Early warning method and device for operation risk of power equipment, and electronic equipment

Through the combination of long-term and short-term memory neural network and three-dimensional panoramic model, the problem of low accuracy in the operation risk assessment of power equipment is solved, intelligent prediction and risk warning of equipment operation status are realized, and the accuracy and safety of evaluation results are improved. .

CN118941072APending Publication Date: 2024-11-12GUANGDONG DIANWANG GONGSI YUNFU POWER SUPPLY BUREAU
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410887750.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-03
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing method of operating risk assessment of power equipment is based on image processing technology, and the results are low and the environmental and location information of the equipment is not effectively considered.

Method used

Using a trajectory prediction model based on long and short-term memory neural network, combined with three-dimensional panoramic model and RTK positioning technology, simulated prediction trajectory comparison is carried out by obtaining positioning information of power equipment, building position vectors and predicted trajectory curves, and determining whether the equipment has operating risks. , trigger risk warning.

Benefits of technology

It improves the accuracy of the operation risk prediction of power equipment, comprehensively considers the environment and location information of the equipment, and enhances the guarantee of the operation safety of large power equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941072A_ABST
    Figure CN118941072A_ABST
Patent Text Reader

Abstract

The invention discloses a power equipment operation risk early warning method and device and electronic equipment, and relates to the technical field of power safety, and the early warning method comprises the steps: obtaining a positioning information set of power equipment in a transformer substation, and constructing a position vector based on the positioning information set; inputting the position vector into a trajectory prediction model, and outputting a control point information set; constructing a prediction trajectory curve based on the control point information set, and fusing the prediction trajectory curve with a pre-constructed three-dimensional panoramic model to obtain a simulation prediction trajectory of the power equipment; and comparing the simulated prediction trajectory with a preset moving trajectory range to obtain a comparison result, and when the comparison result indicates that the simulated prediction trajectory exceeds the moving trajectory range, determining that the electrical equipment has a running risk, and triggering risk early warning. According to the invention, a technical problem that the accuracy of an obtained result is relatively low when the operation risk of the power equipment is evaluated based on an image processing technology in related technologies is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of power grid safety technology, and in particular to an early warning method and device for operation risk of power equipment, and electronic equipment. Background Art

[0002] The power system is one of the indispensable infrastructures in modern society, and the substation, as the hub of the power system, undertakes the functions of power conversion, distribution and dispatching. In the substation, the operating status of large equipment such as transformers and circuit breakers is directly related to the safety and stability of the power grid. However, due to the complex and changeable environment of the substation, the narrow working environment involved in large equipment and the operating errors of operators, there is a certain risk of dangerous behavior in the equipment. Therefore, accurate prediction of the operating risks of large power equipment and timely intervention are of great significance to ensure the safety of power grid operation.

[0003] In the related technologies, for the monitoring of the operating status of large-scale power equipment, the posture and operating status of the equipment can be monitored by sensors to detect abnormal behavior of large-scale power equipment. In addition to sensor technology, image processing technology is also widely used in the monitoring of the operating status of large-scale power equipment. By taking images of power equipment and performing image recognition, intelligent monitoring of the operating status of large-scale power equipment can be achieved. However, the existing monitoring methods do not take into account the environmental information and location information of large equipment, resulting in low accuracy of the results.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method and device for early warning of operation risk of electric power equipment, and electronic equipment, so as to at least solve the technical problem in the related art that the operation risk of electric power equipment is evaluated based on image processing technology, and the accuracy of the obtained results is low.

[0006] According to one aspect of an embodiment of the present invention, there is provided an early warning method for operation risk of electric power equipment, comprising: obtaining a positioning information set of electric power equipment in a substation, and constructing a position vector based on the positioning information in the positioning information set; inputting the position vector into a trajectory prediction model, and outputting a control point information set, wherein the control point information set includes N control points and coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operation trajectory of the electric power equipment based on a long short-term memory neural network; constructing a predicted trajectory curve based on the control point information in the control point information set, and fusing the predicted trajectory curve with a pre-constructed three-dimensional panoramic model to obtain a simulated predicted trajectory of the electric power equipment; comparing the simulated predicted trajectory with a preset operation trajectory range to obtain a comparison result, and when the comparison result indicates that the simulated predicted trajectory exceeds the operation trajectory range, determining that the electric power equipment has an operation risk and triggering a risk warning.

[0007] Optionally, the step of constructing a predicted trajectory curve based on the control point information in the control point information set includes: setting the order of a target B-spline curve; selecting a node vector set based on the number of control points and the order of the target B-spline curve; calculating a B-spline basis function based on the node vector set and the order of the B-spline curve; constructing a target B-spline curve based on the B-spline basis function and the control point information to obtain the predicted trajectory curve.

[0008] Optionally, before obtaining the positioning information set of the power equipment in the substation, it also includes: obtaining the oblique image data of the substation, and preprocessing the oblique image data to obtain preprocessed oblique image data; generating an initial three-dimensional model based on the preprocessed oblique image data; fusing the initial three-dimensional model with the pre-built building information model of the substation to obtain a three-dimensional oblique image model.

[0009] Optionally, after obtaining the three-dimensional oblique image model, it also includes: collecting point cloud data of the substation and preprocessing the point cloud data to obtain preprocessed point cloud data; constructing a triangulated network model based on the preprocessed point cloud data; and fusing the three-dimensional oblique image model with the triangulated network model to obtain the three-dimensional panoramic model.

[0010] Optionally, the trajectory prediction model is pre-constructed, and the steps of constructing the trajectory prediction model include: obtaining a set of historical positioning information of the power equipment; constructing a sample set based on the set of historical positioning information, and dividing the sample set into a training set and a test set based on a preset ratio; building an initial trajectory prediction model based on a long short-term memory neural network; iteratively training the initial trajectory prediction model based on the training set to obtain a trained trajectory prediction model; testing the trained trajectory prediction model based on the test set to obtain a test result, and when the test result indicates that the trained trajectory prediction model passes the test, the trained trajectory prediction model is obtained.

[0011] Optionally, the step of constructing a sample set based on the historical positioning information set includes: calculating the parameter value and node vector of each trajectory point corresponding to the historical positioning information in the historical positioning information set on the B-spline curve; calculating the parameter value and the node vector of each trajectory point by the least squares method to obtain the historical control point set of the B-spline curve; constructing training samples based on the historical positioning information set and the historical control point set; and vectorizing the training samples to obtain the sample set.

[0012] Optionally, the step of calculating the parameter values ​​and node vectors of each trajectory point on the B-spline curve corresponding to the historical positioning information in the historical positioning information set includes: fitting the B-spline curve based on the historical positioning information in the historical positioning information set to obtain a trajectory point set of the power equipment on the B-spline curve, wherein the trajectory point set includes M trajectory points and coordinate values ​​corresponding to the trajectory points; calculating the total chord length of the B-spline curve based on the coordinate values ​​of the trajectory points; calculating the parameter values ​​of the trajectory points based on the coordinate values ​​and the total chord length of two adjacent trajectory points to obtain the parameter values ​​of each trajectory point; obtaining the order of the B-spline curve, and calculating the node vectors of each trajectory point based on the order of the B-spline curve and the parameter values ​​of each trajectory point.

[0013] According to another aspect of an embodiment of the present invention, there is also provided an early warning device for operation risk of electric power equipment, comprising: an acquisition unit, used to acquire a positioning information set of electric power equipment in a substation, and construct a position vector based on the positioning information in the positioning information set; an output unit, used to input the position vector into a trajectory prediction model, and output a control point information set, wherein the control point information set includes N control points and coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operation trajectory of the electric power equipment based on a long short-term memory neural network; a fusion unit, used to construct a predicted trajectory curve based on the control point information in the control point information set, and fuse the predicted trajectory curve with a pre-constructed three-dimensional panoramic model to obtain a simulated predicted trajectory of the electric power equipment; an early warning unit, used to compare the simulated predicted trajectory with a preset operation trajectory range to obtain a comparison result, and when the comparison result indicates that the simulated predicted trajectory exceeds the operation trajectory range, it is determined that the electric power equipment has an operation risk and a risk warning is triggered.

[0014] Optionally, the fusion unit includes: a first setting subunit, used to set the order of the target B-spline curve; a first selection subunit, used to select a node vector set based on the number of control points and the order of the target B-spline curve; a first calculation subunit, used to calculate the B-spline basis function based on the node vector set and the order of the B-spline curve; and a first construction subunit, used to construct the target B-spline curve based on the B-spline basis function and the control point information to obtain the predicted trajectory curve.

[0015] Optionally, the early warning device for the operation risk of the power equipment also includes: a first acquisition subunit, used to acquire the oblique image data of the substation, and preprocess the oblique image data to obtain preprocessed oblique image data; a first generation subunit, used to generate an initial three-dimensional model based on the preprocessed oblique image data; a first fusion subunit, used to fuse the initial three-dimensional model with a pre-built building information model of the substation to obtain a three-dimensional oblique image model.

[0016] Optionally, the early warning device for the operation risk of the power equipment also includes: a first acquisition subunit, used to acquire point cloud data of the substation, and preprocess the point cloud data to obtain preprocessed point cloud data; a second construction subunit, used to construct a triangulated network model based on the preprocessed point cloud data; a second fusion subunit, used to fuse the three-dimensional oblique image model with the triangulated network model to obtain the three-dimensional panoramic model.

[0017] Optionally, the early warning device for the operation risk of the power equipment also includes: a second acquisition subunit, used to acquire a set of historical positioning information of the power equipment; a third construction subunit, used to construct a sample set based on the set of historical positioning information, and divide the sample set into a training set and a test set based on a preset ratio; a first construction subunit, used to build an initial trajectory prediction model based on a long short-term memory neural network; a first training subunit, used to iteratively train the initial trajectory prediction model based on the training set to obtain a trained trajectory prediction model; a first testing subunit, used to test the trained trajectory prediction model based on the test set to obtain a test result, and when the test result indicates that the trained trajectory prediction model passes the test, the trained trajectory prediction model is obtained.

[0018] Optionally, the third construction subunit includes: a first calculation module, used to calculate the parameter value and node vector of each trajectory point corresponding to the historical positioning information in the historical positioning information set on the B-spline curve; a second calculation module, used to calculate the parameter value of each trajectory point and the node vector by the least squares method to obtain the historical control point set of the B-spline curve; a first construction module, used to construct a training sample based on the historical positioning information set and the historical control point set; a first acquisition module, used to vectorize the training sample to obtain the sample set.

[0019] Optionally, the first calculation module includes: a first fitting submodule, used to fit the B-spline curve based on the historical positioning information in the historical positioning information set, and obtain a trajectory point set of the power equipment on the B-spline curve, wherein the trajectory point set includes M trajectory points and coordinate values ​​corresponding to the trajectory points; a first calculation submodule, used to calculate the total chord length of the B-spline curve based on the coordinate values ​​of the trajectory points; a second calculation submodule, used to calculate the parameter value of the trajectory point based on the coordinate values ​​of two adjacent trajectory points and the total chord length, and obtain the parameter value of each trajectory point; a third calculation submodule, used to obtain the order of the B-spline curve, and calculate the node vector of each trajectory point based on the order of the B-spline curve and the parameter value of each trajectory point.

[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned early warning methods for the operation risks of power equipment.

[0021] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned early warning methods for operation risks of power equipment.

[0022] In the present application, the following steps are taken: first, a positioning information set of power equipment in the substation is obtained, and a position vector is constructed based on the positioning information in the positioning information set, and then the position vector is input into a trajectory prediction model to output a control point information set, wherein the control point information set includes N control points and the coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operating trajectory of power equipment based on a long short-term memory neural network, and then a prediction trajectory curve is constructed based on the control point information in the control point information set, and the prediction trajectory curve is fused with a pre-constructed three-dimensional panoramic model to obtain a simulated prediction trajectory of the power equipment, and finally the simulated prediction trajectory is compared with a preset operating trajectory range to obtain a comparison result, and when the comparison result indicates that the simulated prediction trajectory exceeds the operating trajectory range, it is determined that the power equipment has an operating risk and a risk warning is triggered.

[0023] In the present application, the trajectory prediction model analyzes and calculates the positioning information of the power equipment, outputs a control point information set, and fits the predicted trajectory curve based on the control point information set. The trajectory prediction curve is then integrated with the pre-built three-dimensional panoramic model of the substation to determine the simulated predicted trajectory of the power equipment. Based on the simulated predicted trajectory, it is determined whether the power equipment has an operation risk, and an early warning is issued for the power equipment with an operation risk. The operation status of the power equipment can be predicted, and the environment and location of the power equipment are comprehensively considered. The accuracy of the prediction and evaluation results is improved, and the operation safety of large-scale power equipment is ensured, thereby solving the technical problem in the related technology of evaluating the operation risk of power equipment based on image processing technology and obtaining the low accuracy of the results. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0025] Figure 1 is a flow chart of an optional early warning method for power equipment operation risk according to an embodiment of the present invention;

[0026] Figure 2 is a schematic diagram of an optional early warning process for power equipment operation risk according to an embodiment of the present invention;

[0027] Figure 3 is a schematic diagram of an optional early warning device for electric power equipment operation risk according to an embodiment of the present invention;

[0028] Figure 4 The present invention is a hardware structure block diagram of an electronic device (or mobile device) for an early warning method for electric power equipment operation risk according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] To facilitate those skilled in the art to understand the present invention, some terms or nouns involved in the embodiments of the present invention are explained below:

[0032] OSGB format, short for Open Scene Graph Binary, is a file format used to store 3D model data.

[0033] Building Information Modeling, referred to as BIM model, can include the building's geometry, materials, structure, system, service and performance information.

[0034] TIN model, short for Triangulated Irregular Network, is a three-dimensional model used to represent the surface or any irregular surface terrain. TIN model creates a three-dimensional representation of the terrain by connecting a series of points (called nodes or vertices) that are not on the same plane to form a series of triangles.

[0035] Real-Time Kinematic technology, referred to as RTK technology, is a high-precision global positioning measurement method that uses carrier phase observations for real-time dynamic positioning and can achieve centimeter-level positioning accuracy.

[0036] It should be noted that the early warning method and device for the operation risk of power equipment in the present application can be used in the field of power grid safety technology when predicting the operation trajectory of power equipment and providing safety warnings, and can also be used in any field other than the field of power grid safety technology when predicting the operation trajectory of power equipment and providing safety warnings. The application field of the early warning method and device for the operation risk of power equipment in the present application is not limited.

[0037] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0038] It should be noted that in this application, when collecting and analyzing customer information, corresponding operation entrances are provided for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0039] The following embodiments of the present invention can be applied to various systems / applications / devices for early warning of operation risks of power equipment. The present invention makes intelligent predictions of the operation risks of large-scale power equipment based on three-dimensional panoramic technology and RTK positioning technology. The three-dimensional panoramic technology can obtain spatial information of the environment around the power equipment, providing spatial reference information for the identification of the operation risks of the power equipment, while the RTK positioning technology can obtain the location information of the power equipment in real time, providing time and space reference information for the monitoring of the equipment operation status. When predicting the operation risks, the environment and location of the large-scale power equipment are fully considered, which improves the accuracy of the prediction and evaluation results and ensures the safe operation of the large-scale power equipment.

[0040] The present invention is described in detail below in conjunction with various embodiments.

[0041] Embodiment 1

[0042] According to an embodiment of the present invention, an embodiment of an early warning method for operation risks of power equipment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0043] Figure 1 is a flow chart of an optional early warning method for power equipment operation risk according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0044] Step S101, obtaining a set of positioning information of power equipment in a substation, and constructing a position vector based on the positioning information in the positioning information set;

[0045] Step S102, inputting the position vector into the trajectory prediction model, and outputting a control point information set, wherein the control point information set includes N control points and coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operation trajectory of the power equipment based on the long short-term memory neural network;

[0046] Step S103, constructing a predicted trajectory curve based on the control point information in the control point information set, and fusing the predicted trajectory curve with the pre-constructed three-dimensional panoramic model to obtain a simulated predicted trajectory of the power equipment;

[0047] Step S104, comparing the simulated predicted trajectory with the preset operating trajectory range to obtain a comparison result. When the comparison result indicates that the simulated predicted trajectory exceeds the operating trajectory range, it is determined that there is an operating risk for the power equipment and a risk warning is triggered.

[0048] Through the above steps, firstly, a positioning information set of the power equipment in the substation is obtained, and a position vector is constructed based on the positioning information in the positioning information set, and then the position vector is input into the trajectory prediction model to output a control point information set, wherein the control point information set includes N control points and the coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operation trajectory of the power equipment based on the long short-term memory neural network, and then a prediction trajectory curve is constructed based on the control point information in the control point information set, and the prediction trajectory curve is fused with the pre-constructed three-dimensional panoramic model to obtain a simulated prediction trajectory of the power equipment, and finally the simulated prediction trajectory is compared with the preset operation trajectory range to obtain a comparison result, and when the comparison result indicates that the simulated prediction trajectory exceeds the operation trajectory range, it is determined that the power equipment has an operation risk and a risk warning is triggered.

[0049] In this embodiment, the trajectory prediction model analyzes and calculates the positioning information of the power equipment, outputs a control point information set, and fits the predicted trajectory curve according to the control point information set, and then merges the trajectory prediction curve with the pre-constructed three-dimensional panoramic model of the substation to determine the simulated predicted trajectory of the power equipment, and determines whether the power equipment has an operation risk based on the simulated predicted trajectory, and issues an early warning for the power equipment with an operation risk. This can realize the prediction of the operating status of the power equipment, comprehensively consider the environment and location of the power equipment, improve the accuracy of the prediction and evaluation results, and ensure the safe operation of large-scale power equipment, thereby solving the technical problem in the related technology of evaluating the operation risk of power equipment based on image processing technology and obtaining the low accuracy of the results.

[0050] The embodiment of the present invention is described in detail below in combination with the above steps.

[0051] It should be noted that substations, as the hub of the power system, play an indispensable role in the power system. In order to smoothly complete the conversion, distribution and control of electric energy, substations deploy many large-scale power equipment, such as transformers and circuit breakers. The working environment of these large equipment is narrow, complex and changeable. Therefore, monitoring the operating status of large equipment in substations is an important part of ensuring the safe operation of substations.

[0052] The embodiment of the present invention combines three-dimensional panoramic technology with RTK positioning technology to predict and evaluate the operating risks of power equipment and realize intelligent prejudgment of dangerous situations in the power grid. The three-dimensional panoramic technology can obtain spatial information of the environment around the power equipment and provide spatial reference information for the identification of operating risks of the power equipment; while the RTK positioning technology can obtain the location information of the power equipment in real time and provide spatiotemporal reference information for monitoring the operating status of the power equipment. Combined with artificial intelligence algorithms, it can perform intelligent analysis on the operating risks of equipment and realize the prediction and intervention of dangerous situations in the power grid.

[0053] Optionally, before obtaining the positioning information set of the power equipment in the substation, it also includes: obtaining oblique image data of the substation, and preprocessing the oblique image data to obtain preprocessed oblique image data; generating an initial three-dimensional model based on the preprocessed oblique image data; and fusing the initial three-dimensional model with a pre-built building information model of the substation to obtain a three-dimensional oblique image model.

[0054] It should be noted that based on the 3D panoramic technology, a 3D panoramic model can be constructed for the substation, thereby providing a spatial information basis for the operation risk prediction of the substation. When constructing a 3D panoramic model, it is necessary to first obtain 3D panoramic data, which can be obtained through oblique photography and laser scanning. Oblique photography can quickly obtain high-resolution image data, can achieve wide-area rapid shooting, and is suitable for the collection of complex scenes such as urban buildings and forests; while laser scanning can obtain high-precision point cloud data, which can accurately measure the position and morphological information of surface objects. In the process of 3D panorama construction, by combining oblique photography and laser scanning, the advantages of the two technologies can be fully utilized to improve the efficiency and accuracy of 3D panoramic model construction.

[0055] Oblique image data of the substation is obtained through oblique photography, and high-resolution images of the same position and multiple angles are obtained by oblique photography aerial survey. The oblique image data is then preprocessed, and geometric preprocessing is performed on the multi-view images. The surface projection range of all images including the oblique images is simulated, and the same-name point automatic matching and free-net bundle adjustment are performed on images at all levels to obtain the same-name point matching results, thereby obtaining the preprocessed oblique image data, and then generating a three-dimensional model in the OSGB format to obtain an initial three-dimensional model. Finally, the initial three-dimensional model is imported into the pre-constructed BIM model (i.e., building information model) to obtain a three-dimensional oblique image model.

[0056] Optionally, after obtaining the three-dimensional oblique image model, it also includes: collecting point cloud data of the substation and preprocessing the point cloud data to obtain preprocessed point cloud data; constructing a triangulated network model based on the preprocessed point cloud data; and fusing the three-dimensional oblique image model with the triangulated network model to obtain a three-dimensional panoramic model.

[0057] After obtaining the 3D oblique image model of the substation, high-precision point cloud data of the substation is obtained through laser scanning, and denoising and smoothing are performed on it. Then, an irregular triangulated network TIN model (corresponding to the above-mentioned triangulated network model) is constructed based on the preprocessed point cloud data; and the 3D oblique image model is matched with the irregular triangulated network TIN model to complete the construction of the 3D panoramic model.

[0058] Step S101: Acquire a positioning information set of power equipment in a substation, and construct a position vector based on the positioning information in the positioning information set.

[0059] It should be noted that a substation is a facility used to realize the transmission, distribution and conversion of electric energy, and power equipment refers to large-scale machinery in a substation, such as transformers, circuit breakers, etc. The above-mentioned positioning information set contains multiple pieces of positioning information, which may specifically be the coordinate information of the power equipment.

[0060] It should be noted that after the three-dimensional panoramic model of the substation is established, it can provide spatial information for the operating risks of power equipment and assist in the assessment of the operating risks of power equipment. When assessing the operating risks of power equipment, the positioning information set of the power equipment in the substation is first collected. The location information of the power equipment can be obtained in real time through RTK technology, and then a model-readable vector is constructed based on the positioning information to obtain the position vector.

[0061] Step S102, input the position vector into the trajectory prediction model, and output a control point information set.

[0062] It should be noted that the trajectory prediction model uses a long short-term memory neural network as the model skeleton, and is a model obtained by training with control point information as training samples for predicting the control points of power equipment. Control points refer to key nodes used to control and adjust the operating status of power equipment. By obtaining a set of control point information and restoring the control point information to a trajectory curve based on a B-spline curve, the predicted trajectory curve of the power equipment in the future can be obtained. The operating risk of the power equipment can be evaluated by predicting the trajectory curve, and then early warning of dangerous situations in substations can be issued. The above control point information set includes N control points and the coordinate information of the control points.

[0063] Optionally, the trajectory prediction model is pre-constructed, and the steps of constructing the trajectory prediction model include: obtaining a set of historical positioning information of the power equipment; constructing a sample set based on the historical positioning information set, and dividing the sample set into a training set and a test set based on a preset ratio; building an initial trajectory prediction model based on a long short-term memory neural network; iteratively training the initial trajectory prediction model based on the training set to obtain a trained trajectory prediction model; testing the trained trajectory prediction model based on the test set to obtain a test result, and when the test result indicates that the trained trajectory prediction model passes the test, a trained trajectory prediction model is obtained.

[0064] It should be noted that the trajectory prediction model is pre-built, specifically including: first, based on the RTK positioning technology, a set of historical positioning information of the power equipment is collected, and the historical positioning information of the power equipment is fitted through the B-spline curve to obtain the prediction curve of the power equipment, and labels are configured for the historical positioning information of the power equipment through the prediction curve, and then training samples are constructed according to the historical positioning information and the labels corresponding to the historical positioning information, and the training samples are divided into training sets and test sets, and an initial trajectory prediction model is built based on the long short-term memory neural network. The training set is used to train the model, and the test set is used to test the trained model. If the test passes, a trained trajectory prediction model is obtained.

[0065] Optionally, the step of constructing a sample set based on a historical positioning information set includes: calculating parameter values ​​and node vectors of each trajectory point on a B-spline curve corresponding to the historical positioning information in the historical positioning information set; calculating the parameter value and node vector of each trajectory point by a least squares method to obtain a historical control point set of the B-spline curve; constructing training samples based on the historical positioning information set and the historical control point set; and vectorizing the training samples to obtain a sample set.

[0066] It should be noted that the embodiment of the present invention uses B-spline curve fitting to construct training samples. The B-spline curve can fit discrete points to create a continuous path. Specifically, the coordinate points in the historical positioning information are fitted based on the B-spline to obtain multiple trajectory points, and the parameter values ​​and node vectors of the trajectory points corresponding to the historical positioning information on the B-spline curve are calculated. Then, the parameter values ​​and node vectors of each trajectory point are calculated by the least squares method to obtain a historical control point set of the B-spline curve. The least squares method finds the best function match for the data by minimizing the sum of squares of the errors, so that the sum of squares of the errors between the control points finally fitted and the historical positioning information of the given data is minimized. After obtaining the historical control point set, the training sample is constructed according to the historical positioning information set and the historical control point set, and the data in the training sample is vectorized to obtain a sample set.

[0067] Optionally, the step of calculating the parameter value and node vector of each trajectory point on the B-spline curve corresponding to the historical positioning information in the historical positioning information set includes: fitting the B-spline curve based on the historical positioning information in the historical positioning information set to obtain a trajectory point set of the power equipment on the B-spline curve, wherein the trajectory point set includes M trajectory points and coordinate values ​​corresponding to the trajectory points; calculating the total chord length of the B-spline curve based on the coordinate values ​​of the trajectory points; calculating the parameter value of the trajectory point based on the coordinate values ​​and the total chord length of two adjacent trajectory points to obtain the parameter value of each trajectory point; obtaining the order of the B-spline curve, and calculating the node vector of each trajectory point based on the order of the B-spline curve and the parameter value of each trajectory point.

[0068] It should be noted that when calculating the parameter values ​​and node vectors of the trajectory points on the B-spline curve, the B-spline curve is fitted according to the historical positioning information to obtain multiple trajectory points and the coordinate values ​​of each trajectory point, and then the total chord length of the B-spline curve is calculated based on the coordinate values ​​of the trajectory points, the parameter values ​​of the trajectory points are calculated based on the coordinate values ​​of the trajectory points and the total chord length, and then the node vectors of each trajectory point are calculated based on the order of the B-spline curve and the parameter values ​​of each trajectory point.

[0069] Specifically, the calculation formula for the total chord length is expressed as:

[0070]

[0071] Where d represents the total chord length of the B-spline curve, Q k is the coordinate value of the kth trajectory point, and n is the total number of trajectory points.

[0072] The chord length parameterization method is used to calculate the parameter values ​​corresponding to the trajectory points:

[0073]

[0074] Among them, t k represents the parameter value of the kth trajectory, t 0 =0,t n =1.

[0075] make The calculation formula of the node vector is expressed as:

[0076] u p+j =(1-α)t i-1 +αt i ,

[0077] Where p is the B-spline order, n+1 is the number of control points, m+1 is the number of trajectory points, i=int(jd), j=1,2...np, α=jd-i.

[0078] Step S103, constructing a predicted trajectory curve based on the control point information in the control point information set, and fusing the predicted trajectory curve with the pre-constructed three-dimensional panoramic model to obtain a simulated predicted trajectory of the power equipment.

[0079] It should be noted that the output of the trajectory prediction model is a set of control point information, including multiple discrete points. Therefore, it is also necessary to restore the prediction results to a continuous trajectory curve, and then merge the restored curve with the three-dimensional panoramic model to obtain the predicted trajectory curve in the three-dimensional panoramic model. The expression form, to achieve the prediction of the motion trajectory of large-scale power equipment.

[0080] Optionally, the step of constructing a predicted trajectory curve based on the control point information in the control point information set includes: setting the order of the target B-spline curve; selecting a node vector set based on the number of control points and the order of the target B-spline curve; calculating the B-spline basis function based on the node vector set and the order of the B-spline curve; constructing the target B-spline curve based on the B-spline basis function and the control point information to obtain the predicted trajectory curve.

[0081] It should be noted that constructing a predicted trajectory curve based on control point information specifically includes: selecting the order of the target B-spline curve to be constructed, and then selecting a set of node vectors based on the number of control points and the order of the target B-spline curve. The node vector is a key part of defining the B-spline curve, which determines the local control characteristics of the curve. Then, the B-spline basis function is calculated based on the node vector set and the order of the B-spline curve. Finally, the target B-spline curve is constructed to obtain the predicted trajectory curve of the power equipment.

[0082] Step S104, comparing the simulated predicted trajectory with the preset operating trajectory range to obtain a comparison result. When the comparison result indicates that the simulated predicted trajectory exceeds the operating trajectory range, it is determined that there is an operating risk for the power equipment and a risk warning is triggered.

[0083] It should be noted that after completing the prediction of the motion trajectory of the power equipment, it can be integrated with the three-dimensional panoramic model, and then according to the preset standards (such as equipment safety standards, motion trajectory setting requirements, equipment safe working range, etc.), the operation risk of the power equipment can be predicted, and early warning reminders can be issued in time, and timely intervention can be made to ensure the safe operation of the power system.

[0084] Another optional specific implementation is described in detail below.

[0085] Figure 2 is a schematic diagram of an optional power equipment operation risk warning process according to an embodiment of the present invention, such as Figure 2 As shown in the figure, the risk warning process includes:

[0086] Step 1, start;

[0087] Step 2: Obtain oblique photography data of the substation and construct a three-dimensional oblique image model of the substation;

[0088] Step 3: Obtain high-precision point cloud data of the substation and construct a triangulated network (TIN) model of the substation;

[0089] Step 4: Fuse the 3D oblique image model, triangulated network TIN model and substation BIM model to obtain a 3D panoramic model of the substation;

[0090] Step 5: Collect real-time location information of power equipment in the substation;

[0091] Step 6: Input the positioning information into the trajectory prediction model and output the control point set;

[0092] Step 7: Draw a trajectory curve according to the control point set to obtain a trajectory prediction curve;

[0093] Step 8: Fusing the trajectory prediction curve with the three-dimensional panoramic model to determine the operation risk of the power equipment;

[0094] Step nine, triggering risk warning according to the operation risk of power equipment;

[0095] Step 10, end.

[0096] In an embodiment of the present invention, an intelligent prediction of the operation risk of large-scale power equipment is performed based on the three-dimensional panoramic technology and the RTK positioning technology. The three-dimensional panoramic technology can obtain the spatial information of the environment around the power equipment, and provides spatial reference information for the identification of the operation risk of the power equipment. The RTK positioning technology can obtain the location information of the power equipment in real time, and provides time and space reference information for the equipment operation status monitoring. When predicting the operation risk, the environment and location of the large-scale power equipment are fully considered, which improves the accuracy of the prediction and evaluation results and ensures the safe and stable operation of the power system.

[0097] The following is a detailed description in conjunction with another embodiment.

[0098] Embodiment 2

[0099] An early warning device for operation risk of electric power equipment provided in this embodiment includes multiple implementation units, each implementation unit corresponds to each implementation step in the above-mentioned embodiment 1. Its specific implementation methods and beneficial effects can refer to the above-mentioned method embodiments and will not be repeated here.

[0100] Figure 3 is a schematic diagram of an optional early warning device for power equipment operation risk according to an embodiment of the present invention, such as Figure 3As shown, the early warning device for the operation risk of the power equipment may include: an acquisition unit 31, an output unit 32, a fusion unit 33, and an early warning unit 34, wherein:

[0101] An acquisition unit 31 is used to acquire a set of positioning information of power equipment in the substation, and construct a position vector based on the positioning information in the set of positioning information;

[0102] The output unit 32 is used to input the position vector into the trajectory prediction model and output a control point information set, wherein the control point information set includes N control points and coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operation trajectory of the power equipment based on the long short-term memory neural network;

[0103] A fusion unit 33 is used to construct a predicted trajectory curve based on the control point information in the control point information set, and fuse the predicted trajectory curve with the pre-constructed three-dimensional panoramic model to obtain a simulated predicted trajectory of the power equipment;

[0104] The early warning unit 34 is used to compare the simulated predicted trajectory with the preset operating trajectory range to obtain a comparison result. When the comparison result indicates that the simulated predicted trajectory exceeds the operating trajectory range, it is determined that there is an operating risk for the power equipment and a risk early warning is triggered.

[0105] The above-mentioned early warning device for the operation risk of power equipment obtains the positioning information set of the power equipment in the substation through the acquisition unit 31, and constructs a position vector based on the positioning information in the positioning information set; inputs the position vector into the trajectory prediction model through the output unit 32, and outputs a control point information set, wherein the control point information set includes N control points and the coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operation trajectory of the power equipment based on the long short-term memory neural network; constructs a predicted trajectory curve based on the control point information in the control point information set through the fusion unit 33, and fuses the predicted trajectory curve with the pre-constructed three-dimensional panoramic model to obtain a simulated predicted trajectory of the power equipment; compares the simulated predicted trajectory with the preset operation trajectory range through the early warning unit 34 to obtain a comparison result. When the comparison result indicates that the simulated predicted trajectory exceeds the operation trajectory range, it is determined that the power equipment has an operation risk and a risk warning is triggered.

[0106] In this embodiment, the trajectory prediction model analyzes and calculates the positioning information of the power equipment, outputs a control point information set, and fits the predicted trajectory curve according to the control point information set, and then merges the trajectory prediction curve with the pre-constructed three-dimensional panoramic model of the substation to determine the simulated predicted trajectory of the power equipment, and determines whether the power equipment has an operation risk based on the simulated predicted trajectory, and issues an early warning for the power equipment with an operation risk. This can realize the prediction of the operating status of the power equipment, comprehensively consider the environment and location of the power equipment, improve the accuracy of the prediction and evaluation results, and ensure the safe operation of large-scale power equipment, thereby solving the technical problem in the related technology of evaluating the operation risk of power equipment based on image processing technology and obtaining the low accuracy of the results.

[0107] Optionally, the fusion unit includes: a first setting subunit, used to set the order of the target B-spline curve; a first selection subunit, used to select a node vector set based on the number of control points and the order of the target B-spline curve; a first calculation subunit, used to calculate the B-spline basis function based on the node vector set and the order of the B-spline curve; and a first construction subunit, used to construct the target B-spline curve based on the B-spline basis function and control point information to obtain a predicted trajectory curve.

[0108] Optionally, the early warning device for power equipment operation risks also includes: a first acquisition subunit, used to acquire oblique image data of the substation, and preprocess the oblique image data to obtain preprocessed oblique image data; a first generation subunit, used to generate an initial three-dimensional model based on the preprocessed oblique image data; a first fusion subunit, used to fuse the initial three-dimensional model with a pre-built building information model of the substation to obtain a three-dimensional oblique image model.

[0109] Optionally, the early warning device for power equipment operation risks also includes: a first acquisition subunit, used to collect point cloud data of the substation, and preprocess the point cloud data to obtain preprocessed point cloud data; a second construction subunit, used to construct a triangulated network model based on the preprocessed point cloud data; a second fusion subunit, used to fuse the three-dimensional oblique image model with the triangulated network model to obtain a three-dimensional panoramic model.

[0110] Optionally, the early warning device for the operation risk of power equipment also includes: a second acquisition subunit, used to acquire a set of historical positioning information of the power equipment; a third construction subunit, used to construct a sample set based on the set of historical positioning information, and divide the sample set into a training set and a test set based on a preset ratio; a first construction subunit, used to build an initial trajectory prediction model based on a long short-term memory neural network; a first training subunit, used to iteratively train the initial trajectory prediction model based on the training set to obtain a trained trajectory prediction model; a first testing subunit, used to test the trained trajectory prediction model based on the test set to obtain a test result, and when the test result indicates that the trained trajectory prediction model passes the test, a trained trajectory prediction model is obtained.

[0111] Optionally, the third construction subunit includes: a first calculation module, used to calculate the parameter value and node vector of each trajectory point on the B-spline curve corresponding to the historical positioning information in the historical positioning information set; a second calculation module, used to calculate the parameter value and node vector of each trajectory point by the least squares method to obtain the historical control point set of the B-spline curve; a first construction module, used to construct a training sample based on the historical positioning information set and the historical control point set; a first acquisition module, used to vectorize the training sample to obtain a sample set.

[0112] Optionally, the first calculation module includes: a first fitting submodule, used to fit a B-spline curve based on the historical positioning information in the historical positioning information set, and obtain a trajectory point set of the power equipment on the B-spline curve, wherein the trajectory point set includes M trajectory points and coordinate values ​​corresponding to the trajectory points; a first calculation submodule, used to calculate the total chord length of the B-spline curve based on the coordinate values ​​of the trajectory points; a second calculation submodule, used to calculate the parameter value of the trajectory point based on the coordinate values ​​of two adjacent trajectory points and the total chord length, and obtain the parameter value of each trajectory point; a third calculation submodule, used to obtain the order of the B-spline curve, and calculate the node vector of each trajectory point based on the order of the B-spline curve and the parameter value of each trajectory point.

[0113] The above-mentioned early warning device for the operation risk of power equipment may also include a processor and a memory. The above-mentioned acquisition unit 31, output unit 32, fusion unit 33, early warning unit 34, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0114] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the operating risk of the power equipment can be warned by adjusting the kernel parameters.

[0115] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (fl ash RAM), and the memory includes at least one storage chip.

[0116] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned early warning methods for the operation risks of power equipment.

[0117] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any one of the above-mentioned early warning methods for operation risks of power equipment.

[0118] According to another aspect of an embodiment of the present invention, a computer program product is further provided. The computer program product includes a computer program, wherein when the computer program is executed by a processor, any one of the above-mentioned early warning methods for operation risks of power equipment is implemented.

[0119] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: obtaining a positioning information set of power equipment in a substation, and constructing a position vector based on the positioning information in the positioning information set; inputting the position vector into a trajectory prediction model, and outputting a control point information set, wherein the control point information set includes N control points and coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operating trajectory of power equipment based on a long short-term memory neural network; constructing a predicted trajectory curve based on the control point information in the control point information set, and fusing the predicted trajectory curve with a pre-constructed three-dimensional panoramic model to obtain a simulated predicted trajectory of the power equipment; comparing the simulated predicted trajectory with a preset operating trajectory range to obtain a comparison result, and when the comparison result indicates that the simulated predicted trajectory exceeds the operating trajectory range, determining that the power equipment has an operating risk and triggering a risk warning.

[0120] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: the step of constructing a predicted trajectory curve based on the control point information in the control point information set includes: setting the order of the target B-spline curve; selecting a node vector set based on the number of control points and the order of the target B-spline curve; calculating the B-spline basis function based on the node vector set and the order of the B-spline curve; constructing the target B-spline curve based on the B-spline basis function and the control point information to obtain the predicted trajectory curve.

[0121] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: before obtaining a set of positioning information of power equipment in a substation, it also includes: obtaining oblique image data of the substation, and preprocessing the oblique image data to obtain preprocessed oblique image data; generating an initial three-dimensional model based on the preprocessed oblique image data; and fusing the initial three-dimensional model with a pre-built building information model of the substation to obtain a three-dimensional oblique image model.

[0122] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: after obtaining the three-dimensional oblique image model, it also includes: collecting point cloud data of the substation and preprocessing the point cloud data to obtain preprocessed point cloud data; constructing a triangulated network model based on the preprocessed point cloud data; and fusing the three-dimensional oblique image model with the triangulated network model to obtain a three-dimensional panoramic model.

[0123] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program initialized with the following method steps: a trajectory prediction model is pre-constructed, and the steps of constructing the trajectory prediction model include: obtaining a historical positioning information set of the power equipment; constructing a sample set based on the historical positioning information set, and dividing the sample set into a training set and a test set based on a preset ratio; building an initial trajectory prediction model based on a long short-term memory neural network; iteratively training the initial trajectory prediction model based on the training set to obtain a trained trajectory prediction model; testing the trained trajectory prediction model based on the test set to obtain a test result, and when the test result indicates that the trained trajectory prediction model passes the test, a trained trajectory prediction model is obtained.

[0124] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that is initialized with the following method steps: the step of constructing a sample set based on a historical positioning information set includes: calculating the parameter value and node vector of each trajectory point corresponding to the historical positioning information in the historical positioning information set on the B-spline curve; calculating the parameter value and node vector of each trajectory point by the least squares method to obtain a historical control point set of the B-spline curve; constructing a training sample based on the historical positioning information set and the historical control point set; vectorizing the training sample to obtain a sample set.

[0125] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that is initialized with the following method steps: the step of calculating the parameter value and node vector of each trajectory point corresponding to the historical positioning information in the historical positioning information set on the B-spline curve includes: fitting the B-spline curve based on the historical positioning information in the historical positioning information set to obtain a trajectory point set of the power equipment on the B-spline curve, wherein the trajectory point set includes M trajectory points and coordinate values ​​corresponding to the trajectory points; calculating the total chord length of the B-spline curve based on the coordinate values ​​of the trajectory points; calculating the parameter value of the trajectory point based on the coordinate values ​​and the total chord length of two adjacent trajectory points to obtain the parameter value of each trajectory point; obtaining the order of the B-spline curve, and calculating the node vector of each trajectory point based on the order of the B-spline curve and the parameter value of each trajectory point.

[0126] Figure 4 1 is a hardware structure block diagram of an electronic device (or mobile device) according to an early warning method for power equipment operation risk according to an embodiment of the present invention. Figure 4 As shown, the electronic device may include one or more ( Figure 4 402a, 402b, ..., 402n are used to illustrate) processor 402 (processor 402 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), memory 404 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 4 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 4 More or fewer components as shown, or with Figure 4 Different configurations are shown.

[0127] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0128] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0131] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0132] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0133] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for early warning of power equipment operation risk, characterized in that: include: Acquire a set of positioning information of power equipment in the substation, and construct a position vector based on the positioning information in the set of positioning information; The position vector is input into a trajectory prediction model, and a control point information set is output, wherein the control point information set includes N control points and coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operation trajectory of the power equipment based on a long short-term memory neural network; Constructing a predicted trajectory curve based on the control point information in the control point information set, and fusing the predicted trajectory curve with a pre-constructed three-dimensional panoramic model to obtain a simulated predicted trajectory of the power equipment; The simulated predicted trajectory is compared with a preset operating trajectory range to obtain a comparison result. When the comparison result indicates that the simulated predicted trajectory exceeds the operating trajectory range, it is determined that the power equipment has an operating risk and a risk warning is triggered.

2. The early warning method according to claim 1, characterized in that: The step of constructing a predicted trajectory curve based on the control point information in the control point information set includes: Set the order of the target B-spline curve; Selecting a set of node vectors based on the number of control points and the order of the target B-spline curve; Calculating a B-spline basis function based on the set of node vectors and the order of the B-spline curve; A target B-spline curve is constructed based on the B-spline basis function and the control point information to obtain the predicted trajectory curve.

3. The early warning method according to claim 1, characterized in that: Before obtaining the location information set of the power equipment in the substation, it also includes: Obtaining oblique image data of the substation, and preprocessing the oblique image data to obtain preprocessed oblique image data; Generate an initial three-dimensional model based on the preprocessed oblique image data; The initial three-dimensional model is merged with the pre-constructed building information model of the substation to obtain a three-dimensional oblique image model.

4. The early warning method according to claim 3, characterized in that: After obtaining the 3D oblique image model, it also includes: Collecting point cloud data of the substation, and preprocessing the point cloud data to obtain preprocessed point cloud data; Constructing a triangulated network model based on the preprocessed point cloud data; The three-dimensional oblique image model is fused with the triangulated network model to obtain the three-dimensional panoramic model.

5. The early warning method according to claim 1, characterized in that: The trajectory prediction model is pre-constructed, and the steps of constructing the trajectory prediction model include: Acquire a set of historical positioning information of the electric power equipment; Constructing a sample set based on the historical positioning information set, and dividing the sample set into a training set and a test set based on a preset ratio; Build an initial trajectory prediction model based on long short-term memory neural network; Iteratively training the initial trajectory prediction model based on the training set to obtain a trained trajectory prediction model; The trained trajectory prediction model is tested based on the test set to obtain a test result. When the test result indicates that the trained trajectory prediction model passes the test, the trained trajectory prediction model is obtained.

6. The early warning method according to claim 5, characterized in that: The step of constructing a sample set based on the historical positioning information set includes: Calculating parameter values ​​and node vectors of each trajectory point corresponding to the historical positioning information in the historical positioning information set on the B-spline curve; Calculating the parameter value of each trajectory point and the node vector by the least square method to obtain a historical control point set of the B-spline curve; Constructing a training sample based on the historical positioning information set and the historical control point set; The training samples are vectorized to obtain the sample set.

7. The early warning method according to claim 6, characterized in that: The step of calculating the parameter value and the node vector of each trajectory point corresponding to the historical positioning information in the historical positioning information set on the B-spline curve comprises: Fitting the B-spline curve based on the historical positioning information in the historical positioning information set to obtain a trajectory point set of the power equipment on the B-spline curve, wherein the trajectory point set includes M trajectory points and coordinate values ​​corresponding to the trajectory points; Calculate the total chord length of the B-spline curve based on the coordinate values ​​of the trajectory points; Calculate the parameter value of the trajectory point based on the coordinate values ​​of two adjacent trajectory points and the total chord length to obtain the parameter value of each trajectory point; The order of the B-spline curve is obtained, and the node vector of each trajectory point is calculated based on the order of the B-spline curve and the parameter value of each trajectory point.

8. An early warning device for power equipment operation risk, characterized in that: include: An acquisition unit, used to acquire a set of positioning information of power equipment in the substation, and construct a position vector based on the positioning information in the set of positioning information; An output unit, used to input the position vector into a trajectory prediction model, and output a control point information set, wherein the control point information set includes N control points and coordinate information of the control points, N is a positive integer, and the trajectory prediction model is a model for predicting the operation trajectory of the power equipment based on a long short-term memory neural network; a fusion unit, configured to construct a predicted trajectory curve based on the control point information in the control point information set, and fuse the predicted trajectory curve with a pre-constructed three-dimensional panoramic model to obtain a simulated predicted trajectory of the power equipment; The early warning unit is used to compare the simulated predicted trajectory with a preset operating trajectory range to obtain a comparison result. When the comparison result indicates that the simulated predicted trajectory exceeds the operating trajectory range, it is determined that the power equipment has an operating risk and a risk early warning is triggered.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the early warning method for the operation risk of the power equipment as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the early warning method for operation risks of power equipment as described in any one of claims 1 to 7.