A method, device, equipment and storage medium for monitoring operation of electric power equipment

Abstract

The present application discloses a method, device, equipment and storage medium for monitoring the operation of electric equipment, and relates to the field of electric digital data processing technology. The method obtains the electromagnetic radiation intensity of each device; defines an electromagnetic radiation ball based on the electromagnetic radiation intensity of each electric equipment at a preset ratio; responds to the entry signal of the operator at the entrance and exit and obtains the person detection frame; marks the electric equipment that needs to be operated as the electric equipment to be operated according to the operation requirements; obtains the shortest inspection route of all the electric equipment to be operated through the path search algorithm and outputs it to the operator; obtains the single intersection time of the person detection frame with each electromagnetic radiation ball respectively, and the total intersection time with all electromagnetic radiation balls; and generates a warning signal and sends it to the operator when the single intersection time is overtime or the total intersection time is overtime. The present application starts timing when approaching the equipment, and promptly reminds the operator of overtime operation to ensure safety and health.

Description

Technical Field

[0001] The present application relates to the technical field of electrical digital data processing, and in particular to a method, device, equipment and storage medium for monitoring the operation of electric power equipment. Background Art

[0002] Power generation equipment, power transmission equipment and other equipment used to generate and transmit electricity will generate electromagnetic radiation to a greater or lesser extent. Electromagnetic radiation is the transfer of momentum and energy in the form of waves by electric and magnetic fields that oscillate in the same direction and are perpendicular to each other in space. Its propagation direction is perpendicular to the plane formed by the electric and magnetic fields. The interactive changes of electric and magnetic fields generate electromagnetic waves, which are emitted or propagated into the air to form electromagnetic radiation. The general definition of the radio frequency part of the electromagnetic spectrum refers to radiation with a frequency of about 3 kHz to 300 GHz. Some electromagnetic radiation has a certain impact on the human body.

[0003] The energy derived from electromagnetic radiation depends on the frequency and intensity. Generally speaking, the higher the frequency, the greater the intensity, and the greater the energy. Photons of high-frequency (short-wavelength) electromagnetic waves carry more energy than photons of low-frequency (long-wavelength) electromagnetic waves. The energy carried by each photon of some electromagnetic waves can be so great that it has the ability to destroy chemical bonds between molecules. The electromagnetic radiation range generated by power equipment is relatively small, ranging from 0.1m to 10m, and the impact range increases with the power of the power equipment.

[0004] During the process of power production and maintenance, maintenance personnel are usually required to be within the reach of power equipment for a long time. During actual operation, the electromagnetic radiation and heat generated by the power equipment can easily cause discomfort and negative impacts to maintenance personnel, causing physical discomfort to maintenance personnel. The physical discomfort will increase with the increase in operation time, thereby increasing the safety risks of maintenance personnel and affecting their physical health. Summary of the invention

[0005] The main purpose of the present application is to provide an operation monitoring method, device, equipment and storage medium for power equipment, so as to solve the problem in the prior art that the electromagnetic radiation generated by power equipment can easily cause physiological discomfort to operators during maintenance and repair, thereby increasing the safety risks of the repair personnel and affecting the physical health of the repair personnel.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] A method for monitoring the operation of an electric power device, wherein the electric power device has a plurality of electric power devices and all of the electric power devices are located in a preset area, and the method for monitoring the operation of the electric power device comprises:

[0008] Step S1, obtaining a three-dimensional layout of the preset area, wherein the three-dimensional layout includes the locations of all power equipment, all roads, and all entrances and exits within the preset area;

[0009] Step S2, obtaining the electromagnetic radiation intensity of each device respectively through a preset strategy;

[0010] Step S3, defining an electromagnetic radiation sphere based on the electromagnetic radiation intensity of each power device in a preset ratio, wherein the center of the current electromagnetic radiation sphere coincides with the midpoint of the current power device;

[0011] Step S4, responding to an entry signal of a worker at the entrance and exit, and acquiring a person detection frame matching the entry signal based on a target detection algorithm;

[0012] Step S5, obtaining the preset operation requirements of the operator, and marking the power equipment that needs to be operated as the power equipment to be operated according to the operation requirements;

[0013] Step S6, obtaining the shortest inspection route of all the power equipment to be operated through a path search algorithm and outputting it to the operator;

[0014] Step S7, obtaining the individual intersection duration of the person detection frame with each electromagnetic radiation sphere, and the total intersection duration with all electromagnetic radiation spheres;

[0015] Step S8, respectively judging whether the current single intersection duration exceeds the first preset threshold value and whether the total intersection duration exceeds the second preset threshold value, if the current single intersection duration exceeds the first preset threshold value or the total intersection duration exceeds the second preset threshold value, executing step S9;

[0016] Step S9: determine that the operation has timed out, generate a warning signal and send it to the operator.

[0017] As a further improvement of the present application, step S3, based on the electromagnetic radiation intensity of each power device, defines an electromagnetic radiation sphere in a preset ratio, and the center of the current electromagnetic radiation sphere coincides with the midpoint of the current power device, including:

[0018] Step S31, sorting all electromagnetic radiation intensities from small to large;

[0019] Step S32, obtaining the minimum and maximum values ​​of the electromagnetic radiation intensity to establish an electromagnetic radiation intensity interval;

[0020] Step S33, equally dividing the electromagnetic radiation intensity interval to form at least two sub-intervals, and the sub-intervals at the two ends are the minimum sub-interval and the maximum sub-interval respectively;

[0021] Step S34, sequentially numbering each sub-interval from small to large, and defining the number of the current sub-interval as the proportional constant of the current sub-interval, the proportional constant of the minimum sub-interval is the minimum proportional constant, and the proportional constant of the maximum sub-interval is the maximum proportional constant;

[0022] Step S35, defining the minimum electromagnetic radiation sphere as the minimum enclosing sphere of the electric equipment within the minimum value subinterval multiplied by the minimum proportional constant, and the maximum electromagnetic radiation sphere as the minimum enclosing sphere of the electric equipment within the maximum value subinterval multiplied by the maximum proportional constant;

[0023] Step S36, based on the sub-interval where each power device is located and the corresponding proportional constant, the electromagnetic radiation sphere of each power device is obtained respectively.

[0024] As a further improvement of the present application, step S4, in response to an entry signal of a worker at the entrance and exit, and based on a target detection algorithm, obtaining a person detection frame matching the entry signal, includes:

[0025] Step S41, in response to the entry signal, acquiring image data matching the entry signal through an external preset camera terminal;

[0026] Step S42, dividing the image data into a preset number of grids on average;

[0027] Step S43, predicting a plurality of bounding boxes for the moving target in the image data according to the target detection algorithm based on all grids;

[0028] Step S44, respectively obtaining the confidence of each bounding box, and obtaining the bounding box with the largest confidence and marking it as a first-order bounding box;

[0029] Step S45, calculating the intersection-over-union ratio of each other bounding box with the first-order bounding box;

[0030] Step S46, selecting a bounding box whose intersection-over-union ratio is greater than or equal to a preset threshold as a second-order bounding box;

[0031] Step S47, obtaining a second-order bounding box with the highest confidence and defining it as the person detection box.

[0032] As a further improvement of the present application, step S6, obtaining the shortest inspection route of all the power equipment to be operated through a path search algorithm and outputting it to the operator, includes:

[0033] Step S61, obtaining a digital elevation model of the preset area and outputting all power equipment to be operated and all roads to the digital elevation model;

[0034] Step S62, dividing the digital elevation model by horizontal grids of preset density;

[0035] Step S63, detecting and acquiring all horizontal grids with all roads through a target detection algorithm, and defining them as a candidate grid set for inspection routes;

[0036] Step S64, defining each grid in the inspection route candidate grid set as a node, and defining all entrances and exits and all power equipment to be operated as starting points and end points respectively;

[0037] Step S65, defining one of all the end points as the inspection route end point, and defining the other end points as waypoints, and calculating the minimum number of grids required for the starting point to pass through all the waypoints and finally reach the inspection route end point by using the A-star algorithm;

[0038] Step S66, obtaining all horizontal grids corresponding to the minimum number of grids, and sequentially connecting them to form the shortest inspection route;

[0039] Step S67, outputting the shortest inspection route to the receiving end of the operator.

[0040] As a further improvement of the present application, in step S65, one of all the end points is defined as the end point of the inspection route, and the other end points are defined as waypoints, and the minimum number of grids required for the starting point to pass through all the waypoints and finally reach the end point of the inspection route is calculated by the A-star algorithm, including:

[0041] Step S651, creating a grid set to be checked;

[0042] Step S652, adding the starting point, all the waypoints, and the end point to the grid set to be checked, and setting the priority of the starting point to the highest, setting the priority of all the waypoints to the middle, and setting the priority of the end point to the lowest;

[0043] Step S653, determining whether the to-be-checked grid set is empty, if the to-be-checked grid set is not empty, executing step S654;

[0044] Step S654, selecting a node with the highest priority from the set of grids to be checked;

[0045] Step S655, determining whether the node is one of the waypoints, if the node is one of the waypoints, executing step S656;

[0046] Step S656, starting from the current waypoint, gradually tracking the parent node until reaching the starting point;

[0047] Step S657, respectively obtaining the number of grids required for each waypoint to reach the starting point, and defining the waypoint with the least number of grids required as the starting point for the next path search;

[0048] Step S658, iterating steps S651 to S657 for several times until the starting point, all the waypoints, and the end point are sequentially connected in a single line to obtain the shortest inspection route;

[0049] Step S659, obtaining all grids covered by the shortest inspection route to obtain the minimum number of grids.

[0050] As a further improvement of the present application, step S653, determining whether the grid set to be checked is empty, then includes:

[0051] Step S10, if the grid set to be checked is empty, traverse all neighboring nodes of the node and add all neighboring nodes to the grid set to be checked;

[0052] Step S20, obtaining the neighboring node with the highest priority among all neighboring nodes as the parent node for the next traversal;

[0053] Step S30, starting from the current parent node, gradually tracing the parent node of the next traversal until reaching one of the waypoints;

[0054] Step S40, defining one of the waypoints reached as the starting point of the next path search;

[0055] Step S50, iterating steps S10 to S40 several times until the starting point, all the waypoints, and the end point are sequentially connected in a single line to obtain the shortest inspection route;

[0056] Step S60, obtaining all grids covered by the shortest inspection route to obtain the minimum number of grids.

[0057] As a further improvement of the present application, step S7, obtaining the single intersection duration of the person detection frame with each electromagnetic radiation sphere, and the total intersection duration with all electromagnetic radiation spheres, includes:

[0058] Step S71, defining a world coordinate system according to any horizontal plane and any vertical plane of the preset area;

[0059] Step S72, mapping the person detection frame to the world coordinate system through a homography matrix to form a two-dimensional person detection frame, and the two-dimensional person detection frame is parallel to or coplanar with the arbitrary vertical plane;

[0060] Step S73, obtaining the symmetry axis of the two-dimensional person detection frame in the vertical direction;

[0061] Step S74, rotating the two-dimensional person detection frame based on the symmetry axis;

[0062] Step S75, obtaining a complete rotation trajectory of the two-dimensional person detection frame, and defining the complete rotation trajectory as a three-dimensional person detection frame;

[0063] Step S76, obtaining the Euclidean distance between the three-dimensional person detection frame and all electromagnetic radiation spheres based on the world coordinate system;

[0064] Step S77, determining whether the Euclidean distance is less than or equal to zero, if the Euclidean distance is less than or equal to zero, executing step S78;

[0065] Step S78, obtaining a first intersection duration of the electromagnetic radiation sphere intersecting with the three-dimensional person detection frame to obtain the single intersection duration;

[0066] Step S79, obtaining the second intersection duration between the three-dimensional person detection frame and each electromagnetic radiation sphere respectively, and adding up all the second intersection durations to obtain the total intersection duration.

[0067] In order to achieve the above objectives, this application also provides the following technical solutions:

[0068] An operation monitoring device for electric power equipment, the operation monitoring device for electric power equipment is applied to the above-mentioned operation monitoring method, the operation monitoring device comprises:

[0069] A three-dimensional layout acquisition module, used to acquire the three-dimensional layout of the preset area, wherein the three-dimensional layout includes the locations of all power equipment, all roads, and all entrances and exits located in the preset area;

[0070] An electromagnetic radiation intensity acquisition module is used to obtain the electromagnetic radiation intensity of each device respectively through a preset strategy;

[0071] An electromagnetic radiation sphere definition module is used to define an electromagnetic radiation sphere based on the electromagnetic radiation intensity of each power device in a preset ratio, and the center of the current electromagnetic radiation sphere coincides with the midpoint of the current power device;

[0072] A person detection frame acquisition module, used to respond to an entry signal of a worker at the entrance and to acquire a person detection frame matching the entry signal based on a target detection algorithm;

[0073] A power equipment to be operated marking module is used to obtain preset operation requirements of the operator and mark the power equipment that needs to be operated as the power equipment to be operated according to the operation requirements;

[0074] The shortest inspection route acquisition and output module is used to acquire the shortest inspection routes of all the power equipment to be operated through a path search algorithm and output them to the operator;

[0075] An intersection duration acquisition module, used to acquire a single intersection duration of the person detection frame with each electromagnetic radiation sphere, and a total intersection duration with all electromagnetic radiation spheres;

[0076] An intersection duration judgment module, used to judge whether the current single intersection duration exceeds a first preset threshold and whether the total intersection duration exceeds a second preset threshold;

[0077] The operation timeout judgment module is used to judge that the operation is overtime if the current single intersection duration exceeds the first preset threshold or the total intersection duration exceeds the second preset threshold, and generate a warning signal and send it to the operator.

[0078] In order to achieve the above objectives, this application also provides the following technical solutions:

[0079] An electronic device comprises a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the operation monitoring method of the electric power equipment as described above is implemented.

[0080] To achieve the above objectives, this application also provides the following technical solutions:

[0081] A storage medium stores program instructions, and when the program instructions are executed by a processor, the method for monitoring the operation of the electric power equipment as described above can be implemented.

[0082] The present application obtains a three-dimensional layout of a preset area, which includes the locations of all power equipment, all roads, and all entrances and exits within the preset area; obtains the electromagnetic radiation intensity of each device respectively through a preset strategy; defines an electromagnetic radiation ball based on the electromagnetic radiation intensity of each power equipment at a preset ratio, and the center of the current electromagnetic radiation ball coincides with the midpoint of the current power equipment; responds to the entry signal of the operator at the entrance and exit, and obtains a person detection frame matching the entry signal based on the target detection algorithm; obtains the preset operation requirements of the operator, and marks the power equipment that needs to be operated as the power equipment to be operated according to the operation requirements; obtains the shortest inspection route of all the power equipment to be operated through a path search algorithm and outputs it to the operator; obtains the single intersection time of the person detection frame with each electromagnetic radiation ball respectively, and the total intersection time with all electromagnetic radiation balls; respectively judges whether the current single intersection time exceeds the first preset threshold and the total intersection time exceeds the second preset threshold. If the current single intersection time exceeds the first preset threshold or the total intersection time exceeds the second preset threshold, it is determined that the operation is timed out, and a warning signal is generated and sent to the operator. The present application defines a matching electromagnetic radiation ball based on the electromagnetic radiation intensity of the power equipment to detect the relative position relationship between the power equipment and the operator, and the electromagnetic radiation ball of the power equipment increases as the electromagnetic radiation intensity of the power equipment increases. In addition, the present application utilizes the positive correlation between the electromagnetic radiation intensity, equipment size, and power of common electrical equipment. For small electrical equipment, the electromagnetic radiation of small electrical equipment is weak or negligible (the impact distance is within 0.1m), so that the electromagnetic radiation of this small electrical equipment will not affect or will only slightly affect the operating personnel. The electromagnetic radiation ball of the small electrical equipment is only the size of its own size. For large electrical equipment, the electromagnetic radiation of large electrical equipment is stronger (the impact range is generally 1m to 10m), and the impact range increases with the increase of power. At this time, it is necessary to expand the electromagnetic radiation ball of the large electrical equipment from the size of the equipment itself to the external space of the equipment based on the above-mentioned preset ratio, so that the operating personnel starts the intersection timing when they approach but have not touched the large electrical equipment. Finally, the operating personnel are reminded whether the timeout is reached through the timing of a single device and the total timing, and the operating personnel are reminded after the timeout. After being reminded, the operating personnel can leave the scene, thereby ensuring the safety and health of the operating personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 A schematic diagram of the process steps of an embodiment of the method for monitoring the operation of electric power equipment of the present application;

[0084] Figure 2 A schematic diagram of functional modules of an embodiment of an operation monitoring device for electric power equipment of the present application;

[0085] Figure 3 This is a schematic diagram of the structure of an embodiment of the electronic device of the present application;

[0086] Figure 4 This is a schematic diagram of the structure of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0087] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0088] The terms "first", "second" and "third" in this application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications in the embodiments of the present application (such as up, down, left, right, front, back...) are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or power device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or power devices.

[0089] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0090] like Figure 1 As shown, this embodiment provides an embodiment of a method for monitoring the operation of power equipment. In this embodiment, there are several power equipment and they are all located in a preset area, such as power stations, substations, energy storage stations, high-voltage transmission equipment, radio base stations, signal towers, etc.

[0091] Specifically, the operation monitoring method includes the following steps:

[0092] Step S1, obtaining a three-dimensional layout of a preset area, wherein the three-dimensional layout includes the locations of all power equipment, all roads, and all entrances and exits within the preset area.

[0093] Preferably, the three-dimensional layout can be directly acquired through one or more combinations of digital model acquisition strategies such as remote sensing interpretation, on-site mapping and measurement, drone photogrammetry, and three-dimensional laser scanning, and a three-dimensional finite element model or real-scene model can also be generated for visual output.

[0094] Step S2, obtaining the electromagnetic radiation intensity of each device respectively through a preset strategy.

[0095] Preferably, the measurement of electromagnetic radiation (i.e., the preset strategy mentioned above) can usually be carried out using different methods and tools. For example, magnetic field measuring instruments: can measure the strength and frequency of electromagnetic fields, and common magnetic field measuring instruments include magnetic induction meters and spectrum analyzers; electric field measuring instruments: can measure the strength and frequency of electric fields, and common electric field measuring instruments include electric field intensity meters and voltmeters; radio frequency power meters: used to measure the power of radio frequency radiation, and radio frequency power meters measure by receiving and measuring the energy of electromagnetic waves generated by radio frequency radiation; radiation dosimeters: used to measure the exposure of radiation to the human body, and common radiation dosimeters include personal radiation meters and environmental radiation meters; spectrometers: used to measure the radiation spectrum, and spectrometers can analyze different wavelengths and frequency components in electromagnetic radiation.

[0096] Step S3, defining an electromagnetic radiation sphere based on the electromagnetic radiation intensity of each electric power device in a preset ratio, wherein the center of the current electromagnetic radiation sphere coincides with the midpoint of the current electric power device.

[0097] Step S4, responding to the entry signal of the operator at the entrance and exit, and acquiring a person detection frame matching the entry signal based on the target detection algorithm.

[0098] Preferably, the target detection algorithm can be implemented through target detection algorithms VJ, HOG, DPMDetector; deep learning Two-stage target detection algorithms RCNN, SPPNet, FastRCNN, FasterRCNN; target detection Trick algorithms FPN, CascadeRCNN; deep learning one-stage target detection algorithms Yolo, X, SSD, Ret i naNet; deep learning Anchor-free target detection algorithms CornerNet, CenterNet, FCOS; Transformer-based target detection algorithm DETR, etc.

[0099] Preferably, this embodiment prefers the Yolo algorithm.

[0100] Step S5, obtaining preset operation requirements of the operator, and marking the power equipment that needs to be operated as the power equipment to be operated according to the operation requirements.

[0101] Preferably, the preset operation requirements can be real-time requirements set in advance by the operating personnel, regular inspections and maintenance of the equipment, or operation requirements generated by the external monitoring software itself.

[0102] Step S6, obtaining the shortest inspection route of all the power equipment to be operated through a path search algorithm and outputting it to the operator.

[0103] Preferably, the design of the shortest inspection route in this embodiment is intended to ensure that the total working time of the operating personnel in one inspection is the shortest, so as to minimize the impact of electromagnetic radiation on the operating personnel.

[0104] Step S7, obtaining the individual intersection duration of the person detection frame with each electromagnetic radiation sphere, and the total intersection duration with all electromagnetic radiation spheres.

[0105] Preferably, the intersection of the person detection frame and the electromagnetic radiation sphere is divided into two stages:

[0106] Among them, the first stage is that the operator approaches the power equipment before the operation begins. Specifically, it starts with the person detection frame and the electromagnetic radiation sphere being circumscribed, then the person detection frame and the electromagnetic radiation sphere are intersected, then the person detection frame and the electromagnetic radiation sphere are inscribed, and finally the person detection frame is contained in the electromagnetic radiation sphere.

[0107] The second stage is when the workers start to stay away from the electrical equipment after the work is completed, and the process is the opposite of the first stage.

[0108] It is worth noting that for small-sized, low-power electrical equipment (the electromagnetic radiation sphere is the smallest enclosing sphere of the equipment itself), the size of the person detection frame cannot be ignored. The first stage is simplified to two position relationships: circumscribed to intersected, and the second stage is simplified to two position relationships: intersected to circumscribed.

[0109] Step S8, respectively determine whether the current single intersection duration exceeds the first preset threshold and whether the total intersection duration exceeds the second preset threshold. If the current single intersection duration exceeds the first preset threshold or the total intersection duration exceeds the second preset threshold, execute step S9.

[0110] Preferably, the first preset threshold can be set according to the average maintenance time of a single power equipment, for example, daily inspection can be set to 5 minutes, daily maintenance can be set to 15 minutes, repairs can be set to 30 minutes, etc. The sum of all first preset thresholds is equal to the second preset threshold.

[0111] It is worth noting that the operation duration for the same operation for small power equipment and large power equipment may be different during the actual operation process. At this time, the operation duration can be proportionally amplified based on the size of the electromagnetic radiation ball according to the above-mentioned preset ratio.

[0112] In step S9, it is determined that the operation has timed out, and a warning signal is generated and sent to the operator.

[0113] Further, step S3, based on the electromagnetic radiation intensity of each power device, an electromagnetic radiation sphere is defined in a preset ratio, and the center of the current electromagnetic radiation sphere coincides with the midpoint of the current power device, including:

[0114] Step S31, sorting all electromagnetic radiation intensities from small to large.

[0115] Step S32, obtaining the minimum and maximum values ​​of the electromagnetic radiation intensity to establish an electromagnetic radiation intensity interval.

[0116] Step S33 : equally divide the electromagnetic radiation intensity interval to form at least two sub-intervals, and the sub-intervals at the two ends are the minimum sub-interval and the maximum sub-interval respectively.

[0117] Step S34, sequentially number each sub-interval from small to large, and define the number of the current sub-interval as the proportional constant of the current sub-interval, the proportional constant of the minimum sub-interval is the minimum proportional constant, and the proportional constant of the maximum sub-interval is the maximum proportional constant.

[0118] Preferably, assuming that there are four sub-intervals corresponding to four types of power equipment (taking photovoltaic power generation as an example, from small to large, they are cables, photovoltaic arrays, energy storage stations, and substations, and the above order can be adjusted according to their actual power), the four sub-intervals are numbered 1, 2, 3, and 4 respectively; at this time, the number of the current sub-interval is defined as the proportional constant of the current sub-interval, that is, the proportional constants of the four sub-intervals are also 1, 2, 3, and 4 respectively, among which the proportional constant of the minimum sub-interval 1 (the above-mentioned minimum proportional constant) is 1, and the proportional constant of the maximum sub-interval 4 (the above-mentioned maximum proportional constant) is 4.

[0119] Step S35, define the minimum electromagnetic radiation sphere as the minimum enclosing sphere of the power equipment in the minimum value sub-interval multiplied by the minimum proportional constant, and the maximum electromagnetic radiation sphere as the minimum enclosing sphere of the power equipment in the maximum value sub-interval multiplied by the maximum proportional constant.

[0120] Preferably, the electromagnetic radiation sphere of the power equipment in sub-interval 4 is the smallest enclosing sphere of the equipment itself, which is enlarged to 4 times its radius or volume. Specifically, the radius or volume can be selected by the operator or software. In this embodiment, the radius is preferred.

[0121] For example, if the size of a power device in sub-interval 4 is 5m×5m×5m, then the radius of the minimum enclosing sphere of the power device is Multiplying by the proportional constant 4 of this subinterval 4, we get the radius of the electromagnetic radiation sphere:

[0122] Preferably, for an irregularly shaped electrical device, if the minimum enclosing sphere of the electrical device is to be obtained, the point cloud data of the electrical device may be obtained first, and then the minimum enclosing sphere of the point cloud data may be directly obtained through an O(N) algorithm.

[0123] Step S36, based on the sub-interval where each power device is located and the corresponding proportional constant, the electromagnetic radiation sphere of each power device is obtained respectively.

[0124] Further, step S4, in response to an entry signal of a worker at the entrance, and based on a target detection algorithm, obtaining a person detection frame matching the entry signal, includes:

[0125] Step S41, in response to the entry signal, acquiring image data matching the entry signal through an external preset camera terminal.

[0126] Step S42, dividing the image data into a preset number of grids on average.

[0127] Preferably, the size of the original picture of the image data may be adjusted to 448×448, and then the resized picture may be evenly divided into S×S (eg, 7×7) grids, and the size of each grid is 64×64.

[0128] Preferably, each grid is used to predict the horizontal coordinate, vertical coordinate, width, height of N detection boxes, and the confidence of each detection box, that is, each grid needs to predict N×(4+1) values.

[0129] Step S43, predicting a number of bounding boxes for the moving targets in the image data based on all grids according to the target detection algorithm.

[0130] Preferably, if the center of an object lies on a certain grid, then the grid is responsible for predicting the bounding box of the object.

[0131] Step S44, respectively obtain the confidence of each bounding box, obtain the bounding box with the largest confidence and mark it as the first-order bounding box.

[0132] Step S45, calculating the intersection-over-union ratio between each other bounding box and the first-order bounding box.

[0133] Step S46: Select a bounding box whose intersection-over-union ratio is greater than or equal to a preset threshold as a second-order bounding box.

[0134] Step S47, obtaining a second-order bounding box with the highest confidence and defining it as a person detection box.

[0135] It can be understood that each grid needs to predict N (x, y, w, h, confidence); where (x, y) is the offset of the center of the detection box relative to the grid, (w, h) is the ratio of the detection box to the above resized image, and (confidence) is the confidence of the grid, which takes a value of 1 or 0.

[0136] Preferably, the confidence level can be understood as whether there is a target in the current grid and the accuracy of the detection frame.

[0137] For example: suppose there is an object in a resized image, and the width and height of the resized image are (w a ,h a )but:

[0138] Divide the image into 7×7 (S×S) grids evenly. There is a grid located at the center of the target. The coordinates of the grid are (x i ,y i ), let the coordinates of the center of the target be (x a ,y a ), the above offset (x b ,y b ):

[0139]

[0140] Preferably, in actual detection, if the predicted detection box and the actual bounding box overlap perfectly, the intersection-and-union ratio is 1. In actual application, the value of the first preset threshold can generally be set to 0.5 to determine whether the predicted bounding box is correct, and the accuracy of the bounding box is positively correlated with the intersection-and-union ratio.

[0141] Preferably, the YOLO algorithm also needs to train the detection frame to improve the accuracy of target detection.

[0142] Next, the training model is trained using a preset pedestrian and vehicle training set, and the weights and biases of the training model are iteratively adjusted a first preset number of times using a back propagation algorithm to reduce the value of the loss function of the training model.

[0143] Preferably, the loss function is as shown in formula ②:

[0144]

[0145] in, is the indicator function of whether the j detection box of the i-th grid is responsible for the target, and its value is 1 or 0; x i ,y i 、w i 、h i , C i They correspond to the i-th (x, y, w, h, confidence) prediction values ​​respectively.

[0146] It can be understood that the loss function includes the coordinate value deviation of the detection box, the confidence deviation, and the prediction probability deviation (or category deviation).

[0147] in, is the detection frame midpoint loss in the coordinate value deviation, is the loss of detection box width and height in coordinate value deviation, is the confidence deviation, is the deviation of the predicted probability (or class deviation).

[0148] Among them, λ coord is the positioning error penalty, generally λ coord =5;S 2 That is, the S×S grids mentioned above; B is the number of bounding boxes; and is the estimated value of the horizontal and vertical coordinates of the midpoint of the i-th bounding box; and is the estimated value of the width and height of the i-th bounding box; C i is the confidence of the i-th bounding box; is the estimated value of the confidence of the i-th bounding box; noobj is the confidence prediction loss, usually λ noobj =0.5; p i (c) is the category probability of the i-th bounding box; is the estimated value of the category probability of the i-th bounding box; p i (c) with The c in it corresponds to classes.

[0149] It should be noted that since each grid does not necessarily contain a target, if there is no target in the grid, the value of (confidence) will be 0, making the gradient span in the subsequent back propagation algorithm too large, so λ is introduced coord To control the loss of the predicted position of the detection box, and introduce λ noobj Controls the penalty for non-existent targets within a single grid.

[0150] Furthermore, in step S6, the shortest inspection route of all the power equipment to be operated is obtained through a path search algorithm and output to the operator, including:

[0151] Step S61, obtaining a digital elevation model of a preset area and outputting all power equipment to be operated and all roads to the digital elevation model.

[0152] Preferably, the purpose of obtaining the digital elevation model of the preset area in this embodiment is to utilize the characteristics of high precision and simple acquisition difficulty of the digital elevation model, without the need for manual on-site mapping. DEM (digital elevation model) can be directly obtained from public channels (national high-precision 5m-12m-30m DEM terrain data).

[0153] Step S62, dividing the digital elevation model into horizontal grids with a preset density.

[0154] Step S63: Detect and obtain all horizontal grids with all roads through a target detection algorithm, and define them as a candidate grid set for the inspection route.

[0155] Step S64, each grid in the inspection route candidate grid set is defined as a node, and all entrances and exits and all power equipment to be operated are defined as starting points and end points respectively.

[0156] Step S65, one of all the end points is defined as the inspection route end point, and the other end points are defined as waypoints, and the minimum number of grids required for the starting point to pass through all the waypoints and finally reach the inspection route end point is calculated by the A-star algorithm.

[0157] Preferably, the A-star algorithm in step S25 is the above-mentioned A* algorithm, which does not need to traverse all grids. The A* algorithm is a "search algorithm", which is essentially an optimization of the breadth-first search algorithm (BFS). Starting from the starting point, first traverse the points adjacent to the starting point, and then traverse the points adjacent to the points that have been traversed, and gradually spread outward until the end point is found. The function of the A* algorithm is to "solve the shortest path", such as moving to the target point on a map with obstacles, and digital problems (the shortest way from one state to another). The idea of ​​the A* algorithm is similar to the Dijkstra algorithm, which adopts a greedy strategy, that is, "if the shortest path from A to C passes through B, then the section from A to B must be the shortest", find out the shortest path from the starting point to each possible point and record it. The difference between the A* algorithm and the Dijkstra algorithm is that the A* algorithm is a heuristic algorithm, which has prior knowledge, such as "walking in the direction of the end point is more likely to arrive". The A* algorithm not only pays attention to the path that has been traveled, but also predicts the points or states that have not been traveled. Therefore, compared with Di jkstra, the A* algorithm adjusts the order of BFS, searches fewer "unlikely points", and finds the shortest path to the target point faster.

[0158] Step S66, obtaining all horizontal grids corresponding to the minimum number of grids, and connecting them in sequence to form the shortest inspection route.

[0159] Step S67, output the shortest inspection route to the receiving end of the operator.

[0160] Further, in step S65, one of all the end points is defined as the inspection route end point, the other end points are defined as waypoints, and the minimum number of grids required for the starting point to pass through all the waypoints and finally reach the inspection route end point is calculated by the A-star algorithm, including:

[0161] Step S651, creating a grid set to be checked.

[0162] Step S652, adding the starting point, all waypoints, and the end point to the grid set to be checked, and setting the priority of the starting point to the highest, the priority of all waypoints to the middle, and the priority of the end point to the lowest.

[0163] Step S653, determining whether the grid set to be checked is empty, if the grid set to be checked is not empty, executing step S654.

[0164] Step S654, selecting the node with the highest priority from the set of grids to be checked.

[0165] Step S655, determine whether the node is one of the waypoints. If the node is one of the waypoints, execute step S656.

[0166] Step S656, starting from the current waypoint, gradually track the parent node until reaching the starting point.

[0167] Step S657, respectively obtain the number of grids required for each waypoint to reach the starting point, and define the waypoint with the least number of grids required as the starting point of the next path search.

[0168] Step S658, iterate steps S651 to S657 several times until the starting point, all the waypoints, and the end point are connected in sequence with a single line to obtain the shortest inspection route.

[0169] Step S659, obtaining all grids covered by the shortest inspection route to obtain the minimum number of grids.

[0170] Preferably, the priority is related to the heuristic function of the A-star algorithm:

[0171] F=G+H③.

[0172] Among them, G is the movement cost of moving from the starting point to the specified grid, and the path generated along the grid is derived from the known grid information; H is the estimated cost of moving from the specified grid to the end point, and H is derived from the estimation of the unknown grid information; F is the basis for selecting the next node to be traversed.

[0173] Preferably, for a grid-like graph, the following heuristic functions can be used:

[0174] If the graph allows only four directions of movement, up, down, left, and right, the Manhattan distance can be used to calculate the number of grids that need to be moved horizontally or vertically from the current grid to the target; if the graph allows eight directions of movement, the diagonal distance can be used. Both horizontal and vertical movement and diagonal movement are legal. To improve efficiency, the horizontal and vertical movement is usually an integer of 10, and the diagonal movement is usually an integer of 14 ( If the graph allows movement in any direction, the Euclidean distance, which is the straight-line distance between two points, can be used.

[0175] Further, step S653 determines whether the grid set to be checked is empty, and then includes:

[0176] Step S10: If the grid set to be checked is empty, all neighboring nodes of the node are traversed, and all neighboring nodes are added to the grid set to be checked.

[0177] Step S20, obtaining the neighboring node with the highest priority among all neighboring nodes as the parent node for the next traversal.

[0178] Step S30, starting from the current parent node, gradually tracing the parent node of the next traversal until reaching one of the waypoints.

[0179] Step S40, defining one of the waypoints reached as the starting point of the next path search.

[0180] Step S50, iterate steps S10 to S40 several times until the starting point, all the waypoints, and the end point are connected in sequence with a single line to obtain the shortest inspection route.

[0181] Step S60, obtaining all grids covered by the shortest inspection route to obtain the minimum number of grids.

[0182] Preferably, the set of grids to be checked is the open list. In actual application, the A* algorithm implements the shortest path search through the following steps:

[0183] (1) Start from the starting point and add the starting point to an open list for storing grids. Currently, there is only one item in the open list, namely the starting point. More grids will be gradually added in the subsequent search process. The grids in the open list are all grids that can be reached in the next step and are used as alternative grids. In the final shortest path, the grids in the open list may be passed along the way or not. That is, the open list is a list of grids to be checked.

[0184] (2) Check the grids adjacent to the starting point and add the walkable or reachable grids to the open list. Set the starting point to the parent node (parentnode or parentsquare) of these grids. When tracing the path, these parent nodes record the last node passed on the shortest path from the starting point to the node.

[0185] (3) Remove the starting point from the open list and add it to the closed list. Each grid in the closed list no longer needs to be paid attention to.

[0186] (4) Select the grid with the smallest F value from the open list and repeat steps (2) to (3).

[0187] In summary, by repeatedly traversing the open list, selecting the grid with the smallest F value, and generating new available grids, until the grid where the end point is found.

[0188] Preferably, for the cost of each grid, it is necessary to calculate the heuristic function of each grid separately. The calculation idea of ​​G is similar to the Dijkstra algorithm, which adopts a greedy strategy, that is, "if the shortest path from A to C passes through B, then the section from A to B must be the shortest", find the shortest path from the starting point to each possible point and record it. If 10 and 14 in this embodiment are used as coefficients, the horizontal or vertical movement cost is 10, and the diagonal movement cost is 14.

[0189] Furthermore, step S7, obtaining the single intersection duration of the person detection frame with each electromagnetic radiation sphere, and the total intersection duration with all electromagnetic radiation spheres, includes:

[0190] Step S71, defining a world coordinate system according to any horizontal plane and any vertical plane in a preset area.

[0191] Step S72, mapping the person detection frame to the world coordinate system through the homography matrix to form a two-dimensional person detection frame, and the two-dimensional person detection frame is parallel to or coplanar with any vertical plane.

[0192] Preferably, in practical applications, radar data of the same scene needs to be added to ensure the accuracy of detection box mapping.

[0193] Preferably, the homography matrix can be obtained by express.

[0194] Among them, u and v are the location information of the current device, x and y are the pixel coordinate values ​​of the current device in the image data, H is the homography matrix, and By solving the homography matrix, all radar points whose pixel coordinate system coincides with the world coordinate system of the same external scene are obtained.

[0195] Step S73, obtaining the symmetry axis of the two-dimensional person detection frame in the vertical direction.

[0196] Step S74, rotating the two-dimensional person detection frame based on the axis of symmetry.

[0197] Step S75, obtaining the complete rotation trajectory of the two-dimensional person detection frame, and defining the complete rotation trajectory as a three-dimensional person detection frame.

[0198] Preferably, the three-dimensional person detection frame is cylindrical, which is obtained by rotating the rectangle of the two-dimensional person detection frame.

[0199] Step S76, obtaining the Euclidean distance between the three-dimensional person detection frame and all electromagnetic radiation spheres based on the world coordinate system.

[0200] Step S77, determine whether the Euclidean distance is less than or equal to zero. If the Euclidean distance is less than or equal to zero, execute step S78.

[0201] Step S78, obtaining the first intersection duration of the electromagnetic radiation sphere intersecting with the three-dimensional person detection frame, and obtaining a single intersection duration.

[0202] Step S79, obtaining the second intersection duration between the three-dimensional person detection frame and each electromagnetic radiation sphere respectively, and adding up all the second intersection durations to obtain a total intersection duration.

[0203] In this embodiment, a three-dimensional layout of a preset area is obtained, and the three-dimensional layout includes the locations of all power equipment, all roads, and all entrances and exits located in the preset area; the electromagnetic radiation intensity of each device is obtained respectively through a preset strategy; an electromagnetic radiation ball is defined based on the electromagnetic radiation intensity of each power equipment at a preset ratio, and the center of the current electromagnetic radiation ball coincides with the midpoint of the current power equipment; in response to the entry signal of the operator located at the entrance and exit, a person detection frame matching the entry signal is obtained based on the target detection algorithm; the preset operation requirements of the operator are obtained, and the power equipment that needs to be operated is marked as the power equipment to be operated according to the operation requirements; the shortest inspection route of all the power equipment to be operated is obtained through a path search algorithm and output to the operator; the single intersection time of the person detection frame with each electromagnetic radiation ball and the total intersection time with all electromagnetic radiation balls are obtained; it is judged whether the current single intersection time exceeds the first preset threshold and the total intersection time exceeds the second preset threshold respectively. If the current single intersection time exceeds the first preset threshold or the total intersection time exceeds the second preset threshold, it is determined that the operation is timed out, and a warning signal is generated and sent to the operator. This embodiment defines a matching electromagnetic radiation ball based on the electromagnetic radiation intensity of the power equipment to detect the relative position relationship between the power equipment and the operator, and the electromagnetic radiation ball of the power equipment increases as the electromagnetic radiation intensity of the power equipment increases. In addition, this embodiment utilizes the positive correlation between the electromagnetic radiation intensity, equipment size, and power of common power equipment. For small power equipment, the electromagnetic radiation of small power equipment is weak or negligible (the impact distance is within 0.1m), so that the electromagnetic radiation of this small power equipment will not affect or will only slightly affect the operator. The electromagnetic radiation ball of the small power equipment is only the size of its own size. For large power equipment, the electromagnetic radiation of large power equipment is stronger (the impact range is generally 1m to 10m), and the impact range increases with the increase of power. At this time, it is necessary to expand the electromagnetic radiation ball of the large power equipment from the size of the equipment itself to the external space of the equipment based on the above-mentioned preset ratio, so that the operator starts the intersection timing when he approaches but has not touched the large power equipment. Finally, the operator is reminded whether the time is overtime through the timing of a single device and the total timing, and the operator is reminded after the timeout. The operator can leave the scene after being reminded, thereby ensuring the safety and health of the operator.

[0204] like Figure 2 As shown, this embodiment provides an embodiment of an operation monitoring device for electric power equipment. In this embodiment, the operation monitoring device is applied to the operation monitoring method in the above-mentioned embodiment.

[0205] Specifically, the operation monitoring device includes a three-dimensional layout acquisition module 1, an electromagnetic radiation intensity acquisition module 2, an electromagnetic radiation ball definition module 3, a person detection frame acquisition module 4, a power equipment to be operated marking module 5, a shortest inspection route acquisition and output module 6, an intersection time acquisition module 7, an intersection time judgment module 8, and an operation timeout judgment module 9, which are electrically connected in sequence.

[0206] Among them, the three-dimensional layout acquisition module 1 is used to obtain the three-dimensional layout of the preset area, and the three-dimensional layout includes the locations of all power equipment, all roads, and all entrances and exits located in the preset area; the electromagnetic radiation intensity acquisition module 2 is used to obtain the electromagnetic radiation intensity of each device respectively through a preset strategy; the electromagnetic radiation ball definition module 3 is used to define an electromagnetic radiation ball based on the electromagnetic radiation intensity of each power device in a preset ratio, and the center of the current electromagnetic radiation ball coincides with the midpoint of the current power device; the person detection frame acquisition module 4 is used to respond to the entry signal of the operator at the entrance and exit, and obtain the person detection frame matching the entry signal based on the target detection algorithm; the power equipment to be operated marking module 5 is used to obtain the preset operation requirements of the operator, and according to The operation requirement marks the power equipment that needs to be operated as the power equipment to be operated; the shortest inspection route acquisition and output module 6 is used to obtain the shortest inspection route of all the power equipment to be operated through the path search algorithm and output it to the operator; the intersection time acquisition module 7 is used to obtain the single intersection time of the human detection frame with each electromagnetic radiation ball respectively, and the total intersection time with all electromagnetic radiation balls; the intersection time judgment module 8 is used to judge whether the current single intersection time exceeds the first preset threshold and the total intersection time exceeds the second preset threshold; the operation timeout judgment module 9 is used to judge whether the current single intersection time exceeds the first preset threshold or the total intersection time exceeds the second preset threshold, if it is determined that the operation is timed out, and generate a warning signal and send it to the operator.

[0207] Furthermore, the electromagnetic radiation sphere definition module includes a first electromagnetic radiation sphere definition submodule, a second electromagnetic radiation sphere definition submodule, a third electromagnetic radiation sphere definition submodule, a fourth electromagnetic radiation sphere definition submodule, a fifth electromagnetic radiation sphere definition submodule, and a sixth electromagnetic radiation sphere definition submodule, which are electrically connected in sequence; the first electromagnetic radiation sphere definition submodule is electrically connected to the electromagnetic radiation intensity acquisition module, and the sixth electromagnetic radiation sphere definition submodule is electrically connected to the person detection frame acquisition module.

[0208] Among them, the first electromagnetic radiation sphere definition submodule is used to sort all electromagnetic radiation intensities from small to large; the second electromagnetic radiation sphere definition submodule is used to obtain the minimum and maximum values ​​of the electromagnetic radiation intensity to establish an electromagnetic radiation intensity interval; the third electromagnetic radiation sphere definition submodule is used to evenly divide the electromagnetic radiation intensity interval to form at least two sub-intervals, and the sub-intervals located at both ends are the minimum sub-interval and the maximum sub-interval respectively; the fourth electromagnetic radiation sphere definition submodule is used to sequentially number each sub-interval from small to large, and define the number of the current sub-interval as the proportional constant of the current sub-interval, then the proportional constant of the minimum sub-interval is the minimum proportional constant, and the proportional constant of the maximum sub-interval is the maximum proportional constant; the fifth electromagnetic radiation sphere definition submodule is used to define the minimum electromagnetic radiation sphere as the minimum enclosing sphere of the power equipment in the minimum sub-interval multiplied by the minimum proportional constant, then the maximum electromagnetic radiation sphere is the minimum enclosing sphere of the power equipment in the maximum sub-interval multiplied by the maximum proportional constant; the sixth electromagnetic radiation sphere definition submodule is used to obtain the electromagnetic radiation sphere of each power device based on the sub-interval where each power device is located and the corresponding proportional constant.

[0209] Furthermore, the person detection frame acquisition module specifically includes a first person detection frame acquisition submodule, a second person detection frame acquisition submodule, a third person detection frame acquisition submodule, a fourth person detection frame acquisition submodule, a fifth person detection frame acquisition submodule, a sixth person detection frame acquisition submodule, and a seventh person detection frame acquisition submodule, which are electrically connected in sequence; the first person detection frame acquisition submodule is electrically connected to the sixth electromagnetic radiation ball definition submodule, and the seventh person detection frame acquisition submodule is electrically connected to the power equipment to be operated marking module.

[0210] Among them, the first person detection frame acquisition submodule is used to respond to the entry signal and acquire image data matching the entry signal through an external preset camera terminal; the second person detection frame acquisition submodule is used to evenly divide the image data into a preset number of grids; the third person detection frame acquisition submodule is used to predict a number of bounding boxes for moving targets in the image data based on all grids according to the target detection algorithm; the fourth person detection frame acquisition submodule is used to respectively acquire the confidence of each bounding box, and acquire the bounding box with the largest confidence and mark it as a first-order bounding box; the fifth person detection frame acquisition submodule is used to calculate the intersection and union ratio of each other bounding box with the first-order bounding box; the sixth person detection frame acquisition submodule is used to select a bounding box with an intersection and union ratio greater than or equal to a preset threshold as a second-order bounding box; the seventh person detection frame acquisition submodule is used to acquire the second-order bounding box with the highest confidence and define it as a person detection frame.

[0211] Furthermore, the shortest inspection route acquisition and output module specifically includes a first shortest inspection route acquisition and output submodule, a second shortest inspection route acquisition and output submodule, a third shortest inspection route acquisition and output submodule, a fourth shortest inspection route acquisition and output submodule, a fifth shortest inspection route acquisition and output submodule, a sixth shortest inspection route acquisition and output submodule, and a seventh shortest inspection route acquisition and output submodule, which are electrically connected in sequence; the first shortest inspection route acquisition and output submodule is electrically connected to the power equipment to be operated marking module, and the seventh shortest inspection route acquisition and output submodule is electrically connected to the intersection time acquisition module.

[0212] Among them, the first shortest inspection route acquisition and output submodule is used to acquire the digital elevation model of the preset area and output all the power equipment to be operated and all the roads to the digital elevation model; the second shortest inspection route acquisition and output submodule is used to divide the digital elevation model by horizontal grids of preset density; the third shortest inspection route acquisition and output submodule is used to detect and acquire all horizontal grids with all roads through the target detection algorithm, and define them as the inspection route candidate grid set; the fourth shortest inspection route acquisition and output submodule is used to define each grid in the inspection route candidate grid set as a node, and All entrances and exits and all power equipment to be operated are defined as starting points and end points respectively; the fifth shortest inspection route acquisition and output submodule is used to define one of all end points as the end point of the inspection route and the other end points as waypoints, and calculate the minimum number of grids required for the starting point to pass through all waypoints and finally reach the end point of the inspection route through the A-star algorithm; the sixth shortest inspection route acquisition and output submodule is used to obtain all horizontal grids corresponding to the minimum number of grids, and connect them in sequence to form the shortest inspection route; the seventh shortest inspection route acquisition and output submodule is used to output the shortest inspection route to the receiving end of the operator.

[0213] Further, the fifth shortest inspection route acquisition and output submodule specifically includes a first shortest inspection route acquisition and output unit, a second shortest inspection route acquisition and output unit, a third shortest inspection route acquisition and output unit, a fourth shortest inspection route acquisition and output unit, a fifth shortest inspection route acquisition and output unit, a sixth shortest inspection route acquisition and output unit, a seventh shortest inspection route acquisition and output unit, an eighth shortest inspection route acquisition and output unit, and a ninth shortest inspection route acquisition and output unit, which are electrically connected in sequence; the first shortest inspection route acquisition and output unit is electrically connected to the fourth shortest inspection route acquisition and output submodule, and the ninth shortest inspection route acquisition and output unit is electrically connected to the sixth shortest inspection route acquisition and output submodule.

[0214] Among them, the first shortest inspection route acquisition and output unit is used to create a grid set to be inspected; the second shortest inspection route acquisition and output unit is used to add the starting point, all the waypoints, and the end point to the grid set to be inspected, and set the priority of the starting point to the highest, the priority of all the waypoints to the middle, and the priority of the end point to the lowest; the third shortest inspection route acquisition and output unit is used to determine whether the grid set to be inspected is empty; the fourth shortest inspection route acquisition and output unit is used to select the node with the highest priority from the grid set to be inspected if the grid set to be inspected is not empty; the fifth shortest inspection route acquisition and output unit is used to determine whether the node is one of the waypoints; the sixth shortest inspection route acquisition and output unit If the node is one of the waypoints, the parent node is gradually tracked from the current waypoint until the starting point is reached; the seventh shortest inspection route acquisition and output unit is used to respectively obtain the number of grids required for each waypoint to reach the starting point, and define the waypoint with the least number of required grids as the starting point of the next path search; the eighth shortest inspection route acquisition and output unit is used to repeatedly execute the first shortest inspection route acquisition and output unit to the seventh shortest inspection route acquisition and output unit several times in sequence until the starting point, all the waypoints, and the end point are connected in a single line in sequence to obtain the shortest inspection route; the ninth shortest inspection route acquisition and output unit is used to obtain all grids covered by the shortest inspection route to obtain the minimum number of grids.

[0215] Furthermore, the fifth shortest inspection route acquisition and output submodule also includes a tenth shortest inspection route acquisition and output unit, an eleventh shortest inspection route acquisition and output unit, a twelfth shortest inspection route acquisition and output unit, a thirteenth shortest inspection route acquisition and output unit, a fourteenth shortest inspection route acquisition and output unit, and a fifteenth shortest inspection route acquisition and output unit, which are electrically connected in sequence; the tenth shortest inspection route acquisition and output unit is electrically connected to the third shortest inspection route acquisition and output unit, and the fifteenth shortest inspection route acquisition and output unit is electrically connected to the sixth shortest inspection route acquisition and output submodule.

[0216] Among them, the tenth shortest inspection route acquisition and output unit is used to traverse all neighboring nodes of the node if the set of grids to be inspected is empty, and add all neighboring nodes to the set of grids to be inspected; the eleventh shortest inspection route acquisition and output unit is used to obtain the neighboring node with the highest priority among all neighboring nodes as the parent node for the next traversal; the twelfth shortest inspection route acquisition and output unit is used to gradually track the parent node for the next traversal starting from the current parent node until one of the waypoints is reached; the thirteenth shortest inspection route acquisition and output unit is used to define one of the waypoints reached as the starting point for the next path search; the fourteenth shortest inspection route acquisition and output unit is used to repeatedly execute the tenth shortest inspection route acquisition and output unit to the thirteenth shortest inspection route acquisition and output unit several times in sequence until the starting point, all the waypoints, and the end point are connected in sequence with a single line to obtain the shortest inspection route; the fifteenth shortest inspection route acquisition and output unit is used to obtain all grids covered by the shortest inspection route to obtain the minimum number of grids.

[0217] Furthermore, the intersection time acquisition module specifically includes a first intersection time acquisition submodule, a second intersection time acquisition submodule, a third intersection time acquisition submodule, a fourth intersection time acquisition submodule, a fifth intersection time acquisition submodule, a sixth intersection time acquisition submodule, a seventh intersection time acquisition submodule, an eighth intersection time acquisition submodule, and a ninth intersection time acquisition submodule, which are electrically connected in sequence; the first intersection time acquisition submodule is electrically connected to the ninth shortest inspection route acquisition and output unit and the fifteenth shortest inspection route acquisition and output unit, respectively, and the ninth intersection time acquisition submodule is electrically connected to the intersection time judgment module.

[0218] Among them, the first intersection duration acquisition submodule is used to define a world coordinate system according to any horizontal plane and any vertical plane in a preset area; the second intersection duration acquisition submodule is used to map the person detection frame to the world coordinate system through a homography matrix to form a two-dimensional person detection frame, and the two-dimensional person detection frame is parallel or coplanar with any vertical plane; the third intersection duration acquisition submodule is used to obtain the symmetry axis of the two-dimensional person detection frame in the vertical direction; the fourth intersection duration acquisition submodule is used to rotate the two-dimensional person detection frame based on the symmetry axis; the fifth intersection duration acquisition submodule is used to obtain the complete rotation trajectory of the two-dimensional person detection frame, and convert the complete rotation trajectory into a real-time image; The trace is defined as a three-dimensional person detection frame; the sixth intersection duration acquisition submodule is used to obtain the Euclidean distance between the three-dimensional person detection frame and all electromagnetic radiation spheres based on the world coordinate system; the seventh intersection duration acquisition submodule is used to determine whether the Euclidean distance is less than or equal to zero; the eighth intersection duration acquisition submodule is used to obtain the first intersection duration of the electromagnetic radiation sphere intersecting with the three-dimensional person detection frame if the Euclidean distance is less than or equal to zero, and obtain a single intersection duration; the ninth intersection duration acquisition submodule is used to obtain the second intersection duration between the three-dimensional person detection frame and each electromagnetic radiation sphere, and add up all the second intersection durations to obtain the total intersection duration.

[0219] It should be noted that the four embodiments are functional module item embodiments based on the above method embodiments. For additional contents such as the optimization, expansion, and example illustration of this embodiment, please refer to the above method embodiments, and this embodiment will not be repeated.

[0220] In this embodiment, a three-dimensional layout of a preset area is obtained, and the three-dimensional layout includes the locations of all power equipment, all roads, and all entrances and exits located in the preset area; the electromagnetic radiation intensity of each device is obtained respectively through a preset strategy; an electromagnetic radiation ball is defined based on the electromagnetic radiation intensity of each power equipment at a preset ratio, and the center of the current electromagnetic radiation ball coincides with the midpoint of the current power equipment; in response to the entry signal of the operator located at the entrance and exit, a person detection frame matching the entry signal is obtained based on the target detection algorithm; the preset operation requirements of the operator are obtained, and the power equipment that needs to be operated is marked as the power equipment to be operated according to the operation requirements; the shortest inspection route of all the power equipment to be operated is obtained through a path search algorithm and output to the operator; the single intersection time of the person detection frame with each electromagnetic radiation ball and the total intersection time with all electromagnetic radiation balls are obtained; it is judged whether the current single intersection time exceeds the first preset threshold and the total intersection time exceeds the second preset threshold respectively. If the current single intersection time exceeds the first preset threshold or the total intersection time exceeds the second preset threshold, it is determined that the operation is timed out, and a warning signal is generated and sent to the operator. This embodiment defines a matching electromagnetic radiation ball based on the electromagnetic radiation intensity of the power equipment to detect the relative position relationship between the power equipment and the operator, and the electromagnetic radiation ball of the power equipment increases as the electromagnetic radiation intensity of the power equipment increases. In addition, this embodiment utilizes the positive correlation between the electromagnetic radiation intensity, equipment size, and power of common power equipment. For small power equipment, the electromagnetic radiation of small power equipment is weak or negligible (the impact distance is within 0.1m), so that the electromagnetic radiation of this small power equipment will not affect or will only slightly affect the operator. The electromagnetic radiation ball of the small power equipment is only the size of its own size. For large power equipment, the electromagnetic radiation of large power equipment is stronger (the impact range is generally 1m to 10m), and the impact range increases with the increase of power. At this time, it is necessary to expand the electromagnetic radiation ball of the large power equipment from the size of the equipment itself to the external space of the equipment based on the above-mentioned preset ratio, so that the operator starts the intersection timing when he approaches but has not touched the large power equipment. Finally, the operator is reminded whether the time is overtime through the timing of a single device and the total timing, and the operator is reminded after the timeout. The operator can leave the scene after being reminded, thereby ensuring the safety and health of the operator.

[0221] Figure 3 An embodiment of the electronic device of the present application is shown, see Figure 3 The electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101 .

[0222] The memory 102 stores program instructions for implementing the method for monitoring the operation of the electric power equipment according to any of the above-mentioned embodiments.

[0223] The processor 101 is used to execute program instructions stored in the memory 102 to perform operation monitoring of the power equipment.

[0224] The processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having a signal processing capability. The processor 101 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0225] Further, Figure 4 This is a schematic diagram of the structure of a storage medium according to an embodiment of the present application. Figure 4 The storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions to enable a computer power device (which can be a personal computer, server, or network power device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes, or terminal power devices such as computers, servers, mobile phones, tablets, etc.

[0226] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only 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 an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0227] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

[0228] The specific implementation methods of the invention are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A method for monitoring the operation of an electric power device, wherein the electric power device has a plurality of devices and all of the devices are located in a preset area, characterized in that: The operation monitoring method of the electric power equipment comprises: Step S1, obtaining a three-dimensional layout of the preset area, wherein the three-dimensional layout includes the locations of all power equipment, all roads, and all entrances and exits within the preset area; Step S2, obtaining the electromagnetic radiation intensity of each device respectively through a preset strategy; Step S3, defining an electromagnetic radiation sphere based on the electromagnetic radiation intensity of each power device in a preset ratio, wherein the center of the current electromagnetic radiation sphere coincides with the midpoint of the current power device; Step S4, responding to an entry signal of a worker at the entrance and exit, and acquiring a person detection frame matching the entry signal based on a target detection algorithm; Step S5, obtaining the preset operation requirements of the operator, and marking the power equipment that needs to be operated as the power equipment to be operated according to the operation requirements; Step S6, obtaining the shortest inspection route of all the power equipment to be operated through a path search algorithm and outputting it to the operator; Step S7, obtaining a single intersection duration of the person detection frame with each electromagnetic radiation sphere, and a total intersection duration of the person detection frame with all electromagnetic radiation spheres; Step S8, respectively judging whether the current single intersection duration exceeds the first preset threshold value and whether the total intersection duration exceeds the second preset threshold value, if the current single intersection duration exceeds the first preset threshold value or the total intersection duration exceeds the second preset threshold value, executing step S9; Step S9, determining that the operation is timed out, generating a warning signal and sending it to the operator; Step S3, defining an electromagnetic radiation sphere based on the electromagnetic radiation intensity of each power device in a preset ratio, wherein the center of the current electromagnetic radiation sphere coincides with the midpoint of the current power device, including: Step S31, sorting all electromagnetic radiation intensities from small to large; Step S32, obtaining the minimum and maximum values ​​of the electromagnetic radiation intensity to establish an electromagnetic radiation intensity interval; Step S33, equally dividing the electromagnetic radiation intensity interval to form at least two sub-intervals, and the sub-intervals at the two ends are the minimum sub-interval and the maximum sub-interval respectively; Step S34, sequentially numbering each sub-interval from small to large, and defining the number of the current sub-interval as the proportional constant of the current sub-interval, the proportional constant of the minimum sub-interval is the minimum proportional constant, and the proportional constant of the maximum sub-interval is the maximum proportional constant; Step S35, defining the minimum electromagnetic radiation sphere as the minimum enclosing sphere of the electric equipment within the minimum value subinterval multiplied by the minimum proportional constant, and the maximum electromagnetic radiation sphere as the minimum enclosing sphere of the electric equipment within the maximum value subinterval multiplied by the maximum proportional constant; Step S36, based on the sub-interval where each power device is located and the corresponding proportional constant, the electromagnetic radiation sphere of each power device is obtained respectively.

2. The operation monitoring method according to claim 1, characterized in that: Step S4, in response to an entry signal of a worker at the entrance, and based on a target detection algorithm, obtaining a person detection frame matching the entry signal, includes: Step S41, in response to the entry signal, acquiring image data matching the entry signal through an external preset camera terminal; Step S42, dividing the image data into a preset number of grids on average; Step S43, predicting a plurality of bounding boxes for the moving target in the image data according to the target detection algorithm based on all grids; Step S44, respectively obtaining the confidence of each bounding box, and obtaining the bounding box with the largest confidence and marking it as a first-order bounding box; Step S45, calculating the intersection-over-union ratio of each other bounding box with the first-order bounding box; Step S46, selecting a bounding box whose intersection-over-union ratio is greater than or equal to a preset threshold as a second-order bounding box; Step S47, obtaining a second-order bounding box with the highest confidence and defining it as the person detection box.

3. The operation monitoring method according to claim 1, characterized in that: Step S6, obtaining the shortest inspection route of all the power equipment to be operated through a path search algorithm and outputting it to the operator, including: Step S61, obtaining a digital elevation model of the preset area and outputting all power equipment to be operated and all roads to the digital elevation model; Step S62, dividing the digital elevation model by horizontal grids of preset density; Step S63, detecting and acquiring all horizontal grids with all roads through a target detection algorithm, and defining them as a candidate grid set for inspection routes; Step S64, defining each grid in the inspection route candidate grid set as a node, and defining all entrances and exits and all power equipment to be operated as starting points and end points respectively; Step S65, defining one of all the end points as the inspection route end point, and defining the other end points as waypoints, and calculating the minimum number of grids required for the starting point to pass through all the waypoints and finally reach the inspection route end point by using the A-star algorithm; Step S66, obtaining all horizontal grids corresponding to the minimum number of grids, and sequentially connecting them to form the shortest inspection route; Step S67, outputting the shortest inspection route to the receiving end of the operator.

4. The operation monitoring method according to claim 3, characterized in that: Step S65, defining one of all the end points as the inspection route end point, and defining the other end points as waypoints, and calculating the minimum number of grids required for the starting point to pass through all the waypoints and finally reach the inspection route end point by using the A-star algorithm, including: Step S651, creating a grid set to be checked; Step S652, adding the starting point, all the waypoints, and the end point to the grid set to be checked, and setting the priority of the starting point to the highest, setting the priority of all the waypoints to the middle, and setting the priority of the end point to the lowest; Step S653, determining whether the to-be-checked grid set is empty, if the to-be-checked grid set is not empty, executing step S654; Step S654, selecting a node with the highest priority from the set of grids to be checked; Step S655, determining whether the node is one of the waypoints, if the node is one of the waypoints, executing step S656; Step S656, starting from the current waypoint, gradually tracking the parent node until reaching the starting point; Step S657, respectively obtaining the number of grids required for each waypoint to reach the starting point, and defining the waypoint with the least number of grids required as the starting point for the next path search; Step S658, iterating steps S651 to S657 for several times until the starting point, all the waypoints, and the end point are sequentially connected in a single line to obtain the shortest inspection route; Step S659, obtaining all grids covered by the shortest inspection route to obtain the minimum number of grids.

5. The operation monitoring method according to claim 4, characterized in that: Step S653, determining whether the grid set to be checked is empty, and then comprising: Step S10, if the grid set to be checked is empty, traverse all neighboring nodes of the node and add all neighboring nodes to the grid set to be checked; Step S20, obtaining the neighboring node with the highest priority among all neighboring nodes as the parent node for the next traversal; Step S30, starting from the current parent node, gradually tracing the parent node of the next traversal until reaching one of the waypoints; Step S40, defining one of the waypoints reached as the starting point of the next path search; Step S50, iterating steps S10 to S40 several times until the starting point, all the waypoints, and the end point are sequentially connected in a single line to obtain the shortest inspection route; Step S60, obtaining all grids covered by the shortest inspection route to obtain the minimum number of grids.

6. The operation monitoring method according to claim 1, characterized in that: Step S7, obtaining the single intersection duration of the person detection frame with each electromagnetic radiation sphere, and the total intersection duration with all electromagnetic radiation spheres, including: Step S71, defining a world coordinate system according to any horizontal plane and any vertical plane of the preset area; Step S72, mapping the person detection frame to the world coordinate system through a homography matrix to form a two-dimensional person detection frame, and the two-dimensional person detection frame is parallel to or coplanar with the arbitrary vertical plane; Step S73, obtaining the symmetry axis of the two-dimensional person detection frame in the vertical direction; Step S74, rotating the two-dimensional person detection frame based on the symmetry axis; Step S75, obtaining a complete rotation trajectory of the two-dimensional person detection frame, and defining the complete rotation trajectory as a three-dimensional person detection frame; Step S76, obtaining the Euclidean distance between the three-dimensional person detection frame and all electromagnetic radiation spheres based on the world coordinate system; Step S77, determining whether the Euclidean distance is less than or equal to zero, if the Euclidean distance is less than or equal to zero, executing step S78; Step S78, obtaining a first intersection duration of the electromagnetic radiation sphere intersecting with the three-dimensional person detection frame to obtain the single intersection duration; Step S79, obtaining the second intersection duration between the three-dimensional person detection frame and each electromagnetic radiation sphere respectively, and adding up all the second intersection durations to obtain the total intersection duration.

7. An operation monitoring device for electric power equipment, the operation monitoring device for electric power equipment being applied to the operation monitoring method according to any one of claims 1 to 6, characterized in that: The operation monitoring device comprises: A three-dimensional layout acquisition module, used to acquire the three-dimensional layout of the preset area, wherein the three-dimensional layout includes the locations of all power equipment, all roads, and all entrances and exits located in the preset area; An electromagnetic radiation intensity acquisition module is used to obtain the electromagnetic radiation intensity of each device respectively through a preset strategy; An electromagnetic radiation sphere definition module is used to define an electromagnetic radiation sphere based on the electromagnetic radiation intensity of each power device in a preset ratio, and the center of the current electromagnetic radiation sphere coincides with the midpoint of the current power device; A person detection frame acquisition module, used to respond to an entry signal of a worker at the entrance and to acquire a person detection frame matching the entry signal based on a target detection algorithm; A power equipment to be operated marking module is used to obtain the preset operation requirements of the operator and mark the power equipment that needs to be operated as the power equipment to be operated according to the operation requirements; The shortest inspection route acquisition and output module is used to acquire the shortest inspection routes of all the power equipment to be operated through a path search algorithm and output them to the operator; An intersection duration acquisition module, used to acquire a single intersection duration of the person detection frame with each electromagnetic radiation sphere, and a total intersection duration with all electromagnetic radiation spheres; An intersection duration judgment module, used to judge whether the current single intersection duration exceeds a first preset threshold and whether the total intersection duration exceeds a second preset threshold; The operation timeout judgment module is used to judge that the operation is overtime if the current single intersection duration exceeds the first preset threshold or the total intersection duration exceeds the second preset threshold, and generate a warning signal and send it to the operator.

8. An electronic device, characterized in that: It includes a processor and a memory coupled to the processor, the memory storing program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the operation monitoring method of the power equipment as described in any one of claims 1 to 6 is implemented.

9. A storage medium, characterized in that: The storage medium stores program instructions, which, when executed by a processor, can implement the method for monitoring the operation of an electric power device according to any one of claims 1 to 6.

Images