Underground cable path intelligent optimization design method and system based on ant colony algorithm

Abstract

The invention discloses an underground cable path intelligent optimization design method and system based on an ant colony algorithm, and relates to the technical field of electric power engineering.The method comprises the steps that an underground cable planning system is connected to receive initial cable laying path planning, and multiple continuous target laying points are extracted according to the planning; a plurality of environment test areas are established according to a preset environment adaptation distance, environment adaptation tests are performed in the environment test areas, test results are generated, laying control parameter optimization is performed according to the results, and path planning based on an ant colony algorithm is adopted, so that laying control parameters are optimized. According to the method, a subsequent laying path is optimized in real time in combination with a dynamic pheromone rule driven by environmental perception, a mixed multi-target ant colony algorithm and quantum heuristic pheromone updating, the method further relates to a corresponding system, electronic equipment and a computer readable storage medium, and the efficiency and adaptability of underground cable path planning are improved.

Description

Technical Field

[0001] This invention relates to the field of power engineering technology, and more specifically, to a method and system for intelligent optimization design of underground cable routes based on ant colony algorithm. Background Technology

[0002] In modern urban infrastructure construction and industrial development, underground cable laying is a crucial project. With the continuous growth of electricity demand and the increasingly refined requirements of urban planning for space utilization, underground cable networks are becoming increasingly complex and extensive. Traditional cable route planning relies heavily on manual experience and simple algorithms, making it difficult to fully consider the complex and ever-changing underground environmental factors, such as differences in geological conditions, interference from surrounding underground facilities, and the construction difficulties in different areas. This can easily lead to problems such as cost overruns, extended construction periods, and potential safety hazards in cable operation. At the same time, the underground environment is highly uncertain. For example, encountering underground caves, cultural relics, or undetected pipelines can significantly reduce the feasibility of pre-planned routes. Frequent route changes not only increase construction costs but may also affect the normal operation of surrounding areas. Therefore, how to use advanced algorithms to achieve intelligent optimization design of underground cable routes to improve laying efficiency, reduce costs, and ensure cable operation safety has become a key issue that urgently needs to be addressed.

[0003] Existing underground cable laying route planning suffers from problems such as poor adaptability to environmental changes, limited optimization effects, and insufficient interaction with the construction site. Summary of the Invention

[0004] To overcome the problems of poor adaptability to environmental changes, limited optimization effect, and insufficient interaction with the construction site in existing underground cable laying path planning, this invention discloses an intelligent optimization design method and system for underground cable paths based on ant colony algorithm, which can effectively solve the above-mentioned technical problems.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0006] The intelligent optimization design method for underground cable routes based on ant colony algorithm includes the following steps:

[0007] Connect to the underground cable planning system and receive the initial cable laying path plan;

[0008] Based on the initial cable laying path plan, multiple continuous target laying points are extracted, and multiple environmental test areas are established for the multiple continuous target laying points according to the preset environmental adaptation distance.

[0009] Specifically, this includes: obtaining multiple segmented laying paths with the multiple consecutive target laying points as endpoints based on the initial cable laying path planning;

[0010] Obtain the environmental constraints and pre-laying speeds corresponding to the multiple segmented laying paths;

[0011] The environmental constraints and the pre-laying speed are input into the environmental simulation model to perform environmental adaptation simulation, generating the environmental adaptation distances corresponding to the multiple segmented laying paths. The environmental simulation model is trained based on historical environmental adaptation data of the same geographical area and the same cable laying equipment.

[0012] The environmental adaptation distance is amplified according to a preset tolerance constraint to generate the preset environmental adaptation distance corresponding to the segmented laying path;

[0013] According to the preset environmental adaptation distance, the multiple environmental test areas are configured in the multiple segmented laying paths;

[0014] Extract the first environmental test area from the plurality of environmental test areas and obtain the corresponding first target laying point;

[0015] According to the initial cable laying path planning, the cable laying equipment is controlled to travel to the first target laying point. When the cable laying equipment is detected to have entered the first environmental test area, an environmental adaptation test is conducted, and a first environmental adaptation test result is generated.

[0016] Based on the results of the first environmental adaptation test, the laying control parameters of the first laying section between the first environmental test area and the first target laying point are optimized to generate the first segment laying optimization result.

[0017] The first laying segment is optimized and controlled based on the first segment laying optimization results. At the same time, path planning based on ant colony algorithm is adopted, combined with dynamic pheromone rules driven by environmental perception, hybrid multi-objective ant colony algorithm and quantum heuristic pheromone update, to optimize the subsequent laying path in real time.

[0018] Preferably, configuring the multiple environmental testing areas in the multiple segmented laying paths according to the preset environmental adaptation distance includes:

[0019] Configure preset environment adaptation test distance;

[0020] The preset environmental adaptation test distance is used as the area length of the plurality of environmental test areas, and the preset environmental adaptation distance is used as the distance from the plurality of environmental test areas to the plurality of continuous target laying points. The plurality of environmental test areas are configured in the plurality of segmented laying paths.

[0021] The generation of the first environmental adaptation test results includes:

[0022] Establish environmental test sample constraints, wherein the environmental test sample constraints include a first test sample constraint and a second test sample constraint, the first test sample constraint is that the environmental adaptation threshold meets a first preset threshold, and the second test sample constraint is that the environmental adaptation threshold meets a second preset threshold, the first preset threshold and the second preset threshold are set according to cable laying requirements and equipment performance;

[0023] Configure environment adaptation test data based on the first test sample constraints and the second test sample constraints;

[0024] The environmental adaptation test data is input into the controller of the cable laying equipment for environmental adaptation testing, and the environmental adaptation control deviation is analyzed to generate the first environmental adaptation test result.

[0025] Preferably, configuring the environmental adaptation test data according to the first test sample constraints and the second test sample constraints includes:

[0026] When the cable laying equipment is detected to have entered the first environmental test area, the first real-time laying status of the cable laying equipment is obtained.

[0027] Based on the first real-time laying status, continuous environmental adaptation stage data is generated by combining the first test sample constraints and the second test sample constraints.

[0028] The environmental adaptation test data is generated from the continuous environmental adaptation phase data, wherein the environmental adaptation test data includes multiple environmental adaptation control nodes.

[0029] Preferably, generating the first environmental adaptation test result includes:

[0030] The environmental characteristics around the cable laying path are collected, and combined with the segmented environmental constraints, the controller of the cable laying equipment is modeled for environmental adaptation, generating the first environmental adaptation simulation model.

[0031] The environmental adaptation test data is input into the first environmental adaptation simulation model to perform environmental adaptation simulation and generate a standard environmental adaptation state change time series.

[0032] The environmental adaptation test data is input into the controller of the cable laying equipment to conduct environmental adaptation tests, and the timing of changes in the actual test environmental adaptation status is recorded.

[0033] After comparing the time and space alignment of the standard environmental adaptation state change sequence with the actual test environmental adaptation state change sequence, environmental adaptation state deviations corresponding to multiple spatiotemporal nodes are generated.

[0034] The first environmental adaptation test result is generated based on the environmental adaptation state deviations corresponding to the multiple spatiotemporal nodes.

[0035] Preferably, generating the first segmented laying optimization result includes:

[0036] Extract the first laying speed and the first laying point location in the first laying section;

[0037] Based on the results of the first environmental adaptation test, determine whether the environmental adaptation control deviation meets the preset deviation threshold.

[0038] If not, after correcting the first laying speed according to the environmental adaptation control deviation, the environmental adaptation distance is simulated, and the first laying point is optimized according to the prediction results to generate the first segment laying optimization result. At the same time, the ant colony algorithm is used in combination with the dynamic pheromone rules driven by environmental perception to update the path pheromone and optimize the subsequent path. Specifically, if the segment has an environmental adaptation problem, the pheromone concentration of the path and the surrounding paths is reduced; if the environmental adaptation is good, the pheromone concentration of the path and the surrounding paths is increased.

[0039] Preferably, during the cable laying process, a hybrid multi-objective ant colony algorithm is used to optimize the path, wherein the multi-objectives include the shortest path length, the lowest environmental adaptation risk, and the lowest laying cost.

[0040] The specific steps are as follows: Initialize the ant colony and set parameters such as the number of ants and the number of iterations;

[0041] Each ant selects the next laying node and constructs a path based on dynamic pheromone rules driven by environmental perception and heuristic information.

[0042] Calculate multiple target values ​​for each ant's constructed path, and update the pheromone on the path using a quantum heuristic pheromone update rule. Specifically, for paths with high fitness, adjust the pheromone concentration through a quantum rotation gate to enhance their attractiveness to subsequent ants; for paths with low fitness, reduce the pheromone concentration.

[0043] Repeat the above steps until the preset number of iterations is reached, and select the path with the highest fitness as the current optimal path.

[0044] Preferably, it further includes:

[0045] AR-MR equipment is deployed at the cable laying site to acquire real-time three-dimensional information of the underground environment and the real-time status of cable laying.

[0046] The path optimized by the ant colony algorithm is imported into the AR-MR system and integrated with the actual underground environment for display.

[0047] Operators use AR-MR equipment to adjust and verify the path in real time. If a conflict is found between the path and the actual environment, the operator will promptly report it to the ant colony algorithm and re-optimize the path. At the same time, the laying control parameters will be further optimized based on the laying process simulated by the AR-MR system.

[0048] An electronic device includes: a memory and at least one processor, the memory storing instructions, wherein at least one processor invokes the instructions in the memory to cause the device to perform the steps of the method described above.

[0049] A computer-readable storage medium having instructions stored thereon, which, when executed by a processor, implement the steps of the method described above.

[0050] An intelligent optimization design system for underground cable routes based on ant colony algorithm includes:

[0051] The initial path receiving module is used to connect to the underground cable planning system and receive the initial cable laying path plan.

[0052] The environmental testing area establishment module is used to extract multiple continuous target laying points according to the initial cable laying path planning, and to establish multiple environmental testing areas for the multiple continuous target laying points according to the preset environmental adaptation distance.

[0053] The first target laying point acquisition module is used to extract the first environmental test area from the multiple environmental test areas and acquire the corresponding first target laying point;

[0054] The first environmental adaptation test result generation module is used to control the cable laying equipment to travel to the first target laying point according to the initial cable laying path planning. When the cable laying equipment is detected to enter the first environmental test area for environmental adaptation test, the first environmental adaptation test result is generated.

[0055] The laying control parameter optimization module is used to optimize the laying control parameters for the first laying section between the first environmental test area and the first target laying point based on the first environmental adaptation test results, and generate the first segmented laying optimization results.

[0056] The laying optimization control module is used to perform laying optimization control on the first laying section based on the first segment laying optimization result;

[0057] The ant colony algorithm optimization module is used to optimize the cable laying path in real time by using ant colony algorithm-based path planning, combined with environmental perception-driven dynamic pheromone rules, hybrid multi-objective ant colony algorithm and quantum heuristic pheromone update.

[0058] The AR-MR collaborative optimization module integrates the path optimized by the ant colony algorithm with the actual underground environment through the AR-MR collaborative optimization mechanism. This allows operators to adjust and verify the path in real time and optimize the laying control parameters based on the simulated laying process.

[0059] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention connects to an underground cable planning system, receives initial cable laying path planning, extracts multiple continuous target laying points, establishes multiple environmental test areas based on preset environmental adaptation distances and environmental simulation models, performs environmental adaptation simulation and testing on segmented laying paths, generates environmental adaptation distances, generates preset environmental adaptation distances by amplifying the environmental adaptation distances, and configures environmental test areas; during the laying process, environmental adaptation tests are performed in real time, test results are generated, and laying control parameters are optimized accordingly. Simultaneously, an ant colony algorithm is used to optimize subsequent laying paths in real time, combined with dynamic pheromone rules driven by environmental perception, adjusting pheromone concentrations based on environmental adaptation conditions to optimize subsequent paths; furthermore, this method also integrates AR-MR equipment to acquire real-time three-dimensional information of the underground environment and the real-time status of cable laying, merging the optimized path with the actual underground environment for display, supporting operators to adjust and verify paths in real time, and optimizing laying control parameters based on the simulated laying process. Attached Figure Description

[0060] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other embodiments can be derived from the provided drawings without creative effort.

[0061] Figure 1 This is a diagram illustrating the steps of the method of the present invention;

[0062] Figure 2 This is a system structure diagram of the present invention. Detailed Implementation

[0063] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this patent.

[0064] To better illustrate this embodiment, some parts in the accompanying drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions;

[0065] It will be understood by those skilled in the art that certain well-known structures and their descriptions may be omitted in the accompanying drawings.

[0066] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0067] Example 1

[0068] The intelligent optimization design method for underground cable routes based on ant colony algorithm includes the following steps:

[0069] Connect to the underground cable planning system and receive the initial cable laying path plan;

[0070] Based on the initial cable laying path plan, multiple continuous target laying points are extracted, and multiple environmental test areas are established for the multiple continuous target laying points according to the preset environmental adaptation distance.

[0071] Specifically, this includes: obtaining multiple segmented laying paths with the multiple consecutive target laying points as endpoints based on the initial cable laying path planning;

[0072] Obtain the environmental constraints and pre-laying speeds corresponding to the multiple segmented laying paths;

[0073] The environmental constraints and the pre-laying speed are input into the environmental simulation model to perform environmental adaptation simulation, generating the environmental adaptation distances corresponding to the multiple segmented laying paths. The environmental simulation model is trained based on historical environmental adaptation data of the same geographical area and the same cable laying equipment.

[0074] The environmental adaptation distance is amplified according to a preset tolerance constraint to generate the preset environmental adaptation distance corresponding to the segmented laying path;

[0075] According to the preset environmental adaptation distance, the multiple environmental test areas are configured in the multiple segmented laying paths;

[0076] Extract the first environmental test area from the plurality of environmental test areas and obtain the corresponding first target laying point;

[0077] According to the initial cable laying path planning, the cable laying equipment is controlled to travel to the first target laying point. When the cable laying equipment is detected to have entered the first environmental test area, an environmental adaptation test is conducted, and a first environmental adaptation test result is generated.

[0078] Based on the results of the first environmental adaptation test, the laying control parameters of the first laying section between the first environmental test area and the first target laying point are optimized to generate the first segment laying optimization result.

[0079] The first laying segment is optimized and controlled based on the first segment laying optimization results. At the same time, path planning based on ant colony algorithm is adopted, combined with dynamic pheromone rules driven by environmental perception, hybrid multi-objective ant colony algorithm and quantum heuristic pheromone update, to optimize the subsequent laying path in real time.

[0080] According to the preset environmental adaptation distance, the multiple environmental test areas are configured in the multiple segmented laying paths, including:

[0081] Configure preset environment adaptation test distance;

[0082] The preset environmental adaptation test distance is used as the area length of the plurality of environmental test areas, and the preset environmental adaptation distance is used as the distance from the plurality of environmental test areas to the plurality of continuous target laying points. The plurality of environmental test areas are configured in the plurality of segmented laying paths.

[0083] The generation of the first environmental adaptation test results includes:

[0084] Establish environmental test sample constraints, wherein the environmental test sample constraints include a first test sample constraint and a second test sample constraint, the first test sample constraint is that the environmental adaptation threshold meets a first preset threshold, and the second test sample constraint is that the environmental adaptation threshold meets a second preset threshold, the first preset threshold and the second preset threshold are set according to cable laying requirements and equipment performance;

[0085] Configure environment adaptation test data based on the first test sample constraints and the second test sample constraints;

[0086] The environmental adaptation test data is input into the controller of the cable laying equipment for environmental adaptation testing, and the environmental adaptation control deviation is analyzed to generate the first environmental adaptation test result.

[0087] The environmental adaptation test data configured based on the first test sample constraints and the second test sample constraints includes:

[0088] When the cable laying equipment is detected to have entered the first environmental test area, the first real-time laying status of the cable laying equipment is obtained.

[0089] Based on the first real-time laying status, continuous environmental adaptation stage data is generated by combining the first test sample constraints and the second test sample constraints.

[0090] The environmental adaptation test data is generated from the continuous environmental adaptation phase data, wherein the environmental adaptation test data includes multiple environmental adaptation control nodes.

[0091] The generation of the first environmental adaptation test result includes:

[0092] The environmental characteristics around the cable laying path are collected, and combined with the segmented environmental constraints, the controller of the cable laying equipment is modeled for environmental adaptation, generating the first environmental adaptation simulation model.

[0093] The environmental adaptation test data is input into the first environmental adaptation simulation model to perform environmental adaptation simulation and generate a standard environmental adaptation state change time series.

[0094] The environmental adaptation test data is input into the controller of the cable laying equipment to conduct environmental adaptation tests, and the timing of changes in the actual test environmental adaptation status is recorded.

[0095] After comparing the time and space alignment of the standard environmental adaptation state change sequence with the actual test environmental adaptation state change sequence, environmental adaptation state deviations corresponding to multiple spatiotemporal nodes are generated.

[0096] The first environmental adaptation test result is generated based on the environmental adaptation state deviations corresponding to the multiple spatiotemporal nodes.

[0097] The generation of the first segmented laying optimization result includes:

[0098] Extract the first laying speed and the first laying point location in the first laying section;

[0099] Based on the results of the first environmental adaptation test, determine whether the environmental adaptation control deviation meets the preset deviation threshold.

[0100] If not, after correcting the first laying speed according to the environmental adaptation control deviation, the environmental adaptation distance is simulated, and the first laying point is optimized according to the prediction results to generate the first segment laying optimization result. At the same time, the ant colony algorithm is used in combination with the dynamic pheromone rules driven by environmental perception to update the path pheromone and optimize the subsequent path. Specifically, if the segment has an environmental adaptation problem, the pheromone concentration of the path and the surrounding paths is reduced; if the environmental adaptation is good, the pheromone concentration of the path and the surrounding paths is increased.

[0101] During cable laying, a hybrid multi-objective ant colony algorithm is used to optimize the path. The multi-objectives include the shortest path length, the lowest environmental adaptation risk, and the lowest laying cost.

[0102] The specific steps are as follows: Initialize the ant colony and set parameters such as the number of ants and the number of iterations; Each ant selects the next laying node and constructs a path based on the dynamic pheromone rules driven by environmental perception and heuristic information.

[0103] Calculate multiple target values ​​for each ant's constructed path, and update the pheromone on the path using a quantum heuristic pheromone update rule. Specifically, for paths with high fitness, adjust the pheromone concentration through a quantum rotation gate to enhance their attractiveness to subsequent ants; for paths with low fitness, reduce the pheromone concentration.

[0104] Repeat the above steps until the preset number of iterations is reached, and select the path with the highest fitness as the current optimal path.

[0105] Also includes:

[0106] AR-MR equipment is deployed at the cable laying site to acquire real-time three-dimensional information of the underground environment and the real-time status of cable laying.

[0107] The path optimized by the ant colony algorithm is imported into the AR-MR system and integrated with the actual underground environment for display.

[0108] Operators use AR-MR equipment to adjust and verify the path in real time. If a conflict is found between the path and the actual environment, the operator will promptly report it to the ant colony algorithm and re-optimize the path. At the same time, the laying control parameters will be further optimized based on the laying process simulated by the AR-MR system.

[0109] An electronic device includes: a memory and at least one processor, the memory storing instructions, wherein at least one processor invokes the instructions in the memory to cause the device to perform the steps of the method described above.

[0110] A computer-readable storage medium having instructions stored thereon, which, when executed by a processor, implement the steps of the method described above.

[0111] For specific implementation details, please refer to [link / reference]. Figure 1 Taking the underground cable laying project in the city center as an example, the project is connected to the underground cable planning system of the city power grid and receives a pre-planned initial cable laying route from the substation to the commercial center. The route is about 10 kilometers long, is zigzag, and includes multiple turning points and different geological areas.

[0112] Based on the initial route planning, the 10-kilometer-long route is divided into 200 segments, each segment being approximately 50 meters long. The endpoint of each segment is a target laying point, resulting in a total of 200 consecutive target laying points.

[0113] For each segment of the laying path, the geological type, such as sand, clay, and rock, and the distribution of underground obstacles, such as water pipes and gas pipes, are obtained by consulting geological survey reports and equipment parameter tables as environmental constraints. At the same time, the initial laying speed of the cable laying equipment at the starting point of the segment is also obtained, with the speed ranging from 0.5 to 2 meters per minute. The specific speed is related to the complexity of the path and the geological conditions.

[0114] The environmental constraints and the speed before laying are input into a pre-trained environmental simulation model. This model is trained based on historical data of the city over the past years in the same geographical area (city center) and using the same cable laying equipment. It can accurately simulate the adaptability of cable laying equipment under different conditions. The model outputs the environmental adaptation distance corresponding to each segment of the laying path. For example, in a segment with complex geology and many obstacles, the environmental adaptation distance may only be 30 meters, while in a segment with better geology and no obstacles, the environmental adaptation distance can reach 60 meters.

[0115] Based on the preset tolerance constraints, such as increasing the environmental adaptation distance by 1.2 times, the environmental adaptation distance of each segment is increased to obtain the preset environmental adaptation distance of each segment. Based on this, corresponding environmental test areas are configured on the laying path of each segment. For example, for a segment with an original environmental adaptation distance of 30 meters, the preset environmental adaptation distance becomes 36 meters. The environmental test area is the area extending 36 meters from the target laying point of the segment to the starting point.

[0116] Extract the first environmental test area that needs to be laid from all environmental test areas (the environmental test area of ​​the segment closest to the starting point), and obtain the corresponding first target laying point.

[0117] According to the initial cable laying path plan, the cable laying equipment is controlled to move towards the first target laying point. When the laying equipment enters the first environmental test area, the environmental adaptation test is initiated. For example, the operating status of the equipment in the area is monitored in real time by the sensors on the laying equipment, such as the vibration frequency of the equipment, the change of laying speed, and the stress on the cable. At the same time, the prediction of the area by the environmental simulation model is combined to generate the first environmental adaptation test results. If the test results show that the laying speed of the equipment in the area has decreased and the cable stress exceeds the normal range, it indicates that the environment in the area has had a significant adverse impact on the laying.

[0118] Based on the results of the first environmental adaptation test, the laying control parameters are optimized for the first laying section between the first environmental test area and the first target laying point. For example, the laying speed is reduced to 70% of the original speed, and the cable tension control parameters are adjusted to generate the first segment laying optimization results.

[0119] The laying optimization results of the first segment are used to optimize and control the laying of this segment. At the same time, path planning based on ant colony algorithm is adopted, combined with environmental perception-driven dynamic pheromone rules (dynamically adjusting the volatilization and update of pheromones according to real-time monitored environmental information, such as reducing the pheromone volatilization rate in harsh environments to guide the ant colony to find a better path), hybrid multi-objective ant colony algorithm (comprehensively considering three objectives of path length, environmental adaptation risk, and laying cost for path optimization, assigning corresponding weights to each objective, and finding the optimal solution of the three objectives through iterative search of the ant colony), and quantum heuristic pheromone update (using quantum operations such as quantum rotating gate to adjust the pheromone concentration, enhancing the pheromone concentration of paths with high fitness and reducing the pheromone concentration of paths with low fitness) to optimize the subsequent laying path in real time, ensuring the optimality of the entire cable laying path.

[0120] When configuring the environmental testing area, the preset environmental adaptation test distance is set to 50 meters. When the laying equipment enters the first environmental testing area, its first real-time laying status parameters, such as current speed and tension, are obtained. Combined with the first test sample constraint (the environmental adaptation threshold meets the first preset threshold, such as stable equipment operation and cable stress within the normal range) and the second test sample constraint (the environmental adaptation threshold meets the second preset threshold, such as slight equipment vibration and cable stress slightly higher than normal value), continuous environmental adaptation stage data is generated, thereby forming environmental adaptation test data containing multiple environmental adaptation control nodes.

[0121] Environmental characteristics around the cable laying path, such as soil moisture, temperature, and groundwater flow, are collected. Combined with segmented environmental constraints, environmental adaptation modeling is performed on the controller of the cable laying equipment to generate the first environmental adaptation simulation model. Environmental adaptation test data is input into this simulation model for simulation to obtain the time sequence of standard environmental adaptation state changes. At the same time, the test data is input into the actual cable laying equipment controller for testing, and the time sequence of actual test environmental adaptation state changes is recorded. The two are compared after time and space alignment to obtain the environmental adaptation state deviations corresponding to multiple spatiotemporal nodes, and finally the first environmental adaptation test results are generated.

[0122] After extracting the first pre-laying speed and the first laying point in the first laying section, the environmental adaptation control deviation is judged based on the first environmental adaptation test results to determine whether it meets the preset deviation threshold. If it does not meet the threshold, the first pre-laying speed is corrected according to the deviation, such as increasing or decreasing the speed, and the environmental adaptation distance is simulated again. The first laying point is optimized based on the simulation prediction results to generate the first segment laying optimization results. At the same time, the ant colony algorithm is used in combination with the dynamic pheromone rules driven by environmental perception to update the path pheromone and optimize the subsequent path. If the segment has environmental adaptation problems, the pheromone concentration of the path and the surrounding paths is reduced; if the environmental adaptation is good, the pheromone concentration is increased.

[0123] During cable laying, a hybrid multi-objective ant colony algorithm is used to optimize the path. The ant colony is initialized with parameters such as 100 ants and 1000 iterations. Each ant selects the next laying node based on dynamic pheromone rules driven by environmental perception and heuristic information, constructs a path, and calculates three objective values ​​for each ant's path: path length, environmental adaptation risk, and laying cost. A quantum heuristic pheromone update rule is used to update the pheromone on the path. For paths with high fitness, the pheromone concentration is adjusted through a quantum rotation gate to enhance their attractiveness to subsequent ants; for paths with low fitness, the pheromone concentration is reduced. After multiple iterations until the preset number of 1000 iterations is reached, the path with the highest fitness is selected as the current optimal path.

[0124] AR-MR equipment is deployed at the cable laying site to acquire real-time 3D information of the underground environment and the real-time status of cable laying. The path optimized by the ant colony algorithm is imported into the AR-MR system and fused with the actual underground environment. Operators observe the relationship between the fused path and the actual environment through the AR-MR equipment. If a conflict is found between the path and a newly built underground communication pipeline, it is promptly fed back to the ant colony algorithm for path optimization. At the same time, based on the laying process simulated by the AR-MR system, laying control parameters such as the bending radius control parameters of the cable and the turning angle parameters of the laying equipment are further optimized.

[0125] Example 2

[0126] An intelligent optimization design system for underground cable routes based on ant colony algorithm includes:

[0127] The initial path receiving module is used to connect to the underground cable planning system and receive the initial cable laying path plan.

[0128] The environmental testing area establishment module is used to extract multiple continuous target laying points according to the initial cable laying path planning, and to establish multiple environmental testing areas for the multiple continuous target laying points according to the preset environmental adaptation distance.

[0129] The first target laying point acquisition module is used to extract the first environmental test area from the multiple environmental test areas and acquire the corresponding first target laying point;

[0130] The first environmental adaptation test result generation module is used to control the cable laying equipment to travel to the first target laying point according to the initial cable laying path planning. When the cable laying equipment is detected to enter the first environmental test area for environmental adaptation test, the first environmental adaptation test result is generated.

[0131] The laying control parameter optimization module is used to optimize the laying control parameters for the first laying section between the first environmental test area and the first target laying point based on the first environmental adaptation test results, and generate the first segmented laying optimization results.

[0132] The laying optimization control module is used to perform laying optimization control on the first laying section based on the first segment laying optimization result;

[0133] The ant colony algorithm optimization module is used to optimize the cable laying path in real time by using ant colony algorithm-based path planning, combined with environmental perception-driven dynamic pheromone rules, hybrid multi-objective ant colony algorithm and quantum heuristic pheromone update.

[0134] The AR-MR collaborative optimization module integrates the path optimized by the ant colony algorithm with the actual underground environment through the AR-MR collaborative optimization mechanism. This allows operators to adjust and verify the path in real time and optimize the laying control parameters based on the simulated laying process.

[0135] Please see Figure 2 The initial path receiving module is installed on the server of the city power grid control center and is connected to the underground cable planning system via the network. When a new underground cable laying task is received, the module receives the initial cable laying path planning file sent by the planning system. The file contains detailed information such as the coordinates of the start and end points, the route direction, and the expected laying depth. For example, in a cable laying project in a newly built industrial park, the initial path receiving module received an initial cable laying path planning from the park's substation to various factory buildings. The path is distributed in a tree-like pattern, with a total length of 8 kilometers and multiple branch paths.

[0136] The environmental testing area establishment module runs on the server and processes the received initial cable laying path plan. First, it extracts multiple consecutive target laying points. For example, for an 8-kilometer-long path, it extracts 160 target laying points at intervals of 50 meters. Then, based on the preset environmental adaptation distance, initially set to 40 meters, it extends 40 meters from each target laying point as the endpoint to establish the corresponding environmental testing area. At the same time, it obtains the environmental constraints corresponding to each segment of the laying path, such as geological type, underground obstacle distribution, and speed parameters before laying.

[0137] The first target laying point acquisition module is connected to the environmental test area establishment module and runs on the server. From the multiple established environmental test areas, it extracts the first target laying point corresponding to the first environmental test area that needs to be laid according to the laying order, and sends its coordinates and related path information to the subsequent control module.

[0138] The first environmental adaptation test result generation module is installed on the cable laying equipment and includes sensors, a data acquisition unit, and a processor. When the cable laying equipment travels towards the first target laying point according to the initial path plan and enters the first environmental test area, the sensors begin to monitor the operating status of the equipment in real time, such as parameters like speed, tension, and vibration. The data acquisition unit collects this data and transmits it to the processor. The processor combines the predicted data of the area in the environmental simulation model, performs comparative analysis, and generates the first environmental adaptation test result. For example, if the actual monitored equipment speed is 20% lower than the model's predicted speed, and the cable tension is 15% higher than the normal value, it is determined that the environment in that area has an adverse effect on the laying, and a corresponding test result report is generated.

[0139] The cable laying control parameter optimization module is located in the control center of the cable laying equipment. After receiving the results of the first environmental adaptation test, it uses preset optimization algorithms, such as fuzzy control algorithms and neural network algorithms, to optimize the laying control parameters for the first laying section between the first environmental test area and the first target laying point. For example, based on the speed deviation and tension deviation in the test results, it adjusts the motor speed and tension controller parameters of the laying equipment to generate the first segment laying optimization results and sends the optimized parameters to the actuator of the laying equipment.

[0140] The cable laying optimization control module is installed on the cable laying equipment. After receiving the first segment laying optimization results, it controls each actuator of the laying equipment to carry out the laying operation according to the optimized parameters to ensure the laying quality of the first segment. At the same time, the module also communicates with the ant colony algorithm optimization module to feed back the actual situation of the segment laying to the ant colony algorithm optimization module so as to optimize the subsequent path.

[0141] The ant colony optimization module runs on the server and employs an ant colony-based path planning method. It combines environmentally driven dynamic pheromone rules, a hybrid multi-objective ant colony algorithm, and quantum heuristic pheromone update rules to optimize cable laying paths in real time. When initializing the ant colony, parameters such as the number of ants is set to 200 and the number of iterations to 1500 are set. Each ant selects the next laying node based on real-time environmental information and heuristic information, constructs a path, calculates multiple target values ​​for the path constructed by each ant, and then updates the pheromone on the path using quantum heuristic pheromone update rules. During the iteration process, the pheromone concentration is continuously adjusted to guide the ant colony to find the optimal laying path with the shortest path length, the lowest environmental adaptation risk, and the lowest laying cost. The optimized path is then sent to the AR-MR collaborative optimization module and the laying optimization control module.

[0142] The AR-MR collaborative optimization module deploys AR-MR devices, such as head-mounted displays and handheld terminals, at the cable laying site. These devices connect to a server via a wireless network to acquire real-time 3D information about the underground environment and the real-time status of the cable laying. The module imports the ant colony algorithm-optimized path into the AR-MR system and integrates it with the actual underground environment. Operators wearing AR-MR devices can visually observe the relationship between the optimized path and the actual environment. If a conflict is found between the path and existing underground water supply and drainage pipes, feedback can be promptly provided to the ant colony algorithm optimization module through the device's interactive interface, requesting a re-optimization of the path. Simultaneously, based on the laying process simulated by the AR-MR system, laying control parameters such as laying angle and cable slack are further optimized, and the optimized parameters are sent to the laying optimization control module.

[0143] The same or similar labels correspond to the same or similar parts;

[0144] The terms used to describe positional relationships in the accompanying drawings are for illustrative purposes only and should not be construed as limiting this patent.

[0145] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. For those skilled in the art, other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all implementation methods here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the claims of the present invention.

Claims

1. A method for intelligent optimization design of underground cable routes based on ant colony algorithm, characterized in that, Includes the following steps: Connect to the underground cable planning system and receive the initial cable laying path plan; Based on the initial cable laying path plan, multiple continuous target laying points are extracted, and multiple environmental test areas are established for the multiple continuous target laying points according to the preset environmental adaptation distance. Specifically, this includes: obtaining multiple segmented laying paths with the multiple consecutive target laying points as endpoints based on the initial cable laying path planning; Obtain the environmental constraints and pre-laying speeds corresponding to the multiple segmented laying paths; The environmental constraints and the pre-laying speed are input into the environmental simulation model to perform environmental adaptation simulation, generating the environmental adaptation distances corresponding to the multiple segmented laying paths. The environmental simulation model is trained based on historical environmental adaptation data of the same geographical area and the same cable laying equipment. The environmental adaptation distance is amplified according to a preset tolerance constraint to generate the preset environmental adaptation distance corresponding to the segmented laying path; According to the preset environmental adaptation distance, the multiple environmental test areas are configured in the multiple segmented laying paths; Extract the first environmental test area from the plurality of environmental test areas and obtain the corresponding first target laying point; According to the initial cable laying path planning, the cable laying equipment is controlled to travel to the first target laying point. When the cable laying equipment is detected to have entered the first environmental test area, an environmental adaptation test is conducted, and a first environmental adaptation test result is generated. Based on the results of the first environmental adaptation test, the laying control parameters of the first laying section between the first environmental test area and the first target laying point are optimized to generate the first segment laying optimization result. The first laying segment is optimized and controlled based on the first segment laying optimization results. At the same time, path planning based on ant colony algorithm is adopted, combined with dynamic pheromone rules driven by environmental perception, hybrid multi-objective ant colony algorithm and quantum heuristic pheromone update, to optimize the subsequent laying path in real time.

2. The method according to claim 1, characterized in that, According to the preset environmental adaptation distance, the multiple environmental test areas are configured in the multiple segmented laying paths, including: Configure preset environment adaptation test distance; The preset environmental adaptation test distance is used as the area length of the plurality of environmental test areas, and the preset environmental adaptation distance is used as the distance from the plurality of environmental test areas to the plurality of continuous target laying points. The plurality of environmental test areas are configured in the plurality of segmented laying paths. The generation of the first environmental adaptation test results includes: Establish environmental test sample constraints, wherein the environmental test sample constraints include a first test sample constraint and a second test sample constraint, the first test sample constraint is that the environmental adaptation threshold meets a first preset threshold, and the second test sample constraint is that the environmental adaptation threshold meets a second preset threshold, the first preset threshold and the second preset threshold are set according to cable laying requirements and equipment performance; Configure environment adaptation test data based on the first test sample constraints and the second test sample constraints; The environmental adaptation test data is input into the controller of the cable laying equipment for environmental adaptation testing, and the environmental adaptation control deviation is analyzed to generate the first environmental adaptation test result.

3. The method according to claim 2, characterized in that, The environmental adaptation test data configured based on the first test sample constraints and the second test sample constraints includes: When the cable laying equipment is detected to have entered the first environmental test area, the first real-time laying status of the cable laying equipment is obtained. Based on the first real-time laying status, continuous environmental adaptation stage data is generated by combining the first test sample constraints and the second test sample constraints. The environmental adaptation test data is generated from the continuous environmental adaptation phase data, wherein the environmental adaptation test data includes multiple environmental adaptation control nodes.

4. The method according to claim 3, characterized in that, The generation of the first environmental adaptation test result includes: The environmental characteristics around the cable laying path are collected, and combined with the segmented environmental constraints, the controller of the cable laying equipment is modeled for environmental adaptation, generating the first environmental adaptation simulation model. The environmental adaptation test data is input into the first environmental adaptation simulation model to perform environmental adaptation simulation and generate a standard environmental adaptation state change time series. The environmental adaptation test data is input into the controller of the cable laying equipment to conduct environmental adaptation tests, and the timing of changes in the actual test environmental adaptation status is recorded. After comparing the time and space alignment of the standard environmental adaptation state change sequence with the actual test environmental adaptation state change sequence, environmental adaptation state deviations corresponding to multiple spatiotemporal nodes are generated. The first environmental adaptation test result is generated based on the environmental adaptation state deviations corresponding to the multiple spatiotemporal nodes.

5. The method according to claim 1, characterized in that, The generation of the first segmented laying optimization result includes: Extract the first laying speed and the first laying point location in the first laying section; Based on the results of the first environmental adaptation test, determine whether the environmental adaptation control deviation meets the preset deviation threshold. If not, after correcting the first laying speed according to the environmental adaptation control deviation, the environmental adaptation distance is simulated, and the first laying point is optimized according to the prediction results to generate the first segment laying optimization result. At the same time, the ant colony algorithm is used in combination with the dynamic pheromone rules driven by environmental perception to update the path pheromone and optimize the subsequent path. Specifically, if the segment has an environmental adaptation problem, the pheromone concentration of the path and the surrounding paths is reduced; if the environmental adaptation is good, the pheromone concentration of the path and the surrounding paths is increased.

6. The method according to claim 1, characterized in that, During cable laying, a hybrid multi-objective ant colony algorithm is used to optimize the path. The multi-objectives include the shortest path length, the lowest environmental adaptation risk, and the lowest laying cost. The specific steps are as follows: Initialize the ant colony and set parameters such as the number of ants and the number of iterations; Each ant selects the next laying node and constructs a path based on dynamic pheromone rules driven by environmental perception and heuristic information. Calculate multiple target values ​​for each ant's constructed path, and update the pheromone on the path using a quantum heuristic pheromone update rule. Specifically, for paths with high fitness, adjust the pheromone concentration through a quantum rotation gate to enhance their attractiveness to subsequent ants; for paths with low fitness, reduce the pheromone concentration. Repeat the above steps until the preset number of iterations is reached, and select the path with the highest fitness as the current optimal path.

7. The method according to claim 1, characterized in that, Also includes: AR-MR equipment is deployed at the cable laying site to acquire real-time three-dimensional information of the underground environment and the real-time status of cable laying. The path optimized by the ant colony algorithm is imported into the AR-MR system and integrated with the actual underground environment for display. Operators use AR-MR equipment to adjust and verify the path in real time. If a conflict is found between the path and the actual environment, the operator will promptly report it to the ant colony algorithm and re-optimize the path. At the same time, the laying control parameters will be further optimized based on the laying process simulated by the AR-MR system.

8. An intelligent optimization design system for underground cable routes based on ant colony algorithm, characterized in that, The system is used to implement the intelligent optimization design method for underground cable routes based on ant colony algorithm as described in any one of claims 1-7, including: The initial path receiving module is used to connect to the underground cable planning system and receive the initial cable laying path plan. The environmental testing area establishment module is used to extract multiple continuous target laying points according to the initial cable laying path planning, and to establish multiple environmental testing areas for the multiple continuous target laying points according to the preset environmental adaptation distance. The first target laying point acquisition module is used to extract the first environmental test area from the multiple environmental test areas and acquire the corresponding first target laying point; The first environmental adaptation test result generation module is used to control the cable laying equipment to travel to the first target laying point according to the initial cable laying path planning. When the cable laying equipment is detected to enter the first environmental test area for environmental adaptation test, the first environmental adaptation test result is generated. The laying control parameter optimization module is used to optimize the laying control parameters for the first laying section between the first environmental test area and the first target laying point based on the first environmental adaptation test results, and generate the first segmented laying optimization results. The laying optimization control module is used to perform laying optimization control on the first laying section based on the first segment laying optimization result; The ant colony algorithm optimization module is used to optimize the cable laying path in real time by using ant colony algorithm-based path planning, combined with environmental perception-driven dynamic pheromone rules, hybrid multi-objective ant colony algorithm and quantum heuristic pheromone update. The AR-MR collaborative optimization module integrates the path optimized by the ant colony algorithm with the actual underground environment through the AR-MR collaborative optimization mechanism. This allows operators to adjust and verify the path in real time and optimize the laying control parameters based on the simulated laying process.

9. An electronic device, characterized in that, include: The device includes a memory and at least one processor, wherein the memory stores instructions, and at least one processor invokes the instructions in the memory to cause the device to perform the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the steps of the method as described in any one of claims 1-7.

Images