Electric power pipe gallery intelligent inspection method and system based on fault occurrence probability and medium

Abstract

The invention relates to the technical field of inspection monitoring and early warning of electric power lines, in particular to an electric power pipe gallery intelligent inspection method and system based on the fault occurrence probability and a medium. The method comprises the following steps: S1, constructing a daily inspection line; s2, calculating the fault occurrence probability of each node of the power pipe gallery, taking the node of which the fault occurrence probability is in a first interval [a, b] as a first target node, and taking the node of which the fault occurrence probability is in a second interval [b, c] as a second target node; s3, constructing an inspection route based on a multi-objective function; and S4, solving based on a genetic algorithm to obtain an optimal inspection strategy. The time for reaching the second target node with the large fault probability is the shortest, the number of the inspected repeated nodes in the path is the minimum, the nodes with the large risk are rapidly inspected, meanwhile, the minimum path is calculated, the reasonable degree of the inspection route is increased, and maximum effective utilization of resources is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of inspection, monitoring and early warning of power lines, and in particular to an intelligent inspection method, system and computer-readable storage medium for power pipeline corridors based on the probability of failure. Background Art

[0002] The power pipeline gallery, also known as the cable tunnel or power tunnel, is an important municipal infrastructure in the city. The cable tunnel is located deep underground and extends to every corner of the city.

[0003] Traditionally, the protection of underground cables is just to arrange special personnel to patrol. This method has low automation and intelligence, and the actual protection effect is not ideal. At present, the monitoring of underground cables mainly adopts distributed optical fiber sensing technology. However, the signal recognition of current distributed optical fiber sensors is easily affected by environmental factors, such as weather, animals, industrial activities, etc., resulting in a high false alarm rate of optical fiber sensors.

[0004] There are also dedicated inspection robots, such as inspection robots that hang on rails above the power corridor, and walking wheeled inspection robots, which can be used for inspection of power corridors. At present, the power corridor is generally inspected daily according to a schedule through a set fixed inspection route, or the inspection frequency is increased in different areas according to experience and the age of equipment. However, many inspection routes may be invalid, and the inspection intensity is not enough for nodes that may fail.

[0005] Therefore, it is necessary to provide a new intelligent inspection method for power pipeline corridors based on the probability of fault occurrence. Summary of the invention

[0006] Based on this, it is necessary for the present invention to provide a method, system and readable storage medium for intelligent inspection of power pipeline corridors based on the probability of fault occurrence, so as to solve at least one of the above-mentioned technical problems.

[0007] To achieve the above purpose, a method for intelligent inspection of power pipe corridors based on fault probability includes the following steps:

[0008] Step S1, constructing a daily inspection route of one or more inspection robots in the power pipeline corridor;

[0009] Step S2: Obtain the monitoring data monitored by the distributed online monitoring system deployed in the power pipe gallery, and calculate the failure probability of each node in the power pipe gallery through a preset failure probability algorithm; take the nodes with the failure probability in the first interval [a, b) as the first target nodes, and take the nodes with the failure probability in the second interval [b, c) as the second target nodes, where 0 < a < b < c < 100%, sort the first target nodes according to the magnitude of the failure probability, and record them as R = {R1, R2, R3... R N}, where N is the number of nodes with the failure probability in the first interval, sort the second target nodes according to the magnitude of the failure probability, and record them as S = {S1, S2, S3... S M}, where M is the number of nodes with the failure probability in the second interval; among them, the distributed online monitoring system includes multiple of infrared cameras, smoke detectors, thermal detectors, ammeters, voltmeters, temperature sensors, humidity sensors, and partial discharge sensors;

[0010] Step S3: Construct an inspection route. Among them, the nodes passed by when going to the next inspection node are not inspected, and record the number of uninspected nodes passed by during the inspection process as the number of repeated nodes; construct a multi-objective function through the first objective function, the second objective function, and the third objective function. Among them, the first objective function is to minimize the time to reach the second target node, the second objective function is to minimize the number of repeated nodes that have been inspected passed by in the path, and the third objective function is to minimize the time to inspect all nodes;

[0011] Step S4: Calculate the optimal inspection strategy: Based on the failure probability of each current node in the power pipe gallery and the position of the inspection robot, solve the multi-objective function based on the genetic algorithm to obtain the optimal inspection strategy.

[0012] Further, Step S2 further includes: record the set of nodes with the failure probability less than a as Q, and record the set of nodes with the failure probability greater than c as O; the multi-objective function further includes a fourth objective function: the inspection order is the second target nodes, the first target nodes, and other nodes in the sets Q and O are inspected according to the daily inspection line.

[0013] Further, in the fourth objective function:

[0014] Inspect the first target nodes in descending order according to the magnitude of the failure probability of the first target nodes;

[0015] And / or,

[0016] The inspection of the second target node is performed in descending order of the probability of occurrence of failure of the second target node.

[0017] Further, an undirected graph G=(P, L) of the inspection path is constructed, where P is the set of all nodes of R, S and Q, and L is the set of edges between two nodes; the step S3 specifically includes:

[0018] The first objective function is minT(H)=∑ i∈S t i ,

[0019] The second objective function is minC(c)=∑ j∈P c j ,

[0020] The third objective function is minT′(H)=∑ k∈P t k ,

[0021] Where T is the total time to reach all the second target nodes, C is the number of repeated nodes that have been inspected in the path, T′ is the time to inspect all nodes, and t i represents the time from the i-1 node to the i-th second target node, c j Indicates the number of times the jth node is passed again after being inspected during the inspection process, t k It represents the time to reach the kth node from k-1 nodes.

[0022] Furthermore, the step S4 specifically includes:

[0023] Determine the upper and lower boundaries of the population, initialize the population and determine whether the first-generation subgroup can be generated. If not, perform fast non-dominated sorting, generate subgroups through selection, crossover, and mutation, and then use it as the initial population to determine whether the first-generation subgroup can be generated.

[0024] If the initial population can generate the first generation of sub-populations, set the evolutionary generation gen = 2; then merge the parent and sub-generation populations to form a new population, and determine whether a new parent population has been generated;

[0025] If a new parent population is not generated, the objective function is calculated, and a fast non-dominated sort is performed to calculate the crowding degree. Then a new parent individual is generated, and the resulting new population is judged to be a new parent population.

[0026] When it is determined that a new parent population is generated, a child population is generated through selection, crossover, and mutation. Then it is determined whether the evolutionary generation at this time is less than the set maximum generation. If so, the evolutionary generation is set to gen+1, and the parent and child populations are merged to form a new population, and the evolutionary cycle is repeated again;

[0027] If the number of evolution generations has reached the maximum number of generations, the evolution is stopped and the optimal population is output to obtain the optimal solution.

[0028] Furthermore, in step S2, the monitoring data monitored by the distributed online monitoring system deployed in the power pipeline corridor is obtained, and the failure probability of each node of the power pipeline corridor is calculated by a preset failure probability algorithm, including:

[0029] Acquire monitoring data monitored by a distributed online monitoring system deployed in the power pipeline corridor, obtain a characteristic vector of the operating parameter according to the monitoring data and a preset evaluation index of the operating parameter, and form a data set;

[0030] According to the data set and different operating states, a Gaussian probability density function corresponding to different operating states is obtained; the operating states include normal and fault;

[0031] Obtain the feature vector of the node to be judged in the current working time period and the historical feature vector of the node to be judged in each historical working time period;

[0032] According to the feature vector of the node to be judged in the current working time period and each historical feature vector, a Gaussian mixture model to be judged of the node to be judged in the current working time period and each Gaussian probability density function to be judged corresponding to the Gaussian mixture model to be judged are obtained;

[0033] The difference between each Gaussian probability density function to be judged and the standard Gaussian probability density function corresponding to different operating states is calculated, and the difference is converted into the failure probability of the node.

[0034] Furthermore, the step of obtaining the corresponding Gaussian probability density function under different operating states based on the data set and different operating states includes: training a Gaussian mixture model for each feature vector corresponding to different operating states to obtain a basic Gaussian probability density function corresponding to each operating state; using the maximum expectation iteration method to estimate the parameters of the Gaussian mixture model, and recording the basic Gaussian density functions after the parameters of the Gaussian mixture model are estimated using the maximum expectation iteration method as standard Gaussian probability density functions.

[0035] Furthermore, after step S2, the method further includes, when the set O is not empty, controlling the inspection robot or the manual inspection unit to inspect the nodes in the set O, or issuing an alarm signal corresponding to the nodes in the set O.

[0036] The present invention also provides an intelligent inspection system for power pipelines based on the probability of fault occurrence, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the intelligent inspection method for power pipelines based on the probability of fault occurrence as described in any one of the above items are implemented.

[0037] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the intelligent inspection method for power pipeline corridors based on the probability of fault occurrence as described in any of the above items.

[0038] The present invention takes into account the failure probability of each node in the power pipeline corridor, and divides the nodes into second target nodes with a higher failure probability and first target nodes with a lower failure probability according to the size of the failure probability. By constructing a multi-objective function, the time to reach the second target node with a higher failure probability is the shortest, and the number of repeated nodes that have been inspected in the path is the least, so that the nodes with high risks can be quickly inspected and the minimum path can be calculated. Then, through other objective functions and constraints, the rationality of the inspection route is further increased, and the effective utilization of resources is maximized. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Other features, objectives and advantages of the present invention will become more apparent from a reading of the detailed description of a non-limiting implementation made with reference to the following accompanying drawings.

[0040] Figure 1 It is a flow chart of an intelligent inspection method for power pipeline corridors based on the probability of failure provided by the present invention.

[0041] Figure 2 It is a schematic diagram of the hardware structure of a system running an intelligent inspection method for power pipeline corridors based on the probability of failure in one embodiment of the present invention.

[0042] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0043] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0044] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0045] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0046] To achieve this, please refer to Figure 1 and Figure 2 The present invention provides an intelligent inspection method for a power pipeline corridor based on the probability of fault occurrence, comprising the following steps S1-S4.

[0047] Step S1, construct one or more daily inspection routes of inspection robots in the power corridor. Generally speaking, the daily inspection route is divided according to the area of ​​the power corridor. The inspection robot starts from the starting point. Under the premise of no special inspection tasks, it inspects all nodes and returns to the end point (which may be consistent with the starting point or inconsistent). The path in the middle will be the daily inspection route. It can be understood that under the premise of no special inspection tasks, when there is no influence of the following steps S2-S4, such as a new power corridor, normal operation, and the probability of failure of all nodes is very small, the inspection robot generally patrols according to the daily inspection video.

[0048] It can be understood that the intelligent inspection method of power corridors based on fault probability in the present application can be used for inspection robots to inspect fixed power corridor areas, and it can also be used for situations where overlapping inspection areas may occur during the inspection of power corridors by inspection robots.

[0049] Generally speaking, the route of the rail-mounted inspection robot is predetermined according to the track, while the walking inspection robot can inspect any position in the walkable area within the power corridor. The intelligent inspection method for power corridors based on the probability of fault occurrence in this application is applicable.

[0050] Step S2: Obtain the monitoring data monitored by the distributed online monitoring system deployed in the power pipe gallery, and calculate the failure probability of each node in the power pipe gallery through a preset failure probability algorithm; regard the nodes with the failure probability in the first interval [a, b) as the first target nodes, and regard the nodes with the failure probability in the second interval [b, c) as the second target nodes, where 0 < a < b < c < 100%, sort the first target nodes according to the magnitude of the failure probability, and record them as R = {R1, R2, R3... R N}, where N is the number of nodes with the failure probability in the first interval, sort the second target nodes according to the magnitude of the failure probability, and record them as S = {S1, S2, S3... S M}, where M is the number of nodes with the failure probability in the second interval; among them, the distributed online monitoring system includes multiple of an infrared camera, a smoke detector, a thermal detector, an ammeter, a voltmeter, a temperature sensor, a humidity sensor, and a partial discharge sensor.

[0051] In addition, record the set of nodes with the failure probability less than a as Q, and record the set of nodes with the failure probability greater than c as O.

[0052] Generally speaking, the nodes in the set Q represent relatively low risks, the nodes in the set O represent relatively high risks, and the nodes in the sets R and S are matters that need to be confirmed during the inspection, where the priority of the second target nodes is higher than that of the first target nodes.

[0053] Further, after the step S2, it further includes that when the set O is not empty, controlling the inspection robot or the manual inspection unit to inspect the nodes in the set O, or sending out the alarm signals corresponding to the nodes in the set O.

[0054] The distributed online monitoring system can include multiple of an infrared camera, a smoke detector, a thermal detector, an ammeter, a voltmeter, a temperature sensor, a humidity sensor, and a partial discharge sensor. For example, it is used to detect cable current parameter values (such as the ground loop current of the intermediate joint), cable voltage parameter values (such as the voltage of the intermediate joint), cable temperature parameter values, ambient temperature parameter values, ambient humidity parameter values, partial discharge parameter values, a liquid level sensor is used to sense the water level in the tunnel, a smoke sensor is used to detect the flue gas in the tunnel, an infrared thermal imaging camera is used to detect the infrared thermal imaging, etc. Those skilled in the art can set and select according to needs.

[0055] Further, the distributed online monitoring system further includes multiple distributed data nodes, and each data node is matched with the distributed online monitoring system, and is used to receive the data transmitted by the online monitoring system in the corresponding area and transmit it to the monitoring background server.

[0056] Furthermore, the step of obtaining monitoring data monitored by the distributed online monitoring system deployed in the power pipeline corridor and calculating the probability of failure of each node in the power pipeline corridor by a preset failure probability algorithm includes:

[0057] Acquire monitoring data monitored by a distributed online monitoring system deployed in the power pipeline corridor, obtain a characteristic vector of the operating parameter according to the monitoring data and a preset evaluation index of the operating parameter, and form a data set;

[0058] According to the data set and different operating states, a Gaussian probability density function corresponding to different operating states is obtained; the operating states include normal and fault;

[0059] Obtain the feature vector of the node to be judged in the current working time period and the historical feature vector of the node to be judged in each historical working time period;

[0060] According to the feature vector of the node to be judged in the current working time period and each historical feature vector, a Gaussian mixture model to be judged of the node to be judged in the current working time period and each Gaussian probability density function to be judged corresponding to the Gaussian mixture model to be judged are obtained;

[0061] The difference between each Gaussian probability density function to be judged and the standard Gaussian probability density function corresponding to different operating states is calculated, and the difference is converted into the failure probability of the node.

[0062] Furthermore, the step of obtaining the corresponding Gaussian probability density function under different operating states based on the data set and different operating states includes: training a Gaussian mixture model for each feature vector corresponding to different operating states to obtain a basic Gaussian probability density function corresponding to each operating state; using the maximum expectation iteration method to estimate the parameters of the Gaussian mixture model, and recording the basic Gaussian density functions after the parameters of the Gaussian mixture model are estimated using the maximum expectation iteration method as standard Gaussian probability density functions.

[0063] Among them, in the step of training the Gaussian mixture model for each feature vector corresponding to different operating states to obtain the basic Gaussian probability density function corresponding to each operating state, in the m-dimensional feature space, each basic Gaussian probability density function is:

[0064] Among them, p(x|μ,Σ) is the basic Gaussian probability density function, μ is the mean vector, Σ is the covariance matrix, x is the eigenvector, and T is the transpose of the matrix; it should be noted that the Gaussian mixture model regards the observed data as a linear combination of several Gaussian density functions, as shown in the following formula:

[0065] Among them, p(x) is a Gaussian mixture model, k represents the number of basic Gaussian density functions, is the jth basic Gaussian probability density function corresponding to the Gaussian mixture model, is the mixing coefficient of the jth Gaussian component, is also a weight, and the sum of the weights is 1. , the operating state is fault and non-fault, so the Gaussian mixture model is a linear combination of two basic Gaussian probability density functions, that is, k=2, and one operating state corresponds to one Gaussian probability density function; then the maximum expectation iteration method is used to estimate the parameters of the above Gaussian mixture model. The purpose of using the maximum expectation iteration method is to obtain the maximum likelihood estimation of parameters such as mean μ, covariance Σ and mixing coefficient α. This process is a well-known technology and is therefore not described in detail.

[0066] Step S3, constructing an inspection route, wherein the nodes passed by on the way to the next inspection node are not inspected, and the number of nodes passed by but not inspected during the inspection process is recorded as the number of repeated nodes; constructing a multi-objective function through the first objective function, the second objective function and the third objective function, wherein the first objective function is to minimize the time to reach the second target node, the second objective function is to minimize the number of repeated nodes passed by and inspected in the path, and the third objective function is to minimize the time to inspect all nodes.

[0067] Among them, it should be noted that "nodes passed by on the way to the next inspection node are not inspected, and the number of nodes passed by but not inspected during the inspection process is recorded as the number of repeated nodes" means that during the inspection process of the inspection robot, for each other node passed by on the way to the next inspection node (other nodes that are not the next inspection node), the number of repeated nodes is increased by 1.

[0068] Specifically, step S3 constructs an undirected graph G=(P, L) of the inspection path, where P is the set of all nodes of R, S and Q, and L is the set of edges between two nodes; step S3 specifically includes:

[0069] The first objective function is minT(H)=∑ i∈S t i ,

[0070] The second objective function is minC(c)=∑ j∈P c j ,

[0071] The third objective function is minT′(H)=∑ k∈P t k ,

[0072] Where T is the total time to reach all the second target nodes, C is the number of repeated nodes that have been inspected in the path, T′ is the time to inspect all nodes, and t irepresents the time from the i-1 node to the i-th second target node, c j Indicates the number of times the jth node is passed again after being inspected during the inspection process, t k It represents the time to reach the kth node from k-1 nodes.

[0073] Furthermore, the multi-objective function also includes a fourth objective function: the inspection order is the second target node, the first target node, and inspecting the set Q and other nodes in the set O according to the daily inspection route.

[0074] Furthermore, in the fourth objective function:

[0075] The inspection of the first target node is performed in descending order of the probability of occurrence of a failure of the first target node;

[0076] and / or,

[0077] The inspection of the second target node is performed in descending order of the probability of occurrence of failure of the second target node.

[0078] Step S4, calculation of the optimal inspection strategy: according to the current failure probability of each node in the power pipeline corridor and the location of the inspection robot, the objective function is solved based on the genetic algorithm to obtain the optimal inspection strategy.

[0079] Furthermore, the step S4 specifically includes:

[0080] Determine the upper and lower boundaries of the population, initialize the population and determine whether the first-generation subgroup can be generated. If not, perform fast non-dominated sorting, generate subgroups through selection, crossover, and mutation, and then use it as the initial population to determine whether the first-generation subgroup can be generated.

[0081] If the initial population can generate the first generation of sub-populations, set the evolutionary generation gen = 2; then merge the parent and sub-generation populations to form a new population, and determine whether a new parent population has been generated;

[0082] If a new parent population is not generated, the objective function is calculated, and a fast non-dominated sort is performed to calculate the crowding degree. Then a new parent individual is generated, and the resulting new population is judged to be a new parent population.

[0083] When it is determined that a new parent population has been generated, a child population is generated through selection, crossover, and mutation. Then it is determined whether the evolutionary generation is less than the set maximum generation. If so, the evolutionary generation is set to gen+1, and the parent and child populations are merged to form a new population, and the evolutionary cycle is repeated again. If the evolutionary generation has reached the maximum generation, the evolution is stopped and the optimal population is output to obtain the optimal solution.

[0084] The intelligent inspection method for power pipe corridors based on the probability of fault occurrence of the present invention constructs the daily inspection routes of one or more inspection robots in the power pipe corridor through step S1; in step S2, according to the preset fault probability algorithm, based on the monitoring data uploaded by the sensors of the power pipe corridor received, calculate the fault occurrence probability of each node in the power pipe corridor, and take the nodes with the fault occurrence probability in the first interval [a, b) as the first target nodes, and take the nodes with the fault occurrence probability in the second interval [b, c) as the second target nodes, where 0 < a < b < c < 100%; in step S3, construct an inspection route, where the nodes passed by on the way to the next inspection node are not inspected, and record that the number of repeated nodes is incremented by 1; construct a multi-objective function for solving the inspection route through the first objective function: the time to reach the second target node is the shortest, the second objective function: the number of repeated nodes that have been inspected passed by in the path is the least, and the third objective function: the time to inspect all nodes is the least; in step S4, calculate the optimal inspection strategy: based on the fault occurrence probability of each node in the current power pipe corridor and the position of the inspection robot, solve the objective function based on the genetic algorithm to obtain the optimal inspection strategy. The method in the present invention takes into account the fault occurrence probability of each node in the power pipe corridor. According to the magnitude of the fault occurrence probability, the nodes are divided into the second target nodes with a relatively large fault probability and the first target nodes with a relatively small fault occurrence probability. By constructing a multi-objective function, the time to reach the second target node with a relatively large fault probability is the shortest, and the number of repeated nodes that have been inspected passed by in the path is the least, so as to quickly inspect the nodes with a high risk while calculating the minimum path. Then, through other objective functions and constraints, the rationality of the inspection route is further increased to achieve the maximum effective utilization of resources.

[0085] The present invention also provides an intelligent inspection system for power pipe corridors based on the probability of fault occurrence. The system runs on the basis of a computer system and specifically includes a memory 61, a processor 62, and a computer program 63 stored in the memory 61 and executable on the processor 62. When the processor 62 executes the computer program 63, it implements the steps of the intelligent inspection method for power pipe corridors based on the probability of fault occurrence as described in any one of the above.

[0086] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the computer.

[0087] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0088] The memory may be an internal storage unit, such as a hard disk or a memory; the memory may also be an external storage device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory may include both an internal storage unit and an external storage device. The memory is used to store the computer program and other programs and data required by the terminal device. The memory may also be used to temporarily store data that has been output or is to be output.

[0089] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the intelligent inspection method for power pipeline corridors based on the probability of fault occurrence as described in any of the above items.

[0090] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0091] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0093] In the embodiments provided by the present invention, it should be understood that the disclosed devices / systems and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0094] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0096] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0097] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0098] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent inspection method for power pipeline corridor based on fault probability, characterized in that: The following steps are involved: Step S1, constructing a daily inspection route of one or more inspection robots in the power pipeline corridor; Step S2, obtaining monitoring data monitored by the distributed online monitoring system deployed in the power pipeline corridor, and calculating the failure probability of each node in the power pipeline corridor by a preset failure probability algorithm; Nodes with the probability of failure occurring in the first interval [a, b) are regarded as the first target nodes, and nodes with the probability of failure occurring in the second interval [b, c) are regarded as the second target nodes, where 0 < a < b < c < 100%. Sort the first target nodes according to the magnitude of the failure probability and record them as R = {R1, R2, R3... R N}, where N is the number of nodes with the probability of failure occurring in the first interval. Sort the second target nodes according to the magnitude of the failure probability and record them as S = {S1, S2, S3... S M}, where M is the number of nodes with the probability of failure occurring in the second interval. Among them, the distributed online monitoring system includes multiple of an infrared camera, a smoke detector, a thermal detector, an ammeter, a voltmeter, a temperature sensor, a humidity sensor, and a partial discharge sensor; Step S3, constructing an inspection route, wherein the nodes passed by on the way to the next inspection node are not inspected, and the number of nodes passed by but not inspected during the inspection process is recorded as the number of repeated nodes; constructing a multi-objective function through the first objective function, the second objective function and the third objective function, wherein the first objective function is to minimize the time to reach the second target node, the second objective function is to minimize the number of repeated nodes passed by and inspected in the path, and the third objective function is to minimize the time to inspect all nodes; Step S4, calculation of the optimal inspection strategy: according to the current failure probability of each node in the power pipeline corridor and the location of the inspection robot, the multi-objective function is solved based on the genetic algorithm to obtain the optimal inspection strategy.

2. The intelligent inspection method for power pipeline corridor based on fault occurrence probability according to claim 1 is characterized in that: The step S2 also includes: recording the set of nodes with a fault probability less than a as Q, and recording the set of nodes with a fault probability greater than c as O; the multi-objective function also includes a fourth objective function: the inspection order is the second target node, the first target node, and inspecting the set Q and other nodes in the set O according to the daily inspection route.

3. The intelligent inspection method for power pipeline corridor based on fault occurrence probability according to claim 2 is characterized in that: In the fourth objective function: The inspection of the first target node is performed in descending order of the probability of occurrence of a failure of the first target node; and / or, The inspection of the second target node is performed in descending order of the probability of occurrence of failure of the second target node.

4. The intelligent inspection method for power pipeline corridor based on fault occurrence probability according to claim 2 is characterized in that: Construct an undirected graph G = (P, L) of the inspection path, where P is the set of all nodes of R, S and Q, and L is the set of edges between two nodes; The step S3 specifically includes: The first objective function is minT(H)=Σ i∈S t i , The second objective function is minC(c)=Σ j∈P c j , The third objective function is minT′(H)=Σ k∈P t k , Where T is the total time to reach all the second target nodes, C is the number of repeated nodes that have been inspected in the path, T′ is the time to inspect all nodes, and t i represents the time from the i-1 node to the i-th second target node, c j Indicates the number of times the jth node is passed again after being inspected during the inspection process, t k It represents the time to reach the kth node from k-1 nodes.

5. The intelligent inspection method for power pipeline corridor based on fault occurrence probability according to claim 4 is characterized in that: The step S4 specifically includes: Determine the upper and lower boundaries of the population, initialize the population and determine whether the first-generation subgroup can be generated. If not, perform fast non-dominated sorting, generate subgroups through selection, crossover, and mutation, and then use it as the initial population to determine whether the first-generation subgroup can be generated. If the initial population can generate the first generation of sub-populations, set the evolutionary generation gen = 2; then merge the parent and sub-generation populations to form a new population, and determine whether a new parent population has been generated; If a new parent population is not generated, the objective function is calculated, and a fast non-dominated sort is performed to calculate the crowding degree. Then a new parent individual is generated, and the resulting new population is judged to be a new parent population. When it is determined that a new parent population is generated, a child population is generated through selection, crossover, and mutation. Then it is determined whether the evolutionary generation at this time is less than the set maximum generation. If so, the evolutionary generation is set to gen+1, and the parent and child populations are merged to form a new population, and the evolutionary cycle is repeated again; If the number of evolution generations has reached the maximum number of generations, the evolution is stopped and the optimal population is output to obtain the optimal solution.

6. The intelligent inspection method for power pipeline corridor based on fault occurrence probability according to claim 1 is characterized in that: In step S2, the monitoring data monitored by the distributed online monitoring system deployed in the power pipeline corridor is obtained, and the failure probability of each node of the power pipeline corridor is calculated by a preset failure probability algorithm, including: Acquire monitoring data monitored by a distributed online monitoring system deployed in the power pipeline corridor, obtain a characteristic vector of the operating parameter according to the monitoring data and a preset evaluation index of the operating parameter, and form a data set; According to the data set and different operating states, a Gaussian probability density function corresponding to different operating states is obtained; the operating states include normal and fault; Obtain the feature vector of the node to be judged in the current working time period and the historical feature vector of the node to be judged in each historical working time period; According to the feature vector of the node to be judged in the current working time period and each historical feature vector, a Gaussian mixture model to be judged of the node to be judged in the current working time period and each Gaussian probability density function to be judged corresponding to the Gaussian mixture model to be judged are obtained; The difference between each Gaussian probability density function to be judged and the standard Gaussian probability density function corresponding to different operating states is calculated, and the difference is converted into the failure probability of the node.

7. The intelligent inspection method for power pipeline corridor based on fault occurrence probability according to claim 6 is characterized in that: The step of obtaining the corresponding Gaussian probability density function under different operating states based on the data set and different operating states includes: training a Gaussian mixture model for each feature vector corresponding to different operating states to obtain a basic Gaussian probability density function corresponding to each operating state; using the maximum expectation iteration method to estimate the parameters of the Gaussian mixture model, and recording the basic Gaussian density functions after the parameters of the Gaussian mixture model are estimated using the maximum expectation iteration method as standard Gaussian probability density functions.

8. The intelligent inspection method for power pipeline corridor based on fault occurrence probability according to claim 3 is characterized in that: The step S2 further includes, when the set O is not empty, controlling the inspection robot or the manual inspection unit to inspect the nodes in the set O, or issuing an alarm signal corresponding to the nodes in the set O.

9. An intelligent inspection system for power pipeline corridors based on the probability of failure, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the intelligent inspection method for power pipeline corridors based on the probability of fault occurrence as described in any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent inspection method for power pipeline corridors based on fault occurrence probability as described in any one of claims 1 to 8 are implemented.

Images