Intelligent decision-making method and device for power supply operation of generator car, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a power generation vehicle power supply operation intelligent decision-making method and device, electronic equipment and a storage medium, and relates to the technical field of power operation safety, and the method comprises the steps: obtaining the three-dimensional point cloud data of a power generation vehicle power supply operation site; analyzing the three-dimensional point cloud data, and identifying field parameters related to power supply operation of the generator car; and generating a power generation vehicle power supply operation analysis decision based on a pre-constructed multi-dimensional operation condition specification index system and the field parameters. According to the embodiment of the invention, the problems of parameter acquisition distortion caused by dependence on manual on-site investigation, evaluation standard deficiency caused by experience-dominated decision making, error proneness to manual checking and insufficient dynamic early warning in the prior art can be solved.

Description

Technical Field

[0001] The present invention relates to the field of power operation safety technology, and in particular to an intelligent decision-making method, device, electronic equipment and storage medium for power supply operation of a power generation vehicle. Background Art

[0002] With the continuous development of power systems, generator trucks are playing an increasingly important role in critical scenarios such as temporary power supply, emergency repairs, and distributed energy access. Because generator truck power supply operations involve the coordinated use of multiple tools and equipment and complex operational processes (such as cable connection, load matching, and grid-connected / off-grid operation), high requirements are placed on operational safety, reliability, and efficiency. During operation, any minor parameter misconfiguration, operational timing errors, or omissions in safety measures can directly lead to equipment damage, power outages, and even serious personal safety accidents.

[0003] However, the current mainstream power supply operation process of power generation vehicles is still highly dependent on manual on-site surveys and experience-based judgments, which have the following problems: manual surveys are affected by factors such as terrain environment and visual errors, making it difficult to accurately obtain on-site load data and spatial layout information; the scheme design dominated by experience-based judgment lacks a standardized quantitative evaluation system, resulting in uneven risk identification capabilities of different operation teams; when faced with complex operation processes, manual verification is not only time-consuming and labor-intensive, but also prone to missed detections and misjudgments due to fatigue or negligence, and the dynamic risk warning capabilities are obviously insufficient. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides an intelligent decision-making method, device, electronic device and storage medium for power supply operations of a power generation vehicle to solve the problems in the prior art of reliance on manual on-site surveys resulting in distorted parameter acquisition, lack of evaluation standards caused by experience-driven decision-making, and manual verification prone to errors and insufficient dynamic warnings.

[0005] In a first aspect, an embodiment of the present invention provides an intelligent decision-making method for power supply operation of a power generation vehicle, comprising:

[0006] Obtain 3D point cloud data of the power generation truck's power supply operation site;

[0007] Analyzing the three-dimensional point cloud data to identify on-site parameters related to the power supply operation of the generator truck;

[0008] Based on the pre-built multi-dimensional operating condition specification indicator system and the field parameters, an analysis and decision on the power supply operation of the power generation vehicle is generated.

[0009] Furthermore, the three-dimensional point cloud data is analyzed to identify on-site parameters related to the power supply operation of the power generation vehicle, including:

[0010] Performing semantic segmentation on the three-dimensional point cloud data using a deep learning-based network model;

[0011] Based on the semantic segmentation results, the on-site parameters related to the power supply operation of the power generation vehicle are identified.

[0012] Furthermore, a deep learning network model is used to perform semantic segmentation on the three-dimensional point cloud data, including:

[0013] Using a first network model based on deep learning to extract global features of the three-dimensional point cloud data;

[0014] Using a second network model based on deep learning to extract local features of the three-dimensional point cloud data;

[0015] Associating the global features with the local features to construct a multi-scale feature representation;

[0016] Based on the multi-scale feature representation, a semantic segmentation result of the three-dimensional point cloud data is obtained.

[0017] Furthermore, a second network model based on deep learning is used to extract local features of the three-dimensional point cloud data, including:

[0018] embedding intermediate features of the three-dimensional point cloud at a first scale into the three-dimensional point cloud data to obtain first three-dimensional point cloud data;

[0019] embedding intermediate features of the three-dimensional point cloud at a second scale into the three-dimensional point cloud data to obtain second three-dimensional point cloud data;

[0020] Based on the attention mechanism, the association weights between the intermediate features at two scales are calculated;

[0021] weightedly fusing the first three-dimensional point cloud data and the second three-dimensional point cloud data according to the calculated association weight to obtain third three-dimensional point cloud data;

[0022] Performing multi-level downsampling on the third three-dimensional point cloud data, and extracting semantic features of the sampled point cloud data at each level after downsampling;

[0023] The semantic features extracted after multi-level downsampling are propagated step by step to the point cloud resolution before downsampling through upsampling to obtain the local features.

[0024] Furthermore, based on the semantic segmentation results, the on-site parameters related to the power supply operation of the generator truck are identified, including:

[0025] Based on the point cloud data of power facilities identified in the semantic segmentation results, geometric fitting and projection analysis methods are used to calculate the power facility parameters related to the power supply operation of the generator truck;

[0026] Based on the point cloud data of environmental objects identified in the semantic segmentation results, the channel environmental parameters related to the power supply operation of the power generation vehicle are determined.

[0027] Furthermore, based on the power facility point cloud data identified in the semantic segmentation results, geometric fitting and projection analysis methods are used to calculate the power facility parameters related to the power supply operation of the generator truck, including:

[0028] Based on the tower point cloud data identified in the semantic segmentation result: fitting a ground plane; calculating the distance between the tower point cloud and the ground plane to determine the tower height;

[0029] Based on the crossarm point cloud data identified in the semantic segmentation result: fitting a crossarm plane; projecting the crossarm point cloud onto the crossarm plane; fitting a minimum circumscribed circle on the crossarm point cloud projection to determine the crossarm length;

[0030] Based on the insulator point cloud data identified in the semantic segmentation results: fit the axial direction of the insulator; calculate the maximum spacing of the insulator point cloud in the axial direction, and determine the insulator height based on the maximum spacing; project the insulator point cloud onto a plane perpendicular to the axial direction, and fit the minimum circumscribed circle on the insulator point cloud projection to determine the insulator disk diameter.

[0031] Furthermore, based on the point cloud data of environmental objects identified in the semantic segmentation results, the channel environmental parameters related to the power supply operation of the power generation vehicle are determined, including:

[0032] Determine the width and slope of the working channel road surface based on the point cloud data of the working channel road surface identified in the semantic segmentation results;

[0033] Based on the obstacle point cloud data identified in the semantic segmentation results, the obstacle removability judgment results and spatial distribution parameters are determined.

[0034] Furthermore, based on the pre-built multi-dimensional operating condition specification indicator system and the field parameters, a power generation vehicle power supply operation analysis decision is generated, including:

[0035] Based on the pre-established boom truck usage condition specification indicators, combined with the site parameters, the boom truck is evaluated for suitability and an operation plan is generated; wherein the boom truck usage condition specification indicators are implemented by at least the following set specification category constraints: motion range verification rules, parking area screening rules and safe operation rules; and / or

[0036] Based on pre-established generator vehicle usage condition specification indicators and in combination with the site parameters, the generator vehicle is evaluated for suitability and an operation plan is generated; wherein the generator vehicle usage condition specification indicators are implemented by at least the following set specification category constraints: electrical connection rules, space layout rules, and cable laying rules; and / or

[0037] Based on the pre-built insulation shielding specification indicators and combined with the site parameters, an insulation shielding plan is generated.

[0038] Furthermore, based on the pre-established insulation shielding specification indicators and combined with the site parameters, an insulation shielding plan is generated, including:

[0039] Detecting charged objects within the operating range according to the on-site parameters;

[0040] Determine insulation shielding scope, sequence, and tools based on pre-built insulation shielding specifications and test results.

[0041] Furthermore, the insulation shielding range is determined, including:

[0042] Determine whether there is a potential safety risk based on the distance between the working position of the power supply operator on the generator truck and the charged object;

[0043] Calculate the range of motion of the power supply operator on the power generation vehicle: A = B + T + M + N, where B represents the arm span of the power supply operator on the power generation vehicle, T represents the length of the operating tool of the power supply operator on the power generation vehicle, M represents the amplitude of the operating movement of the power supply operator on the power generation vehicle, and N represents the movable distance of the power supply operator on the working bucket of the boom truck;

[0044] Determine the insulation shielding range based on the risk assessment results and activity range calculation results.

[0045] Furthermore, the three-dimensional point cloud data of the power generation vehicle power supply operation site is obtained, including:

[0046] Collect multi-view image sequences of the power generation truck's power supply operation site;

[0047] Processing the multi-view image sequence to construct sparse point cloud data;

[0048] Based on the set depth map fusion algorithm, dense point cloud data is generated based on the sparse point cloud data.

[0049] In a second aspect, an embodiment of the present invention provides an intelligent decision-making device for power supply operation of a power generation vehicle, comprising:

[0050] A data acquisition unit, used to acquire three-dimensional point cloud data of the power supply operation site of the generator truck;

[0051] a parameter identification unit, configured to analyze the three-dimensional point cloud data and identify on-site parameters related to the power supply operation of the power generation vehicle;

[0052] The decision generating unit is used to generate a power generation vehicle power supply operation analysis decision based on a pre-built multi-dimensional operating condition specification indicator system and the field parameters.

[0053] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is placed inside the space enclosed by the housing, and the processor and the memory are arranged on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the above-mentioned electronic device; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the intelligent decision-making method for power supply operation of the power generation vehicle described in the first aspect above.

[0054] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the intelligent decision-making method for power supply operation of the power generation vehicle as described in the first aspect above.

[0055] The technical solution provided by the embodiment of the present invention avoids the parameter distortion problem caused by manual survey by acquiring three-dimensional point cloud data and automatically analyzing on-site parameters. At the same time, it generates analysis decisions based on a multi-dimensional operating condition specification indicator system, breaks away from the limitations of experience-led decision-making, establishes a standardized evaluation system, and can also solve the problems of low efficiency of manual verification and insufficient dynamic early warning, thereby realizing the scientific and intelligent improvement of decision-making under the integration of multiple technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 This is a flow chart of an intelligent decision-making method for power supply operation of a power generation vehicle provided in the first embodiment of the present invention;

[0058] Figure 2 This is a flow chart of an intelligent decision-making method for power supply operation of a power generation vehicle provided in the second embodiment of the present invention;

[0059] Figure 3 A schematic diagram of a design process for extracting local features from three-dimensional point cloud data of a power generation vehicle power supply operation site provided in the second embodiment of the present invention;

[0060] Figure 4 This is a schematic diagram of the structure of an intelligent decision-making device for power supply operation of a power generation vehicle provided in the fifth embodiment of the present invention;

[0061] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0063] It should be understood that the embodiments described are only a portion 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 persons of ordinary skill in the art without creative work are within the scope of protection of the present invention.

[0064] The technical solutions of the present invention are described in detail below through various embodiments.

[0065] Example 1

[0066] This embodiment provides a method for intelligent decision-making on power supply operation of a power generation vehicle, which can be executed by a corresponding intelligent decision-making device for power supply operation of a power generation vehicle. Figure 1 The method specifically includes the following steps 101-103.

[0067] Step 101: Acquire three-dimensional point cloud data of the power supply operation site of the power generation vehicle.

[0068] In this step, a multi-perspective image sequence covering the entire scene of the power supply operation site of the power generation vehicle can be collected in real time, and then computer vision technology is used to deeply analyze the multi-perspective image sequence to complete the three-dimensional reconstruction of the power supply operation site of the power generation vehicle, and then generate three-dimensional point cloud data that can truly reflect the power supply operation site of the power generation vehicle, providing a high-precision spatial digital foundation for subsequent intelligent decision-making.

[0069] Among them, multi-perspective image sequence acquisition is the basic link for constructing the three-dimensional space of the power supply operation site of the power generation vehicle. Specifically, multi-perspective image sequence acquisition can be implemented through a drone equipped with a camera. The shooting range needs to fully cover the power facilities (including the distribution of poles, wires, insulators, etc.), topography (geographical environment characteristics and surface structure) and channel environment (surrounding obstacle distribution and adjacent line direction, etc.) at the power supply operation site of the power generation vehicle to ensure the accuracy and completeness of the three-dimensional reconstruction scene data. Of course, multi-angle sensing equipment such as wide-angle cameras and laser scanners can also be deployed at the operation site to collect multi-perspective image sequences of the power supply operation site of the power generation vehicle in real time. This embodiment does not make specific restrictions on this. For example, multi-perspective image sequence acquisition is performed in accordance with the following requirements:

[0070] ①Shooting angle control

[0071] Adopting multi-angle shooting modes such as orthographic, oblique, and surround to enhance the detail expression and reconstruction accuracy of the 3D spatial model;

[0072] In particular, when photographing the tower structure at the power generation site, the viewing angle of adjacent images should be controlled within the range of 10° to 20°.

[0073] ②Shooting environment requirements

[0074] Shooting should be avoided under complex lighting or weather conditions such as strong light, shadows, rain and fog to ensure the clarity and color reproduction of the captured images; when complex lighting conditions cannot be avoided, a multi-time batch shooting strategy can be adopted, and the images collected at different times can be integrated through image fusion algorithms to improve image quality and reconstruction effects.

[0075] In the above requirements, the viewing angle range of adjacent images of the tower structure is controlled within the range of 10° to 20°. The reasons are:

[0076] An angle of 10° to 20° allows adjacent images to maintain a large overlapping area, ensuring that a sufficient number of points with the same name are captured during feature extraction, thus avoiding feature point matching failures caused by a large viewing angle span.

[0077] This angle range meets the baseline-distance ratio requirement of triangulation (baseline length / shooting distance ≈ tan(10°-20°)), and can control the reconstruction error of 3D points to the centimeter level (when the angle is >20°, the depth calculation error increases exponentially with the angle).

[0078] Compared with smaller angles (such as <10°), the 20° upper limit can reduce the number of shots and avoid redundant data; compared with larger angles (such as >20°), the 10° lower limit can reduce the computational complexity of the hole completion algorithm.

[0079] After collecting the multi-view image sequence of the power generation vehicle power supply operation site, these image sequences can be used to generate three-dimensional point cloud data of the power generation vehicle power supply operation site. Specifically, the following steps (1)-(2) can be included.

[0080] (1) Process the multi-view image sequences and construct sparse point cloud data.

[0081] First, image preprocessing is performed: denoising and contrast enhancement are performed on the acquired multi-view image sequences to eliminate uneven illumination and sensor noise interference, thereby improving image quality.

[0082] Next, feature extraction and matching are performed: feature descriptors such as SIFT, SURF, or ORB are used to detect feature points (such as corner points and edge features) in the preprocessed image, and matching relationships between feature points across the image views are established.

[0083] Then, the camera parameters are estimated: using the feature point matching results, the intrinsic parameters (such as focal length, principal point coordinates) and extrinsic parameters (such as position and attitude matrix) of the camera that captured the image are estimated through optimization algorithms such as bundle adjustment.

[0084] Finally, sparse point cloud data is generated through triangulation: based on the matched feature points and estimated camera parameters, the position of the point in three-dimensional space is calculated to form sparse point cloud data.

[0085] (2) Based on the set depth map fusion algorithm, dense point cloud data is generated based on the sparse point cloud data.

[0086] Specifically, this step (2) can be achieved by the following steps:

[0087] Depth map initialization: Initialize the depth map of each viewpoint based on the camera intrinsic parameters and sparse point cloud data;

[0088] Patch initialization: select a local area (Patch) in the depth map for initialization;

[0089] Depth map propagation optimization: gradually improve the details of the depth map through parallax propagation and optimization algorithms;

[0090] Dense point cloud data generation: Based on the depth map and camera parameters corresponding to each viewpoint, dense 3D point cloud data is generated. The dense 3D point cloud data consists of multiple points, each of which includes the 3D coordinates of the point and its visual attribute characteristics (such as RGB values).

[0091] Optionally, before initializing the depth map, the camera parameters and the positions of the points in the 3D space are globally optimized to minimize the reprojection error and improve the accuracy and consistency of the 3D point cloud. Specifically, based on the preliminary reconstruction results of the sparse point cloud data, the bundle adjustment method can be used to jointly iteratively optimize the camera parameters and the positions of the points in the 3D space. The core of this method is to minimize the reprojection error - that is, to calculate the sum of the squares of the deviations between the theoretical position of the 3D points reprojected onto the image plane and the actual position of the feature points. Through the continuous convergence solution of the nonlinear optimization algorithm, the spatial accuracy and multi-view consistency of the point cloud can be significantly improved.

[0092] Furthermore, an implicit surface representation method can be further used to obtain a three-dimensional model of the power generation vehicle power supply operation site based on dense point cloud data. In specific implementation, an implicit surface can be constructed by solving the Poisson equation based on the dense point cloud data and its normal vector field. Then, a marching cubes algorithm is used to extract a triangular mesh from the implicit surface, and the extracted triangular mesh is simplified and optimized. For example, edge collapse and Laplacian smoothing algorithms are applied to reduce mesh complexity while maintaining geometric features, eliminate triangular facet distortion, and improve model computational efficiency and visualization quality. Finally, the texture of the original multi-view image is mapped onto the triangular mesh to obtain a three-dimensional model with rich details and realism.

[0093] Those skilled in the art will appreciate that the above-described method of generating 3D point cloud data of a power generation truck's power supply operation site based on a multi-view image sequence is merely illustrative. In specific applications, any known 3D perception technology in the art may be used to achieve equivalent results, and this embodiment does not impose any limiting requirements thereon.

[0094] Step 102: Analyze the acquired three-dimensional point cloud data to identify on-site parameters related to the power supply operation of the power generation vehicle.

[0095] In this step 102, the acquired 3D point cloud data can be preprocessed to remove noise and redundant information to improve data quality. Subsequently, different objects in the 3D point cloud data (such as poles, conductors, insulators, ground, obstacles, etc.) are automatically identified and classified based on semantic segmentation technology. On this basis, on-site parameters related to the power supply operation of the generator truck are extracted, including power facility structural parameters (such as pole height, crossarm spacing, insulator size) and environmental spatial distribution parameters (such as terrain slope, channel width, and obstacle distribution), providing data support and decision-making basis for the power supply operation of the generator truck.

[0096] Semantic segmentation technology may adopt deep learning point cloud processing technology, such as PointNet, PointNet++, DGCNN, PointGNN, MV3D, etc., or may adopt traditional machine learning and geometric feature technology, such as Random Forest, Support Vector Machine (SVM), RANSAC (Random Sampling Consensus), Euclidean Clustering, etc. This embodiment does not limit this.

[0097] Step 103: Generate a power generation vehicle power supply operation analysis decision based on the pre-built multi-dimensional operating condition specification indicator system and the analyzed field parameters.

[0098] First, a multi-dimensional operating condition specification indicator system is pre-constructed. The system integrates quantitative indicators of multiple dimensions such as environment, equipment, and personnel (such as load matching threshold, safety distance threshold, etc.). These indicators can be set according to relevant safety standards and operating specifications. Then, based on the actual situation, the on-site parameters related to the power supply operation of the power generation vehicle are identified, and the operating condition analysis indicators of each dimension are checked item by item to determine whether the current operating environment meets the conditions for the use of the bucket truck and the power generation vehicle. Finally, with the support of the indicator engine, the operation analysis decision results are generated, including: operating condition compliance judgment (whether safe operating conditions are met); recommended operation plans (such as vehicle parking location, operation path planning); and shielding plans. The following provides a preferred implementation method of step 103.

[0099] (1) Based on the pre-built boom truck usage condition specification indicators and combined with the on-site parameters related to the power supply operation of the power generation vehicle, the applicability of the boom truck is evaluated and an operation plan is generated.

[0100] Specifically, based on the on-site parameters related to the power generation truck's power supply operation and the on-site 3D point cloud data, the actual working conditions at the power generation truck's power supply operation site can be determined from two aspects: on-site equipment and environmental conditions. This allows for a suitability assessment of the boom truck. The specific assessment content can be as shown in the example given in Table 1. If all the assessment contents are qualified, the boom truck is qualified for use. If one or more of the evaluation contents are not met, the boom truck is not qualified for use.

[0101] Table 1

[0102]

[0103] Based on the boom truck suitability assessment, boom truck usage condition specification indicators can be set to be implemented by at least the following set specification category constraints: motion range verification rules, parking area screening rules, and safe operation rules. Table 2 below shows some examples of boom truck usage condition specification indicators provided in this embodiment.

[0104] Table 2

[0105]

[0106] Exemplarily, generating an operation plan for a boom truck includes the following steps ①-④.

[0107] ①Determine the specifications of the bucket truck

[0108] From the pre-configured bucket trucks of various specifications, select the bucket truck model that meets the requirements of the bucket truck usage conditions and specifications.

[0109] ② Determine the reach of the bucket truck's working bucket

[0110] Combined with the selected boom truck model and on-site parameters related to the power supply operation of the generator truck, the reachable range of the working bucket that meets the requirements of the boom truck's operating conditions and specifications is determined from the three-dimensional point cloud data of the power supply operation site of the generator truck.

[0111] As a specific implementation method, the key parameters of the selected boom truck model, such as boom length, rotation angle, etc., are collected, and a three-dimensional kinematic model is constructed based on this to define the theoretical reachable space; at the same time, the three-dimensional point cloud coordinates of the power supply operation site of the power generation vehicle (referred to as the on-site point cloud coordinates) and the boom truck model are unified in the coordinate system, and the three-dimensional point cloud coordinates of the obstacles in the on-site parameters are obtained (referred to as the obstacle point cloud coordinates). Then, based on the kinematic positive solution, the coordinate range of all possible postures of the working bucket is calculated, and then a Boolean operation is performed with the obstacle point cloud coordinates to exclude the occluded area, and the boundary points of the remaining space are extracted to generate the reachable range outline. Afterwards, the boom truck model, on-site point cloud coordinates and reachable range are visualized in three dimensions with the help of professional software, and verified and corrected in combination with the actual operation scene, uncovered obstacles are excluded, and the reachable range of the boom truck working bucket is output to meet the requirements of the boom truck use condition specification indicators.

[0112] ③Determine the optimal working path of the bucket truck

[0113] A three-dimensional model of the bucket truck's motion envelope, including the working bucket, multi-section arm, and rotating base, is constructed. Interference detection is performed based on this model and point cloud data of environmental obstacles to identify risk areas where the working bucket and arm may collide with surrounding obstacles during movement. Based on the risk area identification results and combined with the constraints required by the bucket truck's usage specification indicators, a path planning algorithm (such as RRT or artificial potential field method) is used to search for the optimal working bucket operation trajectory that meets safety and accessibility, ensuring that the bucket truck dynamically avoids obstacles during movement, and ultimately determining the optimal operating path of the bucket truck.

[0114] ④Determine the parking range of the bucket truck

[0115] Based on the on-site parameters related to the power supply operation of the generator truck, the parking range of the bucket truck is determined from the three-dimensional point cloud data of the power supply operation site of the generator truck, so that it meets the requirements of the standard indicators of the bucket truck's use conditions.

[0116] (2) Based on the pre-built specification indicators of the generator truck's operating conditions and combined with the on-site parameters related to the generator truck's power supply operation, the generator truck's applicability is evaluated and an operation plan is generated.

[0117] The power generation capacity of a generator truck is a key factor in ensuring reliable power supply operations. However, its actual use depends not only on its own performance indicators but also on a combination of factors such as environmental conditions, access point selection, and parking location. Specifically, based on the on-site parameters related to the generator truck's power supply operations and the on-site 3D point cloud data, the actual operating conditions at the generator truck's power supply site can be determined from two perspectives: on-site equipment and environmental conditions. This allows for a suitability assessment of the generator truck. Specific assessment details can be shown in the example provided in Table 3. If all assessment items are met, the generator truck is considered eligible for use; if one or more items are not met, the generator truck is not eligible for use.

[0118] Table 3

[0119]

[0120] Based on the generator vehicle suitability assessment, the generator vehicle usage condition specification indicators can be set to be implemented by at least the following set specification category constraints: electrical connection rules, space layout rules, and cable laying rules. Table 4 below is an example of a generator vehicle usage condition specification indicator provided in this embodiment.

[0121] Table 4

[0122]

[0123]

[0124] Exemplarily, generating an operation plan for a power generation vehicle includes: determining the access point and parking location of the power generation vehicle. Specifically, based on pre-established power generation vehicle usage condition specification indicators, combined with the identified parameters such as the topography, obstacle distribution, and location of the conductors to be operated at the power generation vehicle power supply operation site, first evaluate the area that meets the spatial layout constraints (such as minimum operating space 8m×3m, minimum turning radius ≥6m, slope ≤5°, load-bearing capacity ≥150kPa) and preliminarily determine the parking location of the power generation vehicle; then match the appropriate access point according to electrical access rules such as voltage, phase, and harmonics, and plan the cable path in combination with cable laying rules and constraints; finally, verify and optimize the safety distance, operating range, and environmental constraints to ensure that the access point and parking location of the power generation vehicle achieve the optimal configuration in terms of electrical matching, operational safety, and operating efficiency.

[0125] (3) Based on the pre-built insulation shielding specification indicators and combined with the on-site parameters related to the power supply operation of the power generation vehicle, an insulation shielding plan is generated.

[0126] During implementation, the insulation shielding scope, materials, and operating standards that meet the insulation shielding specification requirements can be determined based on the 3D point cloud data of the generator truck power supply operation site and relevant on-site parameters of the generator truck power supply operation to ensure electrical safety during the operation. Table 5 below provides some examples of insulation shielding specification indicators.

[0127] Table 5

[0128]

[0129] Preferably, generating an insulation shielding scheme includes:

[0130] Detect charged objects within the operating range based on on-site parameters related to the power supply operation of the generator truck;

[0131] Determine insulation shielding scope, sequence, and tools based on pre-built insulation shielding specifications and test results.

[0132] Typically, determining the insulation shielding range includes:

[0133] Determine whether there is a potential safety risk based on the distance between the working position of the power supply operator on the generator truck and the charged object;

[0134] Calculate the range of motion of the power supply operator on the power generation vehicle: A = B + T + M + N, where B represents the arm span of the power supply operator on the power generation vehicle, T represents the length of the operating tool of the power supply operator on the power generation vehicle, M represents the amplitude of the operating movement of the power supply operator on the power generation vehicle, and N represents the movable distance of the power supply operator on the working bucket of the boom truck;

[0135] Determine the insulation shielding range based on the risk assessment results and activity range calculation results.

[0136] Among them, if the distance between the working position of the power supply operator of the power generation vehicle and the charged object is greater than the set distance threshold, it is judged that there is no potential safety risk. At this time, the internal area of ​​the sphere with the waist of the power supply operator of the power generation vehicle as the center and R as the radius is used as the insulation shielding range, where R=A+D, and D represents the safety distance specified by the insulation shielding specification indicators. If the distance between the working position of the power supply operator of the power generation vehicle and the charged object is less than or equal to the set distance threshold, it is judged that there is a potential safety risk. At this time, the internal area of ​​the sphere with the waist of the power supply operator of the power generation vehicle as the center and (R+extended distance) as the radius is used as the insulation shielding range. The extended distance can be set by those skilled in the art based on experience, for example, 0.3m.

[0137] The technical solution provided in this embodiment collects and analyzes three-dimensional point cloud data from the generator truck power supply operation site, automatically identifies key site parameters, and integrates this data with a multi-dimensional operating condition standard indicator system for intelligent analysis to generate a scientific and reliable operation decision-making plan. This solution effectively addresses the data distortion caused by traditional reliance on manual surveys, assessment bias caused by experience-based approaches, low manual verification efficiency, and insufficient early warning capabilities. It achieves standardized and automated operating condition assessments and dynamic risk warnings, significantly improving the safety, standardization, and decision-making efficiency of generator truck power supply operations.

[0138] Example 2

[0139] Based on the above-mentioned embodiment 1, this embodiment further optimizes the step of "identifying on-site parameters related to the power supply operation of the power generation vehicle". Figure 2 , an intelligent decision-making method for power supply operation of a power generation vehicle includes the following steps 201-204.

[0140] Step 201: Acquire three-dimensional point cloud data of the power supply operation site of the power generation vehicle.

[0141] This step 201 is the same as step 101 in the above embodiment 1 and will not be described again here.

[0142] Step 202: Use a deep learning-based network model to perform semantic segmentation on the three-dimensional point cloud data.

[0143] In order to accurately identify and classify various objects in the three-dimensional point cloud data of the power generation truck power supply operation site, this embodiment proposes a semantic segmentation mechanism that integrates global and local features. This step 202 may include the following sub-steps:

[0144] Sub-step 2021: using a first network model based on deep learning to extract global features of the three-dimensional point cloud data;

[0145] Sub-step 2022: using a second network model based on deep learning to extract local features of the three-dimensional point cloud data;

[0146] Sub-step 2023: Associating the global features with the local features to construct a multi-scale feature representation;

[0147] Sub-step 2024: Obtain a semantic segmentation result of the three-dimensional point cloud data based on the multi-scale feature representation.

[0148] In this way, objects and environments in the three-dimensional point cloud data, such as towers, conductors, insulators, ground, and obstacles, can be accurately identified. Among them, the first network model is used to capture the overall structure and scene context information (such as scene type and spatial relationship between objects) of the three-dimensional point cloud data of the power supply operation site of the power generation vehicle. Specifically, the PointNet model can be used. PointNet is a network model that directly performs deep learning on three-dimensional point cloud data. The model takes the three-dimensional point cloud coordinates of the power supply operation site of the power generation vehicle as input, first uses a multi-layer perceptron to perform dimensionality increase on the point cloud, and then obtains global features through maximum pooling.

[0149] The second network model is used to capture the fine structure and local geometric features (such as object edges, surface curvature, and inter-component connectivity) of the 3D point cloud data at the power generation truck operation site. This second network model (such as the FP layer of PointNet++ or the local convolution of PointCNN) is used to segment the 3D point cloud at the power generation truck operation site into local regions (e.g., using KNN or voxel grids) and extract features from each region. For example, identifying local details such as the cable interface of the power generation truck and the joint structure of the boom truck is crucial for accurately segmenting small targets or complex structures.

[0150] After obtaining the global and local features of the 3D point cloud data from the generator truck's power supply operation site, the global and local features are linked together through concatenation, attention mechanisms, or weighted summation to form a multi-scale feature representation that combines scene context and local details. For example, concatenation involves expanding global features to the same dimension as local features and then directly concatenating them; attention mechanisms automatically focus on important local areas (such as obstacle edges) through weighted assignment.

[0151] The multi-scale feature representation is then mapped to a semantic label (e.g., "generator," "cable," "obstacle") for each point in the 3D point cloud of the generator truck's power supply operation site. Specifically, a fully connected layer or decoder network is used to convert the multi-scale feature representation into a classification probability for each point in the 3D point cloud of the generator truck's power supply operation site. Semantic labels are then assigned to each point based on the principle of maximum probability, forming a complete semantic segmentation result.

[0152] As a preferred embodiment, see Figure 3 , the above sub-step 2022 includes the following operations (1)-(6).

[0153] (1) The intermediate features of the three-dimensional point cloud at the first scale are embedded in the three-dimensional point cloud data of the power supply operation site of the generator truck to obtain the first three-dimensional point cloud data.

[0154] The purpose of this operation (1) is to capture the detailed information within a smaller range in the point cloud, such as key local structures such as pole tower connections and conductor bends. For example, based on the original three-dimensional point cloud data of the power generation vehicle power supply operation site, intermediate features at a finer granularity (such as local neighborhood structure) can be extracted. For example, a smaller convolution kernel (such as 3*3) is used to perform sliding window convolution on each point in the three-dimensional point cloud of the power generation vehicle power supply operation site, and the local micro features are captured as intermediate features by calculating the spatial relationship between the center point and the neighborhood point, or with the help of the point cloud convolution operator, the geometric topological relationship of the single point area is focused on with a smaller receptive field (covering the number of points <50), and the subtle structural features are extracted as intermediate features. Then, the intermediate features are embedded into the three-dimensional point cloud data of the power generation vehicle power supply operation site to form a feature-enhanced point cloud representation with first scale information (the number of points remains unchanged, and the feature information is increased), which is called the first three-dimensional point cloud data.

[0155] (2) The intermediate features of the three-dimensional point cloud at the second scale are embedded in the three-dimensional point cloud data of the power supply operation site of the generator truck to obtain the second three-dimensional point cloud data.

[0156] The purpose of this operation (2) is to obtain structural features that are more macroscopic than the first step, such as the overall layout of power facilities, the undulating trend of the terrain, etc. For example, based on the original three-dimensional point cloud data of the power generation vehicle power supply operation site, intermediate features at a coarser granularity (such as a larger range of spatial distribution or contextual information) can be extracted to reflect the structural information of a wider area. For example, a larger convolution kernel (such as 9*9) is used to perform sliding window convolution on each point in the three-dimensional point cloud of the power generation vehicle power supply operation site, and the local medium-scale features are captured as intermediate features by calculating the spatial relationship between the center point and the neighborhood points, or with the help of the point cloud convolution operator, the geometric topological relationship of the single point area is focused on with a larger receptive field (covering 50-200 points), and the medium-scale feature features with structural significance are extracted as intermediate features. Then, similarly, the intermediate features are embedded into the three-dimensional point cloud data of the power generation vehicle power supply operation site to form a feature-enhanced point cloud representation with second-scale information (the number of points remains unchanged, and the feature information is increased), which is called the second three-dimensional point cloud data.

[0157] (3) Based on the attention mechanism, the association weights between the intermediate features at two scales are calculated.

[0158] In operation (3), an attention mechanism (such as Self-Attention or Cross-Attention) is introduced to automatically learn the association weights of the intermediate features extracted at two different scales to avoid information redundancy or loss caused by simple fusion. Specifically, the association weights can be obtained by training a pre-created neural network.

[0159] For example, the intermediate features of the first scale and the second scale are mapped to the shared feature space through linear transformation, generating query and key vectors. The dot product similarity between the two is then calculated and normalized through the softmax function to obtain a weight matrix reflecting the degree of feature association. During the training phase, the neural network can be optimized by using a loss function (such as the cross-entropy loss in semantic segmentation tasks). The loss value is back-propagated to update the parameters of the neural network (such as the weights of the linear transformation), so that the neural network gradually learns to assign higher weights to key features (such as obstacle edges and equipment interfaces) in different scenarios, thereby improving its understanding of complex power operation scenarios.

[0160] (4) According to the calculated association weight, the first three-dimensional point cloud data and the second three-dimensional point cloud data are weightedly fused to obtain the third three-dimensional point cloud data.

[0161] In operation (4), the feature representation of the first three-dimensional point cloud data and the second three-dimensional point cloud data can be determined first, for example, by extracting their respective point cloud feature vectors. Then, the calculated association weight is applied to the feature vectors of the two sets of point cloud data. The size of the weight reflects the importance of each point cloud feature in the two sets of data. For each corresponding point cloud feature, the association weight is used for weighted combination to obtain the fused feature. Finally, the third three-dimensional point cloud data is generated based on the fused feature, so that the third three-dimensional point cloud data can comprehensively retain the key feature information of the first two sets of data and highlight the important feature parts according to the weight.

[0162] The fused point cloud data not only retains local details, but also integrates global structural information, has stronger semantic expression ability and discriminability, and provides high-quality feature input for subsequent semantic segmentation.

[0163] (5) Perform multi-level downsampling on the third 3D point cloud data, and extract the semantic features of the sampled point cloud data at each level after downsampling.

[0164] In operation (5), by downsampling, the point cloud density is gradually reduced, key contour points are retained, and it is easier to extract the edge features of the point cloud, and the semantic segmentation speed can be improved. In specific implementation, each level of downsampling can use the farthest point sampling method to reduce the number of point clouds. As the downsampling proceeds, the detail points are gradually filtered out, and the edge and contour points (points with large curvature changes) are retained to form a "skeletonized" point cloud. At the same time, for each level of downsampling, deep semantic features are further extracted from the point cloud data.

[0165] (6) The semantic features extracted after multi-level downsampling are propagated step by step to the point cloud resolution before downsampling through upsampling to obtain the local features.

[0166] The purpose of operation (6) is to "transfer" the semantic features of the deep level back to the original resolution and generate local features containing multi-scale information. Specifically, the point cloud density can be restored step by step through deconvolution or interpolation (such as nearest neighbor interpolation, bilinear interpolation), for example: semantic features extracted at level 4 -> upsample to level 3 resolution -> fuse semantic features extracted at level 3 -> upsample to level 2 resolution ->... -> restore to original resolution. The feature propagation mechanism can be a skip connection: at each upsampling, the semantic features extracted at the current level are fused with the semantic features of the corresponding level at the time of downsampling. The propagation rule can be: high-level features guide the semantic understanding of low-level features, for example: the "tower" semantics captured at the deep level helps shallow features distinguish insulators from other components.

[0167] Step 203: Identify on-site parameters related to the power supply operation of the power generation vehicle based on the semantic segmentation result.

[0168] The field parameters include power facility parameters (such as the physical dimensions of power equipment such as towers, crossarms, and insulators) and channel environment parameters (such as terrain slope, ground type and load-bearing capacity, and the location and distribution of surrounding obstacles). The following explains the identification process for these two types of parameters in detail.

[0169] (1) Based on the point cloud data of power facilities identified in the semantic segmentation results, the geometric fitting and projection analysis methods are used to calculate the power facility parameters related to the power supply operation of the power generation vehicle.

[0170] ①Calculate tower height

[0171] Based on the tower point cloud data identified in the semantic segmentation results: fitting the ground plane; calculating the distance from the tower point cloud to the ground plane to determine the tower height.

[0172] First, a ground plane is fitted from the tower point cloud data (i.e., the point cloud data of the tower in the three-dimensional point cloud data of the power generation vehicle power supply operation site) as a reference for calculating the tower height. Then, based on the tower point cloud data, a minimum bounding box of the tower point cloud is constructed, and the vertical distance from each tower point to the fitted ground plane is calculated. Finally, the largest distance from all calculated vertical distances is selected as the tower height.

[0173] ②Calculate the crossarm length

[0174] Based on the crossarm point cloud data identified in the semantic segmentation results: fitting the crossarm plane; projecting the crossarm point cloud onto the crossarm plane; fitting the minimum circumscribed circle on the crossarm point cloud projection to determine the crossarm length.

[0175] First, a plane representing the crossarm's position, known as the crossarm plane, is fitted from the crossarm point cloud data (i.e., the crossarm point cloud data from the 3D point cloud data of the generator truck's power supply operation site). The crossarm point cloud is then projected onto the fitted crossarm plane to eliminate any tilt or rotation errors. Next, a minimum circumscribed circle is fitted to the projected crossarm point cloud. The diameter of this circumscribed circle is the length of the crossarm, as crossarms are generally assumed to have a circular or approximately circular cross-section.

[0176] Optionally, the cross-arm spacing may be further calculated: based on the voxelized cross-arm point cloud data, the center position of the cross-arm is identified, and the distance between adjacent cross-arms is calculated.

[0177] ③Calculate the insulator disk diameter

[0178] Based on the insulator point cloud data identified in the semantic segmentation results: fit the axial direction of the insulator; calculate the maximum spacing of the insulator point cloud in the axial direction, and determine the insulator height based on the maximum spacing; project the insulator point cloud onto a plane perpendicular to the axial direction, and fit the minimum circumscribed circle on the insulator point cloud projection to determine the insulator disk diameter.

[0179] Fitting the insulator's axial direction includes constructing a minimum bounding box for the insulator point cloud based on the insulator point cloud data (i.e., the insulator point cloud data in the three-dimensional point cloud data of the power generation vehicle power supply operation site), and determining the axial direction of the insulator point cloud data using principal component analysis. The maximum spacing of the insulator point cloud in the axial direction is the insulator height. The diameter of the minimum circumscribed circle fitted on the insulator point cloud projection is the insulator disc diameter.

[0180] (2) Based on the point cloud data of environmental objects identified in the semantic segmentation results, the channel environmental parameters related to the power supply operation of the power generation vehicle are determined.

[0181] ① Based on the point cloud data of the working channel pavement identified in the semantic segmentation results, determine the width and slope of the working channel pavement.

[0182] Among them, the working channel pavement point cloud data identified in the semantic segmentation results can be plane fitted to extract the plane equation of the pavement; the working channel pavement point cloud data can be projected onto the fitting plane and sliced ​​along the direction of travel to generate a two-dimensional contour line; the pavement width is calculated based on the horizontal distance between the boundary points of the two-dimensional contour line, and the slope is calculated based on the elevation change.

[0183] ② Based on the obstacle point cloud data identified in the semantic segmentation results, determine the obstacle removability judgment results and spatial distribution parameters.

[0184] Non-removable obstacles include houses, light poles, etc., which must be avoided during operations. Removable obstacles include trees, vehicles, etc., which can be removed to optimize the operation path and vehicle parking location when necessary.

[0185] During specific operations, the geometric features and spatial position information of the obstacles identified in the semantic segmentation results can be extracted, and combined with the preset removability judgment rules (such as size, material, fixing method, etc.) to determine whether the obstacles are removable; at the same time, the spatial distribution parameters of the obstacles, including position coordinates, density distribution and relative distance from the operation path, are counted to provide an environmental analysis basis for subsequent operation analysis and decision-making.

[0186] Step 204: Based on the pre-built multi-dimensional operating condition specification indicator system and the field parameters, generate a power generation vehicle power supply operation analysis decision.

[0187] This step 204 is the same as step 103 in the above-mentioned embodiment 1, and will not be described again here.

[0188] The technical solution provided in this embodiment extracts the global features of point cloud data through the first network model, and at the same time obtains local detail features and context information respectively with the help of the second network model, and further strengthens the edge features of the point cloud using the attention mechanism, downsampling and upsampling operations, and can adaptively balance the weights of global semantics and local details. This design not only makes up for the defect of traditional PointNet that ignores local features and solves the limitations of PointNet++ in the segmentation of distribution line components, but also significantly improves the segmentation accuracy of complex structures and small target components through multi-scale feature fusion, effectively reducing the phenomenon of mis-segmentation and missed segmentation.

[0189] Example 3

[0190] This embodiment provides an intelligent decision-making device for power supply operation of a power generation vehicle, which can be used to execute the intelligent decision-making method for power supply operation of a power generation vehicle described in an embodiment of the present invention and can be implemented by software and / or hardware.

[0191] See also Figure 4 , the device specifically includes the following modules:

[0192] The data acquisition module 401 is used to acquire three-dimensional point cloud data of the power supply operation site of the power generation vehicle;

[0193] A parameter identification module 402 is used to analyze the three-dimensional point cloud data and identify on-site parameters related to the power supply operation of the power generation vehicle;

[0194] The decision generation module 403 is used to generate a power generation vehicle power supply operation analysis decision based on a pre-built multi-dimensional operating condition specification indicator system and the field parameters.

[0195] Furthermore, the parameter identification module 402 includes:

[0196] A semantic segmentation unit 4021 is configured to perform semantic segmentation on the three-dimensional point cloud data using a deep learning network model;

[0197] The on-site parameter determination unit 4022 is used to identify on-site parameters related to the power supply operation of the power generation vehicle based on the semantic segmentation results of the semantic segmentation subunit.

[0198] Furthermore, the semantic segmentation unit 4021 includes:

[0199] a global feature extraction subunit, configured to extract global features of the three-dimensional point cloud data using a first network model based on deep learning;

[0200] a local feature extraction subunit, configured to extract local features of the three-dimensional point cloud data using a second network model based on deep learning;

[0201] A feature fusion subunit, configured to associate the global features with the local features to construct a multi-scale feature representation;

[0202] The segmentation result generating subunit is used to obtain a semantic segmentation result of the three-dimensional point cloud data based on the multi-scale feature representation.

[0203] Exemplarily, the local feature extraction subunit is specifically configured to extract local features of the three-dimensional point cloud data using a second network model based on deep learning, and may include:

[0204] embedding intermediate features of the three-dimensional point cloud at a first scale into the three-dimensional point cloud data to obtain first three-dimensional point cloud data;

[0205] embedding intermediate features of the three-dimensional point cloud at a second scale into the three-dimensional point cloud data to obtain second three-dimensional point cloud data;

[0206] Based on the attention mechanism, the association weights between the intermediate features at two scales are calculated;

[0207] weightedly fusing the first three-dimensional point cloud data and the second three-dimensional point cloud data according to the calculated association weight to obtain third three-dimensional point cloud data;

[0208] Performing multi-level downsampling on the third three-dimensional point cloud data, and extracting semantic features of the sampled point cloud data at each level after downsampling;

[0209] The semantic features extracted after multi-level downsampling are propagated step by step to the point cloud resolution before downsampling through upsampling to obtain the local features.

[0210] Exemplarily, the field parameter determination unit 4022 is specifically configured to identify field parameters related to the power supply operation of the power generation vehicle based on the semantic segmentation result, including:

[0211] Based on the point cloud data of power facilities identified in the semantic segmentation results, geometric fitting and projection analysis methods are used to calculate the power facility parameters related to the power supply operation of the generator truck;

[0212] Based on the point cloud data of environmental objects identified in the semantic segmentation results, the channel environmental parameters related to the power supply operation of the power generation vehicle are determined.

[0213] The field parameter determination unit 4022 is specifically used to calculate the power facility parameters related to the power supply operation of the power generation vehicle based on the power facility point cloud data identified in the semantic segmentation results, using geometric fitting and projection analysis methods, which may include:

[0214] Based on the tower point cloud data identified in the semantic segmentation result: fitting a ground plane; calculating the distance between the tower point cloud and the ground plane to determine the tower height;

[0215] Based on the crossarm point cloud data identified in the semantic segmentation result: fitting a crossarm plane; projecting the crossarm point cloud onto the crossarm plane; fitting a minimum circumscribed circle on the crossarm point cloud projection to determine the crossarm length;

[0216] Based on the insulator point cloud data identified in the semantic segmentation results: fit the axial direction of the insulator; calculate the maximum spacing of the insulator point cloud in the axial direction, and determine the insulator height based on the maximum spacing; project the insulator point cloud onto a plane perpendicular to the axial direction, and fit the minimum circumscribed circle on the insulator point cloud projection to determine the insulator disk diameter.

[0217] The field parameter determination unit 4022 is specifically used to determine the channel environment parameters related to the power supply operation of the power generation vehicle based on the point cloud data of the environmental objects identified in the semantic segmentation results, which may include:

[0218] Determine the width and slope of the working channel road surface based on the point cloud data of the working channel road surface identified in the semantic segmentation results;

[0219] Based on the obstacle point cloud data identified in the semantic segmentation results, the obstacle removability judgment results and spatial distribution parameters are determined.

[0220] Exemplarily, the decision generation module 403 includes:

[0221] The boom truck operation decision unit 4031 is configured to evaluate the suitability of the boom truck and generate an operation plan based on pre-established boom truck use condition specification indicators and the site parameters; wherein the boom truck use condition specification indicators are implemented by at least the following set specification category constraints: motion range verification rules, parking area screening rules, and safe operation rules; and / or

[0222] The generator vehicle operation decision unit 4032 is configured to evaluate the suitability of the generator vehicle and generate an operation plan based on pre-established generator vehicle usage condition specification indicators and the site parameters; wherein the generator vehicle usage condition specification indicators are implemented by at least the following set specification category constraints: electrical connection rules, space layout rules, and cable laying rules; and / or

[0223] The insulation shielding decision unit 4033 is used to generate an insulation shielding plan based on the pre-built insulation shielding specification indicators and the field parameters.

[0224] The insulation shielding decision unit 4033 is specifically configured to generate an insulation shielding plan based on pre-built insulation shielding specification indicators and the field parameters, and may include:

[0225] Detecting charged objects within the operating range according to the on-site parameters;

[0226] Determine insulation shielding scope, sequence, and tools based on pre-built insulation shielding specifications and test results.

[0227] Typically, the insulation shielding decision unit 4033 is specifically used to determine the insulation shielding range, including:

[0228] Determine whether there is a potential safety risk based on the distance between the working position of the power supply operator on the generator truck and the charged object;

[0229] Calculate the range of motion of the power supply operator on the power generation vehicle: A = B + T + M + N, where B represents the arm span of the power supply operator on the power generation vehicle, T represents the length of the operating tool of the power supply operator on the power generation vehicle, M represents the amplitude of the operating movement of the power supply operator on the power generation vehicle, and N represents the movable distance of the power supply operator on the working bucket of the boom truck;

[0230] Determine the insulation shielding range based on the risk assessment results and activity range calculation results.

[0231] Furthermore, the data acquisition module 401 may include:

[0232] The image acquisition unit 4011 is used to acquire a multi-view image sequence of the power supply operation site of the power generation vehicle;

[0233] A point cloud data construction unit 4012 is configured to process the multi-view image sequence to construct sparse point cloud data;

[0234] The point cloud data optimization unit 4013 is used to generate dense point cloud data based on the sparse point cloud data based on the set depth map fusion algorithm.

[0235] The intelligent decision-making device for power supply operation of a power generation vehicle in this embodiment can implement the intelligent decision-making method for power supply operation of a power generation vehicle described in any of the aforementioned embodiments. Its implementation principles and corresponding technical effects are basically the same and will not be repeated here.

[0236] Figure 5 FIG. 1 is a schematic diagram of the structure of an embodiment of an electronic device of the present invention, which can implement the process of the embodiment of the method of the present invention, such as Figure 5 As shown, the above-mentioned electronic device may include: a shell 51, a processor 52, a memory 53, a circuit board 54 and a power supply circuit 55, wherein the circuit board 54 is placed inside the space enclosed by the shell 51, and the processor 52 and the memory 53 are arranged on the circuit board 54; the power supply circuit 55 is used to supply power to various circuits or devices of the above-mentioned electronic device; the memory 53 is used to store executable program code; the processor 52 runs the program corresponding to the executable program code by reading the executable program code stored in the memory 53, so as to execute the intelligent decision-making method for power supply operation of the power generation vehicle described in any of the above-mentioned embodiments.

[0237] The specific execution process of the above steps by the processor 52 and the steps further executed by the processor 52 by running the executable program code can be found in the description of the embodiment of the method of the present invention, and will not be repeated here.

[0238] This electronic device exists in many forms, including but not limited to:

[0239] (1) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server has a similar architecture to a general computer, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0240] (2) Other electronic equipment with data processing and communication functions.

[0241] Furthermore, an embodiment of the present invention also provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the intelligent decision-making method for power supply operation of the power generation vehicle described in the above embodiment.

[0242] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0243] In embodiments of the present invention, the term "and / or" describes the association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0244] Each embodiment in this specification is described in a related manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0245] In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0246] For the convenience of description, the above device is described as being divided into various units / modules based on their functions. Of course, when implementing the present invention, the functions of each unit / module can be implemented in the same or multiple software and / or hardware.

[0247] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0248] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An intelligent decision-making method for power supply operation of a power generation vehicle, characterized in that: include: Obtain 3D point cloud data of the power generation truck's power supply operation site; Analyzing the three-dimensional point cloud data to identify on-site parameters related to the power supply operation of the generator truck; Based on the pre-built multi-dimensional operating condition specification indicator system and the field parameters, an analysis and decision on the power supply operation of the power generation vehicle is generated.

2. The method according to claim 1, characterized in that Analyze the three-dimensional point cloud data to identify on-site parameters related to the power supply operation of the generator truck, including: Performing semantic segmentation on the three-dimensional point cloud data using a deep learning-based network model; Based on the semantic segmentation results, the on-site parameters related to the power supply operation of the power generation vehicle are identified.

3. The method according to claim 2, characterized in that Using a deep learning network model, semantic segmentation is performed on the three-dimensional point cloud data, including: Using a first network model based on deep learning to extract global features of the three-dimensional point cloud data; Using a second network model based on deep learning to extract local features of the three-dimensional point cloud data; Associating the global features with the local features to construct a multi-scale feature representation; Based on the multi-scale feature representation, a semantic segmentation result of the three-dimensional point cloud data is obtained.

4. The method according to claim 3, characterized in that A second network model based on deep learning is used to extract local features of the three-dimensional point cloud data, including: embedding intermediate features of the three-dimensional point cloud at a first scale into the three-dimensional point cloud data to obtain first three-dimensional point cloud data; embedding intermediate features of the three-dimensional point cloud at a second scale into the three-dimensional point cloud data to obtain second three-dimensional point cloud data; Based on the attention mechanism, the association weights between the intermediate features at two scales are calculated; weightedly fusing the first three-dimensional point cloud data and the second three-dimensional point cloud data according to the calculated association weight to obtain third three-dimensional point cloud data; Performing multi-level downsampling on the third three-dimensional point cloud data, and extracting semantic features of the sampled point cloud data at each level after downsampling; The semantic features extracted after multi-level downsampling are propagated step by step to the point cloud resolution before downsampling through upsampling to obtain the local features.

5. The method according to claim 2, identifying on-site parameters related to the power supply operation of the power generation vehicle based on the semantic segmentation results, comprises: Based on the point cloud data of power facilities identified in the semantic segmentation results, geometric fitting and projection analysis methods are used to calculate the power facility parameters related to the power supply operation of the generator truck; Based on the point cloud data of environmental objects identified in the semantic segmentation results, the channel environmental parameters related to the power supply operation of the power generation vehicle are determined.

6. The method according to claim 5, based on the power facility point cloud data identified in the semantic segmentation results, uses geometric fitting and projection analysis methods to calculate power facility parameters related to the power supply operation of the power generation vehicle, including: Based on the tower point cloud data identified in the semantic segmentation results: fit the ground plane; Calculating the distance between the tower point cloud and the ground plane to determine the tower height; Based on the crossarm point cloud data identified in the semantic segmentation result: fitting a crossarm plane; projecting the crossarm point cloud onto the crossarm plane; fitting a minimum circumscribed circle on the crossarm point cloud projection to determine the crossarm length; Based on the insulator point cloud data identified in the semantic segmentation results: fit the axial direction of the insulator; calculate the maximum spacing of the insulator point cloud in the axial direction, and determine the insulator height based on the maximum spacing; project the insulator point cloud onto a plane perpendicular to the axial direction, and fit the minimum circumscribed circle on the insulator point cloud projection to determine the insulator disk diameter.

7. The method according to claim 5, determining channel environmental parameters related to the power supply operation of the power generation vehicle based on the point cloud data of the environmental objects identified in the semantic segmentation results, comprises: Determine the width and slope of the working channel road surface based on the point cloud data of the working channel road surface identified in the semantic segmentation results; Based on the obstacle point cloud data identified in the semantic segmentation results, the obstacle removability judgment results and spatial distribution parameters are determined.

8. The method according to claim 1, characterized in that Based on the pre-built multi-dimensional operating condition specification indicator system and the site parameters, the power generation vehicle power supply operation analysis decision is generated, including: Based on the pre-established boom truck usage condition specification indicators, combined with the site parameters, the boom truck is evaluated for suitability and an operation plan is generated; wherein the boom truck usage condition specification indicators are implemented by at least the following set specification category constraints: motion range verification rules, parking area screening rules and safe operation rules; and / or Based on pre-established generator vehicle usage condition specification indicators and in combination with the site parameters, the generator vehicle is evaluated for suitability and an operation plan is generated; wherein the generator vehicle usage condition specification indicators are implemented by at least the following set specification category constraints: electrical connection rules, space layout rules, and cable laying rules; and / or Based on the pre-built insulation shielding specification indicators and combined with the site parameters, an insulation shielding plan is generated.

9. The method according to claim 8, characterized in that Based on the pre-built insulation shielding specification indicators and combined with the site parameters, an insulation shielding plan is generated, including: Detecting charged objects within the operating range according to the on-site parameters; Determine insulation shielding scope, sequence, and tools based on pre-built insulation shielding specifications and test results.

10. The method according to claim 9, characterized in that Determine the insulation shielding range, including: Determine whether there is a potential safety risk based on the distance between the working position of the power supply operator on the generator truck and the charged object; Calculate the range of motion of the power supply operator on the power generation vehicle: A = B + T + M + N, where B represents the arm span of the power supply operator on the power generation vehicle, T represents the length of the operating tool of the power supply operator on the power generation vehicle, M represents the amplitude of the operating movement of the power supply operator on the power generation vehicle, and N represents the movable distance of the power supply operator on the working bucket of the boom truck; Determine the insulation shielding range based on the risk assessment results and activity range calculation results.

11. The method according to claim 1, wherein Obtain 3D point cloud data of the generator truck power supply operation site, including: Collect multi-view image sequences of the power generation truck's power supply operation site; Processing the multi-view image sequence to construct sparse point cloud data; Based on the set depth map fusion algorithm, dense point cloud data is generated based on the sparse point cloud data.

12. An intelligent decision-making device for power supply operation of a power generation vehicle, characterized in that: include: A data acquisition unit, used to acquire three-dimensional point cloud data of the power supply operation site of the generator truck; a parameter identification unit, configured to analyze the three-dimensional point cloud data and identify on-site parameters related to the power supply operation of the power generation vehicle; The decision generating unit is used to generate a power generation vehicle power supply operation analysis decision based on a pre-built multi-dimensional operating condition specification indicator system and the field parameters.

13. An electronic device, characterized in that: The electronic device includes: a housing, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is placed inside the space enclosed by the housing, and the processor and the memory are arranged on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the above-mentioned electronic device; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in any of the above claims 1-11.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method described in any one of claims 1 to 11.

Images