speed information and the wind direction information, the temperature information, and the air pressure information based on the time information; The second data processing module is used to obtain a second information relationship between the wind speed information, the location information, and the time information based on the location information of the target area, wherein the location information is used to represent the geographical location information of the target area; The wind speed prediction module is used to process the first information relationship and the second information relationship based on a linear fitting method to construct a wind speed prediction model for the target area. The wind speed prediction model is used to predict the location distribution and trend of wind speed by acquiring the current wind speed data of the target area.

Images