A Transmission Line Planning Method Based on Artificial Intelligence

Abstract

The present invention relates to the field of artificial intelligence technology, and specifically discloses a transmission line planning method based on artificial intelligence, comprising the following steps: S1: gridding the planning area, collecting engineering geological conditions at the grid intersections, and determining the construction difficulty coefficient at the grid intersections based on an optimized construction difficulty recognition model; S2: planning a selected path according to the grid intersections, the starting point and the end point of the transmission line, generating coordinate points, and obtaining a target image by connecting two adjacent coordinate points by a straight line; setting a construction difficulty coefficient level, and determining a target ratio of the target image in each construction difficulty coefficient level; S3: calculating a reference value of the selected path according to the target image and the target ratio, and using the selected path corresponding to the minimum reference value as a planning scheme for the transmission line. The present invention processes complex engineering geological conditions through an artificial intelligence model, thereby optimizing the path planning of the transmission line.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a power transmission line planning method based on artificial intelligence. Background Art

[0002] Artificial intelligence is a discipline that studies the use of computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It mainly includes the principles of how computers achieve intelligence and how to create computers that are similar to human brain intelligence, so that computers can achieve higher-level applications.

[0003] Transmission lines refer to power transmission facilities used to transmit electricity from power plants to load centers (such as cities, industrial areas, etc.). Transmission lines usually transmit the electricity produced by power plants in the form of high voltage to substations or distribution networks through overhead lines or underground cables, and then transmit it to various users after reducing the voltage.

[0004] In the existing technology, the planning of transmission lines still relies mainly on manual methods. In areas with complex terrain, manual judgment is often limited by personal experience and it is difficult to fully consider various environmental factors, especially when dealing with large-scale data and multiple variables (such as complex engineering geological conditions). Misjudgment or omission is prone to occur. Artificial intelligence, with its powerful data processing capabilities and highly automated decision-making process, can avoid the above situation to a great extent. Therefore, it is necessary to study a transmission line planning method based on artificial intelligence. Summary of the invention

[0005] The purpose of the present invention is to provide a transmission line planning method based on artificial intelligence to solve the following technical problems:

[0006] In the existing technology, the planning of transmission lines still relies mainly on manual methods. When faced with areas with complex terrain, manual judgment is often limited by personal experience and it is difficult to fully consider various environmental factors, especially when dealing with large-scale data and the interweaving influence of multiple variables (such as complex engineering geological conditions), which can easily lead to misjudgments or omissions.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] A transmission line planning method based on artificial intelligence comprises the following steps:

[0009] S1: Determine the planning area according to the starting point and the end point of the transmission line, divide the planning area into grids, the length and width of the grids are both preset lengths, collect the engineering geological conditions at the intersections of the grids, and determine the construction difficulty coefficient at the intersections of the grids based on the optimized construction difficulty identification model;

[0010] S2: Plan the selected path according to the grid intersection, the starting point and the end point of the transmission line, and generate the coordinate point (b, D b ), D b The construction difficulty coefficient of the b-th grid intersection on the selected path is represented by connecting two adjacent coordinate points by a straight line to obtain a target image;

[0011] Determine the range of construction difficulty coefficient [D min , D max ], D min =min(Djh),D max =max(Djh),Djh=(D1,D2,…,D n ), D n Indicates the construction difficulty coefficient corresponding to the nth grid intersection, and sets a number of construction difficulty coefficient levels from low to high at preset construction difficulty coefficient intervals within the construction difficulty coefficient range, and determines that the target image is within the cth construction difficulty coefficient range [Dks c ,Djs c ], determine the domain value range Y corresponding to this part of the target image, and determine the target ratio C c , the target ratio represents the ratio of the domain value range Y to the domain of the target image;

[0012] S3: Calculate the reference value K of the path to be selected, and the calculation formula is:

[0013] ;

[0014] Among them, djtot represents the total number of construction difficulty coefficient levels, [0, xqz] represents the domain value range of the target image f(x), and ε is the preset correction coefficient;

[0015] The minimum reference value Kmin is obtained, and the candidate path corresponding to the minimum reference value Kmin is used as the planning scheme of the transmission line.

[0016] As a further solution of the present invention: in the step S2, the process of planning the selected path according to the grid intersection, the starting point and the end point of the transmission line specifically includes:

[0017] A path starting from the starting point of the transmission line and passing through any number of grid intersections to reach the end point of the transmission line is taken as an initial path, where two adjacent grid intersections on the initial path are connected by a straight line, and the same grid intersections in the same initial path do not appear repeatedly;

[0018] The initial paths are sorted according to the length of the distance. The longer the distance, the lower the ranking. The first m initial paths in the sorting are selected as the candidate paths, where m is a preset number.

[0019] As a further solution of the present invention: in the step S1, the process of determining the construction difficulty coefficient at the grid intersection based on the pre-trained engineering geological condition recognition model specifically includes:

[0020] Establishing a database, wherein the database stores engineering geological conditions with marked construction difficulty levels;

[0021] A construction difficulty recognition model is established through a deep learning model, and the model is trained and optimized using a labeled database, and the engineering geological conditions at the grid intersections are input into the optimized construction difficulty recognition model to output the construction difficulty of the grid intersections;

[0022] The grid intersections are sorted according to the degree of construction difficulty. The greater the construction difficulty, the lower the ranking of the grid intersections, thereby obtaining a difficulty ranking;

[0023] Let the initial construction difficulty coefficient of the grid intersection at the ath position in the sorting be a, and map it to (0, 1] by a normalization method. The value A after the initial construction difficulty coefficient a is mapped to (0, 1] is recorded as the construction difficulty coefficient of the grid intersection at the ath position in the sorting.

[0024] As a further solution of the present invention: in the step S2, the process of planning the selected path according to the grid intersection, the starting point and the end point of the transmission line also includes the following steps:

[0025] When, among the candidate paths, there is a grid intersection whose initial construction difficulty coefficient is greater than or equal to a preset initial construction difficulty coefficient threshold, the corresponding candidate path is removed, and the initial path at the m+1th position in the sorting is used as the candidate path.

[0026] As a further solution of the present invention: a reference line segment is obtained by connecting the starting point and the end point of the transmission line by a straight line, a straight line passing through the starting point of the reference line segment and perpendicular to the reference line segment is used as the starting line, the foot of the perpendicular is point A, and a point on the starting line that is at a distance μ*L from point A is used as the starting reference point, where μ is a preset coefficient and L is the length of the reference line segment;

[0027] Determine the end line and the end reference point on the end line, connect the starting reference point and the end reference point to obtain a rectangular area, and use the rectangular area as the planning area.

[0028] As a further solution of the present invention: in the step S3, in the process of determining the planning scheme of the transmission line, when there are two or more reference values ​​that are the same and are the minimum reference values, the candidate path with the longest distance is selected as the planning scheme of the transmission line.

[0029] As a further solution of the present invention: in the step S1, the engineering geological conditions at the grid intersections are obtained based on drone surveying.

[0030] As a further solution of the present invention: another method for determining the target image specifically includes: fitting the coordinate points to obtain a fitting curve, and using the image of the fitting curve as the target image.

[0031] Beneficial effects of the present invention: In the present invention, the planning area is first determined according to the starting point and the end point of the transmission line. The two positions between which the transmission line is planned are the starting point and the end point of the transmission line. The purpose of determining the planning area is to prevent the increase of the cost due to the excessive length of the transmission line. The length and width of the grid intersection are set based on historical experience. Then the planning area is gridded and the engineering geological conditions at the grid intersection are collected. The construction difficulty coefficient at the grid intersection is determined based on the optimized construction difficulty identification model. It can be understood that different engineering geological conditions correspond to different construction difficulties. Quantifying the construction difficulty through the optimized construction difficulty identification model can reduce the error caused by human processing. The target image is drawn according to the construction difficulty coefficient of the grid intersection on the selected path, that is, an image reflecting the change of construction difficulty on the selected path; then, several construction difficulty coefficient levels are set within the construction difficulty coefficient range, and the target ratio of the target image in each construction difficulty coefficient level is determined; it is worth noting that the target ratio reflects the situation that the construction difficulty on the selected path belongs to different construction difficulty levels, and the product of the target ratio and the construction difficulty level to the total construction difficulty level ratio reflects the distribution characteristics of different selected paths in construction difficulty, thereby ensuring that the final planning scheme avoids high construction difficulty to the greatest extent; finally, the reference value of the selected path is calculated, and the planning scheme of the transmission line is determined according to the reference value. The present invention processes complex engineering geological conditions through an artificial intelligence model, thereby optimizing the path planning of the transmission line. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention will be further described below in conjunction with the accompanying drawings.

[0033] Figure 1 It is a flow chart of a power transmission line planning method based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] See also Figure 1 As shown, the present invention is a transmission line planning method based on artificial intelligence, comprising the following steps:

[0036] S1: Determine the planning area according to the starting point and the end point of the transmission line, divide the planning area into grids, the length and width of the grids are both preset lengths, collect the engineering geological conditions at the intersections of the grids, and determine the construction difficulty coefficient at the intersections of the grids based on the optimized construction difficulty identification model;

[0037] S2: Plan the selected path according to the grid intersection, the starting point and the end point of the transmission line, and generate the coordinate point (b, D b ), D b The construction difficulty coefficient of the b-th grid intersection on the selected path is represented by connecting two adjacent coordinate points by a straight line to obtain a target image;

[0038] Determine the range of construction difficulty coefficient [D min , D max ], D min =min(Djh),D max =max(Djh),Djh=(D1,D2,…,D n ), D n Indicates the construction difficulty coefficient corresponding to the nth grid intersection, and sets a number of construction difficulty coefficient levels from low to high at preset construction difficulty coefficient intervals within the construction difficulty coefficient range, and determines that the target image is within the cth construction difficulty coefficient range [Dks c ,Djs c ], determine the domain value range Y corresponding to this part of the target image, and determine the target ratio C c , the target ratio represents the ratio of the domain value range Y to the domain of the target image;

[0039] S3: Calculate the reference value K of the path to be selected, and the calculation formula is:

[0040] ;

[0041] Among them, djtot represents the total number of construction difficulty coefficient levels, [0, xqz] represents the domain value range of the target image f(x), and ε is the preset correction coefficient;

[0042] The minimum reference value Kmin is obtained, and the candidate path corresponding to the minimum reference value Kmin is used as the planning scheme of the transmission line.

[0043] It should be noted that, first, the planning area is determined according to the starting point and the end point of the transmission line. The two positions between which the transmission line is planned are the starting point and the end point of the transmission line. The purpose of determining the planning area is to prevent the increase of the cost due to the excessive length of the transmission line. The length and width of the grid intersection are set based on historical experience. Then, the planning area is gridded and the engineering geological conditions at the grid intersection are collected. The construction difficulty coefficient at the grid intersection is determined based on the optimized construction difficulty identification model. It can be understood that different engineering geological conditions correspond to different construction difficulties. Quantifying the construction difficulty through the optimized construction difficulty identification model can reduce the error caused by human processing. Then, the selected path is planned, and the target image is drawn according to the construction difficulty coefficient of the grid intersection on the selected path, that is, the image reflecting the change of construction difficulty on the selected path. After that, several construction difficulty coefficient levels are set within the construction difficulty coefficient range, and the target proportion of the target image in each construction difficulty coefficient level is determined. It is worth noting that the cth construction difficulty coefficient range is [Dks c ,Djs c ], Dks c Indicates the construction difficulty coefficient at the beginning of the cth construction difficulty coefficient range, Djs c It represents the construction difficulty coefficient at the end of the cth construction difficulty coefficient range. The target ratio reflects the situation that the construction difficulty on the selected path belongs to different construction difficulty levels. The product of the target ratio and the proportion of the construction difficulty level to the total construction difficulty level reflects the distribution characteristics of the construction difficulty of different selected paths, thereby ensuring that the final planning scheme avoids high construction difficulty to the greatest extent. Finally, the reference value of the selected path is calculated, and the planning scheme of the transmission line is determined based on the reference value.

[0044] In another preferred implementation of the present invention, in step S2, the process of planning a path to be selected according to the grid intersection, the starting point and the end point of the transmission line specifically includes:

[0045] A path starting from the starting point of the transmission line and passing through any number of grid intersections to reach the end point of the transmission line is taken as an initial path, where two adjacent grid intersections on the initial path are connected by a straight line, and the same grid intersections in the same initial path do not appear repeatedly;

[0046] The initial paths are sorted according to the length of the distance. The longer the distance, the lower the ranking. The first m initial paths in the sorting are selected as the candidate paths, where m is a preset number.

[0047] It is worth noting that in order to ensure that all possible paths are fully explored, thereby covering different engineering geological conditions and construction difficulties, multiple paths starting from the starting point, passing through multiple grid intersections and reaching the end point can fully consider different path combinations to avoid missing any potential preferred paths; the reason for selecting the first m initial paths in the sorting as candidate paths is that the longer the path, the greater the construction difficulty and material consumption, which will lead to an increase in the cost of the actual construction of the transmission line in the later stage.

[0048] In another preferred implementation of the present invention, in step S1, the process of determining the construction difficulty coefficient at the grid intersection based on the pre-trained engineering geological condition recognition model specifically includes:

[0049] Establishing a database, wherein the database stores engineering geological conditions with marked construction difficulty levels;

[0050] A construction difficulty recognition model is established through a deep learning model, and the model is trained and optimized using a labeled database, and the engineering geological conditions at the grid intersections are input into the optimized construction difficulty recognition model to output the construction difficulty of the grid intersections;

[0051] The grid intersections are sorted according to the degree of construction difficulty. The greater the construction difficulty, the lower the ranking of the grid intersections, thereby obtaining a difficulty ranking;

[0052] Let the initial construction difficulty coefficient of the grid intersection at the ath position in the sorting be a, and map it to (0, 1] by a normalization method. The value A after the initial construction difficulty coefficient a is mapped to (0, 1] is recorded as the construction difficulty coefficient of the grid intersection at the ath position in the sorting.

[0053] It is understandable that by using deep learning models to identify the degree of construction difficulty, the subjective errors caused by manual judgment can be reduced. The engineering geological conditions are complex and diverse. Through the model, the relationship between geological conditions and construction difficulty can be systematically learned and automatically identified, ensuring the accuracy and consistency of the construction difficulty assessment. The deep learning model refers to an artificial intelligence model that uses a multi-layer neural network to simulate the learning process of the human brain, and is used to automatically extract features from a large amount of data and perform pattern recognition and decision-making. Its core idea is to use the structure of multi-layer neurons (network layers) to allow the model to gradually extract more advanced abstract features from the data to achieve automated prediction tasks. Establish a labeled construction difficulty database, use these historical data to train the model, so that the model can effectively predict the construction difficulty when facing different geological conditions. The initial construction difficulty coefficient is mapped to the (0,1] interval through the normalization method, which can ensure that the construction difficulty coefficient is within a standard range for easy comparison, while eliminating the absolute numerical differences in construction difficulty between different regions, which is convenient for subsequent path optimization calculations.

[0054] In another preferred implementation of the present invention, in the step S2, the process of planning the selected path according to the grid intersection, the starting point and the end point of the transmission line further includes the following steps:

[0055] When, among the candidate paths, there is a grid intersection whose initial construction difficulty coefficient is greater than or equal to a preset initial construction difficulty coefficient threshold, the corresponding candidate path is removed, and the initial path at the m+1th position in the sorting is used as the candidate path.

[0056] It should be noted that when the construction difficulty coefficient of a certain grid intersection reaches or exceeds the preset threshold, it means that the construction difficulty at the grid intersection is relatively high, which may increase the complexity and cost of construction. In order to reduce construction risks and costs, directly removing the path can avoid encountering extremely difficult situations in actual construction, thereby improving the feasibility of the planning scheme; high construction difficulty means that more resources and time are required, which may lead to a sharp increase in project costs. Removing these paths helps optimize resource allocation and ensure that the selected path is optimal in terms of technology and economy; through reasonable path screening and substitution mechanisms, the diversity and feasibility of the paths are guaranteed. Eliminating high-difficulty paths and adding new paths in a timely manner ensures that the final output plan is feasible and economical in construction.

[0057] In another preferred implementation of the present invention, a reference line segment is obtained by connecting the starting point and the end point of the transmission line by a straight line, a straight line passing through the starting point of the reference line segment and perpendicular to the reference line segment is used as the starting line, the foot of the perpendicular is point A, and a point on the starting line that is at a distance μ*L from point A is used as the starting reference point, where μ is a preset coefficient and L is the length of the reference line segment;

[0058] Determine the end line and the end reference point on the end line, connect the starting reference point and the end reference point to obtain a rectangular area, and use the rectangular area as the planning area.

[0059] It should be noted that by connecting the starting point and the end point of the transmission line with a straight line, a reference line segment is generated, and a vertical line is used to define the boundary of the planning area, thereby ensuring that the planning area is based on a reasonable geometric structure and avoiding the planning area being too broad or inaccurate, thereby reducing the complexity of calculation and simplifying the subsequent path selection and construction difficulty analysis; the selection of rectangular areas facilitates the gridding of the area and the analysis of construction difficulty and path planning at each grid intersection. The rectangular geometric structure is simple and easy to calculate, and can be efficiently applied in a variety of planning algorithms, reducing the amount of calculation required to process complex geometric shapes.

[0060] In another preferred implementation of the present invention, in the step S3, when determining the planning scheme of the transmission line, when there are two or more reference values ​​that are the same and are the minimum reference values, the candidate path with the longest distance is selected as the planning scheme of the transmission line.

[0061] It is understandable that, when the reference values ​​are the same, a longer path usually means that the construction difficulty is more evenly and dispersedly distributed throughout the path. In contrast, a shorter path may pass through certain areas with higher construction difficulty, thus facing greater challenges in local construction. A longer path can avoid the concentrated construction pressure in these high-difficulty areas, disperse the difficulty over a larger area, and reduce the complexity of local construction. In path planning, areas with high construction difficulty are often accompanied by more uncertainties and risks. Choosing a longer path can help avoid these local high-difficulty construction areas and ensure that the entire construction process is smoother and more controllable.

[0062] In another preferred implementation of the present invention, in the step S1, the engineering geological conditions at the grid intersections are obtained based on drone surveying.

[0063] It is worth noting that drones can quickly fly over large areas of terrain and conduct surveying and mapping through high-precision sensors to obtain detailed geological condition data. Compared with traditional manual surveys, drones can more efficiently complete the collection of large-scale geological data, especially in remote or complex terrain, which can save a lot of time and manpower.

[0064] In another preferred implementation of the present invention, another method for determining the target image specifically includes: fitting the coordinate points to obtain a fitting curve, and using the image of the fitting curve as the target image.

[0065] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A transmission line planning method based on artificial intelligence, characterized in that: The following steps are involved: S1: Determine the planning area according to the starting point and the end point of the transmission line, divide the planning area into grids, the length and width of the grids are both preset lengths, collect the engineering geological conditions at the intersections of the grids, and determine the construction difficulty coefficient at the intersections of the grids based on the optimized construction difficulty identification model; S2: planning a candidate path according to the grid intersections, the starting point and the end point of the transmission line, generating a coordinate point (b, Db), where Db represents the construction difficulty coefficient of the b-th grid intersection on the candidate path, and connecting two adjacent coordinate points by straight lines to obtain a target image; Determine the construction difficulty coefficient range [Dmin, Dmax], Dmin = min(Djh), Dmax = max(Djh), Djh = (D1, D2, ..., Dn), Dn represents the construction difficulty coefficient corresponding to the nth grid intersection, set a number of construction difficulty coefficient levels from low to high at preset construction difficulty coefficient intervals within the construction difficulty coefficient range, determine the portion of the target image within the cth construction difficulty coefficient range [Dksc, Djsc], determine the definition domain value range Y corresponding to the portion of the target image, and determine the target ratio Cc, the target ratio represents the ratio of the definition domain value range Y to the definition domain of the target image; S3: Calculate the reference value K of the path to be selected, and the calculation formula is: Wherein, djtot represents the total number of construction difficulty coefficient levels, [0, xqz] represents the value range of the definition domain of the target image f(x), and ε is the preset correction coefficient; Obtaining a minimum reference value Kmin, and taking the candidate path corresponding to the minimum reference value Kmin as a planning scheme for the transmission line; When, among the candidate paths, there is a grid intersection whose initial construction difficulty coefficient is greater than or equal to a preset initial construction difficulty coefficient threshold, the corresponding candidate path is removed, and the initial path at the m+1th position in the sorting is used as the candidate path; When there are two or more reference values ​​that are the same and the minimum reference value, the candidate path with the longest distance is selected as the planning scheme for the transmission line.

2. The method for power transmission line planning based on artificial intelligence according to claim 1, characterized in that: In the step S2, the process of planning the selected path according to the grid intersection, the starting point and the end point of the transmission line specifically includes: A path starting from the starting point of the transmission line and passing through any number of grid intersections to reach the end point of the transmission line is taken as an initial path, where two adjacent grid intersections on the initial path are connected by a straight line, and the same grid intersections in the same initial path do not appear repeatedly; The initial paths are sorted according to the length of the distance. The longer the distance, the lower the ranking. The first m initial paths in the sorting are selected as the candidate paths, where m is a preset number.

3. The power transmission line planning method based on artificial intelligence according to claim 2, characterized in that: In step S1, the process of determining the construction difficulty coefficient at the grid intersection based on the pre-trained engineering geological condition recognition model specifically includes: Establishing a database, wherein the database stores engineering geological conditions with marked construction difficulty levels; A construction difficulty recognition model is established through a deep learning model, and the model is trained and optimized using a labeled database, and the engineering geological conditions at the grid intersections are input into the optimized construction difficulty recognition model to output the construction difficulty of the grid intersections; The grid intersections are sorted according to the degree of construction difficulty. The greater the construction difficulty, the lower the ranking of the grid intersections, thereby obtaining a difficulty ranking; Let the initial construction difficulty coefficient of the grid intersection at the ath position in the sorting be a, and map it to (0, 1] by a normalization method. The value A after the initial construction difficulty coefficient a is mapped to (0, 1] is recorded as the construction difficulty coefficient of the grid intersection at the ath position in the sorting.

4. The method for power transmission line planning based on artificial intelligence according to claim 1, characterized in that: A reference line segment is obtained by connecting the starting point and the end point of the transmission line by a straight line, a straight line passing through the starting point of the reference line segment and perpendicular to the reference line segment is used as the starting line, the foot of the perpendicular is point A, and a point on the starting line that is at a distance μ*L from point A is used as the starting reference point, where μ is a preset coefficient and L is the length of the reference line segment; Determine the end line and the end reference point on the end line, connect the starting reference point and the end reference point to obtain a rectangular area, and use the rectangular area as the planning area.

5. The method for power transmission line planning based on artificial intelligence according to claim 1, characterized in that: In the step S1, the engineering geological conditions at the grid intersections are obtained based on drone surveying.

6. The method for power transmission line planning based on artificial intelligence according to claim 1, characterized in that: Another method for determining the target image specifically includes: fitting the coordinate points to obtain a fitting curve, and using the image of the fitting curve as the target image.

Images