Inspection path planning method and device, electronic equipment and storage medium

Abstract

The invention discloses a routing inspection path planning method and device, electronic equipment and a storage medium, and relates to the field of automatic control. The method comprises the following steps: dividing a to-be-inspected area into a plurality of sub-areas, obtaining map data, equipment information, dangerous object information and temperature information in each sub-area, and carrying out danger level assessment on each sub-area according to the map data, the equipment information, the dangerous object information and the temperature information, the method comprises the following steps: acquiring a plurality of sub-regions, acquiring danger levels of the sub-regions, adding the danger levels into map data, pre-defining path fragments, generating a high-quality path by the path fragments, generating an initial path population based on the high-quality path by utilizing a genetic algorithm, and performing iterative operation on the initial path population to obtain an optimal path. The map data, the equipment information, the dangerous object information and the temperature information of the to-be-inspected area are acquired, the path fragment is predefined based on the acquired data and information, the high-quality path and the initial path population are generated, and the convergence speed of the algorithm and the quality of the generated optimal path are improved.

Description

Technical Field

[0001] The present application belongs to the field of automatic control, and specifically relates to a patrol route planning method, device, electronic device and storage medium. Background Art

[0002] Optimization algorithms are often used in the path planning process. Among them, genetic algorithms are based on the survival of the fittest and are a meta-heuristic algorithm that imitates natural gene selection. They are widely used in path planning.

[0003] Although the initial population generated by the existing genetic algorithm has high diversity, it also limits the convergence speed and cannot guarantee the quality of the final result when faced with complex situations. Summary of the invention

[0004] In order to solve at least one of the above-mentioned defects, the present invention application proposes a patrol path planning method, device, electronic device and storage medium, which are used to solve the convergence speed defect of the genetic algorithm and ensure the quality of the planned patrol path.

[0005] According to a first aspect of the present application, a method for inspection path planning is provided, comprising:

[0006] Divide the area to be inspected into multiple sub-areas, and obtain map data, equipment information, hazardous material information, and temperature information in each sub-area;

[0007] Evaluate the danger level of each sub-area according to the map data, the dangerous object information and the temperature information, and add the danger level of each sub-area to the map data;

[0008] According to the acquired map data, equipment information, dangerous object information, temperature information and danger level of each sub-area, a number of high-quality path segments are generated in each sub-area, and a number of high-quality paths are generated by combining the high-quality path segments in each sub-area;

[0009] Genetic algorithms are used to generate an initial path population based on the plurality of high-quality paths, and the initial path population is iterated to obtain an optimal path for the area to be inspected.

[0010] Preferably, the step of evaluating the danger level of each sub-area according to the map data, the dangerous object information and the temperature information, and adding the danger level of each sub-area to the map data specifically includes:

[0011] Performing a dangerous area level assessment on each of the sub-areas according to the dangerous object information to obtain a dangerous area level for each sub-area;

[0012] Performing a temperature region level evaluation on each of the sub-regions according to the temperature information to obtain a temperature region level of each sub-region;

[0013] Determine the hazard coefficient of each sub-area according to the hazard area level and temperature area level of each sub-area;

[0014] The danger zone level, temperature zone level and danger factor of each sub-area are added to the map data.

[0015] The factors considered in the hazardous area level assessment include the type, quantity, and storage method of the hazardous materials; the factors considered in the temperature area level assessment include the temperature range, duration, etc.

[0016] Preferably, according to the acquired map data, equipment information, dangerous object information, temperature information and danger level of each sub-area, a number of high-quality path segments are generated in each sub-area, specifically including:

[0017] The equipment information includes equipment type, equipment quantity and operating status; the dangerous object information includes dangerous object type, quantity and storage status; the temperature information includes equipment temperature, dangerous object temperature and duration corresponding to each temperature;

[0018] According to the map data, equipment information, dangerous object information, temperature information and danger level in each sub-area, a number of high-quality path segments are generated in each sub-area, and a number of high-quality paths are generated based on the number of path segments in each sub-area.

[0019] Preferably, the method of using a genetic algorithm to generate an initial path population according to the plurality of high-quality paths, and iterating the initial path population to obtain an optimal path for the area to be inspected specifically includes:

[0020] Generate a number of random paths, wherein the number of random paths and the number of high-quality paths together constitute an initial path population;

[0021] Obtaining a fitness function based on the map data, equipment information, dangerous object information, temperature information and danger level;

[0022] The initial path population is iterated, specifically:

[0023] Select paths from the initial path population to perform crossover and mutation operations to generate new paths and path populations;

[0024] Based on the fitness function, a global search is performed on the entire new path population to obtain the path with the highest fitness value;

[0025] Perform local search based on the path with the highest fitness value to obtain candidate paths and their fitness values;

[0026] Determine whether the candidate path and its fitness value meet the termination conditions,

[0027] If satisfied, terminate the iteration operation, take the candidate path as the optimal path of the area to be inspected, and output the optimal path and its fitness value;

[0028] If not satisfied, an elite retention operation is performed on the initial path population, several paths in the initial path population are selected to enter a new path population, and a diversity monitoring and maintenance operation is performed on the new path population to generate new paths. The new path population is updated based on the new paths, and the updated new path population is used as the initial path population for the next iterative operation to execute the iterative operation.

[0029] Optionally, the random paths are generated in a completely random manner to form an initial path population together with the high-quality paths, thereby improving the diversity of the path population and ensuring the extensiveness of the search space.

[0030] Optionally, after performing several global searches, a local search is performed based on the fitness function, searching within the domain of the path with the highest current fitness value.

[0031] If the fitness value of the path of the local search result is not greater than that of the path of the global search result, the path of the global search result is used as a candidate path;

[0032] If the fitness value of the path of the local search result is greater than the path of the global search result, the path of the local search result is used as a candidate path.

[0033] Optionally, a termination condition is preset, and at least one of the termination conditions may be set. When at least one termination condition is met, the iterative operation is terminated, the candidate path is taken as the optimal path, and the optimal path and its fitness value are output.

[0034] Preferably, the fitness function includes a path length evaluation function, a safety evaluation function and a reachability evaluation function. The fitness function is used to perform fitness evaluation on each path. The fitness function is expressed as:

[0035] F(x)=w_1cdot L(x)+w_2cdot S(x)+w_3cdot A(x)

[0036] Where x represents the path, F(x) represents the fitness value of the path, the fitness value determines the quality of the path, cdotL(x) represents the path length evaluation function, cdot S(x) represents the safety evaluation function, cdot A(x) represents the accessibility evaluation function, w_1, w_2 and w_3 represent the weights of the path length evaluation function, safety evaluation function and accessibility evaluation function respectively;

[0037] The path length evaluation function is evaluated by the length of the path, wherein the length of the path is calculated based on the map data;

[0038] The safety assessment function is evaluated by the safety distance between the path and each sub-area, wherein the safety distance is calculated based on the danger level of each sub-area in the map data; the higher the danger level of the sub-area, the smaller its safety distance, and the lower the safety of the path close to the sub-area.

[0039] The accessibility evaluation function is evaluated by the smoothness and the number of turns of the path, wherein the smoothness and the number of turns of the path are calculated based on the map data.

[0040] Optionally, when the status of the inspection area changes, such as equipment operating abnormally, hazardous material leaking, or equipment or hazardous material temperature changing, the fitness values ​​of the paths in the path population are adjusted by adjusting the weights of the path length evaluation function, the safety evaluation function, and the accessibility evaluation function to ensure that the generated inspection path adapts to changes in the inspection area.

[0041] Preferably, a crossover rate and a mutation rate are set, wherein the crossover rate determines the frequency of the crossover operation, and the mutation rate determines the frequency of the mutation operation;

[0042] The crossover operation combines the path segments of the paths in the initial path population to generate a new path;

[0043] The mutation operation changes the path segments of the paths in the initial path population to generate new paths;

[0044] A new path population is obtained according to the new path.

[0045] Optionally, the crossover operation may be a single-point crossover, a two-point crossover or a multi-point crossover, and the mutation operation may be a positioning mutation, a reversal mutation or an insertion mutation.

[0046] Optionally, when the iteration of the path population is stagnant and / or the diversity is lower than the diversity threshold, the crossover rate and mutation rate may be increased to enable the path population to continue to iterate.

[0047] Preferably, an elite retention operation is performed on the initial path population, and several paths in the initial path population are selected to enter a new path population. The elite retention operation is based on a selection function, and the selection function is expressed as:

[0048]

[0049] Among them, x represents the path, P(x) represents the probability of path x being selected, and F(x) represents the fitness value of path x. represents the sum of the fitness values ​​of all paths in the population, and N represents the number of paths in the population.

[0050] Preferably, performing diversity monitoring and maintenance operations on the new path population to generate new paths, updating the new path population based on the new paths, and using the updated new path population as the initial path population for the next iterative operation specifically includes:

[0051] A diversity threshold is preset, and the new path population is analyzed to obtain diversity. When the diversity is lower than the diversity threshold, the crossover rate, the mutation rate and / or a new random path is generated, and the random path is updated to the new path population. The updated new path population is used as the initial path population for the next iterative operation.

[0052] According to a second aspect of the present application, a patrol path planning device is provided, comprising:

[0053] An acquisition module is used to divide the area to be inspected into multiple sub-areas and obtain map data, equipment information, hazardous material information and temperature information in each sub-area;

[0054] Evaluate the danger level of each sub-area according to the map data, the dangerous object information and the temperature information, and add the danger level of each sub-area to the map data;

[0055] A path pre-definition module is used to generate a number of high-quality path segments in each sub-area based on the acquired map data, equipment information, hazardous material information, and temperature information of each sub-area, and to generate a number of high-quality paths by combining the high-quality path segments in each sub-area;

[0056] The genetic module is used to generate an initial path population according to the plurality of high-quality paths by using a genetic algorithm, and perform iterative operations on the initial path population to obtain an optimal path of the area to be inspected.

[0057] According to a third aspect of the present application, an electronic device is provided, including:

[0058] a memory for storing one or more computer programs;

[0059] The processor implements a patrol path planning method of the first aspect when the one or more computer programs are executed by the processor.

[0060] According to a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a patrol path planning method according to the first aspect when executed.

[0061] Based on any one of the above aspects, an inspection path planning method, device, electronic device and storage medium provided in an embodiment of the present application divides the inspection area into multiple sub-areas, obtains map data, equipment information, hazardous material information and temperature information of each sub-area, determines the danger level of each sub-area based on the map data, equipment information, hazardous material information and temperature information, predefines path segments, generates high-quality paths from the path segments, and uses a genetic algorithm to generate an initial path population based on the high-quality paths, thereby improving the convergence speed of the algorithm and the quality of the generated optimal path. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0063] Figure 1 A flow chart of an inspection path planning method provided in the present application.

[0064] Figure 2 A schematic diagram of the functional modules of a patrol route planning device provided in an embodiment of the present application.

[0065] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0066] Figure 4 A schematic application scenario diagram of a patrol route planning method provided in an embodiment of the present application.

[0067] Icons: 100, server; 200, terminal; 201, measurement module; 202, path predefinition module; 203, genetic module; 710, electronic device; 711, memory; 712, processor; 713, communication module; 714, input / output interface; 715, bus. DETAILED DESCRIPTION

[0068] The present invention provides a method for patrol route planning. To make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific examples described herein are only used to explain the present invention and are not used to limit the present invention.

[0069] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0070] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0071] The application content is further explained below through the description of embodiments in conjunction with the accompanying drawings.

[0072] The drawings of the present invention are only for illustrative purposes and should not be construed as limiting the present invention. In order to better illustrate the following embodiments, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product; it is understandable to those skilled in the art that some well-known structures and their descriptions in the drawings may be omitted.

[0073] On the one hand, an inspection path planning method provided in an embodiment of the present application is as follows: Figure 1 As shown, the method at least includes:

[0074] S101, dividing the inspection area into multiple sub-areas, and obtaining map data in each sub-area, wherein the map data at least includes equipment information, dangerous object information, temperature information, and road network;

[0075] S201, evaluating the danger level of each sub-area according to the map data, dangerous object information, and temperature information, and adding the danger level of each sub-area to the map data;

[0076] S301 generates a number of high-quality path segments in each sub-area according to the acquired map data, equipment information, dangerous object information, temperature information and danger level of each sub-area, and generates a number of high-quality paths by combining the high-quality path segments in each sub-area;

[0077] S401 , using a genetic algorithm to generate an initial path population according to the plurality of high-quality paths, and performing an iterative operation on the initial path population to obtain an optimal path for the area to be inspected.

[0078] The technical solution provided in this application is described in detail below in conjunction with specific embodiments.

[0079] In step S101, the area to be inspected is divided into multiple sub-areas, and map data, equipment information, hazardous material information, and temperature information in each sub-area are obtained;

[0080] In the embodiment of the present application, the map data includes a road network, a location of a device, a location of a dangerous object, a distance between a road and the device, a distance between a dangerous object and the device, and a distance between a dangerous object and the device. The road network includes the length, width, flatness and number of turns of the road. The map data may be obtained by a distance meter, a sensor, a GPS, etc.;

[0081] The device information may include the type, quantity and operation status of the devices in the inspection area, and the device information is provided by the devices;

[0082] The hazardous material information includes the type, quantity and storage status of hazardous materials in the inspection area; the temperature information includes the equipment temperature, hazardous material temperature and the duration corresponding to each temperature in the inspection area, etc., and preferably, it can also include the ambient temperature and the duration corresponding to the ambient temperature, etc. The temperature information can be obtained through a temperature measuring device.

[0083] In the specific implementation process, step S201 may include the following specific steps:

[0084] S2011, performing a dangerous area level assessment on each of the sub-areas according to the dangerous object information to obtain a dangerous area level for each sub-area; wherein the factors considered in the dangerous level assessment include the type, quantity, and storage method of the dangerous object;

[0085] S2012, performing a temperature zone level assessment on each of the sub-areas according to the temperature information to obtain a temperature zone level for each of the sub-areas; wherein the factors considered for the temperature zone level include temperature range, duration, etc., and specifically may include the temperature range of equipment temperature, hazardous material temperature, ambient temperature, and duration corresponding to each temperature range, etc.;

[0086] S2013, determining a hazard coefficient of each sub-region according to the hazard region level and the temperature region level of each sub-region;

[0087] S2014: Add the danger zone level, temperature zone level and danger coefficient of each sub-area to the map data.

[0088] In this embodiment, the algorithm performs path planning based on map data that clearly marks dangerous areas and high-temperature areas, which can improve the accuracy and efficiency of planning.

[0089] In the embodiment of the present application, the generation process of the high-quality path includes generating a number of high-quality path segments based on the map data, equipment information, dangerous object information, temperature information and danger level, generating a number of high-quality paths based on the number of high-quality path segments, and the high-quality paths realize the inspection of the inspection area. In the specific implementation process, each sub-area can correspond to one or more high-quality path segments, and one or more high-quality paths can be formed between one area or multiple sub-areas.

[0090] In the embodiment of the present application, a genetic algorithm is used to generate the optimal path, and the specific process steps are as follows:

[0091] Generate a number of random paths, wherein the number of random paths and the number of high-quality paths together constitute an initial path population;

[0092] Obtaining a fitness function based on the map data, equipment information, dangerous object information, temperature information and danger level;

[0093] Iterate the initial path population, including:

[0094] Select paths from the initial path population to perform crossover and mutation operations to generate new paths and path populations;

[0095] Based on the fitness function, a global search is performed on the entire new path population to obtain the path with the highest fitness value;

[0096] Perform local search based on the path with the highest fitness value to obtain candidate paths and their fitness values;

[0097] Determine whether the candidate path and its fitness value meet the termination conditions,

[0098] If satisfied, terminate the iteration operation, take the candidate path as the optimal path of the area to be inspected, and output the optimal path and its fitness value;

[0099] If not satisfied, an elite retention operation is performed on the initial path population, several paths in the initial path population are selected to enter a new path population, and a diversity monitoring and maintenance operation is performed on the new path population to generate new paths. The new path population is updated based on the new paths, and the updated new path population is used as the initial path population for the next iterative operation to execute the iterative operation.

[0100] The embodiment of the present application generates a number of random paths in a completely random manner. The number of random paths and the number of high-quality paths together constitute an initial path population, thereby improving the diversity of the population and ensuring the extensiveness of the space.

[0101] In an optional solution, the inspection requirements of the area to be inspected are integrated, and the embodiment of the present application considers the length, safety and accessibility of the path when designing the fitness function, and adds a dynamic weight evaluation function to the fitness function. The fitness function can be expressed as:

[0102] F(x)=w_1cdot L(x)+w_2cdot S(x)+w_3cdot A(x)

[0103] Where x represents the path, F(x) represents the fitness value of the path, and the fitness value determines the quality of the path. cdotL(x) represents the path length evaluation function, cdot S(x) represents the safety evaluation function, cdot A(x) represents the reachability evaluation function, and w_1, w_2, and w_3 represent the weights of the path length evaluation function, the safety evaluation function, and the reachability evaluation function, respectively.

[0104] The path length evaluation function is evaluated by the length of the path, wherein the length of the path is calculated based on the map data;

[0105] The safety assessment function is evaluated by the safety distance between the path and each sub-area, wherein the safety distance is calculated according to the danger level of each sub-area in the map data;

[0106] The accessibility evaluation function is evaluated by the smoothness and the number of turns of the path, wherein the smoothness and the number of turns of the path are calculated based on the map data.

[0107] It can be understood that when using the genetic algorithm including the fitness function for path planning, safety is given top priority. When the state of the area to be inspected changes, such as abnormal operation of the equipment, leakage of hazardous materials, or temperature changes of the equipment or hazardous materials, the weights of the path length evaluation function, the safety evaluation function, and the accessibility evaluation function are adjusted to reduce the generation of path segments in the sub-area where the state has changed, and to reduce the fitness value of the path passing through the sub-area where the state has changed, so that inspectors can avoid dangerous areas or take corresponding safety measures.

[0108] In the embodiment of the present application, a crossover rate and a mutation rate are set. The crossover rate determines the frequency of the crossover operation, and the mutation rate determines the frequency of the mutation operation. The crossover rate and the mutation rate can be adjusted according to the diversity of the path population.

[0109] Optionally, the crossover operation adopts two-point crossover to generate a new path by combining path segments in two paths as parents. Single-point crossover or multi-point crossover may also be used.

[0110] Optionally, the mutation operation generates a new path by randomly changing several path segments in the path, and positioning mutation, inversion mutation or insertion mutation may be selected.

[0111] When the iteration of the path population stagnates and / or the diversity is lower than the diversity threshold, the crossover rate and mutation rate can be increased to enable the path population to continue to iterate.

[0112] Optionally, a local search trigger condition is preset, such as performing a local search every time a certain number of global searches are performed.

[0113] In the embodiment of the present application, several termination conditions are preset, including a maximum number of iterative operations, a fitness value threshold of a candidate path, or an improvement value threshold of a candidate path fitness value.

[0114] The embodiment of the present application is also based on the elite retention strategy and the diversity monitoring and maintenance strategy.

[0115] The specific elite retention strategy is:

[0116] After each crossover operation and mutation operation, if the candidate path does not meet the termination condition, the initial path population is subjected to elite retention operation. Through the selection function, some paths in the initial path population are selected to enter the new path population.

[0117] Optionally, the selection function is expressed as:

[0118]

[0119] Among them, x represents an individual, P(x) represents the probability of path x being selected, and F(x) represents the fitness value of path x. represents the sum of the fitness values ​​of all paths in the population, and N represents the number of paths in the population.

[0120] The diversity monitoring and maintenance strategy is specifically as follows:

[0121] Preset diversity threshold,

[0122] After the elite retention operation is performed, a diversity monitoring and maintenance operation is performed to analyze the new path population to obtain diversity. When the diversity is lower than the diversity threshold, the crossover rate, mutation rate and / or new random paths are generated to join the new path population.

[0123] In this embodiment, the genetic algorithm is based on knowledge-guided initialization, comprehensive evaluation fitness function, adaptive genetic operation, elite retention and diversity maintenance, and a path planning strategy that balances local search and global search, achieving better convergence speed and solution quality.

[0124] At the same time, the algorithm flexibly adjusts the inspection strategy and path planning method according to the danger level and danger factor, the particularities of different factory areas, safety regulations and changes in actual safety status, and dynamically adjusts the inspection path to ensure the real-time and effectiveness of the inspection work.

[0125] In summary, the improved genetic algorithm has been significantly optimized and improved in initialization, fitness function design, genetic operation, elite retention and diversity maintenance, local and global search balance, convergence speed and solution quality.

[0126] On the other hand, an embodiment of the present application provides an inspection path planning device, comprising:

[0127] The acquisition module 201 is used to divide the inspection area into multiple sub-areas, obtain map data, equipment information, dangerous object information and temperature information in each sub-area; evaluate the danger level of each sub-area according to the map data, dangerous object information and temperature information, and add the danger level evaluation result of each sub-area to the map data;

[0128] The path pre-definition module 202 is used to generate a number of high-quality path segments in each sub-area according to the acquired map data, equipment information, dangerous object information, and temperature information of each sub-area, and generate a number of high-quality paths by combining the high-quality path segments in each sub-area;

[0129] The genetic module 203 is used to generate an initial path population according to the plurality of high-quality paths by using a genetic algorithm, and perform an iterative operation on the initial path population to obtain an optimal path of the area to be inspected.

[0130] It can be understood that the above-mentioned system embodiment and the above-mentioned method embodiment can correspond to each other, and similar descriptions of the system embodiment can refer to the method embodiment. To avoid repetition, it will not be repeated here. A patrol path planning device provided in an embodiment of the present application can execute a patrol path planning method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method. The functional modules of the patrol path planning device can be implemented in the form of hardware, can be implemented by instructions in the form of software, and can also be implemented by a combination of hardware and software modules.

[0131] Optionally, the software module may be located in a random access memory, a read-only memory, a programmable read-only memory, a flash memory, an electrically erasable programmable memory, a register, or other storage media. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps in the above method embodiment in combination with its hardware.

[0132] The present application embodiment provides an electronic device 710, whose structure is as follows: Figure 3 The electronic device 710 may be an embodiment of the present application Figure 4 The server 100 or the terminal 200 is shown.

[0133] like Figure 3 As shown, the electronic device 710 includes a memory 711, a processor 712, a communication module 713 and an input / output interface 714, etc. Optionally, the memory 711, the processor 712, the communication module 713 and the input / output interface 714 can be connected and communicated through a bus 715.

[0134] The memory 711 is used to store one or more computer programs and transmit the code of the computer program to the processor 712; when the one or more computer programs are executed by the processor 711, a patrol path planning method in an embodiment of the present application is implemented.

[0135] Optionally, the electronic device 710 can be connected to a network via a communication module 713 to communicate with other devices, such as a terminal or a server, through the network to achieve data interaction. The electronic device 710 can be various forms of digital computers, such as desktop computers, servers, workstations, mainframe computers or other types of computers. The electronic device 710 can also be various forms of mobile terminals, such as smart phones, tablet computers, wearable devices (such as helmets, glasses, watches, etc.) and other similar mobile terminals.

[0136] Optionally, the electronic device 710 can be connected to a required input / output device, such as a keyboard, a display device, etc., through the input / output interface 714. The electronic device 710 itself can have a display device, and can also be connected to other external display devices through the input / output interface 714. Optionally, a storage device, such as a hard disk, can be connected through the input / output interface 714, so that data in the electronic device 710 can be stored in the storage device, or data in the storage device can be read, and data in the storage device can also be stored in the memory 711.

[0137] It is understandable that the input / output interface 714 may be a wired interface or a wireless interface. Depending on the actual application scenario, the device connected to the input / output interface 714 may be a component of the electronic device 710 or an external device connected to the electronic device 710 when needed.

[0138] Optionally, the memory 711 may be a volatile memory and / or a non-volatile memory, the volatile memory may be a random access memory, etc., and the non-volatile memory may be a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory or a flash memory, etc.

[0139] Optionally, the computer program stored in the processor 711 may be divided into one or more modules, which are stored in the memory 711 and executed by the processor 712 to complete the method provided in the embodiment. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the computer program instruction segments are used to describe the execution process of the computer program in the electronic device 710.

[0140] Optionally, the processor 712 may be various general and / or special processing components with processing and computing capabilities. Some examples of the processor 712 include, but are not limited to, a central processing unit, a graphics processing unit, a digital signal processor, various special artificial intelligence computing chips, various processors running machine learning model algorithms, and may also be any appropriate controller, microcontroller, processor, etc. The processor 712 executes various methods and processes of the embodiments of the present application, for example, a patrol path planning method of the embodiments of the present application.

[0141] Optionally, the bus 715 may include a path for transmitting information. The bus 715 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. According to different functions, the bus 715 may be divided into an address bus, a data bus, a control bus, etc.

[0142] In an optional implementation, the embodiment of the present application further provides a computer storage medium on which a computer program is stored, and when the computer program is executed by a computer, the computer can perform the method of the above method embodiment. Part or all of the computer program can be loaded and / or installed on the memory 711 of the electronic device 710. When the computer program is executed by the processor 712, one or more steps of a patrol path planning method of the embodiment of the present application can be executed.

[0143] Optionally, the computer-readable storage medium may be a random access memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or the like.

[0144] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the technical solution of the present invention, and are not intended to limit the specific implementation methods of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the claims of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. A patrol route planning method, characterized in that: include, Divide the area to be inspected into multiple sub-areas, and obtain map data, equipment information, hazardous material information, and temperature information in each sub-area; Evaluate the danger level of each sub-area according to the map data, the dangerous object information and the temperature information, and add the danger level of each sub-area to the map data; According to the acquired map data, equipment information, dangerous object information, temperature information and danger level of each sub-area, a number of high-quality path segments are generated in each sub-area, and a number of high-quality paths are generated by combining the high-quality path segments in each sub-area; Genetic algorithms are used to generate an initial path population based on the plurality of high-quality paths, and the initial path population is iterated to obtain an optimal path for the area to be inspected.

2. A patrol route planning method according to claim 1, characterized in that: The step of evaluating the danger level of each sub-area according to the map data, the dangerous object information and the temperature information, and adding the danger level of each sub-area to the map data specifically includes: Performing a dangerous area level assessment on each of the sub-areas according to the dangerous object information to obtain a dangerous area level for each sub-area; Performing a temperature region level evaluation on each of the sub-regions according to the temperature information to obtain a temperature region level of each sub-region; Determine the hazard coefficient of each sub-area according to the hazard area level and temperature area level of each sub-area; The danger zone level, temperature zone level and danger factor of each sub-area are added to the map data.

3. The inspection path planning method according to claim 1, characterized in that: Based on the map data, equipment information, hazardous material information, temperature information and hazard level of each sub-area, several high-quality path segments are generated in each sub-area, including: The equipment information includes equipment type, equipment quantity and operating status; the dangerous object information includes dangerous object type, quantity and storage status; the temperature information includes equipment temperature, dangerous object temperature and duration corresponding to each temperature; According to the map data, equipment information, dangerous object information, temperature information and danger level in each sub-area, a number of high-quality path segments are generated in each sub-area, and a number of high-quality paths are generated based on the number of path segments in each sub-area.

4. The inspection path planning method according to claim 1, characterized in that: Genetic algorithms are used to generate an initial path population based on the several high-quality paths, and the initial path population is iterated to obtain the optimal path of the area to be inspected, specifically including: Generate a number of random paths, wherein the number of random paths and the number of high-quality paths together constitute an initial path population; Obtaining a fitness function based on the map data, equipment information, dangerous object information, temperature information and danger level; The initial path population is iterated, specifically: Select paths from the initial path population to perform crossover and mutation operations to generate new paths and path populations; Perform a global search on the new path population based on the fitness function to obtain the path with the highest fitness value; Perform local search based on the path with the highest fitness value to obtain candidate paths and their fitness values; Determine whether the candidate path and its fitness value meet the termination conditions, If satisfied, terminate the iteration operation, take the candidate path as the optimal path of the area to be inspected, and output the optimal path and its fitness value; If not satisfied, perform an elite retention operation on the initial path population, select several paths in the initial path population to enter a new path population, perform a diversity monitoring and maintenance operation on the new path population to generate new paths, update the new path population based on the new paths, and use the updated new path population as the initial path population for the next iterative operation; The iterative operation is performed.

5. A patrol route planning method according to claim 4, characterized in that: The fitness function includes a path length evaluation function, a safety evaluation function and a reachability evaluation function. The fitness function is expressed as: F(x)=w_1cdot L(x)+w_2cdot S(x)+w_3cdot A(x) Where x represents the path, F(x) represents the fitness value of the path, cdot L(x) represents the path length evaluation function, cdot S(x) represents the safety evaluation function, cdot A(x) represents the reachability evaluation function, w_1, w_2, and w_3 represent the weights of the path length evaluation function, the safety evaluation function, and the reachability evaluation function, respectively; The path length evaluation function is evaluated by the length of the path, wherein the length of the path is calculated based on the map data; The safety assessment function is evaluated by the safety distance between the path and each sub-area, wherein the safety distance is calculated according to the danger level of each sub-area in the map data; The accessibility evaluation function is evaluated by the smoothness and the number of turns of the path, wherein the smoothness and the number of turns of the path are calculated based on the map data.

6. The inspection path planning method according to claim 4, characterized in that: Performing an elite retention operation on the initial path population, selecting several paths in the initial path population to enter a new path population, specifically including: A number of paths in the initial population are selected by a selection function, and the selected paths enter a new path population. The selection function is expressed as: Among them, x represents the path, P(x) represents the probability of path x being selected, and F(x) represents the fitness value of path x. represents the sum of the fitness values ​​of all paths in the population, and N represents the number of paths in the population.

7. The inspection path planning method according to claim 4, characterized in that: Performing a diversity monitoring and maintenance operation on the new path population to generate a new path, updating the new path population based on the new path, and using the updated new path population as the initial path population for the next iterative operation, specifically includes: A diversity threshold is preset, and the new path population is analyzed to obtain diversity. When the diversity is lower than the diversity threshold, the crossover rate, the mutation rate and / or a new random path is generated, and the random path is updated to the new path population. The updated new path population is used as the initial path population for the next iterative operation.

8. A patrol route planning device, characterized in that: include: An acquisition module is used to divide the area to be inspected into multiple sub-areas and obtain map data, equipment information, hazardous material information and temperature information in each sub-area; Evaluate the danger level of each sub-area according to the map data, the dangerous object information and the temperature information, and add the danger level of each sub-area to the map data; A path pre-definition module is used to generate a number of high-quality path segments in each sub-area based on the acquired map data, equipment information, hazardous material information, and temperature information of each sub-area, and to generate a number of high-quality paths by combining the high-quality path segments in each sub-area; The genetic module is used to generate an initial path population according to the plurality of high-quality paths by using a genetic algorithm, and perform iterative operations on the initial path population to obtain an optimal path of the area to be inspected.

9. An electronic device, characterized in that: include: a memory for storing one or more computer programs; A processor, when the one or more computer programs are executed by the processor, implements a patrol path planning method as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a processor to execute and implement a patrol path planning method according to any one of claims 1 to 7.

Images