A cable laying planning system and method in a slope environment based on big data

Abstract

The present invention discloses a cable laying planning system and method in a slope environment based on big data, belonging to the technical field of cable laying planning. The system includes: a remote sensing information acquisition module, a three-dimensional model building module, a cable laying path analysis module, a comprehensive factor prediction module, and an optimal path planning module; the output end of the remote sensing information acquisition module is connected to the input end of the three-dimensional model building module; the output end of the three-dimensional model building module is connected to the input end of the cable laying path analysis module; the output end of the cable laying path analysis module is connected to the input end of the comprehensive factor analysis module; the output end of the comprehensive factor analysis module is connected to the input end of the optimal path planning module. The present invention also provides a cable laying planning method, which can ensure that the path with the lowest cost is obtained when planning to lay cables under the consideration of various factors.

Description

Technical Field

[0001] The present invention relates to the technical field of cable laying planning, and in particular to a cable laying planning system and method in a slope environment based on big data. Background Art

[0002] Generally speaking, cable laying refers to the way the cable is routed from the distribution box to the electrical equipment or another distribution box. For example, concealed or open laying along the ground, wall, or ceiling, cable laying along bridges, cable trenches, or cable troughs are all common cable laying methods. The appropriate cable laying method is selected according to different environments, conditions, and properties. However, in a slope environment, due to the geographical location, laying will increase certain difficulties.

[0003] Among the current technical means, the laying is generally carried out according to the planned drawings. When encountering a slope environment, a serpentine method is generally adopted for laying. The serpentine method will have bends, and errors will occur at the bends compared with the original planned laying, which usually causes the actual length of the laid cable to be higher than the planned length. There is currently no effective technology to adjust or avoid this error. At the same time, after the cable is laid, it is easy to develop an area due to economic development, business changes and other factors, resulting in the need for the laid cable to be dismantled or modified again. The reduction in service life will have a huge impact on the cost of cable laying, and there is currently no digital technology to accurately analyze it. Summary of the invention

[0004] The purpose of the present invention is to provide a cable laying planning system and method in a slope environment based on big data to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A cable laying planning system in a slope environment based on big data, the system comprising: a remote sensing information acquisition module, a three-dimensional model building module, a cable laying path analysis module, a comprehensive factor prediction module, and an optimal path planning module;

[0007] The remote sensing information acquisition module is used to collect terrain, building, and traffic information data in the cable laying area; the three-dimensional model building module is used to build a three-dimensional model based on the remote sensing information data, and establish a three-dimensional scene for cable laying; the cable laying path analysis module is used to collect terrain factor information in the cable laying area and construct a cable laying path set; the comprehensive factor prediction module is used to obtain the cost factor of cable laying, and respectively construct a first prediction model and a second prediction model to predict the cost error in the cable laying area; the optimal path planning module is used to construct a cost function based on the prediction results of the comprehensive factor prediction model, and select the optimal planning path for cable laying;

[0008] The output end of the remote sensing information acquisition module is connected to the input end of the three-dimensional model building module; the output end of the three-dimensional model building module is connected to the input end of the cable laying path analysis module; the output end of the cable laying path analysis module is connected to the input end of the comprehensive factor analysis module; the output end of the comprehensive factor analysis module is connected to the input end of the optimal path planning module.

[0009] According to the above technical solution, the cable laying path analysis module includes a regional terrain acquisition unit and a laying path construction unit;

[0010] The regional terrain acquisition unit is used to collect terrain factor information data in the cable laying area; the laying path construction unit is used to construct the cable laying path and store all the cable laying paths to obtain a cable laying path set;

[0011] The output end of the regional terrain acquisition unit is connected to the input end of the laying path construction unit; the output end of the laying path construction unit is connected to the input end of the comprehensive factor analysis module.

[0012] According to the above technical solution, the comprehensive factor prediction module includes a first prediction unit and a second prediction unit;

[0013] The first prediction unit is used to obtain the mountain slope environment angle experienced by the cable laying path, establish a first prediction model, calculate the number of serpentine bends of the laid cable, and predict the laying error amount based on big data; the second prediction unit is used to obtain traffic data, residents' life data, and social data in area A, build a second prediction model, and predict whether area A is developed;

[0014] The output end of the first prediction unit is connected to the input end of the optimal path planning module; the output end of the second prediction unit is connected to the input end of the optimal path planning module.

[0015] According to the above technical solution, the optimal path planning module includes a cost function establishment unit and an output unit;

[0016] The cost function establishment unit is used to establish a cost function according to the prediction result of the comprehensive factor prediction module, and calculate the cost of each cable laying path in the cable laying area; the output unit is used to select the cable laying path with the lowest cost as the optimal cable laying planning path for output;

[0017] The output terminal of the cost function building unit is connected to the input terminal of the output unit.

[0018] A cable laying planning method in a slope environment based on big data, the method comprising the following steps:

[0019] S1. Obtain the starting point and the end point of the cable laying, construct a circular area A with the line connecting the starting point and the end point as the diameter, and obtain data information in area A by remote sensing;

[0020] S2, constructing a three-dimensional model of area A, and analyzing terrain factors in area A, wherein the terrain factors include mountain slope environment, rivers, roads, and residential areas;

[0021] S3, constructing a cable laying path set in the three-dimensional model, and obtaining cost factors on each path, wherein the cost factors include the mountain slope environment angle experienced by the path, the width and depth of the river, and whether the area A is developed;

[0022] S4, obtaining the mountain slope environment angle experienced by the cable laying path, calculating the number of serpentine bends of the laid cable, constructing a first prediction model based on big data, and predicting the laying error amount;

[0023] S5, obtaining traffic data, residents' life data, and social data in area A, constructing a second prediction model, and predicting whether area A is developed;

[0024] S6. Based on steps S3-S5, a cost function is constructed, and the path with the lowest cost is selected from the cable laying path set as the optimal planned cable laying path.

[0025] According to the above technical solution, in steps S1-S2, the data information in area A includes all terrain, buildings, and transportation in area A, which can be collected using remote sensing technology; the analysis of terrain factors includes statistics on the number of mountain slope environments and rivers, statistics on the width and length of roads, and statistics on the distribution area of ​​residential areas.

[0026] According to the above technical solution, in step S4, the construction of the first prediction model includes:

[0027] Obtain historical data and construct the average cable length error of the serpentine bend when the slope environment angle is 0 degrees, that is, the cable is laid in a serpentine manner on a flat area, and is recorded as

[0028] A historical data training set is constructed, wherein the historical data training set includes the average cable length errors of different serpentine bends at different mountain slope environment angles. A damping trend model is constructed based on the historical data training set to determine the influence trend of different mountain slope environment angles on the average cable length error of the serpentine bend:

[0029]

[0030] in, is the solution of the horizontal smoothing equation, i.e. the environmental angle of the mountain slope estimated level of is the solution of the trend smoothing equation, i.e., the environmental angle of the mountain slope forecast trends; is the current mountain slope environment angle; is the forecast period; It is the environmental angle of the mountain slope in the period before the current period, that is, 1 represents the period number, not the angle; The angle of the mountain slope environment Actual error average; is the horizontal smoothing parameter; is the smoothing parameter of the trend; is the predicted value of the mountain slope environmental angle at the hth period; is the damping parameter, which is greater than 0 and less than or equal to 1; the slope environment angle of the mountain does not exceed 45 degrees;

[0031] Construct a linear function of the number of serpentine corners under different mountain slope environment angles:

[0032]

[0033] Where, L is the number of serpentine bends; is the environmental angle of the mountain slope; is the influence coefficient;

[0034] Construct the period function:

[0035]

[0036] in, The angles included in each issue;

[0037] Build the first prediction model:

[0038]

[0039] in, The angle of the mountain slope environment is The average value of the predicted serpentine cable length error when .

[0040] During the cable laying process, when encountering a slope environment, according to the relevant recommendations in the national GB 50217-2016 power cable laying specification, a serpentine laying method should be adopted to avoid breakage during collapse. When the serpentine laying method is adopted, at the serpentine bend, due to the difference between computer calculation and manual means, a large number of errors often occur in the serpentine laying method, resulting in the actual length of the cable line being higher than the planned value, and different angles will cause different effects. For example, at the extreme value of 0 degrees, that is, on a flat ground, the general error is the smallest; at the extreme value of 45 degrees, the laying difficulty is greatly increased, and the error generated is also correspondingly larger; 45 degrees is used as the extreme value because in daily practice, it generally exceeds about 30 degrees, and then special cables are used for laying. The present invention considers the ideal state according to daily experiments and appropriately relaxes it. The damping trend model is quoted mainly because Holt's linear model and exponential model have too high prediction values ​​for the future. Based on the small angle range of the present invention, a shorter and more accurate prediction method should be adopted.

[0041] According to the above technical solution, in step S5, the traffic data includes traffic flow, traffic peak time and duration, and the number of traffic intersections; the residents' life data includes the average consumption level of residents, the average economic level of residents, the age distribution of residents, and the number of foreign population; the social data includes housing price factors, the number of education and medical centers, the number of high-tech enterprises, and the number of commercial plazas.

[0042] According to the above technical solution, in step S5, the construction of the second prediction model includes:

[0043] Construct a standard virtual economic indicator data, denoted as M, wherein the standard virtual economic indicator data indicates that when the economic level in region A reaches the standard virtual economic indicator data M, region A is redeveloped by the government;

[0044] Construct functions of virtual economic indicators, traffic data, residents' life data, and social data:

[0045]

[0046] in, is the variable parameter; Normalized data types for traffic data, residents’ life data, and social data; It is a virtual economic indicator;

[0047] A training group is constructed, in which there is historical data of the areas that were redeveloped in group P, and the change parameters are constructed using factor analysis:

[0048]

[0049] in, represents the change parameter of any region from i to j; is the virtual economic index of the region at time j; is the virtual economic index of the region at time i; is the normalized data type of any one of the traffic data, residents’ life data, and social data of the region at time j; is the normalized data type of any one of the traffic data, residents’ life data, and social data of the region at time i, and The corresponding data types are the same; i and j represent cycles.

[0050] i and j represent two periods, such as last year and this year, that is, i represents last year and j represents this year; This represents the change parameter from last year to this year. The change parameter here is It refers to any one of the traffic data, residents' life data, and social data. For example, there were only 10 schools last year, but there are 15 this year, which means that the social data in this area has changed. The change of social data will inevitably drive the development of the economy. There is a certain connection between the degree of change of economic indicators and the change of social data, and this connection is affected by the change parameters.

[0051] The change parameters corresponding to each group of data in the training group are obtained respectively, and the change parameter sets of three data types, namely traffic data, residents' life data and social data, are established. The average values ​​of the change parameters under the three data types, namely traffic data, residents' life data and social data, are obtained respectively as

[0052] According to the above technical solution, in step S6, obtaining the optimal planned path for laying the cable includes:

[0053] Construct the cost function:

[0054]

[0055] Where D represents the total cost of the cable laying path; represents the cable cost; represents the cost of reduced efficiency, that is, the cost that can be reduced for each year of cable laying; R is the expected service life, that is, the number of years from the planned laying time to the standard virtual economic indicator data M according to the second prediction model; Represents the protection cost, which is the cost of making waterproof sets for laying cables; represents the length of the river area that the cable passes through on its route;

[0056] According to the formula:

[0057]

[0058] in, represents the total cost of error caused by the environmental angle of the mountain slope, Represents the total length of the cables laid in the planned path; Represents the unit price for laying the cable;

[0059] in:

[0060]

[0061] Represents the error cost caused by any mountain slope environment angle, Representatives in The number of serpentine corners under the mountain slope environment angle; For all in a path The sum of

[0062] Obtain the costs of all paths in the cable laying path set, and select the smallest one as the optimal planned cable laying path.

[0063] The protection cost here is mainly due to the presence of humid areas such as rivers or ditches in the laying area. When laying cables in this area, it is necessary to protect the cables. It may be that a certain path can greatly reduce the distance by passing through the river, but protection is required. In this case, it is necessary to compare the cost of the protection treatment with the increased cable cost due to the detour. After comprehensive analysis,

[0064] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0065] The present invention uses a remote sensing information acquisition module to collect terrain, building, and traffic information data in the cable laying area; uses a three-dimensional model building module to build a three-dimensional model according to the remote sensing information data, and establishes a three-dimensional scene for the laying of cables; in the three-dimensional scene, the cable laying path analysis module is used to collect terrain factor information in the cable laying area, and a cable laying path set is constructed, all laying paths are analyzed, and a first prediction model and a second prediction model are constructed respectively, and the cable laying error under the slope environment is predicted, and the development trend in the area is also predicted, and the cost is comprehensively calculated, and finally the path with the minimum cost is selected as the optimal planning path for cable laying. The present invention can fully take into account various realistic factors, conduct a comprehensive analysis, so as to achieve accurate results in cost prediction, and finally select the best path for laying, which can meet the country's sustainable development strategy and fill the gap in prediction errors in the field of cable laying. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0067] Figure 1 It is a flow chart of a cable laying planning system and method in a slope environment based on big data of the present invention;

[0068] Figure 2 It is a schematic diagram of the steps of a cable laying planning method in a slope environment based on big data of the present invention. DETAILED DESCRIPTION

[0069] 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.

[0070] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0071] A cable laying planning system in a slope environment based on big data, the system comprising: a remote sensing information acquisition module, a three-dimensional model building module, a cable laying path analysis module, a comprehensive factor prediction module, and an optimal path planning module;

[0072] The remote sensing information acquisition module is used to collect terrain, building, and traffic information data in the cable laying area; the three-dimensional model building module is used to build a three-dimensional model based on the remote sensing information data, and establish a three-dimensional scene for cable laying; the cable laying path analysis module is used to collect terrain factor information in the cable laying area and construct a cable laying path set; the comprehensive factor prediction module is used to obtain the cost factor of cable laying, and respectively construct a first prediction model and a second prediction model to predict the cost error in the cable laying area; the optimal path planning module is used to construct a cost function based on the prediction results of the comprehensive factor prediction model, and select the optimal planning path for cable laying;

[0073] The output end of the remote sensing information acquisition module is connected to the input end of the three-dimensional model building module; the output end of the three-dimensional model building module is connected to the input end of the cable laying path analysis module; the output end of the cable laying path analysis module is connected to the input end of the comprehensive factor analysis module; the output end of the comprehensive factor analysis module is connected to the input end of the optimal path planning module.

[0074] The cable laying path analysis module includes a regional terrain acquisition unit and a laying path construction unit;

[0075] The regional terrain acquisition unit is used to collect terrain factor information data in the cable laying area; the laying path construction unit is used to construct the cable laying path and store all the cable laying paths to obtain a cable laying path set;

[0076] The output end of the regional terrain acquisition unit is connected to the input end of the laying path construction unit; the output end of the laying path construction unit is connected to the input end of the comprehensive factor analysis module.

[0077] The comprehensive factor prediction module includes a first prediction unit and a second prediction unit;

[0078] The first prediction unit is used to obtain the mountain slope environment angle experienced by the cable laying path, establish a first prediction model, calculate the number of serpentine bends of the laid cable, and predict the laying error amount based on big data; the second prediction unit is used to obtain traffic data, residents' life data, and social data in area A, build a second prediction model, and predict whether area A is developed;

[0079] The output end of the first prediction unit is connected to the input end of the optimal path planning module; the output end of the second prediction unit is connected to the input end of the optimal path planning module.

[0080] The optimal path planning module includes a cost function establishment unit and an output unit;

[0081] The cost function establishment unit is used to establish a cost function according to the prediction result of the comprehensive factor prediction module, and calculate the cost of each cable laying path in the cable laying area; the output unit is used to select the cable laying path with the lowest cost as the optimal cable laying planning path for output;

[0082] The output terminal of the cost function building unit is connected to the input terminal of the output unit.

[0083] A cable laying planning method in a slope environment based on big data, the method comprising the following steps:

[0084] S1. Obtain the starting point and the end point of the cable laying, construct a circular area A with the line connecting the starting point and the end point as the diameter, and obtain data information in area A by remote sensing;

[0085] S2, constructing a three-dimensional model of area A, and analyzing terrain factors in area A, wherein the terrain factors include mountain slope environment, rivers, roads, and residential areas;

[0086] S3, constructing a cable laying path set in the three-dimensional model, and obtaining cost factors on each path, wherein the cost factors include the mountain slope environment angle experienced by the path, the width and depth of the river, and whether the area A is developed;

[0087] S4, obtaining the mountain slope environment angle experienced by the cable laying path, calculating the number of serpentine bends of the laid cable, constructing a first prediction model based on big data, and predicting the laying error amount;

[0088] S5, obtaining traffic data, residents' life data, and social data in area A, constructing a second prediction model, and predicting whether area A is developed;

[0089] S6. Based on steps S3-S5, a cost function is constructed, and the path with the lowest cost is selected from the cable laying path set as the optimal planned cable laying path.

[0090] In steps S1-S2, the data information in area A includes all terrain, buildings, and transportation in area A, which can be collected using remote sensing technology; the analysis of terrain factors includes statistics on the number of mountain slope environments and rivers, statistics on the width and length of roads, and statistics on the distribution area of ​​residential areas.

[0091] In step S4, the construction of the first prediction model includes:

[0092] Obtain historical data and construct the average cable length error of the serpentine bend when the slope environment angle is 0 degrees, that is, the cable is laid in a serpentine manner on a flat area, and is recorded as

[0093] A historical data training set is constructed, wherein the historical data training set includes the average cable length errors of different serpentine bends at different mountain slope environment angles. A damping trend model is constructed based on the historical data training set to determine the influence trend of different mountain slope environment angles on the average cable length error of the serpentine bend:

[0094]

[0095] in, is the solution of the horizontal smoothing equation, i.e. the environmental angle of the mountain slope estimated level of is the solution of the trend smoothing equation, i.e., the environmental angle of the mountain slope forecast trends; is the current mountain slope environmental angle; h is the prediction period; It is the environmental angle of the mountain slope in the period before the current period, that is, 1 represents the period number, not the angle; The angle of the mountain slope environment Actual error average; is the horizontal smoothing parameter; is the smoothing parameter of the trend; is the predicted value of the mountain slope environmental angle at the hth period; is the damping parameter, which is greater than 0 and less than or equal to 1; the slope environment angle of the mountain does not exceed 45 degrees;

[0096] Construct a linear function of the number of serpentine corners under different mountain slope environment angles:

[0097]

[0098] Where, L is the number of serpentine bends; is the environmental angle of the mountain slope; is the influence coefficient;

[0099] Construct the period function:

[0100]

[0101] in, The angles included in each issue;

[0102] Build the first prediction model:

[0103]

[0104] in, The angle of the mountain slope environment is The average value of the predicted serpentine cable length error when .

[0105] In step S5, the traffic data includes traffic flow, traffic peak time and duration, and the number of traffic intersections; the residents' life data includes the average consumption level of residents, the average economic level of residents, the age distribution of residents, and the number of foreign population; the social data includes housing price factors, the number of education and medical centers, the number of high-tech enterprises, and the number of commercial plazas.

[0106] In step S5, the construction of the second prediction model includes:

[0107] Construct a standard virtual economic indicator data, denoted as M, wherein the standard virtual economic indicator data indicates that when the economic level in region A reaches the standard virtual economic indicator data M, region A is redeveloped by the government;

[0108] Construct functions of virtual economic indicators, traffic data, residents' life data, and social data:

[0109]

[0110] in, is the variable parameter; Normalized data types for traffic data, residents’ life data, and social data; It is a virtual economic indicator;

[0111] A training group is constructed, in which there is historical data of the areas that were redeveloped in group P, and the change parameters are constructed using factor analysis:

[0112]

[0113] in, represents the change parameter of any region from i to j; is the virtual economic index of the region at time j; is the virtual economic index of the region at time i; is the normalized data type of any one of the traffic data, residents’ life data, and social data of the region at time j; is the normalized data type of any one of the traffic data, residents’ life data, and social data of the region at time i, and The corresponding data types are the same; i and j represent cycles.

[0114] The change parameters corresponding to each group of data in the training group are obtained respectively, and the change parameter sets of three data types, namely traffic data, residents' life data and social data, are established. The average values ​​of the change parameters under the three data types, namely traffic data, residents' life data and social data, are obtained respectively as

[0115] In step S6, obtaining the optimal planned path for laying the cable includes:

[0116] Construct the cost function:

[0117]

[0118] Where D represents the total cost of the cable laying path; represents the cable cost; represents the cost of reduced efficiency, that is, the cost that can be reduced for each year of cable laying; R is the expected service life, that is, the number of years from the planned laying time to the standard virtual economic indicator data M according to the second prediction model; Represents the protection cost, which is the cost of making waterproof sets for laying cables; represents the length of the river area that the cable passes through on its route;

[0119] According to the formula:

[0120]

[0121] in, represents the total cost of error caused by the environmental angle of the mountain slope, Represents the total length of the cables laid in the planned path; Represents the unit price for laying the cable;

[0122] in:

[0123]

[0124] Represents the error cost caused by any mountain slope environment angle, Representatives in The number of serpentine corners under the mountain slope environment angle; For all in a path The sum of

[0125] Obtain the costs of all paths in the cable laying path set, and select the smallest one as the optimal cable laying path.

[0126] In this embodiment:

[0127] There is an area A where cables need to be laid. The best path for laying cables is as follows:

[0128] A first prediction model is constructed to predict the cable error value of the path in the laying path in area A where there is a mountain slope environment; a second prediction model is constructed to predict whether area A is developed;

[0129] The first prediction model construction includes:

[0130] A historical data training set is constructed, wherein the historical data training set includes the average cable length errors of different serpentine bends at different mountain slope environment angles. A damping trend model is constructed based on the historical data training set to determine the influence trend of different mountain slope environment angles on the average cable length error of the serpentine bend:

[0131]

[0132] in, is the solution of the horizontal smoothing equation, i.e. the environmental angle of the mountain slope estimated level of is the solution of the trend smoothing equation, i.e., the environmental angle of the mountain slope forecast trends; is the current mountain slope environmental angle; h is the prediction period; It is the environmental angle of the mountain slope in the period before the current period, that is, 1 represents the period number, not the angle; The angle of the mountain slope environment Actual error average; is the horizontal smoothing parameter; is the smoothing parameter of the trend; is the predicted value of the mountain slope environmental angle at the hth period; is the damping parameter, which is greater than 0 and less than or equal to 1; the slope environment angle of the mountain does not exceed 45 degrees;

[0133] Construct a linear function of the number of serpentine corners under different mountain slope environment angles:

[0134]

[0135] Where, L is the number of serpentine bends; is the environmental angle of the mountain slope; is the influence coefficient;

[0136] Construct the period function:

[0137]

[0138] in, The angles included in each issue;

[0139] Build the first prediction model:

[0140]

[0141] in, The angle of the mountain slope environment is The average value of the predicted serpentine cable length error when .

[0142] The construction of the second prediction model includes:

[0143] Construct a standard virtual economic indicator data, denoted as M, wherein the standard virtual economic indicator data indicates that when the economic level in region A reaches the standard virtual economic indicator data M, region A is redeveloped by the government;

[0144] Construct functions of virtual economic indicators, traffic data, residents' life data, and social data:

[0145]

[0146] in, is the variable parameter; Normalized data types for traffic data, residents’ life data, and social data; It is a virtual economic indicator;

[0147] A training group is constructed, in which there is historical data of the areas that were redeveloped in group P, and the change parameters are constructed using factor analysis:

[0148]

[0149] in, represents the change parameter of any region from i to j; is the virtual economic index of the region at time j; is the virtual economic index of the region at time i; is the normalized data type of any one of the traffic data, residents’ life data, and social data of the region at time j; is the normalized data type of any one of the traffic data, residents’ life data, and social data of the region at time i, and The corresponding data types are the same; i and j represent cycles.

[0150] In this embodiment, the data of the first year and the second year are selected for calculation:

[0151]

[0152] According to the formula:

[0153]

[0154] Traffic data

[0155] Residents’ living data

[0156] Social Data

[0157] All data in the training group are obtained in the above way, and the average value is finally obtained as

[0158] Construct the cost function:

[0159]

[0160] Where D represents the total cost of the cable laying path; represents the cable cost; represents the cost of reduced efficiency, that is, the cost that can be reduced for each year of cable laying; R is the expected service life, that is, the number of years from the planned laying time to the standard virtual economic indicator data M according to the second prediction model; Represents the protection cost, which is the cost of making waterproof sets for laying cables; represents the length of the river area that the cable passes through on its route;

[0161] According to the formula:

[0162]

[0163] in, represents the total cost of error caused by the environmental angle of the mountain slope, Represents the total length of the cables laid in the planned path; Represents the unit price for laying the cable;

[0164] in:

[0165]

[0166] Represents the error cost caused by any mountain slope environment angle, Representatives in The number of serpentine corners under the mountain slope environment angle; For all in a path The sum of

[0167] Obtain the costs of all paths in the cable laying path set, and select the smallest one as the optimal cable laying path.

[0168] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0169] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A cable laying planning method in a slope environment based on big data, characterized in that: The method comprises the following steps: S1. Obtain the starting point and the end point of the cable laying, construct a circular area A with the line connecting the starting point and the end point as the diameter, and obtain data information in area A by remote sensing; S2, constructing a three-dimensional model of area A, and analyzing terrain factors in area A, wherein the terrain factors include mountain slope environment, rivers, roads, and residential areas; S3, constructing a cable laying path set in the three-dimensional model, and obtaining cost factors on each path, wherein the cost factors include the mountain slope environment angle experienced by the path, the width and depth of the river, and whether the area A is developed; S4, obtaining the mountain slope environment angle experienced by the cable laying path, calculating the number of serpentine bends of the laid cable, constructing a first prediction model based on big data, and predicting the laying error amount; S5, obtaining traffic data, residents' life data, and social data in area A, constructing a second prediction model, and predicting whether area A is developed; S6. Based on steps S3-S5, construct a cost function, and select the path with the lowest cost in the cable laying path set as the optimal cable laying planning path; In step S4, the construction of the first prediction model includes: A historical data training set is constructed, wherein the historical data training set includes the average cable length errors of different serpentine bends at different mountain slope environment angles. A damping trend model is constructed based on the historical data training set to determine the influence trend of different mountain slope environment angles on the average cable length error of the serpentine bend: Among them, l θ is the solution of the horizontal smoothing equation, i.e. the estimated level of the mountain slope environmental angle θ; b θ is the solution of the trend smoothing equation, i.e., the predicted trend of the mountain slope environmental angle θ; θ is the mountain slope environmental angle of the current period; h is the predicted period; θ-1 is the mountain slope environmental angle of the period before the current period, i.e., 1 represents the period, not the angle; x θ is the average value of the actual error of the mountain slope environmental angle θ; α is the horizontal smoothing parameter; β is the trend smoothing parameter; is the predicted value of the mountain slope environmental angle at the hth period; is the damping parameter, which is greater than 0 and less than or equal to 1; the slope environment angle of the mountain does not exceed 45 degrees; Construct a linear function of the number of serpentine corners under different mountain slope environment angles: L=k1*θ0 Among them, L is the number of serpentine bends; θ0 is the environmental angle of the mountain slope; k1 is the influence coefficient; Construct the period function: Among them, w is the angle contained in each period; Build the first prediction model: in, is the average value of the predicted serpentine cable length error when the mountain slope environment angle is θ0; In step S6, obtaining the optimal planned path for laying the cable includes: Construct the cost function: D=d1-d2*R+d3*c2 Among them, D represents the total cost of the cable laying route; d1 represents the cable cost; d2 represents the efficiency reduction cost, that is, the cost that can be reduced for each year of cable laying; R is the expected service life, that is, the number of years from the planned laying time to the standard virtual economic indicator data M according to the second prediction model; d3 represents the protection cost, that is, the cost of waterproofing the cable; c2 represents the length of the river area where the cable passes on the route; According to the formula: d1=K 误 +c1*g1 Among them, K 误 represents the total cost of error caused by the environmental angle of the mountain slope, c1 represents the total length of the cable laid in the planned path; g1 represents the unit price of laying the cable; in: K2 represents the error cost caused by any hill slope environment angle, and u represents the number of serpentine corners under the hill slope environment angle of θ0; is the sum of all K2 in a path; Obtain the costs of all paths in the cable laying path set, and select the smallest one as the optimal planned cable laying path.

2. The cable laying planning method in a slope environment based on big data according to claim 1 is characterized by: In steps S1-S2, the data information in area A includes all terrain, buildings, and transportation in area A, which can be collected using remote sensing technology; the analysis of terrain factors includes statistics on the number of mountain slope environments and rivers, statistics on the width and length of roads, and statistics on the distribution area of ​​residential areas.

3. The cable laying planning method in a slope environment based on big data according to claim 2 is characterized by: In step S5, the traffic data includes traffic flow, traffic peak time and duration, and the number of traffic intersections; the residents' life data includes the average consumption level of residents, the average economic level of residents, the age distribution of residents, and the number of foreign population; the social data includes housing price factors, the number of education and medical centers, the number of high-tech enterprises, and the number of commercial plazas.

4. The cable laying planning method in a slope environment based on big data according to claim 3 is characterized by: In step S5, the construction of the second prediction model includes: Construct a standard virtual economic indicator data, denoted as M, wherein the standard virtual economic indicator data indicates that when the economic level in region A reaches the standard virtual economic indicator data M, region A is redeveloped by the government; Construct functions of virtual economic indicators, traffic data, residents' life data, and social data: M0=[(1+y1)*m1]*[(1+y2)*m2]*[(1+y3)*m3] Among them, y1, y2, y3 are variable parameters; m1, m2, m3 are the normalized data types of traffic data, residents’ life data, and social data; M0 is a virtual economic indicator; A training group is constructed, in which there is historical data of the areas that were redeveloped in group P, and the change parameters are constructed using factor analysis: Among them, y i，j represents the change parameter of any region from i to j; M j is the virtual economic index of the region at time j; M i is the virtual economic index of the region at time i; m j is the normalized data type of any one of the traffic data, residents’ life data, and social data of the region at time j; m i is the normalized data type of any one of the traffic data, resident life data, and social data of the region at time i, and is related to m j The corresponding data types are the same; i and j represent periods, i<j; The changing parameters corresponding to each group of data in the P groups in the training group are obtained respectively, and a set of changing parameters for the three data types of traffic data, residents' life data, and social data are established. The average values ​​of the changing parameters under the three data types of traffic data, residents' life data, and social data are obtained as y1, y2, and y3 respectively.

5. A cable laying planning system in a slope environment based on big data, using a cable laying planning method in a slope environment based on big data as claimed in claim 1, characterized in that: The system includes: remote sensing information acquisition module, three-dimensional model building module, cable laying path analysis module, comprehensive factor prediction module, and optimal path planning module; The remote sensing information acquisition module is used to collect terrain, building, and traffic information data in the cable laying area; the three-dimensional model building module is used to build a three-dimensional model based on the remote sensing information data, and establish a three-dimensional scene for cable laying; the cable laying path analysis module is used to collect terrain factor information in the cable laying area and construct a cable laying path set; the comprehensive factor prediction module is used to obtain the cost factor of cable laying, and respectively construct a first prediction model and a second prediction model to predict the cost error in the cable laying area; the optimal path planning module is used to construct a cost function based on the prediction results of the comprehensive factor prediction model, and select the optimal planning path for cable laying; The output end of the remote sensing information acquisition module is connected to the input end of the three-dimensional model building module; the output end of the three-dimensional model building module is connected to the input end of the cable laying path analysis module; the output end of the cable laying path analysis module is connected to the input end of the comprehensive factor analysis module; the output end of the comprehensive factor analysis module is connected to the input end of the optimal path planning module.

6. The cable laying planning system in a slope environment based on big data according to claim 5 is characterized by: The cable laying path analysis module includes a regional terrain acquisition unit and a laying path construction unit; The regional terrain acquisition unit is used to collect terrain factor information data in the cable laying area; The laying path construction unit is used to construct a laying path for the cable, and store all the cable laying paths to obtain a cable laying path set; The output end of the regional terrain acquisition unit is connected to the input end of the laying path construction unit; The output end of the laying path construction unit is connected to the input end of the comprehensive factor analysis module.

7. The cable laying planning system in a slope environment based on big data according to claim 5 is characterized by: The comprehensive factor prediction module includes a first prediction unit and a second prediction unit; The first prediction unit is used to obtain the mountain slope environment angle experienced by the cable laying path, establish a first prediction model, calculate the number of serpentine bends of the laid cable, and predict the laying error amount based on big data; the second prediction unit is used to obtain traffic data, residents' life data, and social data in the area, build a second prediction model, and predict whether the area is developed; The output end of the first prediction unit is connected to the input end of the optimal path planning module; the output end of the second prediction unit is connected to the input end of the optimal path planning module.

8. The cable laying planning system in a slope environment based on big data according to claim 5, characterized in that: The optimal path planning module includes a cost function establishment unit and an output unit; The cost function establishment unit is used to establish a cost function according to the prediction result of the comprehensive factor prediction module, and calculate the cost of each cable laying path in the cable laying area; the output unit is used to select the cable laying path with the lowest cost as the optimal cable laying planning path for output; The output terminal of the cost function building unit is connected to the input terminal of the output unit.

Images