UAV health status evaluation method, device, equipment and computer storage medium

Through image acquisition and recognition technology, the evaluation of drone health status is automatically calculated, which solves the problem of inaccurate evaluation caused by subjective impact in the existing technology, and achieves a more accurate and comprehensive integrated health status assessment.

CN111814730BActive Publication Date: 2024-11-22SHENZHEN JIUYI TONGHANG ELECTRONIC EQUIP TECH CO LTD
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202010713899.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-07-21
Publication Date
2024-11-22
Estimated Expiration
2040-07-21

AI Technical Summary

Technical Problem

The evaluation of the health status of existing drones depends on subjective observations of technicians, resulting in inaccurate evaluation results.

Method used

The image acquisition device is used to collect images on the surface of the drone, compare image recognition technology, determine characterization problems, and calculate appearance scores and weighted comprehensive scores based on the preset score table to realize automated evaluation.

Benefits of technology

It avoids subjective deviations, improves the accuracy and automation of drone health status evaluation, and provides scientific maintenance strategy guidance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111814730B_ABST
    Figure CN111814730B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for evaluating the health status of a drone, comprising the following steps: acquiring an image of the drone surface by a preset image acquisition device to obtain a representation image; preprocessing the representation image and comparing it with a standard image in a preset appearance recognition library to determine various representation problems of the drone; querying a preset first scoring table according to the various representation problems of the drone to determine the score corresponding to each representation problem; accumulating the scores corresponding to each representation problem to obtain the appearance score of the drone. The present invention also discloses a drone health status evaluation device, equipment and computer storage medium, which realizes automated evaluation of the drone health status and avoids the problem of inaccurate evaluation results caused by subjective evaluation by technicians.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a method, device, equipment and computer storage medium for evaluating the health status of unmanned aerial vehicles. Background Art

[0002] With the continuous development of drone patrol and maintenance technology, the demand for drones in various industries is increasing. Drones are particularly widely used in power grid inspections. While the use of drones to assist operations has improved work efficiency, drone management is facing new challenges due to the increasing demand for drones in power grids.

[0003] In the current drone management, the health status evaluation of drones mainly relies on the observation of technicians. The evaluation results produced by this evaluation method are easily affected by the subjective influence of technicians, resulting in inaccurate evaluation results. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, equipment and computer storage medium for evaluating the health status of a UAV, aiming to solve the technical problem that the health status evaluation of a UAV is not accurate enough due to the subjective influence of the evaluator.

[0005] To achieve the above object, the present invention provides a method for evaluating the health status of a drone, the method comprising the following steps:

[0006] The image of the surface of the UAV is acquired by a preset image acquisition device to obtain a representative image;

[0007] Preprocessing the representation image and comparing it with a standard image in a preset appearance recognition library to determine various representation problems of the drone;

[0008] According to the representation problems of the drone, a preset first scoring table is searched to determine the score corresponding to each representation problem;

[0009] The scores corresponding to the characterization questions are accumulated to obtain the appearance score of the drone.

[0010] In one embodiment, the step of acquiring a representative image by acquiring an image of the surface of the drone through a preset image acquisition device includes:

[0011] Capture images of the drone surface through a preset image acquisition device;

[0012] After adjusting the acquisition angle and / or acquisition center of the preset image acquisition device, the image of the surface of the drone is acquired again until the image acquisition of the entire surface of the drone is completed;

[0013] All images acquired by the preset image acquisition device are recorded as representative images.

[0014] In one embodiment, before the step of acquiring the representation image by using the preset image acquisition device to acquire the image of the surface of the drone, the following steps are included:

[0015] A standard image is obtained by collecting images of a new drone surface through a preset image collection device;

[0016] The standard image is preprocessed, and a preset appearance recognition library is established according to the preprocessed standard image.

[0017] In one embodiment, after the step of accumulating the scores corresponding to the characterization questions to obtain the appearance score of the drone, the following steps are included:

[0018] Query the preset database to obtain the commissioning time, maintenance times, operation times, bad weather operation times and maintenance rate of the same batch of drones within one year of the drone;

[0019] A preset second scoring table is queried according to the appearance score, commissioning time, number of maintenance times, number of operations, number of operations in severe weather, and the maintenance rate of the same batch of drones within one year to obtain a weighted comprehensive score of the drone.

[0020] In one embodiment, the step of querying a preset second scoring table according to the appearance score, commissioning time, number of maintenance times, number of operations, number of operations in severe weather, and the maintenance rate of the same batch of drones within one year to obtain a weighted comprehensive score of the drone includes:

[0021] The appearance score, commissioning time, number of overhauls and number of operations are recorded as sub-parameters of the state characteristic parameter, the number of operations in severe weather and the overhaul rate of the same batch of drones within one year are recorded as sub-parameters of the state influencing parameter, and the score values ​​of each sub-parameter of the state characteristic parameter and the state influencing parameter are obtained by querying the preset second scoring table;

[0022] Querying a preset weight table to obtain weight values ​​of the state characteristic parameter and the state influencing parameter;

[0023] The weighted comprehensive score of the UAV is calculated according to the score values ​​of each sub-parameter and the weight values ​​of the state characteristic parameter and the state influencing parameter.

[0024] In one embodiment, the step of calculating the weighted comprehensive score of the drone according to the score values ​​of each sub-parameter and the weight values ​​of the state characteristic parameter and the state influencing parameter includes:

[0025] The weighted comprehensive score of the drone is calculated using a first preset formula, where the first preset formula is: Wherein, B is the weighted comprehensive score, n is the total number of sub-parameters, i is the i-th sub-parameter, and A is i is the score value of the i-th sub-parameter, and the B i The weight value of the state characteristic parameter or the state influencing parameter corresponding to the i-th sub-parameter.

[0026] In one embodiment, after the step of calculating the weighted comprehensive score of the drone according to the effectiveness coefficient, the following steps are performed:

[0027] Querying a preset maintenance strategy table according to the weighted comprehensive score to obtain a maintenance strategy for the drone;

[0028] The maintenance strategy is output to guide the UAV maintenance personnel to maintain the UAV.

[0029] In addition, to achieve the above-mentioned purpose, the present invention also provides a drone health status evaluation device, characterized in that the drone health status evaluation device comprises:

[0030] An acquisition module is used to acquire an image of the surface of the drone by using a preset image acquisition device to obtain a representative image;

[0031] A recognition module, used to pre-process the representation image and compare it with a standard image in a preset appearance recognition library to determine various representation problems of the drone;

[0032] A scoring module, configured to query a preset first scoring table according to each of the characterization problems of the drone, and determine a score corresponding to each of the characterization problems;

[0033] The calculation module is used to accumulate the scores corresponding to the characterization questions to obtain the appearance score of the drone.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also provides a drone health status evaluation device, characterized in that the drone health status evaluation device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein:

[0035] When the computer program is executed by the processor, the steps of the above-mentioned method for evaluating the health status of a UAV are implemented.

[0036] In addition, to achieve the above-mentioned purpose, the present invention also provides a drone health status evaluation device;

[0037] The drone health status evaluation device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein:

[0038] When the computer program is executed by the processor, the steps of the drone health status assessment method as described above are implemented.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer storage medium;

[0040] The computer storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the above-mentioned method for evaluating the health status of a drone are implemented.

[0041] The embodiments of the present invention provide a method, device, equipment and computer storage medium for evaluating the health status of a drone. A preset image acquisition device is used to acquire an image of the drone surface to obtain a characterization image, so that an abnormality in the characterization image can be subsequently determined by image recognition technology. The characterization image is preprocessed and compared with a standard image in a preset appearance recognition library to determine various characterization problems of the drone. An automated method is used to replace manual observation that may have subjective biases in the existing method. A preset first scoring table is queried according to the various characterization problems of the drone to determine the score corresponding to each characterization problem. The characterization problems determined by image recognition are quantified into specific scores. The scores corresponding to the various characterization problems are accumulated to obtain the appearance score of the drone, thereby realizing automated evaluation of the health status of the drone and avoiding the problem of inaccurate evaluation results caused by subjective evaluation by technicians. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention;

[0043] Figure 2 This is a flow chart of a first embodiment of a method for evaluating the health status of a drone according to the present invention;

[0044] Figure 3 Schematic diagram of the flow chart of the second embodiment of the method for evaluating the health status of a UAV according to the present invention.

[0045] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0047] In the current drone management, the health status evaluation of drones mainly relies on the observation of technicians. The evaluation results produced by this evaluation method are easily affected by the subjective influence of technicians, resulting in inaccurate evaluation results.

[0048] The present invention provides a solution, which uses a preset image acquisition device to acquire an image of the surface of a drone to obtain a characterization image, so that an abnormality in the characterization image can be determined later by image recognition technology, and the characterization image is pre-processed and compared with a standard image in a preset appearance recognition library to determine various characterization problems of the drone, and an automated method is used to replace manual observation that may have subjective bias in the existing method. A preset first scoring table is queried according to the various characterization problems of the drone to determine the score corresponding to each characterization problem, and the characterization problems determined by image recognition are quantified into specific scores, and the scores corresponding to the various characterization problems are accumulated to obtain the appearance score of the drone, thereby realizing automated evaluation of the health status of the drone and avoiding the problem of inaccurate evaluation results caused by subjective evaluation by technicians.

[0049] like Figure 1 As shown, Figure 1 It is a structural diagram of a terminal (also called a UAV health status evaluation device, wherein the UAV health status evaluation device may be composed of a separate UAV health status evaluation device or may be formed by a combination of other devices and the UAV health status evaluation device) of the hardware operating environment involved in the embodiment of the present invention.

[0050] The terminal of the embodiment of the present invention can be a fixed terminal or a mobile terminal, such as a smart air conditioner with networking function, a smart light, a smart power supply, a smart speaker, an automatic driving car, a PC (personal computer), a smart phone, a tablet computer, an e-book reader, a portable computer, etc.

[0051] like Figure 1 As shown, the terminal may include: a processor 1001, for example, a central processing unit (CPU), a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity WIreless-FIdelity, WIFI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), for example, a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0052] Optionally, the terminal may also include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module; an input unit, such as a display screen, a touch screen; the network interface may be Bluetooth, a probe, etc. in addition to WiFi in the wireless interface. Among them, sensors such as light sensors, motion sensors and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor; of course, the mobile terminal may also be equipped with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., which will not be repeated here.

[0053] Those skilled in the art will understand that Figure 1 The terminal structure shown in the figure does not constitute a limitation on the terminal, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0054] like Figure 1 As shown, the computer software product is stored in a storage medium (storage medium: also called computer storage medium, computer medium, readable medium, readable storage medium, computer-readable storage medium or directly called medium, etc., the storage medium can be a non-volatile readable storage medium, such as RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present invention. The memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module and a computer program.

[0055] exist Figure 1 In the terminal shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1001 can be used to call the computer program stored in the memory 1005 and execute the steps in the drone health status evaluation method provided in the following embodiments of the present invention.

[0056] Reference Figure 2 In a first embodiment of a method for evaluating the health status of a drone of the present invention, the method for evaluating the health status of a drone comprises:

[0057] Step S10, capturing images of the surface of the drone using a preset image capture device to obtain a representative image.

[0058] The drone health status evaluation device acquires a representation image by acquiring images of the drone surface through a preset image acquisition device. The drone health status evaluation device may be a smart phone, PAD, PC or other smart terminal. In order to automatically determine scratches, rust and other problems on the drone surface, it is necessary to acquire images of the drone through an image acquisition device. In order to enable the image acquired by the preset image acquisition device to cover the entire surface of the drone, the drone is usually placed on a platform such as a workbench in a preset manner. The number of preset image acquisition devices may be one or more. When there is one preset image acquisition device, the preset image acquisition device acquires the representation image of the drone in a comprehensive manner by moving on a preset track. When there are multiple threshold image acquisition devices, the representation image of the drone is directly acquired in multiple directions.

[0059] Furthermore, the step S10 may include:

[0060] Step a1: collect images of the surface of the drone using a preset image collection device.

[0061] Step a2, adjusting the acquisition angle and / or acquisition center of the preset image acquisition device and then acquiring images of the surface of the drone until the entire surface of the drone is imaged.

[0062] Step a3: record all images acquired by the preset image acquisition device as representative images.

[0063] When there is one preset image acquisition device, the UAV health status evaluation equipment acquires images of the surface of the UAV through the preset image acquisition device. After acquiring the image of the UAV once, the acquisition angle and / or acquisition center of the preset image acquisition device are changed. The acquisition angle and / or acquisition center refers to that the preset image acquisition device is installed on a preset track or on a multi-joint gimbal. After acquiring an image of the UAV once, the device is moved on the track or the multi-joint gimbal is changed to change the acquisition angle and / or acquisition center so as to acquire images of the UAV in all directions. It can be understood that in order to fully acquire the image of the UAV, the preset image acquisition device must acquire multiple images, and all the multiple images are recorded as representation images of the UAV so that the representation images can be sent or processed in batches later.

[0064] Furthermore, the step before step S10 may include:

[0065] Step b1, acquiring a standard image by capturing an image of a new drone surface through a preset image capture device.

[0066] Step b2, preprocessing the standard image, and establishing a preset appearance recognition library based on the preprocessed standard image.

[0067] The drone health status evaluation device acquires a standard image by using a preset image acquisition device to acquire an image of a brand new drone surface, preprocesses the standard image, and establishes a preset appearance recognition library based on the preprocessed standard image. In order to determine the problems existing in the representation image of the drone to be evaluated acquired by the drone health status evaluation device, it is necessary to obtain an image for comparison with the representation image. The image used for comparison is the standard image. The standard image is acquired by the drone health status evaluation device by using a preset image acquisition device to acquire an image of a brand new drone. In order to enhance the features of the standard image, the standard image is preprocessed, and the preprocessing includes grayscale processing, image enhancement, etc. A preset appearance recognition library is established based on the preprocessed standard image.

[0068] Step S20, pre-processing the representation image and comparing it with the standard image in the preset appearance recognition library to determine the representation problems of the drone.

[0069] The drone health status evaluation device preprocesses the characterization image and then compares it with the standard image in the preset appearance recognition library to determine the various characterization problems of the drone. The drone health status evaluation device first preprocesses the characterization image. The preprocessing includes grayscale processing, image enhancement, etc., the purpose of which is to enhance the detail information in the characterization image, and then compares the processed characterization image with the appearance recognition library. The appearance recognition library is a pre-established library containing characterization images of drones without any damage, which is used to compare with the characterization images collected by the drone health status evaluation device to determine the abnormality of the drone's appearance. The abnormality is the characterization problem, and the characterization problem includes whether there are scratches, whether the paint is evenly sprayed, whether the metal parts are cracked, whether the metal parts are rusted, whether the component plug-ins are clearly marked, and whether the battery casing is deformed.

[0070] Step S30, querying a preset first scoring table according to each of the characterization questions of the drone to determine a score corresponding to each of the characterization questions.

[0071] The drone health status evaluation device queries a preset first scoring table according to the characterization problems of the drone to determine the score corresponding to each characterization problem. The preset first scoring table is shown in Table 1. If it is determined in step S20 that the drone surface has scratches and the battery shell is deformed, the two characterization problems are scored -20 and -20 respectively. Multiple scratches are not counted repeatedly, and other characterization problems are also not counted repeatedly, that is, multiple scratches are also recorded as -20 points.

[0072]

[0073] Table 1

[0074] Step S40, accumulating the scores corresponding to the characterization questions to obtain the appearance score of the drone.

[0075] The drone health status evaluation device accumulates the scores corresponding to the various characterization problems to obtain the appearance score of the drone. For example, if the characterization problems of the drone include scratches and deformation of the battery casing, the scores are -20 and -20 respectively. The appearance score of the drone obtained by accumulating the characterization problems is -40 points.

[0076] In this embodiment, a preset image acquisition device is used to acquire an image of the surface of the drone to obtain a characterization image, so that an abnormality in the characterization image can be determined later by image recognition technology. The characterization image is preprocessed and compared with a standard image in a preset appearance recognition library to determine various characterization problems of the drone. An automated method is used to replace manual observation that may have subjective biases in the existing method. A preset first scoring table is queried according to the various characterization problems of the drone to determine the score corresponding to each characterization problem. The characterization problems determined by image recognition are quantified into specific scores. The scores corresponding to the various characterization problems are accumulated to obtain the appearance score of the drone, thereby realizing automated evaluation of the health status of the drone and avoiding the problem of inaccurate evaluation results caused by subjective evaluation by technicians.

[0077] Further, see Figure 3 Based on the first embodiment of the present invention, a second embodiment of the method for evaluating the health status of a drone of the present invention is further proposed. This embodiment is a post-step of step S40 in the first embodiment. The method for evaluating the health status of a drone includes:

[0078] Step S50, querying a preset database to obtain the commissioning time, maintenance times, operation times, bad weather operation times, and maintenance rate of the same batch of drones within one year of the drone.

[0079] Step S60, querying a preset second scoring table according to the appearance score, commissioning time, number of maintenance times, number of operations, number of operations in severe weather, and the maintenance rate of the same batch of drones within one year to obtain a weighted comprehensive score of the drone.

[0080] The drone health status evaluation device queries a preset database to obtain the commissioning time, maintenance times, operation times, bad weather operation times and the maintenance rate of drones of the same batch within one year of the drone, and queries a preset second scoring table according to the appearance score, commissioning time, maintenance times, operation times, bad weather operation times and the maintenance rate of drones of the same batch within one year to obtain the score values ​​corresponding to the parameters, and accumulates the score values ​​corresponding to the parameters to obtain the weighted comprehensive score of the drone. In order to achieve a more comprehensive and comprehensive evaluation of the health status of the drone, in addition to the appearance score in the first embodiment, more parameters are introduced. The preset database is a database established in advance by technicians according to the working conditions of the drone, recording the commissioning time, The number of overhauls, the number of operations, the number of operations in severe weather and the overhaul rate of the same batch of drones within one year can be understood as other parameters can be added to achieve a more comprehensive evaluation of the health status of the drone. The parameters can be reduced by several to more streamlinedly evaluate the appearance of the drone. The preset second scoring table is shown in Table 2. If the score of the drone is -40, the commissioning time is 0.4 years, the number of overhauls is 7 times, the number of operations is 70 times, the number of operations in severe weather is 8 times, and the overhaul rate of the same batch of drones within one year is 30%, then the scores of each parameter are determined by the preset second scoring table as 0 points, 1 point, 0 points, 0 points, 1 point and 1 point respectively, and the weighted comprehensive score of the drone obtained by accumulating the score values ​​corresponding to the parameters is 3 points.

[0081]

[0082] Table 2

[0083] Specifically, the step S60 may include:

[0084] Step c1, record the appearance score, commissioning time, number of maintenances and number of operations as sub-parameters of the state characteristic parameter, record the number of operations in severe weather and the maintenance rate of the same batch of drones within one year as sub-parameters of the state influencing parameter, and query the preset second scoring table to obtain the score values ​​of each sub-parameter of the state characteristic parameter and the state influencing parameter.

[0085] Step c2, querying a preset weight table to obtain weight values ​​of the state characteristic parameters and the state influencing parameters.

[0086] Step c3, calculating the weighted comprehensive score of the UAV according to the score values ​​of each sub-parameter and the weight values ​​of the state characteristic parameter and the state influencing parameter.

[0087] The drone health status evaluation device queries a preset database to obtain the commissioning time, maintenance times, operation times, severe weather operation times and the maintenance rate of the same batch of drones within one year of the drone, and records the appearance score, commissioning time, maintenance times and operation times as sub-parameters of the state characteristic parameter, and records the severe weather operation times and the maintenance rate of the same batch of drones within one year as sub-parameters of the state influencing parameter, queries a preset second scoring table to obtain the score values ​​of each sub-parameter of the state characteristic parameter and the state influencing parameter, queries a preset weight table to obtain the weight values ​​of the state characteristic parameter and the state influencing parameter, and calculates the weighted comprehensive health status of the drone according to the score values ​​of each sub-parameter and the weight values ​​of the state characteristic parameter and the state influencing parameter. In order to achieve a more comprehensive and integrated evaluation of the health status of the drone, in addition to the appearance score in the first embodiment, more standards are introduced. The standards in this embodiment are all called sub-parameters, which are subordinate to state characteristic parameters or state influencing parameters, and the preset weight table is the weight value of the state characteristic parameters and state influencing parameters preset by the user in the subsequent calculation of the weighted comprehensive score, as shown in Table 3. It can be understood that the weight value can be changed according to the actual application, and the weight value of the state characteristic parameter and the weight value of the state influencing parameter are equivalent to the weight value of their corresponding parameters. The weighted comprehensive score of the drone can be calculated according to the score value of each sub-parameter and the weight value of the state characteristic parameter and the state influencing parameter.

[0088] Parameter Type State characteristic parameters Status influence parameters Weight value 0.8 0.2

[0089] Table 3

[0090] Specifically, the step c3 may include:

[0091] Step c31, using a first preset formula to calculate the weighted comprehensive score of the drone, the first preset formula is Wherein, B is the weighted comprehensive score, n is the total number of sub-parameters, i is the i-th sub-parameter, and A is i is the score value of the i-th sub-parameter, and the B i The weight value of the state characteristic parameter or the state influencing parameter corresponding to the i-th sub-parameter.

[0092] The drone health status evaluation device uses a first preset formula to calculate the weighted comprehensive score of the drone. The first preset formula is: Wherein, B is the weighted comprehensive score, n is the total number of sub-parameters, i is the i-th sub-parameter, and A is i is the score value of the i-th sub-parameter, and the B iThe weight value of the state characteristic parameter or the state influencing parameter corresponding to the i-th sub-parameter, such as a UAV's appearance score is 1 point, the commissioning time score is 1 point, the UAV maintenance number score is 1 point, the UAV operation number score is -1 point, the bad weather operation number score is 1 point, and the maintenance rate score of the same batch of UAVs within one year is -1 point, then the weighted comprehensive score of the UAV is B=A1B1+A2B2+A3B3+A4B4+A5B5+A6B6=1*0.8+1*0.8+1*0.8-1*0.8+1*0.2-1*0.2=1.6 points.

[0093] In this embodiment, by introducing data from the historical work of multiple drones as parameters, the health status of the drone is comprehensively scored from the appearance and historical working conditions, and the weights of each parameter are introduced to calculate the weighted comprehensive score of the drone, thereby achieving a more comprehensive evaluation of the health status of the drone. At the same time, it also avoids the problem of too low equipment evaluation scores and inaccurate evaluations due to excessive cumulative deductions for a certain type of deduction parameters.

[0094] Further, based on the above embodiments of the present invention, a fourth embodiment of the drone health status evaluation method of the present invention is further proposed. This embodiment is a post-step of step c5 in the third embodiment. The drone health status evaluation method includes:

[0095] Step c6, querying a preset maintenance strategy table according to the weighted comprehensive score to obtain a maintenance strategy for the drone.

[0096] Step c7: output the maintenance strategy to guide the UAV maintenance personnel to maintain the UAV.

[0097] The drone health status evaluation device queries the preset maintenance strategy table according to the weighted comprehensive score, obtains the maintenance strategy of the drone, and outputs the maintenance strategy to guide drone maintenance personnel to maintain the drone. The preset maintenance strategy table is a mapping table of weighted comprehensive scores and maintenance strategies pre-formulated by technicians, as shown in Table 4. If the weighted comprehensive score of a drone is 2 points, its maintenance strategy this time is to maintain the maintenance strategy and maintain the regular inspection cycle.

[0098]

[0099]

[0100] Table 4

[0101] In this embodiment, by associating the corresponding maintenance strategy with the weighted comprehensive score of the drone's health status, the health status assessment of the drone is converted into maintenance measures that actually improve the drone's working status, thereby achieving the role of score-guided maintenance.

[0102] In addition, an embodiment of the present invention further provides a drone health status evaluation device, the drone health status evaluation device comprising:

[0103] An acquisition module is used to acquire an image of the surface of the drone by using a preset image acquisition device to obtain a representative image;

[0104] A recognition module, used to pre-process the representation image and compare it with a standard image in a preset appearance recognition library to determine various representation problems of the drone;

[0105] A scoring module, configured to query a preset first scoring table according to each of the characterization problems of the drone, and determine a score corresponding to each of the characterization problems;

[0106] A calculation module, used for accumulating the scores corresponding to the characterization questions to obtain the appearance score of the drone;

[0107] Among them, the steps implemented by each functional module of the drone health status evaluation device can refer to the various embodiments of the drone health status evaluation method of the present invention, and will not be repeated here.

[0108] In addition, an embodiment of the present invention further provides a drone health assessment device, the drone health assessment device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein:

[0109] When the computer program is executed by the processor, the operations in the drone health status evaluation method provided in the above embodiment are implemented.

[0110] In addition, an embodiment of the present invention further provides a computer storage medium.

[0111] The computer storage medium stores a computer program, and when the computer program is executed by the processor, the operations in the method for evaluating the health status of a drone provided in the above embodiment are implemented.

[0112] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such actual relationship or order between these entities / operations / objects; the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0113] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment. The device embodiment described above is only illustrative, and the units described as separate components may or may not be physically separated. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the present invention. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0114] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0115] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0116] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for evaluating the health status of drones. It is characterized in that The method for evaluating the health status of a drone comprises the following steps: The image of the surface of the UAV is acquired by a preset image acquisition device to obtain a representative image; Preprocessing the representation image and comparing it with a standard image in a preset appearance recognition library to determine various representation problems of the drone; According to the representation problems of the drone, a preset first scoring table is searched to determine the score corresponding to each representation problem; Accumulating the scores corresponding to the characterization questions to obtain the appearance score of the drone; Wherein, after the step of accumulating the scores corresponding to the characterization questions to obtain the appearance score of the drone, the following steps are included: Query the preset database to obtain the commissioning time, maintenance times, operation times, bad weather operation times and maintenance rate of the same batch of drones within one year of the drone; A preset second scoring table is queried according to the appearance score, commissioning time, number of maintenance times, number of operations, number of operations in severe weather, and the maintenance rate of the same batch of drones within one year to obtain a weighted comprehensive score of the drone; The step of querying a preset second scoring table according to the appearance score, commissioning time, number of maintenance times, number of operations, number of operations in severe weather, and the maintenance rate of the same batch of drones within one year to obtain a weighted comprehensive score of the drone includes: The appearance score, commissioning time, number of overhauls and number of operations are recorded as sub-parameters of the state characteristic parameter, the number of operations in severe weather and the overhaul rate of the same batch of drones within one year are recorded as sub-parameters of the state influencing parameter, and the score values ​​of each sub-parameter of the state characteristic parameter and the state influencing parameter are obtained by querying the preset second scoring table; Querying a preset weight table to obtain weight values ​​of the state characteristic parameter and the state influencing parameter; Calculating a weighted comprehensive score of the drone according to the score values ​​of each sub-parameter and the weight values ​​of the state characteristic parameter and the state influencing parameter; The step of calculating the weighted comprehensive score of the drone according to the score values ​​of each sub-parameter and the weight values ​​of the state characteristic parameter and the state influencing parameter comprises: The weighted comprehensive score of the drone is calculated using a first preset formula, where the first preset formula is: Wherein, B is the weighted comprehensive score, n is the total number of sub-parameters, i is the i-th sub-parameter, and A is i is the score value of the i-th sub-parameter, and the B i The weight value of the state characteristic parameter or the state influencing parameter corresponding to the i-th sub-parameter.

2. The method for evaluating the health status of a drone according to claim 1, It is characterized in that The step of acquiring a representative image by acquiring an image of the surface of the drone through a preset image acquisition device comprises: Capture images of the drone surface through a preset image acquisition device; After adjusting the acquisition angle and / or acquisition center of the preset image acquisition device, the image of the surface of the drone is acquired again until the image acquisition of the entire surface of the drone is completed; All images acquired by the preset image acquisition device are recorded as representative images.

3. The method for evaluating the health status of a drone according to claim 1, It is characterized in that Before the step of acquiring an image of the surface of the drone by using a preset image acquisition device to obtain a representative image, the method includes: A standard image is obtained by collecting images of a new drone surface through a preset image collection device; The standard image is preprocessed, and a preset appearance recognition library is established according to the preprocessed standard image.

4. The method for evaluating the health status of a drone according to claim 1, It is characterized in that After the step of calculating the weighted comprehensive score of the drone according to the effectiveness coefficient, the method further comprises: Querying a preset maintenance strategy table according to the weighted comprehensive score to obtain a maintenance strategy for the drone; The maintenance strategy is output to guide the UAV maintenance personnel to maintain the UAV.

5. A drone health status assessment device, It is characterized in that The drone health status evaluation device comprises: An acquisition module is used to acquire an image of the surface of the drone by using a preset image acquisition device to obtain a representative image; A recognition module, used to pre-process the representation image and compare it with a standard image in a preset appearance recognition library to determine various representation problems of the drone; A scoring module, configured to query a preset first scoring table according to each of the characterization problems of the drone, and determine a score corresponding to each of the characterization problems; A calculation module, used for accumulating the scores corresponding to the characterization questions to obtain the appearance score of the drone; The calculation module is also used to query a preset database to obtain the commissioning time, maintenance times, operation times, bad weather operation times and maintenance rate of the same batch of drones within one year of the drone; A preset second scoring table is queried according to the appearance score, commissioning time, number of maintenance times, number of operations, number of operations in severe weather, and the maintenance rate of the same batch of drones within one year to obtain a weighted comprehensive score of the drone; The appearance score, commissioning time, number of overhauls and number of operations are recorded as sub-parameters of the state characteristic parameter, the number of operations in severe weather and the overhaul rate of the same batch of drones within one year are recorded as sub-parameters of the state influencing parameter, and the score values ​​of each sub-parameter of the state characteristic parameter and the state influencing parameter are obtained by querying the preset second scoring table; Querying a preset weight table to obtain weight values ​​of the state characteristic parameter and the state influencing parameter; Calculating a weighted comprehensive score of the drone according to the score values ​​of each sub-parameter and the weight values ​​of the state characteristic parameter and the state influencing parameter; The weighted comprehensive score of the drone is calculated using a first preset formula, where the first preset formula is: Wherein, B is the weighted comprehensive score, n is the total number of sub-parameters, i is the i-th sub-parameter, and A is i is the score value of the i-th sub-parameter, and the B i The weight value of the state characteristic parameter or the state influencing parameter corresponding to the i-th sub-parameter.

6. A drone health status assessment device, It is characterized in that The drone health status evaluation device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by the processor, the steps of the method for evaluating the health status of a drone according to any one of claims 1 to 4 are implemented.

7. A computer storage medium, It is characterized in that The computer storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the method for evaluating the health status of a drone according to any one of claims 1 to 4 are implemented.

Citation Information

Patent Citations

  • Machine vision-based real-time detection and grading method and machine vision-based real-time detection and grading device for pork appearance quality

    CN101561402A

  • Unmanned aerial vehicle system health status evaluation device

    CN104765968A

  • Operation state prediction method and system based on BP (Back Propagation) neural network algorithm

    CN105225020A

  • Display method of hotel images, storage medium, and push method of hotel information

    CN107194898A

  • Information display method and device based on reality enhancement equipment and storage medium

    CN110264320A