Route control method, control device and inspection control system for substation inspection

Abstract

The application provides a route control method, a control device and a patrol control system for a transformer substation. The method comprises the following steps: acquiring environmental parameters, historical records, equipment conditions and other data of each point to be inspected in the transformer substation in real time, calculating static weights and dynamic weights based on the information, wherein the dynamic weights consider the waiting and maintenance time length of the inspection points, the emergency degree of the equipment and external influencing factors; generating a random inspection path as an initial population of a genetic algorithm, combining the weights to construct a fitness function for optimization, determining a priority and a penalty value, and thus obtaining an optimal inspection path; and finally, the path is sent to a terminal device of an inspector, so as to realize dynamic updating of the inspection route. The method solves the problem that in the prior art, when a sudden condition or an equipment problem occurs in the process of transformer substation inspection, the inspection route cannot be effectively adjusted, resulting in low inspection efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power equipment inspection, in particular to a route control method for substation inspection, a control device, a computer readable storage medium and an inspection control system. BACKGROUND

[0002] The stability and reliability of the power system operation require that the substation equipment must be in good condition, and the operation and maintenance of the substation equipment need to rely on a large number of personnel inspection. The inspection work of the substation mainly focuses on checking, maintaining and recording the equipment, and timely discovering the potential faults of the equipment to provide protection for the normal operation of the equipment. The traditional substation inspection work mainly relies on manual inspection, and the inspection personnel check the equipment one by one on site, and rely on the appearance of the equipment to judge the faults. The inspection work completely depends on the experience of the personnel, and the efficiency of the inspection is low and prone to missing inspection. With the development of technologies such as Internet of Things, big data, cloud computing and artificial intelligence, the digital transformation of the power industry has become urgent, and the intelligent inspection of the substation has become an inevitable trend of the industry development.

[0003] At present, a large number of literatures have adopted methods such as machine learning, graph theory, genetic algorithm and trajectory planning to realize intelligent inspection. In the machine learning method, some literatures use logistic regression to analyze the relationship between the faults of the substation equipment and the inspection data, so as to predict the faults of the equipment; some literatures construct a fault diagnosis model based on deep learning to realize the fault detection of the equipment. In the graph theory method, some literatures connect the substations, lines and switch stations of the power grid equipment into a graph to realize the fault positioning of the power grid; some literatures construct a fault diagnosis model of the substation equipment based on the graph. In the genetic algorithm and trajectory planning method, some literatures abstract the optimization problem of the inspection path as an optimization problem of the genetic algorithm; some literatures abstract the optimization problem of the inspection path as an optimization problem of the trajectory planning.

[0004] However, the substation inspection methods in the above literatures have certain deficiencies. For the machine learning method, although the fault detection of the substation equipment can be realized, the fault diagnosis of the equipment only depends on the fault data of the equipment itself, and ignores the influence of external factors such as the operating environment of the substation on the equipment. For the graph theory method, although the fault positioning of the power grid can be realized, the optimization problem of the inspection path of the substation equipment has not been widely applied in the graph theory. For the genetic algorithm and trajectory planning method, although the optimization of the inspection path can be realized, it usually needs to rely on a large amount of historical inspection data, and the equipment inspection data of the substation is difficult to obtain. In summary, the current intelligent inspection method of the substation is difficult to realize the real-time dynamic optimization of the inspection path. SUMMARY

[0005] The main purpose of the present application is to provide a route control method, control device, computer readable storage medium and inspection control system for substation inspection, so as to at least solve the problem that in the prior art, when a sudden situation or equipment problem is encountered in the substation inspection process, the inspection route cannot be effectively adjusted, resulting in low inspection efficiency.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a route control method for substation inspection is provided, comprising: acquiring real-time relevant data of each to-be-inspected point in the substation to obtain corresponding first target data, the first target data including environmental parameters, historical inspection records, equipment parameters, fault information and real-time operation parameters of the to-be-inspected point; determining a static weight of each to-be-inspected point based on the first target data, and simultaneously adjusting a dynamic weight of each to-be-inspected point in real time based on the first target data, the static weight being determined based on the historical inspection records, the real-time operation parameters and the equipment parameters, and the dynamic weight being determined based on a to-be-inspected point inspection waiting time, a to-be-inspected point inspection consumption time, a to-be-inspected point equipment operation parameter, the fault information and an external influence score determined by a to-be-inspected point before inspection; generating a random path as an initial population based on each to-be-inspected point, constructing a fitness function based on the static weight and the dynamic weight corresponding to each to-be-inspected point, optimizing through a genetic algorithm, and obtaining a target inspection path; and issuing the target inspection path to a terminal device carried by an inspection personnel to realize real-time updating of an inspection route of the work personnel.

[0007] Optionally, determining the static weight of each to-be-inspected point based on the first target data comprises: determining a historical failure rate of the to-be-inspected point based on the historical inspection records, estimating a fault repair time of the to-be-inspected point based on the real-time operation parameters; scoring based on the historical failure rate and the fault repair time, and performing weighted calculation based on the scoring result to obtain an emergency degree; determining a fault influence range, a fault influence degree and a device availability of the to-be-inspected point based on the equipment parameters, determining a device operation record of the to-be-inspected point according to the equipment operation parameters, and acquiring a device cost of the to-be-inspected point; scoring based on the fault influence range, the fault influence degree, the device availability, the device operation record and the device cost, and performing weighted calculation based on the scoring result to obtain a device importance; and performing weighted calculation based on the emergency degree and the device importance to obtain the static weight.

[0008] Optionally, the dynamic weight of each of the to-be-inspected points is adjusted in real time based on the first target data, including: determining a time length expected to be consumed by the work personnel to reach the to-be-inspected point from a current position based on a current inspection route, to obtain the inspection waiting time length; determining an average maintenance time length of the to-be-inspected point based on the historical inspection records, to obtain the inspection consuming time length; determining a damage probability of the to-be-inspected point based on the equipment operation parameters, and determining an emergency degree of the to-be-inspected point according to the damage probability; determining a target point before the to-be-inspected point in the current inspection route and a point changed in a previous inspection route, to obtain the target point, and determining the external influence score based on a sudden event corresponding to the target point; scoring based on the inspection waiting time length, the inspection consuming time length and the emergency degree respectively, and performing weighted calculation according to the score results and the external influence score, to obtain the dynamic weight.

[0009] Optionally, a random path is generated based on each of the to-be-inspected points as an initial population, and a fitness function is constructed based on the static weight and the dynamic weight corresponding to each of the to-be-inspected points, including: randomly coding each of the to-be-inspected points in the transformer substation to obtain a plurality of coding sequences, and determining each of the coding sequences as a chromosome, the coding sequence including a code corresponding to all of the to-be-inspected points in the transformer substation; taking each of the chromosomes as an alternative inspection path to obtain an initial population; substituting the static weight and the dynamic weight into a first preset formula p(v i )=w 静态 (v i )*w 动态 (v i ), to obtain a priority of the inspection point, w 静态 (v i ) being the static weight of node vi, w 动态 (v i ) being the dynamic weight of node vi at iteration number t, w 动态 (v i ) satisfying where w 动态 (v i , 0) is an initial dynamic weight of node vi, t is a current iteration number, and tmax is a maximum iteration number; substituting the priority into a second preset formula priority penalty to obtain a priority penalty, where x is a chromosome x, v i is the i-th node in a path corresponding to the chromosome x, and n is a total number of nodes included in the chromosome x; constructing the fitness function based on the chromosome and the priority penalty: fitness where path length(x) is a total length of an inspection path corresponding to the chromosome x, ε is a positive number less than a first threshold, and α is a weight coefficient.

[0010] Optionally, the optimization is performed by a genetic algorithm to obtain the target inspection path, including: a selection step of performing a selection operation based on a current population, selecting a preset number of the chromosomes from the current population as parent individuals based on the fitness; a crossover step of performing a crossover operation based on the parent individuals to obtain offspring individuals; a mutation step of performing a mutation operation based on the parent individuals and the offspring individuals to obtain an updated population; a calculation step of calculating the fitness of all the chromosomes in the updated population respectively; and repeating the selection step, the crossover step, the mutation step and the mutation step at least once in turn until a deviation of the maximum fitness in the updated population of adjacent two iterations is less than a preset proportion or a maximum iteration number is reached.

[0011] Optionally, the crossover operation is performed in a preset range centered on the to-be-inspected point with the dynamic weight difference greater than a second threshold in adjacent two iterations.

[0012] Optionally, the mutation operation is performed on the to-be-inspected point corresponding to the priority less than a third threshold.

[0013] According to another aspect of the present application, there is provided a route control device for substation inspection, the device comprising: a first acquisition unit configured to acquire relevant data of each to-be-inspected point in a substation in real time to obtain corresponding first target data, the first target data including environmental parameters, historical inspection records, device parameters, fault information and real-time operation parameters of the to-be-inspected point; a first calculation unit configured to determine a static weight of each to-be-inspected point based on the first target data, and simultaneously adjust a dynamic weight of each to-be-inspected point in real time based on the first target data, the static weight being determined based on the historical inspection records, the real-time operation parameters and the device parameters, and the dynamic weight being determined based on an inspection waiting time, an inspection consuming time, a device operation parameter, the fault information and an external influence score of the to-be-inspected point, wherein the external influence score is determined by a pre-inspection sequence of the to-be-inspected point; a second calculation unit configured to generate a random path as an initial population based on each to-be-inspected point, construct a fitness function based on the static weight and the dynamic weight corresponding to each to-be-inspected point, and perform optimization by a genetic algorithm to obtain a target inspection path; and a sending unit configured to send the target inspection path to a terminal device carried by an inspection personnel to realize real-time update of an inspection route of the inspection personnel.

[0014] According to still another aspect of the present application, there is provided a computer readable storage medium comprising a stored program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to perform any one of the methods when the program is run.

[0015] According to a further aspect of the present application, there is provided a route control system for substation inspection, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods described above.

[0016] In the route control method for substation inspection described above, according to the technical solution of the present application, first, the relevant data of each to-be-inspected point in the substation is acquired in real time to obtain corresponding first target data, the first target data including the environmental parameters, historical inspection records, device parameters, fault information, and real-time operation parameters of the to-be-inspected point; then, the static weight of each to-be-inspected point is determined based on the first target data, and the dynamic weight of each to-be-inspected point is adjusted in real time based on the first target data, the static weight being determined based on the historical inspection records, real-time operation parameters, and device parameters, and the dynamic weight being determined based on the inspection waiting time, inspection consuming time, device operation parameters, fault information, and external influence score of the to-be-inspected point, wherein the external influence score is determined by the to-be-inspected point before inspection; thereafter, a random path is generated as an initial population based on each to-be-inspected point, an adaptive function is constructed based on the static weight and dynamic weight of each to-be-inspected point, and optimization is performed through a genetic algorithm to obtain a target inspection path; finally, the target inspection path is sent to a terminal device carried by an inspection personnel to realize real-time updating of the inspection route of the work personnel. By adjusting the dynamic weight of the inspection point in real time and combining the genetic algorithm for optimal route planning, not only the static importance of the device is considered, but also the real-time changes of the device state in the substation are flexibly responded to, ensuring the optimization of the inspection route, reducing the influence of device faults on power grid operation, improving the work efficiency of the work personnel and the operation and maintenance management level of the substation, and solving the problem of low inspection efficiency in the existing technology when the inspection route cannot be effectively adjusted when a sudden situation or device problem occurs during substation inspection. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 Fig. 1 shows a hardware structure block diagram of a mobile terminal according to the route control method for substation inspection provided in an embodiment of the present application;

[0018] Figure 2 Fig. 2 shows a flowchart of a route control method for substation inspection according to an embodiment of the present application;

[0019] Figure 3 Fig. 3 shows a structure block diagram of a route control device for substation inspection according to an embodiment of the present application.

[0020] Wherein, the above-mentioned drawings include the following reference signs:

[0021] 102, processor; 104, memory; 106, transmission device; 108, input and output device. DETAILED DESCRIPTION

[0022] It should be noted that the embodiments and features in the present application can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0023] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, not necessarily to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0025] As introduced in the background, the existing intelligent inspection method of transformer substation is difficult to realize real-time dynamic optimization of inspection path. In order to solve the problem that the existing transformer substation inspection process cannot effectively adjust the inspection route when encountering sudden conditions or equipment problems, resulting in low inspection efficiency, the embodiments of the present application provide a route control method, control device, computer readable storage medium and inspection control system for transformer substation inspection.

[0026] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking the case of running on a mobile terminal, Figure 1 is a hardware structure block diagram of a mobile terminal of a route control method for transformer substation inspection according to an embodiment of the present application. As shown in Figure 1As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0028] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the device information display method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] This embodiment provides a route control method for substation inspection that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0030] Figure 2 This is a flowchart of a route control method for substation inspection according to an embodiment of this application.Figure 2 The method comprises the following steps:

[0031] In step S201, real-time relevant data of each inspection point in the substation is acquired to obtain corresponding first target data, wherein the first target data includes environmental parameters, historical inspection records, device parameters, fault information and real-time operation parameters of the inspection point.

[0032] Specifically, environmental information, historical inspection information, device basic information, fault information, real-time running state and other data related to the inspection point are acquired to obtain the first target data.

[0033] In a specific implementation, the system collects internal environmental information of the substation in real time through an integrated sensor network (including but not limited to temperature sensors, humidity sensors, vibration sensors, cameras, etc.), such as temperature, humidity, device vibration conditions, etc. These information can reflect the current running environmental conditions of the device. Secondly, historical inspection records are queried through a database, including device fault history, maintenance records, device running time, etc. These data are used to assess the potential fault risk of the device. Thirdly, device basic information (such as device type, importance level, location, etc.) and current fault information (such as device status, fault alarm) are also collected to determine the importance and urgency of the device. Finally, the system also acquires the running state of the substation device in real time, including voltage, current, temperature and other key parameters to ensure the real-time and accuracy of the data.

[0034] In step S202, static weights of each inspection point are determined based on the first target data, and dynamic weights of each inspection point are adjusted in real time based on the first target data. The static weights are determined based on the historical inspection records, real-time operation parameters and device parameters. The dynamic weights are determined based on the inspection waiting time, inspection consuming time, device running parameters, fault information and external influence score of the inspection point, wherein the external influence score is determined by the inspection point before the inspection.

[0035] Specifically, according to the relevant data of the inspection point, the static weight and the dynamic weight of the inspection point are determined. The static weight is calculated according to the urgency and the importance of the device. The dynamic weight is adjusted according to the waiting time, the urgency, the inspection time and the external influence factors, and is updated and calculated after each change of the inspection point.

[0036] In a specific implementation, the calculation of the static weight is based on inherent attributes and historical data of the equipment. For example, equipment A is assigned a higher w1 (urgency weight) and w2 (equipment importance weight) because of its critical function and failure frequency, resulting in a higher static weight. The dynamic weight is more complex and is adjusted according to real-time conditions of the inspection operation, such as the current waiting time, the real-time urgency of equipment A (based on failure information and real-time operating status), the estimated inspection time (taking into account the complexity of the equipment and the difficulty of inspection), and the prediction of the impact of external emergencies on equipment A (through a recurrent neural network RNN). After completing each inspection point, the system recalculates the dynamic weight of all un-inspected points based on the latest information to ensure the optimality of the route planning.

[0037] In step S203, a random path is generated as an initial population based on each of the above-mentioned to-be-inspected points, an adaptive function is constructed based on the above-mentioned static weight and the above-mentioned dynamic weight corresponding to each of the above-mentioned to-be-inspected points, and an optimal inspection path is obtained through genetic algorithm optimization.

[0038] Specifically, the genetic algorithm is used to generate an optimal inspection route according to the static weight and the dynamic weight.

[0039] In a specific implementation, the process of the genetic algorithm includes initialization of the population, selection, crossover and mutation operations, and evaluation of the adaptive function. Specifically, the system first generates an initial population, with each individual representing a possible inspection path. The adaptive function takes into account the length of the path and the priority of each inspection point to evaluate the quality of the path. The selection operation is based on the results of the adaptive function, so that paths with higher adaptability have a greater chance of being selected for genetic operation. The crossover operation intelligently selects crossover points and uses the dynamic weight change range to guide the selection of crossover points, increasing the intelligence and adaptability of the algorithm. The mutation operation selects paths with lower adaptability for local adjustment under new dynamic weights to accelerate the search for the optimal path. Through multiple generations of genetic operations, an optimal inspection route is finally obtained.

[0040] In step S204, the above-mentioned target inspection path is sent to the terminal device carried by the inspection personnel to realize real-time updating of the inspection route of the above-mentioned operation personnel.

[0041] Specifically, during the inspection process, the inspection route is updated in real time according to the dynamic adjustment of external emergencies.

[0042] In a specific implementation, in an actual inspection process, the system collects state information of each inspection point in real time through a terminal device worn by an operator. If an external emergency occurs in the substation, such as power grid fluctuation, extreme weather conditions, etc., the recurrent neural network predicts the external influence of the emergency on subsequent un-inspected points. Based on the updated dynamic weight (considering the new score of external influence), the system recalculates the priority of all un-inspected points and quickly generates a new optimal inspection route using a genetic algorithm. After the operator's terminal device receives the adjusted route, the operator immediately inspects according to the new route, ensuring inspection efficiency and equipment safety under the influence of the emergency.

[0043] Through the embodiment, first, relevant data of each to-be-inspected point in the substation is acquired in real time to obtain corresponding first target data, the first target data including environmental parameters, historical inspection records, device parameters, fault information, and real-time operation parameters of the to-be-inspected point; then, static weights of each to-be-inspected point are determined based on the first target data, and dynamic weights of each to-be-inspected point are adjusted in real time based on the first target data, the static weights being determined based on the historical inspection records, the real-time operation parameters, and the device parameters, the dynamic weights being determined based on a waiting time for inspection, a consumed time for inspection, the device operation parameters, the fault information, and an external influence score of the to-be-inspected point, wherein the external influence score is determined by the to-be-inspected point before inspection; thereafter, a random path is generated as an initial population based on each to-be-inspected point, an adaptive function is constructed based on the static weights and the dynamic weights corresponding to each to-be-inspected point, and optimization is performed through a genetic algorithm to obtain a target inspection path; finally, the target inspection path is sent to a terminal device carried by an inspector to realize real-time updating of an inspection route of the operator. The application adjusts the dynamic weights of the inspection points in real time, plans an optimal route through a genetic algorithm, considers not only the static importance of the equipment but also real-time changes in the state of the equipment in the substation, ensures optimization of the inspection route, reduces the influence of equipment failure on power grid operation, improves the work efficiency of the operator and the operation and maintenance management level of the substation, and solves the problem in the prior art that when an emergency or equipment problem occurs during substation inspection, the inspection route cannot be effectively adjusted, resulting in low inspection efficiency.

[0044] To determine the static weights, in an optional implementation, the step S202 includes:

[0045] In step S20201, a historical failure rate of the to-be-inspected point is determined based on the historical inspection records, and a fault repair time of the to-be-inspected point is estimated based on the real-time operation parameters;

[0046] Specifically, based on historical inspection records, the historical failure rate of each point to be inspected is determined. The historical failure rate refers to the proportion of the number of failures of the point (device) to the total number of inspections in a certain period of time (such as one year, half a year), which can reflect the reliability of the device. The failure repair time of the point to be inspected is estimated by real-time running parameters (such as the running temperature, voltage, current, etc. of the device). The estimation method can combine device type, historical maintenance records and current failure situation, and use statistical models or machine learning algorithms for prediction.

[0047] Step S20202, scoring based on the historical failure rate and the failure repair time, and weighting calculation based on the scoring result to obtain the emergency degree;

[0048] Specifically, the historical failure rate and the failure repair time are used as the core indicators for emergency degree scoring. The higher the historical failure rate, the more likely the device will fail again in the short term, and the higher the score; the longer the failure repair time, the greater the impact of the device failure, and the higher the score.

[0049] In specific implementation, weighting calculation is performed to obtain the score of the emergency degree. The weighting coefficients can be adjusted according to the type, importance of the device, and the potential impact on the stability of the power system, to ensure that the score accurately reflects the emergency degree of the device. For example, emergency degree = w3*historical failure rate + w4*failure repair time, where w3 and w4 are the weight parameters of the historical failure rate and the failure repair time, respectively.

[0050] Step S20203, determining the failure impact range, failure impact degree and device availability of the point to be inspected based on the device parameters, determining the device running record of the point to be inspected based on the device running parameters, and obtaining the device cost of the point to be inspected;

[0051] Specifically, the failure impact range, failure impact degree and device availability of the point to be inspected are determined according to the device parameters. The failure impact range refers to the range of other devices or areas that may be affected by the device failure; the failure impact degree reflects the degree of impact of the failure on system operation; the device availability refers to the probability of normal operation of the device within the predicted period. The device running record is determined according to the device running parameters, including the running time, maintenance record, failure frequency, etc. of the device, which can reflect the running state and maintenance demand of the device. The device cost of the point to be inspected is obtained, including the purchase cost and maintenance cost, and the higher the cost of the device, the more important it is.

[0052] Step S20204, scoring based on the failure impact range, the failure impact degree, the device availability, the device running record and the device cost, and weighting calculation based on the scoring result to obtain the device importance;

[0053] Specifically, the device importance score is obtained by weighting calculation based on the above indicators. For example, device importance = w5*failure impact range + w6*failure impact degree + w7*device availability + w8*device cost, where w5, w6, w7 and w8 are weight parameters of failure impact range, failure impact degree, device availability and device cost, respectively.

[0054] Step S20205, the static weight is obtained by weighting calculation based on the above emergency degree and the above device importance.

[0055] Specifically, the static weight is obtained by weighting calculation based on the emergency degree score and the device importance score. For example, static weight = w1*emergency degree + w2*device importance, where w1 and w2 are weight parameters of emergency degree and device importance, which can be adjusted according to specific circumstances.

[0056] In order to obtain the above dynamic weight, in an optional embodiment, the above step S202 further comprises:

[0057] Step S20206, the inspection waiting time is obtained by determining the time length that the work personnel is expected to consume from the current position to the to-be-inspected point based on the current inspection route;

[0058] Specifically, the system calculates the time that is expected to be consumed from the current position to each to-be-inspected point based on the current position and the expected travel speed of the work personnel, i.e. the inspection waiting time. This calculation takes into account the layout of the substation and the shortest path for the work personnel to move to each device point, ensuring the accuracy of the time estimation.

[0059] Step S20207, the inspection consumption time is obtained by determining the average maintenance time of the to-be-inspected point based on the historical inspection records;

[0060] Specifically, according to the historical inspection records, the system analyzes and determines the average maintenance time of each to-be-inspected point, i.e. the inspection consumption time. This average value reflects the time required for possible device inspection, maintenance or minor repair work during actual inspection.

[0061] Step S20208, the damage probability of the to-be-inspected point is determined based on the device operation parameters, and the emergency degree of the to-be-inspected point is determined according to the damage probability;

[0062] Specifically, based on real-time device operating parameters, the system estimates the damage probability of each point to be inspected, i.e., the possibility of device failure in the current or future period of time. According to the damage probability, the system further determines the emergency level score of each point, and a high damage probability will result in a high emergency level score. The calculation of the emergency level also needs to combine the importance of the device and the impact range of the failure to comprehensively evaluate the potential consequences of device failure.

[0063] Step S20209, determining the point changed in the previous inspection route before the point to be inspected in the current inspection route to obtain a target point, and determining the external influence score based on the emergency corresponding to the target point;

[0064] Specifically, the system identifies the point changed in the previous inspection route before the point to be inspected in the current inspection route, i.e., the target point. For each target point, the external influence score is calculated by analyzing the influence degree of the emergency related thereto. The external influence score reflects the influence of the current emergency on the un-inspected device, including but not limited to the influence of power grid fluctuation and adverse weather, etc.

[0065] Step S20210, scoring based on the inspection waiting time, the inspection consumption time and the emergency level respectively, and calculating the dynamic weight according to the scoring results and the external influence score.

[0066] Specifically, the inspection waiting time, the inspection consumption time, the emergency level score and the external influence score are quantitatively scored respectively, and the scoring standard can be set based on historical data and expert experience. According to the scoring results of each factor, the weighted formula is used for calculation to obtain the dynamic weight of the point to be inspected. The dynamic weight formula is: dynamic weight = w9inspection waiting time + w10inspection consumption time + w11emergency level score + w12external influence score, wherein w9, w10, w11and w12are weight parameters of the inspection waiting time, the inspection consumption time, the emergency level score and the external influence score, respectively.

[0067] In the above embodiment, the real-time update of the dynamic weight will affect the priority ranking of the points to be inspected in the genetic algorithm and the calculation of the fitness function. The system combines the dynamic weight with the static weight to reevaluate the fitness of all inspection routes and select and generate a better inspection path.

[0068] In order to construct the initial population and the fitness function, in an optional implementation, the above step S203 includes:

[0069] Step S20301: Randomly encode each of the above-mentioned inspection points in the above-mentioned substation to obtain multiple coding sequences, and determine each of the above-mentioned coding sequences as chromosomes. The coding sequences include the codes corresponding to all the above-mentioned inspection points in the above-mentioned substation.

[0070] Specifically, in the random path generation and encoding process, the system first generates multiple encoded sequences containing all points to be inspected through randomization. Each encoded sequence represents a possible inspection route, and the positional order in the sequence reflects the access order of the inspection points. These encoded sequences are then converted into chromosomes.

[0071] Step S20302: Each of the above chromosomes is used as an alternative inspection path to obtain the initial population;

[0072] Specifically, an initial population is constructed based on the aforementioned chromosomes. Each chromosome in the population represents an inspection route plan, containing information on all points in the substation to be inspected.

[0073] Step S20303: Substitute the above static weights and the above dynamic weights into the first preset formula p(v) i ) = w 静态 (v i )*w 动态 (v i ), thus obtaining the priority of the above inspection points, w 静态 (v i ) represents the static weights of node vi, w 动态 (v i ) represents the dynamic weight of node vi for iteration number t, w 动态 (v i )satisfy Where w 动态 (v i ,0) is the initial dynamic weight of node vi, t is the current iteration number, and tmax is the maximum iteration number;

[0074] Specifically, the integrated system of static and dynamic weights incorporates the static and dynamic weights of each inspection point into the priority calculation. The dynamic weight changes with the real-time status of the inspection point, reflecting its current urgency and maintenance needs. The calculation of the dynamic weight takes into account the impact of the iteration number t. As t increases, the dynamic weight wdynamic(vi,t) gradually approaches the static weight wstatic(vi), ensuring that the static weight's influence on priority gradually increases in the later stages of the iteration process, which helps to stabilize the search for the optimal path.

[0075] Step S20304: Substitute the priority into the second preset formula for priority penalty. Receive priority penalty, where x is chromosome x, vi for the i-th node in the path corresponding to chromosome x, n is the total number of nodes included in chromosome x;

[0076] Specifically, for each chromosome x in the population, the system calculates the priority p(vi), which integrates the static weight and the dynamic weight, reflecting the comprehensive priority of the inspection point vi under the current iteration. The calculation of the priority penalty P(x) is based on the priority order of all nodes in chromosome x. If the nodes with higher priority in path x are placed after the nodes with lower priority, the penalty term will increase to reflect the suboptimality of the path planning.

[0077] Step S20305, based on the chromosome and the above priority penalty, the above fitness function is constructed:

[0078]

[0079] where path length(x) is the total length of the inspection path corresponding to chromosome x, ε is a positive number less than the first threshold, and α is a weight coefficient.

[0080] Specifically, according to the path length and the priority penalty, the system constructs the fitness function F(x). The path length(x) is the total length of the inspection path corresponding to chromosome x, which reflects the physical distance of the inspection route. The design of the fitness function F(x) ensures the balance between the path length and the priority penalty. α is a weight coefficient, used to adjust the relative importance of the path length and the priority penalty, which can be adjusted according to actual needs. ε is a very small positive number, used to avoid the error of division by zero in the fitness function when the priority penalty term is zero. This small value ensures that even if the path priority is excellent, the fitness function will not be infinite, but will remain within a reasonable range.

[0081] In the above embodiment, a genetic algorithm fitness function construction method is provided, which considers the static weight and dynamic weight comprehensively, effectively balances the relationship between the length of the inspection route and the priority of the point, and ensures the efficiency and flexibility of the inspection operation. When dealing with substation inspection route planning problems, this method can dynamically adjust the priority according to the real-time state of the equipment and the external environmental changes, and quickly find the optimal inspection route through genetic algorithm iteration.

[0082] In order to determine the optimal path, the above target inspection path is obtained by optimization through genetic algorithm. In an optional implementation, the above step S203 further comprises:

[0083] Step S20306, selection step, based on the current population, performing a selection operation, selecting a predetermined number of chromosomes from the current population based on the above fitness, as parent individuals;

[0084] Specifically, in the current population, the system performs a selection operation based on the fitness value of each chromosome (i.e., the inspection path). The higher the fitness value of a chromosome, the greater the probability of being selected as a parent individual. The selection operation usually adopts roulette wheel selection or tournament selection. In roulette wheel selection, the probability of each chromosome being selected is proportional to its fitness value; while in tournament selection, a few chromosomes are randomly selected from the population for comparison, and the chromosome with the highest fitness value is selected as the parent individual. A predetermined number of chromosomes are selected as parent individuals to ensure the diversity of the population while reducing the population size and improving the execution efficiency of the algorithm.

[0085] Step S20307, a crossover step, performing a crossover operation based on the parent individuals to obtain offspring individuals;

[0086] Specifically, for the selected parent individuals, the system performs a crossover operation to generate new offspring individuals. The crossover operation can be single-point crossover, multi-point crossover or uniform crossover, depending on the encoding method of the chromosome and the characteristics of the problem. The crossover operation generates two or more new offspring individuals by exchanging part of the chromosome information between parent individuals, which contain inherited characteristics from the parents but different orders or combinations, thereby exploring new solution spaces.

[0087] Step S20308, a mutation step, performing a mutation operation based on the parent individuals and the offspring individuals to obtain an updated population;

[0088] Specifically, the mutation operation is performed on the parent individuals and offspring individuals by randomly changing some genes in the chromosomes to introduce new changes and improve the exploration ability of the population. The frequency and intensity of the mutation operation need to be moderate to avoid premature convergence of the population or falling into local optima, while promoting the search process of the global optimal solution.

[0089] Step S20309, a calculation step, calculating the fitness of each chromosome in the updated population;

[0090] Specifically, after the crossover and mutation operations are completed, the system recalculates the fitness values of all chromosomes to evaluate the quality of the inspection routes of the newly generated offspring individuals and the mutated individuals. According to the newly calculated fitness values, the system combines the parent individuals and offspring individuals into an updated population. This process may involve the elimination of some individuals to ensure that individuals with higher fitness remain in the population.

[0091] Step S20310, repeating the selection step, the crossover step, the mutation step and the mutation step at least once in turn until the deviation of the maximum fitness value in the updated population of the adjacent two iterations is less than a predetermined proportion or the maximum number of iterations is reached.

[0092] Specifically, the system repeatedly performs the operations of selection, crossover, mutation, and updating the population, and recalculates the fitness values of all chromosomes in the updated population after each iteration. The optimization process will continue until the stopping conditions are met. The stopping conditions include: the deviation of the maximum fitness value in the updated population between two adjacent iterations is less than a preset proportion, indicating that the algorithm has approached the optimal solution; or the maximum number of iterations is reached to prevent the algorithm from running indefinitely.

[0093] Through the implementation of the above steps, the genetic algorithm can effectively find the optimal inspection path that adapts to dynamic environmental changes, not only improving the flexibility and efficiency of substation inspection operations, but also ensuring timely maintenance of critical equipment and stable operation of the power system. This process fully considers the real-time state of equipment, historical data, and external environmental factors, and achieves intelligentization and adaptability of inspection route planning through intelligent selection and optimization mechanisms.

[0094] In the above embodiment, as a preferred solution, the above-mentioned crossover operation is performed in a preset range centered on the above-mentioned to-be-inspected point with a dynamic weight difference greater than the second threshold value in the adjacent two iterations.

[0095] Specifically, intelligent selection is guided by the change range of dynamic weight. In each iteration, the system calculates the dynamic weight of all to-be-inspected points and compares it with the dynamic weight of the last iteration. A large dynamic weight difference of a point indicates that the priority of the point has changed significantly in a short time, which may be caused by equipment state abnormalities, external sudden events, or other important factors. The preset range determines that the system sets a preset range, usually centered on the point with the largest dynamic weight change, and the size of this range is determined by the second threshold value. The second threshold value is a pre-set parameter for judging whether the dynamic weight change is sufficient to trigger intelligent crossover operation. The setting of the preset range ensures that the crossover operation can focus on the vicinity of the points with the largest weight change, and use these change information to optimize the inspection route. Intelligent selection of crossover points When the system detects that the dynamic weight difference of a to-be-inspected point is greater than the second threshold value, it will preferentially perform crossover operation in the preset range centered on the point. This selection mechanism can quickly respond to weight changes and generate offspring individuals that better meet the current priority requirements by exchanging information about related nodes on the chromosomes.

[0096] The above-mentioned embodiments improve the efficiency and adaptability of the algorithm. The cross operation based on weight change can more efficiently utilize information in substation inspection route planning, reduce unnecessary search, speed up convergence, maintain population diversity, and avoid the trap of local optimal solution. However, the system should also consider using alternative solutions in certain situations, such as when the dynamic weight change of all points is not sufficient to trigger intelligent crossover. In this case, random crossover based on fixed probability or crossover based on chromosome fitness can be used to maintain population diversity and avoid premature convergence of the algorithm.

[0097] In the above-mentioned embodiments, as a preferred solution, the mutation operation is performed on the points to be inspected corresponding to the priority less than the third threshold.

[0098] The third threshold is used to filter out points to be inspected with lower priority. After each dynamic weight update, the system recalculates the priority score of all points to be inspected. The priority score takes into account both static and dynamic weights, reflecting the current urgency and importance of the equipment. Points with lower scores may be identified due to stable equipment status, low maintenance needs, or less external influence. The system selects points with priority scores below the third threshold as the target of mutation operation. This selection mechanism ensures that the algorithm can focus on optimizing points with lower current priority, improving their priority score or adjusting their position in the inspection route through mutation operation, thereby better adapting to changes in inspection needs.

[0099] In specific implementation, the algorithm may adopt one of the following mutation methods:

[0100] a. Point replacement: replace a point with lower priority with another point with higher priority to improve the priority balance of the overall route.

[0101] b. Position adjustment: in the chromosome, move a point with lower priority to a more forward position to perform inspection in advance to respond to possible equipment status changes.

[0102] c. Attribute modification: indirectly improve the priority of a point by adjusting some of its attributes (such as a factor score in the dynamic weight), which may involve machine learning model prediction or rule adjustment.

[0103] The prior art usually adopts random mutation or mutation operation based on fixed probability, while the present invention introduces a priority threshold to guide mutation, achieving optimization of mutation operation. It not only considers the dynamic state of the equipment and external influences, but also avoids population degradation caused by blind mutation by intelligently selecting mutation points, making the genetic algorithm more efficient and intelligent in solving substation inspection route planning problems.

[0104] In order for those skilled in the art to more clearly understand the technical solutions of the present application, the implementation process of the substation inspection route control method of the present application will be described in detail below in conjunction with specific embodiments.

[0105] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0106] The present application also provides a substation inspection route control device, it should be noted that the substation inspection route control device of the present application can be used to execute the substation inspection route control method provided by the present application. The device is used to realize the above-mentioned embodiments and preferred embodiments, which have been described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware implementation is also possible and is contemplated.

[0107] The substation inspection route control device provided by the present application is described below.

[0108] Figure 3 is a structural block diagram of the substation inspection route control device according to the present application. As shown in Figure 3 , the device comprises:

[0109] The first acquisition unit 10 is configured to acquire the relevant data of each to-be-inspected point in the substation in real time, and obtain the corresponding first target data. The first target data includes the environmental parameters, historical inspection records, device parameters, fault information and real-time operation parameters of the to-be-inspected point.

[0110] Specifically, the environmental information, historical inspection information, device basic information, fault information, real-time running state and other data related to the inspection point are acquired. The first target data is obtained.

[0111] In a specific implementation, the system collects real-time environmental information inside the substation through an integrated sensor network, including but not limited to temperature sensors, humidity sensors, vibration sensors, cameras, etc. For example, temperature, humidity, equipment vibration, etc. These information can reflect the current running environment of the equipment. Secondly, through database query historical inspection records, including equipment fault history, maintenance records, equipment running time, etc. These data are used to assess the potential failure risk of the equipment. Thirdly, the basic information of the equipment (such as equipment type, importance level, location, etc.) and the current fault information (such as equipment status, fault alarm) are also collected to determine the importance and urgency of the equipment. Finally, the system also acquires the running state of the substation equipment in real time, including voltage, current, temperature and other key parameters to ensure the real-time and accuracy of the data.

[0112] The first computing unit 20 is configured to determine a static weight of each of the to-be-inspected points based on the first target data, and adjust a dynamic weight of each of the to-be-inspected points in real time based on the first target data. The static weight is determined based on the historical inspection records, the real-time running parameters and the equipment parameters. The dynamic weight is determined based on a waiting time for inspection, a time consumed for inspection, the equipment running parameters, the fault information and an external influence score of each of the to-be-inspected points, wherein the external influence score is determined by the to-be-inspected points before inspection.

[0113] Specifically, according to the relevant data of the inspection points, the static weight and the dynamic weight of the inspection points are determined. The static weight is calculated according to the emergency level and the equipment importance. The dynamic weight is adjusted according to the waiting time, the emergency level, the inspection time and the external influence factors, and is updated and calculated after each change of the inspection points.

[0114] In a specific implementation, the calculation of the static weight is based on the inherent properties and historical data of the equipment. For example, equipment A is given a higher w1 (emergency level weight) and w2 (equipment importance weight) because of its key function and failure frequency, so as to obtain a higher static weight. The dynamic weight is more complex, which is adjusted according to the real-time situation of the inspection operation, such as the current waiting time, the real-time emergency level of equipment A (based on the fault information and the real-time running state), the estimated inspection time (considering the complexity of the equipment and the difficulty of the inspection), and the influence prediction of external sudden events on equipment A (through recurrent neural network RNN). After completing each inspection point, the system recalculates the dynamic weight of all un-inspected points according to the latest information to ensure the optimality of the route planning.

[0115] The second computing unit 30 is configured to generate a random path as an initial population based on each of the to-be-inspected points, construct a fitness function based on the static weight and the dynamic weight corresponding to each of the to-be-inspected points, and obtain a target inspection path through genetic algorithm optimization.

[0116] Specifically, the genetic algorithm is used to generate an optimal inspection route according to the static weight and the dynamic weight.

[0117] In a specific implementation, the process of the genetic algorithm includes initialization of a population, selection, crossover and mutation operations, and evaluation of a fitness function. Specifically, the system first generates an initial population, and each individual represents a possible inspection path. The fitness function comprehensively considers the length of the path and the priority of each inspection point to evaluate the pros and cons of the path. The selection operation is based on the results of the fitness function, so that paths with higher fitness have a greater chance of being selected for genetic operation. The crossover operation intelligently selects crossover points and uses the dynamic weight change range to guide the selection of the crossover points, thereby increasing the intelligence and adaptability of the algorithm. The mutation operation selects paths with lower fitness for local adjustment under new dynamic weights to accelerate the finding of the optimal path. Through multiple generations of genetic operations, the system finally converges to an optimal inspection route.

[0118] The sending unit is configured to send the target inspection path to a terminal device carried by an inspection personnel, so as to realize real-time updating of the inspection route of the inspection personnel.

[0119] Specifically, during the inspection process, the inspection route is updated in real time according to the dynamic adjustment of external emergencies.

[0120] In a specific implementation, during the actual inspection process, the system collects the state information of each inspection point in real time through the terminal device worn by the inspection personnel. If an external emergency occurs at the substation, such as power grid fluctuation, extreme weather conditions, etc., the recurrent neural network predicts the external influence of the emergency on the subsequent un-inspected points. Based on the updated dynamic weight (considering the new score of the external influence), the system recalculates the priority of all un-inspected points and quickly generates a new optimal inspection route using the genetic algorithm. After receiving the adjusted route, the inspection personnel terminal device immediately inspects according to the new route, ensuring the inspection efficiency and equipment safety under the influence of the emergency.

[0121] Through the embodiment, the first acquisition unit acquires relevant data of each to-be-inspected point in the transformer substation in real time to obtain corresponding first target data, the first target data including an environmental parameter, a historical inspection record, a device parameter, fault information, and real-time operation parameters of the to-be-inspected point; the first calculation unit determines a static weight of each to-be-inspected point based on the first target data, and adjusts a dynamic weight of each to-be-inspected point in real time based on the first target data, the static weight being determined based on the historical inspection record, the real-time operation parameters, and the device parameter, the dynamic weight being determined based on an inspection waiting time, an inspection consuming time, the device operation parameter, the fault information, and an external influence score of the to-be-inspected point, wherein the external influence score is determined by the to-be-inspected point before inspection; the second calculation unit generates a random path as an initial population based on each to-be-inspected point, constructs a fitness function based on the static weight and the dynamic weight corresponding to each to-be-inspected point, and obtains a target inspection path through genetic algorithm optimization; and the sending unit sends the target inspection path to a terminal device carried by an inspection personnel to realize real-time updating of an inspection route of the work personnel. The application adjusts the dynamic weight of the inspection point in real time, and performs optimal route planning in combination with the genetic algorithm, which not only considers the static importance of the device, but also flexibly responds to real-time changes in the state of the device in the transformer substation, ensures the optimization of the inspection route, reduces the influence of device faults on power grid operation, improves the work efficiency of the work personnel and the operation and maintenance management level of the transformer substation, and solves the problem of low inspection efficiency in the existing technology when a sudden situation or device problem occurs during transformer substation inspection, which cannot effectively adjust the inspection route.

[0122] To determine the static weight, in an optional implementation, the first calculation unit includes:

[0123] A first determination module is configured to determine a historical failure rate of the to-be-inspected point based on the historical inspection record, and estimate a fault repair time of the to-be-inspected point based on the real-time operation parameters.

[0124] Specifically, the historical failure rate of each to-be-inspected point is determined based on the historical inspection record. The historical failure rate refers to the proportion of the number of failures of the point (device) to the total number of inspections in a certain period of time (such as one year, half a year), which can reflect the reliability of the device. The fault repair time of the to-be-inspected point is estimated based on the real-time operation parameters (such as the operating temperature, voltage, current, etc. of the device). The estimation method can combine device type, historical maintenance record, and current fault condition, and use a statistical model or a machine learning algorithm for prediction.

[0125] A first calculation module is configured to score based on the historical failure rate and the fault repair time, and perform weighted calculation based on the scoring result to obtain an emergency degree.

[0126] Specifically, the historical failure rate and the failure repair duration are taken as the core indicators of the emergency degree score. The higher the historical failure rate, the more likely the device will fail again in the short term, and the higher the score; the longer the failure repair duration, the greater the impact of the device failure, and the higher the score.

[0127] In specific implementation, weighting calculation is performed to obtain the score of the emergency degree. The weighting coefficients can be adjusted according to the type, importance, and potential impact on the stability of the power system of the device, to ensure that the score can accurately reflect the emergency degree of the device. For example, Emergency Degree=w3*Historical Failure Rate+w4*Failure Repair Duration, where w3 and w4 are the weight parameters of the historical failure rate and the failure repair duration, respectively.

[0128] The second determination module is configured to determine the failure impact range, the failure impact degree, and the device availability of the to-be-inspected point based on the device parameters, determine the device operation record of the to-be-inspected point based on the device operation parameters, and obtain the device cost of the to-be-inspected point.

[0129] Specifically, the failure impact range, the failure impact degree, and the device availability of the to-be-inspected point are determined based on the device parameters. The failure impact range refers to the range of other devices or areas that may be affected when the device fails; the failure impact degree reflects the degree of impact of the failure on the system operation; and the device availability refers to the probability that the device can normally operate within the prediction period. The device operation record is determined based on the device operation parameters, and the operation record includes the operation time, maintenance record, and failure frequency of the device, which can reflect the operation state and maintenance demand of the device. The device cost of the to-be-inspected point is obtained, and the device cost includes the purchase cost and the maintenance cost. The higher the cost of the device, the more important it is.

[0130] The second calculation module is configured to score based on the failure impact range, the failure impact degree, the device availability, the device operation record, and the device cost, and perform weighting calculation based on the scoring result to obtain the device importance.

[0131] Specifically, the above indicators are combined for weighting calculation to obtain the score of the device importance. For example, Device Importance=w5*Failure Impact Range+w6*Failure Impact Degree+w7*Device Availability+w8*Device Cost, where w5, w6, w7, and w8 are the weight parameters of the failure impact range, the failure impact degree, the device availability, and the device cost, respectively.

[0132] The third calculation module is configured to perform weighting calculation based on the emergency degree and the device importance to obtain the static weight.

[0133] Specifically, the emergency level score and the equipment importance score are weighted to obtain a static weight. For example, static weight = w1*emergency level + w2*equipment importance, where w1 and w2 are weight parameters of the emergency level and the equipment importance, which can be adjusted according to specific circumstances.

[0134] To obtain the above dynamic weight, in an optional embodiment, the first calculation unit further comprises:

[0135] A third determination module is configured to determine, based on a current inspection route, a time length expected to be consumed by the inspection personnel from a current position to reach the to-be-inspected point, to obtain the inspection waiting time length.

[0136] Specifically, the system calculates the time expected to be consumed from the current position to reach each to-be-inspected point based on the current position and the expected travel speed of the inspection personnel, i.e., the inspection waiting time length. This calculation takes into account the layout of the substation and the shortest path for the inspection personnel to move to each equipment point, ensuring the accuracy of the time estimation.

[0137] A fourth determination module is configured to determine, based on the historical inspection records, an average maintenance time length of the to-be-inspected point, to obtain the inspection consumption time length.

[0138] Specifically, according to the historical inspection records, the system analyzes and determines the average maintenance time length of each to-be-inspected point, i.e., the inspection consumption time length. This average value reflects the time required for possible equipment inspection, maintenance, or minor repair work during actual inspection.

[0139] A fifth determination module is configured to determine a damage probability of the to-be-inspected point based on the equipment operation parameters, and determine the emergency level of the to-be-inspected point based on the damage probability.

[0140] Specifically, based on real-time equipment operation parameters, the system estimates the damage probability of each to-be-inspected point, i.e., the possibility of equipment failure in the current or future period of time. According to the damage probability, the system further determines the emergency level score of each point, and high damage probability will result in high emergency level score. The calculation of the emergency level also needs to be combined with the importance of the equipment and the impact range of the failure, to comprehensively evaluate the potential consequences of equipment failure.

[0141] A sixth determination module is configured to determine a point changed in the previous inspection route before the to-be-inspected point in the current inspection route, to obtain a target point, and determine the external influence score based on the sudden event corresponding to the target point.

[0142] Specifically, the system identifies the point in the current inspection route before the point in the previous inspection route that has changed, i.e., the target point. For each target point, the external influence score is calculated by analyzing the impact of the related sudden event. The external influence score reflects the impact of the current sudden event on the un-inspected equipment, including but not limited to the impact of power grid fluctuations and severe weather.

[0143] The fourth calculation module is configured to score based on the inspection waiting time, the inspection consumption time, and the emergency degree respectively, and to calculate a weighted score based on the score results and the external influence score to obtain the dynamic weight.

[0144] Specifically, the inspection waiting time, the inspection consumption time, the emergency degree score, and the external influence score are quantitatively scored respectively, and the scoring standards can be set based on historical data and expert experience. According to the scoring results of each factor, a weighted formula is used for calculation to obtain the dynamic weight of the point to be inspected. The dynamic weight formula is: dynamic weight = w9inspection waiting time + w10inspection consumption time + w11emergency degree score + w12external influence score, where w9, w10, w11, and w12 are weight parameters of the inspection waiting time, the inspection consumption time, the emergency degree score, and the external influence score, respectively.

[0145] In the above embodiment, the real-time updating of the dynamic weight will affect the priority ranking of the points to be inspected in the genetic algorithm and the calculation of the fitness function. The system combines the dynamic weight with the static weight to reevaluate the fitness of all inspection routes and select and generate a better inspection path.

[0146] In order to construct the initial population and the fitness function, in an optional implementation, the second calculation unit includes:

[0147] The seventh determination module is configured to randomly encode each of the points to be inspected in the substation to obtain a plurality of encoding sequences, and determine each of the encoding sequences as a chromosome, wherein the encoding sequence includes the codes corresponding to all the points to be inspected in the substation.

[0148] Specifically, the random path generation and coding, first, the system generates a plurality of encoding sequences containing all the points to be inspected by randomization. Each encoding sequence represents a possible inspection route, and the position order in the sequence reflects the access order of the inspection points. These encoding sequences are then converted into chromosomes.

[0149] The eighth determination module is configured to determine each of the chromosomes as an alternative inspection path to obtain an initial population.

[0150] Specifically, an initial population is constructed based on the aforementioned chromosomes. Each chromosome in the population represents an inspection route plan, containing information on all points in the substation to be inspected.

[0151] The fifth calculation module is used to substitute the aforementioned static weights and dynamic weights into the first preset formula p(v) i ) = w 静态 (v i )*w 动态 ( i v), to obtain the priority of the above inspection points, w 静态 (v i ) represents the static weights of node vi, w 动态 (v i ) represents the dynamic weight of node vi for iteration number t, w 动态 (v i )satisfy Where w 动态 (v i ,0) is the initial dynamic weight of node vi, t is the current iteration number, and tmax is the maximum iteration number;

[0152] Specifically, the integrated system of static and dynamic weights incorporates the static and dynamic weights of each inspection point into the priority calculation. The dynamic weight changes with the real-time status of the inspection point, reflecting its current urgency and maintenance needs. The calculation of the dynamic weight takes into account the impact of the iteration number t. As t increases, the dynamic weight wdynamic(vi,t) gradually approaches the static weight wstatic(vi), ensuring that the static weight's influence on priority gradually increases in the later stages of the iteration process, which helps to stabilize the search for the optimal path.

[0153] The sixth calculation module is used to apply priority penalties when substituting into the second preset formula based on priority. Receive priority penalty, where x is chromosome x, v i Let be the i-th node in the path corresponding to chromosome x, and n be the total number of nodes included in chromosome x;

[0154] Specifically, for each chromosome x in the population, the system calculates a priority p(vi), which combines static and dynamic weights to reflect the overall priority of the inspection point vi in ​​the current iteration. The priority penalty P(x) is calculated based on the priority order of all nodes in chromosome x. If a higher-priority node in path x is placed after a lower-priority node, the penalty term increases to reflect the imperfections in path planning.

[0155] The building block is used to construct the fitness function based on chromosomes and the aforementioned priority penalty:

[0156]

[0157] wherein the path length (x) is the total length of the inspection path corresponding to chromosome x, ε is a positive number less than the first threshold, and a is a weight coefficient.

[0158] Specifically, according to the path length and the priority penalty, the system constructs a fitness function F(x). The path length (x) is the total length of the inspection path corresponding to chromosome x, which reflects the physical distance of the inspection route. The design of the fitness function F(x) ensures the balance between the path length and the priority penalty. a is a weight coefficient, used to adjust the relative importance of the path length and the priority penalty, which can be adjusted according to actual needs. ε is a very small positive number, used to avoid the error of division by zero in the fitness function when the priority penalty term is zero. This small value ensures that even if the path priority is excellent, the fitness function will not be infinite, but will remain within a reasonable range.

[0159] In the above embodiment, a genetic algorithm fitness function construction method considering static weight and dynamic weight is provided, which effectively balances the relationship between the length of the inspection route and the priority of the point, and ensures the efficiency and flexibility of the inspection operation. When dealing with substation inspection route planning problems, this method can dynamically adjust the priority according to the real-time state of the equipment and the external environmental changes, and quickly find the optimal inspection route through genetic algorithm iteration.

[0160] In order to determine the optimal path, the above target inspection path is obtained by optimization through genetic algorithm. In an optional implementation, the second calculation unit further comprises:

[0161] A selection module is configured to perform a selection step, perform a selection operation based on the current population, select a preset number of chromosomes from the current population based on the fitness value, and select the chromosomes as parent individuals.

[0162] Specifically, in the current population, the system performs a selection operation based on the fitness value of each chromosome (i.e. inspection path). The higher the fitness value of the chromosome, the greater the probability of being selected as a parent individual. The selection operation usually adopts roulette selection or tournament selection. In the roulette selection, the probability of each chromosome being selected is proportional to its fitness value; while in the tournament selection, several chromosomes are randomly selected from the population for comparison, and the chromosome with the highest fitness value is selected as the parent individual. A preset number of chromosomes are selected as parent individuals to ensure the diversity of the population and reduce the population size, thereby improving the execution efficiency of the algorithm.

[0163] A first processing module is configured to perform a crossover step, perform a crossover operation based on the parent individuals, and obtain offspring individuals.

[0164] Specifically, for the selected parent individuals, the system performs a crossover operation to generate new offspring individuals. The crossover operation can be single-point crossover, multi-point crossover or uniform crossover, depending on the encoding method of the chromosome and the characteristics of the problem. The crossover operation generates two or more new offspring individuals by exchanging partial chromosome information between parent individuals, which contain inherited characteristics from the parents but in different orders or combinations, thereby exploring new solution spaces.

[0165] The second processing module is configured to perform a mutation step, and perform a mutation operation based on the parent individuals and the offspring individuals to obtain an updated population.

[0166] Specifically, the mutation operation is performed on the parent individuals and the offspring individuals, and new changes are introduced by randomly changing some genes in the chromosome to improve the exploration ability of the population. The frequency and intensity of the mutation operation need to be moderate to avoid premature convergence of the population or falling into a local optimum, while promoting the search process of the global optimal solution.

[0167] The seventh calculation module is configured to perform a calculation step, and calculate the fitness of each chromosome in the updated population.

[0168] Specifically, after the crossover and mutation operations are completed, the system recalculates the fitness values of all chromosomes to evaluate the quality of the inspection routes of the newly generated offspring individuals and the mutated individuals. According to the newly calculated fitness values, the system combines the parent individuals and the offspring individuals into an updated population. This process may involve the elimination of some individuals to ensure that individuals with higher fitness remain in the population.

[0169] The repeating module is configured to repeat the selection step, the crossover step, the mutation step and the mutation step at least once in turn until the deviation of the maximum fitness value in the updated population of the adjacent two iterations is less than a preset proportion or the maximum iteration number is reached.

[0170] Specifically, the system repeatedly performs the selection, crossover, mutation and population updating operations, and recalculates the fitness values of all chromosomes in the updated population after each iteration. The optimization process will continue until the stop condition is met. The stop conditions include: the deviation of the maximum fitness value in the updated population of the adjacent two iterations is less than a preset proportion, which indicates that the algorithm has approached the optimal solution; or the maximum iteration number is reached to prevent the algorithm from running indefinitely.

[0171] Through the implementation of the above steps, the genetic algorithm can effectively find the optimal inspection path that adapts to dynamic environmental changes, not only improving the flexibility and efficiency of substation inspection operations, but also ensuring timely maintenance of key equipment and stable operation of the power system. This process fully considers the real-time state of the equipment, historical data and external environmental factors, and realizes the intelligentization and adaptability of the inspection route planning through intelligent selection and optimization mechanisms.

[0172] The route control device for substation inspection includes a processor and a memory, and the first acquisition unit, the first calculation unit, the second calculation unit, and the sending unit are all stored in the memory as program units, and the corresponding functions are realized by the processor executing the program units stored in the memory. The modules are located in the same processor, or the modules are located in different processors in any combination.

[0173] The processor includes a core, and the core retrieves the corresponding program unit from the memory. The core can be one or more, and the efficiency of communication can be improved by adjusting the core parameters.

[0174] The memory can include non-permanent memory in a computer readable medium, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

[0175] The embodiment of the application provides a computer readable storage medium, and the computer readable storage medium includes a stored program, wherein the computer readable storage medium controls the device where the computer readable storage medium is located to execute the route control method for substation inspection when the program runs.

[0176] The embodiment of the application provides a processor, and the processor is used to run a program, wherein the processor executes the route control method for substation inspection when the program runs.

[0177] The embodiment of the application provides a communication system, and the communication system includes a first communication domain, a second communication domain processor, a memory, and a program stored in the memory and executable on the processor, and the processor executes the program to realize at least the steps of the route control method for substation inspection:

[0178] The application also provides a computer program product suitable for executing the program that initializes at least the steps of the route control method for substation inspection when executed on a data processing device.

[0179] It should be apparent to those skilled in the art that the modules or steps of the application described above can be implemented with a general purpose computer, and can be centralized in a single computer or distributed among a network of computers, and can be implemented with program code executable by a computer, and thus can be stored in a storage device and executed by a computer, and in some cases, the steps shown or described can be executed in a different order than shown or described, or can be implemented as separate integrated circuit modules or as a single integrated circuit module, and thus the application is not limited to any particular combination of hardware and software.

[0180] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can be in the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage media, etc.) embodying computer readable program code.

[0181] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0182] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0183] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams.Figure 1 one or more processes and / or functions specified in one or more blocks Figure 1 one or more processes and / or functions specified in one or more blocks

[0184] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0185] Memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, such as read-only memory (ROM), EPROM, and / or flash memory, etc. Memory is an example of computer readable storage media.

[0186] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0187] It should also be noted that the terms "comprising", "containing", or any other variant thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0188] From the above description, it can be seen that the above-mentioned embodiments of the present application achieve the following technical effects:

[0189] 1) The substation inspection route control method of the present application, first, the relevant data of each to-be-inspected point in the substation is obtained in real time to obtain the corresponding first target data, the first target data includes the environmental parameters, historical inspection records, device parameters, fault information and real-time operation parameters of the to-be-inspected point; Then, based on the first target data, the static weight of each to-be-inspected point is determined, and the dynamic weight of each to-be-inspected point is adjusted in real time based on the first target data, the static weight is determined based on the historical inspection records, the real-time operation parameters and the device parameters, the dynamic weight is based on the inspection waiting time, the inspection consumption time, the device operation parameters, the fault information and the external influence score of the to-be-inspected point, wherein the external influence score is determined by the to-be-inspected point before inspection; Then, a random path is generated based on each to-be-inspected point as an initial population, a fitness function is constructed based on the static weight and the dynamic weight of each to-be-inspected point, and the optimal path is obtained through genetic algorithm; Finally, the target inspection path is sent to the terminal device carried by the inspection personnel to realize the real-time update of the inspection route of the work personnel. The present application adjusts the dynamic weight of the inspection point in real time, and optimizes the route planning by combining the genetic algorithm, not only considers the static importance of the device, but also flexibly responds to the real-time changes of the device state in the substation, ensures the optimization of the inspection route, reduces the influence of device failure on power grid operation, improves the work efficiency of the work personnel and the operation and maintenance management level of the substation, solves the problem that in the prior art, when a sudden situation or device problem occurs during the substation inspection process, the inspection route cannot be adjusted effectively, resulting in low inspection efficiency.

[0190] 2) The route control device for substation inspection of the present application, a first acquisition unit acquires relevant data of each to-be-inspected point in the substation in real time to obtain corresponding first target data, the first target data includes the environmental parameters, historical inspection records, device parameters, fault information and real-time operation parameters of the to-be-inspected point; a first calculation unit determines the static weight of each to-be-inspected point based on the first target data, and simultaneously adjusts the dynamic weight of each to-be-inspected point in real time based on the first target data, the static weight is determined based on the historical inspection records, the real-time operation parameters and the device parameters, the dynamic weight is based on the inspection waiting time, the inspection consumption time, the device operation parameters, the fault information and the external influence score of the to-be-inspected point, wherein the external influence score is determined by the to-be-inspected point before inspection; a second calculation unit generates a random path as an initial population based on each to-be-inspected point, constructs an adaptive function based on the static weight and the dynamic weight corresponding to each to-be-inspected point, optimizes through a genetic algorithm, and obtains a target inspection path; a sending unit sends the target inspection path to a terminal device carried by an inspection personnel, so as to realize real-time updating of the inspection route of the work personnel. The present application adjusts the dynamic weight of the inspection point in real time, and optimizes the route by combining the genetic algorithm, not only considers the static importance of the device, but also flexibly responds to the real-time change of the device state in the substation, ensures the optimization of the inspection route, reduces the influence of device failure on power grid operation, improves the work efficiency of the work personnel and the operation and maintenance management level of the substation, and solves the problem of low inspection efficiency in the existing substation inspection process when encountering sudden conditions or device problems.

[0191] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Those skilled in the art can make various modifications and changes to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A route control method for substation inspection, characterized by, The method comprises the following steps: Real-time acquisition of relevant data of each to-be-inspected point in the substation, obtaining corresponding first target data, the first target data including environmental parameters, historical inspection records, device parameters, fault information and real-time operation parameters of the to-be-inspected point; Determine the static weight of each to-be-inspected point based on the first target data, and simultaneously adjust the dynamic weight of each to-be-inspected point based on the first target data, the static weight being determined based on the historical inspection records, the real-time operation parameters and the device parameters, the dynamic weight being determined based on the inspection waiting time, the inspection consumption time, the device operation parameters, the fault information and the external influence score of the to-be-inspected point, wherein the external influence score is determined by the to-be-inspected point before inspection; Generate a random path as an initial population based on each to-be-inspected point, construct an adaptive function based on the static weight and the dynamic weight corresponding to each to-be-inspected point, and obtain a target inspection path through genetic algorithm optimization; The target inspection path is sent to the terminal device carried by the inspection personnel to realize real-time updating of the inspection route of the work personnel; Determine the static weight of each to-be-inspected point based on the first target data, comprising: Determine the historical failure rate of the to-be-inspected point based on the historical inspection records, and estimate the fault repair time of the to-be-inspected point based on the real-time operation parameters; Score based on the historical failure rate and the fault repair time, and perform weighted calculation based on the scoring results to obtain the emergency level; Determine the fault influence range, fault influence degree and device availability of the to-be-inspected point based on the device parameters, determine the device operation record of the to-be-inspected point according to the device operation parameters, and obtain the device cost of the to-be-inspected point; Score based on the fault influence range, the fault influence degree, the device availability, the device operation record and the device cost, and perform weighted calculation based on the scoring results to obtain the device importance; Perform weighted calculation based on the emergency level and the device importance to obtain the static weight; Adjust the dynamic weight of each to-be-inspected point based on the first target data, comprising: Determine the time length that the work personnel is expected to consume from the current position to reach the to-be-inspected point based on the current inspection route, to obtain the inspection waiting time; Determine the average repair time of the to-be-inspected point based on the historical inspection records to obtain the inspection consumption time; Determine the damage probability of the to-be-inspected point based on the device operation parameters, and determine the emergency level of the to-be-inspected point according to the damage probability; Determine the target point by determining the point that has changed in the current inspection route and the previous inspection route of the to-be-inspected point, and determine the external influence score based on the sudden event corresponding to the target point; Score based on the inspection waiting time, the inspection consumption time and the emergency level respectively, and perform weighted calculation based on the scoring results and the external influence score to obtain the dynamic weight.

2. The method of claim 1, wherein, The random paths of the to-be-inspected points are generated as initial populations, and a fitness function is constructed based on the static weights and the dynamic weights corresponding to the to-be-inspected points, including: Randomly coding each to-be-inspected point in the transformer substation to obtain a plurality of coding sequences, and determining each coding sequence as a chromosome, the coding sequence including the codes corresponding to all the to-be-inspected points in the transformer substation; Each chromosome is taken as an alternative inspection path to obtain an initial population; based on the static weight and the dynamic weight, a first preset formula is substituted , to obtain the priority of the inspection point, is the static weight of the node for the iteration number t, is the dynamic weight of the node for the iteration number t, satisfies , wherein is the initial dynamic weight of the node , t is the current iteration number, and t max is the maximum iteration number; The priority is substituted into a second preset formula; , to obtain a priority penalty, wherein x is a chromosome x, is the i th node in the path corresponding to the chromosome x, and n is the total number of nodes included in the chromosome x. The fitness function is constructed based on the chromosomes and the priority penalty: ； Wherein, the path length (x) is the total length of the inspection path corresponding to the chromosome x, is a positive number less than the first threshold, and a is a weight coefficient.

3. The method of claim 2, wherein, Optimization is performed through a genetic algorithm to obtain a target inspection path, including: A selection step, based on the current population, performing a selection operation, selecting a preset number of chromosomes from the current population based on the fitness as parent individuals; A crossover step, based on the parent individuals, performing a crossover operation to obtain child individuals; A mutation step, based on the parent individuals and the child individuals, performing a mutation operation to obtain an updated population; A calculation step, based on all the chromosomes in the updated population, calculating the fitness of each chromosome; The selection step, the crossover step, the mutation step, and the mutation step are repeated in turn at least once until the maximum fitness value in the updated population of adjacent two iterations has a deviation less than a preset proportion or reaches a maximum iteration number.

4. The method of claim 3, wherein, The crossover operation is performed in a preset range centered on the to-be-inspected points whose dynamic weight difference is greater than a second threshold in adjacent two iterations.

5. The method of claim 3, wherein, The mutation operation is performed on the to-be-inspected points corresponding to the priority less than a third threshold.

6. A route control device for substation inspection, characterized by, The device includes: A first acquisition unit configured to acquire real-time related data of each to-be-inspected point in a transformer substation to obtain corresponding first target data, the first target data including environmental parameters, historical inspection records, device parameters, fault information, and real-time operation parameters of the to-be-inspected points; A first calculation unit configured to determine static weights of each to-be-inspected point based on the first target data, and simultaneously adjust dynamic weights of each to-be-inspected point in real time based on the first target data, the static weights being determined based on the historical inspection records, the real-time operation parameters, and the device parameters, and the dynamic weights being determined based on an inspection waiting time, an inspection consumption time, a device operation parameter, the fault information, and an external influence score of the to-be-inspected point, wherein the external influence score is determined by a pre-inspection sequence of the to-be-inspected point; A second calculation unit configured to generate random paths of the to-be-inspected points as initial populations, construct a fitness function based on the static weights and the dynamic weights corresponding to the to-be-inspected points, and perform optimization through a genetic algorithm to obtain a target inspection path; A sending unit configured to send the target inspection path to a terminal device carried by an inspection personnel to realize real-time updating of an inspection route of the inspection personnel; The first calculation unit includes: A first determination module configured to determine a historical failure rate of the to-be-inspected point based on the historical inspection records, and estimate a fault repair time of the to-be-inspected point based on the real-time operation parameters; The first calculation module is configured to score based on the historical failure rate and the failure repair duration, and to perform weighted calculation based on the scoring result to obtain an emergency degree. The second determination module is configured to determine a failure influence range, a failure influence degree and a device availability of the to-be-inspected point based on the device parameter, to determine a device operation record of the to-be-inspected point based on the device operation parameter, and to obtain a device cost of the to-be-inspected point. The second calculation module is configured to score based on the failure influence range, the failure influence degree, the device availability, the device operation record and the device cost, and to perform weighted calculation based on the scoring result to obtain a device importance. The third calculation module is configured to perform weighted calculation based on the emergency degree and the device importance to obtain the static weight. The first calculation unit further includes: The third determination module is configured to determine a time length that the work personnel is expected to consume from a current position to the to-be-inspected point based on a current inspection route to obtain an inspection waiting time length. The fourth determination module is configured to determine an average repair time length of the to-be-inspected point based on the historical inspection record to obtain an inspection consuming time length. The fifth determination module is configured to determine a damage probability of the to-be-inspected point based on the device operation parameter, and to determine an emergency degree of the to-be-inspected point based on the damage probability. The sixth determination module is configured to determine a point that is changed in the current inspection route before the to-be-inspected point and in a previous inspection route to obtain a target point, and to determine an external influence score based on a sudden event corresponding to the target point. The fourth calculation module is configured to score based on the inspection waiting time length, the inspection consuming time length and the emergency degree respectively, and to perform weighted calculation based on the scoring result and the external influence score to obtain the dynamic weight.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium includes a stored program, wherein the program controls the device where the computer readable storage medium is located to perform the method of any one of claims 1 to 5 when the program is running.

8. A patrol control system characterized by comprising: The one or more processors, the memory, and the one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a program for performing the method of any one of claims 1 to 5. ​

Images