Transformer substation inspection method and system and electronic equipment

Abstract

The invention discloses a substation inspection method, a substation inspection system and electronic equipment. The method relates to the field of electric power, and comprises the following steps: obtaining detection data of a transformer substation; mapping the detection data to a virtual model of the transformer substation, and performing simulation prediction on the working process of the transformer substation by using the virtual model to obtain prediction data of the transformer substation; generating an inspection path and an inspection scheme based on the prediction data; and inspecting the transformer substation based on the inspection path and the inspection scheme. According to the invention, the technical problem of low efficiency of transformer substation inspection in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of electric power, and in particular, to a substation inspection method, system and electronic device. Background Art

[0002] With the rapid development of technologies in the field of electric power, higher requirements are put forward for the operation and maintenance management of substations, aiming to improve the reliability and safety of the power system. As a key component of the power system, the operating state of a substation directly affects the stability and efficiency of the entire power system. Therefore, in order to ensure the stability of the power system, it is necessary to inspect the substation in a timely manner, regularly check the operating state of the equipment in the substation, so as to ensure the safety of power facilities and ensure that the power system can operate stably and efficiently. However, the efficiency of inspecting substations in related technologies is relatively low.

[0003] In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0004] Embodiments of the present invention provide a substation inspection method, system and electronic device, so as to at least solve the technical problem of relatively low efficiency in inspecting substations in related technologies.

[0005] According to one aspect of the embodiments of the present invention, a substation inspection method is provided, including: obtaining detection data of the substation, where the detection data includes: environmental data of the environment where the substation is located, status data of primary equipment in the substation, and operating data of secondary equipment in the substation; mapping the detection data to a virtual model of the substation, and using the virtual model to simulate and predict the working process of the substation to obtain prediction data of the substation, where the prediction data is used to represent fault data of the substation when a fault occurs; generating an inspection path and an inspection plan based on the prediction data; and inspecting the substation based on the inspection path and the inspection plan.

[0006] Further, mapping the detection data to a virtual model of the substation, and using the virtual model to simulate and predict the working process of the substation to obtain prediction data of the substation includes: determining target detection data that meets a preset condition from the detection data; obtaining target historical detection data of a target device, where the target device is a power device corresponding to the target detection data; mapping the target historical detection data and the target detection data to the virtual model, and using the virtual model to simulate and predict the working process of the substation to obtain prediction data.

[0007] Further, determining target detection data that meets a preset condition from the detection data includes: obtaining multiple historical detection data corresponding to any one detection data; predicting speculative data corresponding to the detection data based on the multiple historical detection data; determining the one-way change gradient of the detection data based on the detection data and the speculative data; and determining the detection data as target detection data when the one-way change gradient is greater than a first threshold.

[0008] Further, predicting speculative data corresponding to the detection data based on the multiple historical detection data includes: sorting the multiple historical detection data in chronological order to obtain a historical detection data sequence; superimposing the historical detection data sequence to obtain multiple superimposed sequences; fitting the multiple superimposed sequences to obtain a fitting function; and determining the speculative data corresponding to the detection data based on the fitting function.

[0009] Further, fitting the multiple superimposed sequences to obtain a fitting function includes: constructing an initial fitting function, where the initial fitting function includes initial values of at least one parameter; solving the initial fitting function based on the multiple superimposed sequences to obtain target values of at least one parameter; and replacing the initial values of at least one parameter in the initial fitting function with the target values of at least one parameter to obtain the fitting function.

[0010] Further, mapping the target historical detection data and the target detection data to a virtual model, and using the virtual model to simulate and predict the working process of the substation to obtain prediction data includes: based on the target historical detection data, adjusting the operating parameters of the target device and associated devices in the virtual model multiple times to obtain multiple simulated detection data, where the associated devices are used to represent power devices having an association relationship with the target device; comparing the target detection data with the multiple simulated detection data to determine the target simulated detection data among the multiple simulated detection data; determining a fault model corresponding to the target operating parameters from the virtual model based on the target operating parameters corresponding to the target simulated detection data; and analyzing the operation risk of the substation in the virtual model based on the fault model to obtain the prediction data.

[0011] Further, comparing the target detection data with the multiple simulated detection data to determine the target simulated detection data among the multiple simulated detection data includes: constructing a target data set based on the target detection data, the target time data corresponding to the target detection data, the device information of the target device, and other detection data of the target device; constructing multiple simulated data sets based on different simulated detection data, the target time data, the device information, and other simulated detection data of the target device; determining the deviation values between the target data set and the different simulated data sets; and determining the simulated detection data corresponding to the simulated data set as the target simulated detection data when the deviation value corresponding to any one simulated data set is greater than a second threshold.

[0012] Further, a patrol path and a patrol plan are generated based on the prediction data, including: obtaining historical detection data corresponding to the prediction data; classifying the substation based on the prediction data and the historical detection data to obtain the defect level of the substation; and generating a patrol path and a patrol plan based on the defect level.

[0013] Further, classifying the substation based on the prediction data and the historical detection data to obtain the defect level of the substation, including: inputting the prediction data and the historical detection data into a patrol warning model, and using the patrol warning model to classify the substation to obtain the defect level of the substation.

[0014] According to another aspect of the embodiments of the present invention, a substation patrol system is further provided for executing the above-mentioned substation patrol method, including: an equipment perception layer, a patrol control layer, an information interaction layer, and patrol equipment; the equipment perception layer is arranged in the physical space of the substation and is used to obtain the detection data of the substation, where the detection data includes: environmental data of the environment where the substation is located, status data of primary equipment in the substation, and operation data of secondary equipment in the substation; the information interaction layer is respectively connected to the equipment perception layer and the patrol control layer and is used to receive the detection data and map the detection data to the virtual model of the substation in the patrol control layer; the patrol control layer is used to simulate and predict the working process of the substation by using the virtual model to obtain the prediction data of the substation, and generate a patrol path and a patrol plan based on the prediction data, where the prediction data is used to represent the fault data of the substation; the patrol equipment is used to patrol the substation based on the patrol path and the patrol plan.

[0015] Further, the virtual model includes a visual interface, and the operation status data of the substation is displayed in the visual interface.

[0016] Further, the system further includes: an alarm module, which is used to output an alarm message when the working process of the substation is simulated and predicted by using the virtual model.

[0017] According to another aspect of the embodiments of the present invention, an electronic device is further provided, including: a memory storing an executable program; a processor for running the program, where when the program runs, it executes the methods in the various embodiments of the present invention.

[0018] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored executable program, where when the executable program runs, it controls the device where the computer-readable storage medium is located to execute the methods in the various embodiments of the present invention.

[0019] According to another aspect of the embodiments of the present invention, there is also provided a computer program product, including a computer program which, when executed by a processor, implements the methods in the various embodiments of the present invention.

[0020] According to another aspect of the embodiments of the present invention, there is also provided a computer program which, when executed by a processor, implements the methods in the various embodiments of the present invention.

[0021] In the embodiments of the present invention, detection data of a substation is obtained; the detection data is mapped to a virtual model of the substation, and the virtual model is used to simulate and predict the working process of the substation to obtain prediction data of the substation; a patrol path and a patrol plan are generated based on the prediction data; and the substation is patrolled based on the patrol path and the patrol plan. By establishing a virtual model in this application and mapping the detection data to the virtual model, the working process of the substation is simulated and predicted through the virtual model to obtain relatively accurate prediction data, so as to generate a relatively reasonable patrol path and patrol plan for the substation according to the prediction data, making the patrol of the substation more reasonable and accurate, effectively improving the efficiency of patrolling the substation, effectively improving the user experience, and thus solving the technical problem of low efficiency in patrolling the substation in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0023] Figure 1 is a flowchart of an optional substation patrol method according to an embodiment of the present invention;

[0024] Figure 2 is a schematic structural diagram of an optional substation patrol system according to an embodiment of the present invention;

[0025] Figure 3 is a schematic structural diagram of an optional substation patrol device according to an embodiment of the present invention;

[0026] Figure 4 is a schematic structural diagram of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0029] According to an embodiment of the present invention, an embodiment of a substation inspection method is provided. 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 a different order than here.

[0030] Figure 1 is a flowchart of an optional substation inspection method according to an embodiment of the present invention, as Figure 1 shown, the method includes the following steps:

[0031] Step S102, obtain the detection data of the substation, where the detection data includes: environmental data of the environment where the substation is located, status data of primary equipment in the substation, and operation data of secondary equipment in the substation.

[0032] The above-mentioned substation refers to a key facility in the power system, which is used to transform voltage levels, collect and distribute electric energy, control the power flow direction, and protect the safe operation of the power system. The above-mentioned substation refers to the substation that needs to be inspected. In this application, by inspecting the substation, the safety and stability of the substation are determined, and thus the safe operation of the substation is ensured.

[0033] The above detection data refers to the data obtained after detecting the equipment and environment of the substation. The above detection data includes but is not limited to: the environmental data of the environment where the substation is located, the status data of the primary equipment in the substation, and the operation data of the secondary equipment in the substation. In this application, through the above detection data, the prediction data of the substation can be obtained, and then the inspection plan and inspection path for the substation can be obtained.

[0034] The above environmental data refers to the data of the working environment of the above substation. Through the above environmental data, the environmental information around the substation can be characterized. Among them, the above environmental data includes but is not limited to: environmental temperature, environmental humidity, or weather conditions, etc.

[0035] The above primary equipment refers to the equipment directly related to the generation, conversion, transmission, and distribution of electric energy in the above substation. Through the above primary equipment, the functions of voltage level transformation, collection and distribution of electric energy, control of power flow direction, and protection of the power system can be realized in the substation. Among them, the above primary equipment includes but is not limited to: transformers, circuit breakers, or disconnectors, etc.

[0036] The above status data refers to the working status data of the above primary equipment. Through the above status data, the working status of the above primary equipment can be determined. Among them, the above status data includes but is not limited to the following of the above primary equipment: equipment temperature, joint temperature, voltage, or current, etc.

[0037] The above secondary equipment refers to the equipment involved in controlling, protecting, measuring, and monitoring the above primary equipment. Through the above secondary equipment, the control, protection, measurement, and monitoring of the above primary equipment can be realized to ensure the safety of the above primary equipment. Among them, the above secondary equipment includes but is not limited to: relay protection devices, automatic control equipment, voltage monitoring devices, or current monitoring devices, etc.

[0038] The above operation data refers to the data during the operation of the above secondary equipment. Through the above operation data, the operation status of the above secondary equipment can be determined to determine whether the above secondary equipment normally performs the functions of control, protection, measurement, and monitoring. Among them, the above operation data includes but is not limited to: voltage, current, or load value, etc.

[0039] In an alternative embodiment, when it is necessary to inspect the above-mentioned substation, the ambient temperature around the substation can be obtained through a temperature sensor, the humidity around the substation can be obtained through a humidity sensor, and the weather conditions around the substation can be obtained through a PM2.5 sensor, a light intensity sensor, a rain gauge, and a wind speed and direction sensor; the equipment temperature and joint temperature of the above-mentioned primary equipment can be obtained through a temperature sensor, and the current or voltage data of the above-mentioned primary equipment can be obtained through a current sensor and a voltage sensor; the current or voltage data of the above-mentioned secondary equipment can be obtained through a current sensor and a voltage sensor, so as to determine the environmental data of the environment where the substation is located, the status data of the primary equipment in the substation, and the operation data of the secondary equipment in the substation, and then determine the above-mentioned detection data.

[0040] In another alternative embodiment, when it is necessary to inspect the above-mentioned substation, the ambient temperature, ambient humidity or weather conditions around the substation can also be obtained through the Internet to determine the above-mentioned environmental data. The equipment temperature, joint temperature, voltage or current of the above-mentioned primary equipment can be obtained through sensors, so as to determine the status data of the primary equipment. The voltage, current or load value of the above-mentioned secondary equipment can be obtained through sensors, so as to determine the operation data of the secondary equipment. The above-mentioned detection data is determined through the above-mentioned environmental data, status data and operation data.

[0041] In this application, by determining the above-mentioned environmental data, the status data of the primary equipment and the operation data of the secondary equipment, more accurate detection data of the substation is determined, thereby effectively improving the comprehensiveness of the inspection of the substation, further improving the accuracy of the inspection of the substation, and improving the user experience.

[0042] Step S104: Map the detection data to the virtual model of the substation, and use the virtual model to simulate and predict the working process of the substation to obtain the prediction data of the substation, where the prediction data is used to represent the fault data of the substation when a fault occurs.

[0043] The above-mentioned virtual model refers to creating a virtual model of a physical entity or system to reflect and predict the state, performance and behavior of the entity or system in real time. In this application, the state, performance and operation conditions of the above-mentioned substation are reflected through the above-mentioned virtual model, and a virtual model corresponding to the actual substation is constructed through the above-mentioned virtual model to simulate the operation environment and equipment state of the above-mentioned substation. The working process of the substation is simulated through the above-mentioned virtual model, and then the above-mentioned prediction data is obtained. In this application, the above-mentioned virtual model can be generated through Digital Twin Technology (DTT).

[0044] The above digital twin technology is a comprehensive information technology that crosses multiple disciplines. By integrating technologies such as the Internet of Things, big data analysis, artificial intelligence, cloud computing, and simulation technology, it creates a virtual digital model of an object or system in the real physical world. This digital model can reflect the state, dynamics, and processes of its corresponding physical entity in real time, enabling data synchronization and interaction between the two to achieve the purposes of monitoring, prediction, control, and optimization. In this application, the above digital twin technology is used to generate the virtual model corresponding to the above substation, and then the prediction data of the above substation is obtained through the above virtual model.

[0045] The above prediction data refers to the prediction data of the operation of the above substation obtained after predicting the working process of the above substation. Through the above prediction data, the operation state of the above substation can be predicted. The above prediction data can represent the possibility of risks occurring in the above substation, and further represent the fault data of the above substation when a fault occurs. Among them, the above prediction data includes but is not limited to: faulty equipment, fault occurrence time, fault type, fault occurrence location, and environmental data, etc.

[0046] In an alternative embodiment, after obtaining the above detection data, the above detection data can be mapped into the above virtual model. The above virtual model can establish an environmental prediction layer, a primary equipment status prediction layer, and a secondary equipment operation prediction layer. The environmental prediction data is output through the above environmental prediction layer, the primary equipment status prediction data is output through the above primary equipment status prediction layer, and the secondary equipment operation prediction data is output through the above secondary equipment operation prediction layer. The prediction data of the above substation is obtained according to the above environmental prediction data, the above primary equipment status prediction data, and the above secondary equipment operation prediction data to represent the fault data of the substation when a fault occurs.

[0047] In another alternative embodiment, the above virtual model includes: an environmental virtual model, a primary equipment virtual model, and a secondary equipment virtual model. After obtaining the above detection data, the environmental data in the above detection data is input into the above environmental virtual model to output environmental prediction data; the status data in the above detection data is input into the above primary equipment virtual model to output primary equipment status prediction data; the operation data in the above detection data is input into the above secondary equipment virtual model to output secondary equipment operation prediction data. The prediction data of the above substation is obtained according to the above environmental prediction data, the above primary equipment status prediction data, and the above secondary equipment operation prediction data to represent the fault data of the substation when a fault occurs.

[0048] In this application, through the above virtual model, by mapping the above detection data to the virtual model, the prediction data of the above substation is obtained, and then the fault data of the substation with a fault is determined, effectively improving the accuracy of predicting the above substation, and further effectively improving the accuracy of inspecting the substation, and further effectively improving the user experience.

[0049] Step S106, generate an inspection path and an inspection plan based on the prediction data.

[0050] The above inspection path refers to a travel route with higher inspection efficiency generated through prediction data for the inspection robot or the user to plan for equipment inspection and maintenance within the substation. Through the above inspection path, the inspection robot or the operation and maintenance personnel can quickly inspect the above substation.

[0051] The above inspection plan refers to a maintenance and repair plan generated through prediction data for the inspection robot or the user to plan for equipment inspection and maintenance within the substation. Through the above inspection plan, the inspection robot or the operation and maintenance personnel can accurately maintain and repair the above substation.

[0052] In an alternative embodiment, after obtaining the above prediction data, the user can manually calculate based on the above prediction data to obtain the inspection path and the inspection plan for inspecting the above substation.

[0053] In another alternative embodiment, an inspection path determination model and an inspection plan determination model can be established in advance. After obtaining the above prediction data, the above prediction data can be used as the input of the above inspection path determination model and the above inspection plan determination model, and respectively input into the above inspection path determination model and the above inspection plan determination model. The above inspection path determination model outputs the inspection path, and the above inspection plan determination model outputs the inspection plan.

[0054] In this application, through the prediction data, a more accurate inspection path and inspection plan are obtained. Through the above inspection path and the above inspection plan, accurate inspection of the above substation is realized, effectively improving the accuracy and speed of inspecting the substation, and improving the user experience.

[0055] Step S108, inspect the substation based on the inspection path and the inspection plan.

[0056] In an alternative embodiment, after obtaining the above inspection path and the above inspection plan, the above inspection path and the above inspection plan can be sent to the user terminal. After receiving the above inspection path and the above inspection plan, the user can inspect the above substation according to the above inspection path and the above inspection plan.

[0057] In another alternative embodiment, after obtaining the above inspection path and the above inspection plan, the above inspection path and the above inspection plan can be sent to the inspection robot. After receiving the above inspection path and the above inspection plan, the inspection robot can inspect the above substation according to the above inspection path and the above inspection plan.

[0058] In the present application, through the above inspection path and inspection plan, not only the inspection rate of the above substation is effectively improved, but also the inspection accuracy of the substation is effectively improved, and the inspection efficiency of the above substation is improved, thereby effectively improving the user experience.

[0059] Through the above steps, the detection data of the substation is obtained; the detection data is mapped to the virtual model of the substation, and the working process of the substation is simulated and predicted by using the virtual model to obtain the prediction data of the substation; the inspection path and inspection plan are generated based on the prediction data; the substation is inspected based on the inspection path and inspection plan. In the present application, by establishing a virtual model and mapping the detection data to the virtual model, the working process of the substation is simulated and predicted by using the virtual model to obtain relatively accurate prediction data, so as to generate a relatively reasonable inspection path and inspection plan for the substation according to the prediction data, making the inspection of the substation more reasonable and accurate, effectively improving the inspection efficiency of the substation, effectively improving the user experience, and thus solving the technical problem of low inspection efficiency of the substation in the related art.

[0060] Optionally, mapping the detection data to the virtual model of the substation and using the virtual model to simulate and predict the working process of the substation to obtain the prediction data of the substation includes: determining the target detection data that meets the preset conditions from the detection data; obtaining the target historical detection data of the target device, where the target device is the power device corresponding to the target detection data; mapping the target historical detection data and the target detection data to the virtual model, and using the virtual model to simulate and predict the working process of the substation to obtain the prediction data.

[0061] The above preset condition refers to a condition preset for judging whether the detection data is abnormal. Among them, the above preset condition can be set according to the state of the above substation, and the above preset condition can also be set manually according to experience and requirements, and the above preset condition can also be set according to the actual application scenario.

[0062] The above target detection data refers to the abnormal data in the above detection data, and the above target detection data refers to the data that meets the above preset conditions in the above detection data. The target device in the above substation can be determined through the above target detection data.

[0063] The above-mentioned target device refers to the power device corresponding to the above-mentioned target detection data. Since the above-mentioned target detection data is abnormal detection data, the target device corresponding to the above-mentioned target detection data is likely to have a fault. Therefore, it is necessary to obtain the prediction data corresponding to the above-mentioned target device.

[0064] The above-mentioned target historical detection data refers to the power data in which the detection data corresponding to the above-mentioned target device detected at a historical time point is abnormal. Through the above-mentioned target historical detection data, the abnormalities that occurred to the above-mentioned target device at the historical time point can be determined, and the inspection plan and inspection path for processing the target device in the past can be determined. Furthermore, when the prediction data corresponding to the target device is abnormal, the above-mentioned target device can be inspected.

[0065] In an alternative embodiment, detection data and historical detection data are obtained. The unidirectional change gradient of the detection data is determined through the above-mentioned detection data and the above-mentioned historical detection data. When the above-mentioned unidirectional change gradient of the detection data is greater than a preset gradient threshold, it is determined that the detection data meets the preset conditions, and the detection data that meets the above-mentioned preset conditions is determined to be the above-mentioned target detection data. After obtaining the above-mentioned target detection data, the target device corresponding to the above-mentioned target detection data is determined, and the target historical detection data corresponding to the above-mentioned target device is obtained. The target historical detection data and the target detection data are mapped to a virtual model, and the virtual model is used to simulate and predict the working process of the substation to obtain the prediction data corresponding to the target device.

[0066] In another alternative embodiment, a data threshold can also be preset. After obtaining the above-mentioned detection data, the above-mentioned detection data is compared with the above-mentioned data threshold. When the above-mentioned detection data is greater than the above-mentioned data threshold, it is determined that the detection data meets the preset conditions, and the detection data that meets the above-mentioned preset conditions is determined to be the above-mentioned target detection data. After obtaining the above-mentioned target detection data, the target device corresponding to the above-mentioned target detection data is determined, and the target historical detection data corresponding to the above-mentioned target device is obtained. The target historical detection data and the target detection data are mapped to a virtual model, and the virtual model is used to simulate and predict the working process of the substation to obtain the prediction data corresponding to the target device.

[0067] In this application, the above-mentioned detection data is screened through preset conditions to obtain the target detection data with abnormalities, thereby accurately determining the target device with a relatively high probability of failure, effectively improving the efficiency of inspecting the above-mentioned substation. Through the above-mentioned target historical detection data, relatively accurate prediction data can be obtained, effectively improving the accuracy of inspecting the above-mentioned substation and enhancing the user experience.

[0068] Optionally, determining target detection data that meets a preset condition from the detection data includes: obtaining multiple historical detection data corresponding to any one detection data; predicting speculative data corresponding to the detection data based on the multiple historical detection data; determining the one-way change gradient of the detection data based on the detection data and the speculative data; and determining the detection data as target detection data when the one-way change gradient is greater than a first threshold.

[0069] The above-mentioned first threshold refers to the threshold for defining the one-way change gradient. Through the first threshold, the above-mentioned detection data can be judged. When the one-way change gradient is greater than the first threshold, the above-mentioned detection data is determined as target detection data.

[0070] The above-mentioned multiple historical detection data refers to the historical detection data at multiple historical time points corresponding to the above-mentioned detection data. Through the above-mentioned multiple historical detection data, the speculative data with the highest matching degree with the above-mentioned detection data among the multiple historical detection data is determined, and then the one-way change gradient of the detection data is determined based on the detection data and the speculative data.

[0071] In an optional embodiment, after obtaining the detection data, multiple historical detection data at multiple historical time points corresponding to any one detection data are obtained, and speculative data corresponding to the detection data is predicted according to the multiple historical detection data. After obtaining the speculative data, the one-way change gradient of the detection data is determined according to the above-mentioned speculative data and the detection data. When the one-way change gradient is greater than the first threshold, the detection data is determined as target detection data. Among them, the expression of the above-mentioned one-way change gradient is as follows:

[0072]

[0073] where λ is the one-way change gradient, R is the detection data, and R 0 (n + 1) is the speculative data. After determining the one-way change gradient of the detection data, the above-mentioned one-way change gradient is compared with the above-mentioned first threshold. When the one-way change gradient is greater than the first threshold, the detection data is determined as target detection data.

[0074] In this application, through multiple historical detection data, the speculative data corresponding to the detection data can be quickly determined through the multiple historical detection data, effectively improving the efficiency of determining the target detection data, and further effectively improving the efficiency of inspecting the above-mentioned substation, thus improving the user experience.

[0075] Optionally, based on multiple historical detection data, speculative data corresponding to the detection data is predicted, including: sorting the multiple historical detection data in chronological order to obtain a historical detection data sequence; superimposing the historical detection data sequence to obtain multiple superimposed sequences; fitting the multiple superimposed sequences to obtain a fitting function; and determining the speculative data corresponding to the detection data based on the fitting function.

[0076] The above-mentioned historical detection data sequence refers to the sequence obtained by sorting the above-mentioned multiple historical detection data according to chronological order. The above-mentioned historical detection data sequence can sort the above-mentioned historical detection data in chronological order from early to late, or can also sort the above-mentioned historical detection data in chronological order from late to early to obtain the above-mentioned historical detection data sequence.

[0077] The above-mentioned superimposed sequence refers to the superimposed sequence obtained by summing the above-mentioned multiple historical detection data. Among them, there are multiple above-mentioned superimposed sequences, and the historical detection data superimposed by each superimposed sequence is the historical moment corresponding to the superimposed sequence, and the sum of multiple detection data corresponding to the historical moments before that historical moment. Through the above-mentioned superimposed sequence, a fitting function can be determined, and thus speculative data can be obtained through the fitting function.

[0078] The above-mentioned fitting function refers to a function used to simulate or approximate a set of data. Through the fitting function, the relationship between data can be described, and then data prediction can be carried out. In this application, by superimposing data and historical detection data to determine the relationship between multiple historical detection data, and then obtaining speculative data. Among them, the above-mentioned fitting function includes but is not limited to: linear fitting, polynomial fitting, exponential fitting, logarithmic fitting, power function fitting, sine function fitting or non-linear fitting, etc.

[0079] The above-mentioned speculative data refers to the data obtained by speculating on the detection data at a future time point according to the fitting function. In this application, the relationship between multiple historical detection data is determined through the fitting function, and then the detection data at a future time point is speculated through the fitting function and historical detection data, and then the above-mentioned speculative data is obtained.

[0080] In an optional embodiment, after obtaining multiple historical detection data, the multiple historical detection data are sorted according to a time series to obtain a historical detection data sequence. After obtaining the above-mentioned historical detection data sequence, the above-mentioned historical detection data sequence is superimposed to obtain multiple superimposed sequences, where the formula for obtaining the above-mentioned superimposed sequence is as follows:

[0081]

[0082] Wherein, R 1 (i) is the superimposed sequence (i = 1, 2, 3,..., n), n is the number of multiple historical detection data, R 0(j) is the historical detection data at time j. After constructing n superimposed sequences, the above n superimposed sequences are fitted to obtain a fitting function. The expression of the fitting function is as follows:

[0083] R 0 (i) = -aR 1 (i) + u,

[0084] where, R 0 (i) is the historical detection data at time i, and R 1 (i) is the superimposed sequence (i = 1, 2, 3,..., n), a is the first parameter, and u is the second parameter. According to the above fitting function, the predicted data R 0 (n + 1) is determined, where R 0 (n + 1) is the predicted detection data at the (n + 1)-th moment, that is, the predicted data.

[0085] In another alternative embodiment, a predicted data determination model can be established in advance. After obtaining the above multiple historical detection data, the above multiple historical detection data can be used as the input of the predicted data determination model and input into the predicted data determination model to output the predicted data.

[0086] In this application, by determining the superimposed sequence and then determining the fitting function to obtain relatively accurate predicted data, the accurate prediction of the detection data is realized, the accuracy of obtaining the predicted data is effectively improved, thereby effectively improving the accuracy of determining the inspection path and inspection plan, and further effectively improving the accuracy of substation inspection, improving the user experience.

[0087] Optionally, fitting the multiple superimposed sequences to obtain a fitting function includes: constructing an initial fitting function, where the initial fitting function includes initial values of at least one parameter; solving the initial fitting function based on the multiple superimposed sequences to obtain target values of at least one parameter; and replacing the initial values of at least one parameter in the initial fitting function with the target values of at least one parameter to obtain the fitting function.

[0088] In an alternative embodiment, the expression of the initial fitting function is as follows:

[0089] R 0 (i) = -bR 1 (i) + c,

[0090] where, R 0 (i) is the historical detection data at time i, and R 1(i) is the superimposed sequence (i = 1, 2, 3, …, n), b is the initial value of the first parameter, and c is the initial value of the second parameter. After establishing the above fitting function, the initial fitting function is solved by the least squares method to determine the target value a of the first parameter and the target value u of the second parameter. After determining the target value a of the first parameter and the target value u of the second parameter, the target value a of the first parameter is used to replace the initial value b of the first parameter, and the target value u of the second parameter is used to replace the initial value c of the second parameter to obtain the fitting function, where the expression of the fitting function is as follows:

[0091] R 0 (i) = -aR 1 (i) + u.

[0092] In another alternative embodiment, a fitting function optimization model can be established in advance. After obtaining the fitting function with the initial values of at least one parameter, the fitting function with the initial values of at least one parameter is used as the input of the fitting function optimization model and input into the fitting function optimization model to output the fitting function.

[0093] In this application, the initial fitting function is optimized through multiple superimposed sequences to adjust the initial values of at least one parameter in the initial fitting function, so as to obtain a more accurate fitting function. Then, a more accurate speculation data is obtained through the fitting function, effectively improving the accuracy of obtaining the speculation data, thus effectively improving the accuracy of determining the inspection path and inspection plan, and further effectively improving the accuracy of substation inspection, enhancing the user experience.

[0094] Optionally, the target historical detection data and the target detection data are mapped to a virtual model, and the virtual model is used to simulate and predict the working process of the substation to obtain prediction data, including: based on the target historical detection data, the operating parameters of the target device and associated devices are adjusted multiple times in the virtual model to obtain multiple simulated detection data, where the associated devices are used to represent power devices having an association relationship with the target device; the target detection data and the multiple simulated detection data are compared to determine the target simulated detection data among the multiple simulated detection data; based on the target operating parameters corresponding to the target simulated detection data, a fault model corresponding to the target operating parameters is determined from the virtual model; and based on the fault model, the operation risk of the substation is analyzed in the virtual model to obtain prediction data.

[0095] The above-mentioned associated device refers to an electrical device that has an association relationship with the above-mentioned target device. Changes in the operating parameters of the target device may cause changes in the operating parameters of the associated device, and changes in the operating parameters of the associated device may also affect the operating parameters of the target device. A fault in the target device may cause a fault in the associated device, and a fault in the associated device may also cause a fault in the target device. Therefore, it is necessary to analyze the target device and the associated device to determine whether the target device and the associated device are abnormal, and then obtain prediction data.

[0096] In an alternative embodiment, after obtaining the target historical detection data, the above-mentioned target historical detection data is used as the input of the above-mentioned virtual model and input into the above-mentioned virtual model. After receiving the above-mentioned target historical detection data, the virtual model adjusts the operating parameters of the target device and the associated device in the virtual model multiple times according to the above-mentioned target historical detection data to obtain multiple simulated detection data. The obtained target detection data is compared with the above-mentioned multiple simulated detection data to determine the target simulated detection data that is closest to the target detection data among the multiple simulated detection data. After determining the above-mentioned target simulated detection data, the target operating parameters corresponding to the above-mentioned target simulated detection data are determined, and the fault model corresponding to the target operating parameters is determined from the virtual model. After determining the above-mentioned fault model, the operating risk of the above-mentioned substation is analyzed in the above-mentioned virtual model according to the above-mentioned fault model, and then the above-mentioned prediction data is determined.

[0097] In another alternative embodiment, a comparison model can be established in advance. After obtaining the target historical detection data, the operating parameters of the target device and the associated device can be adjusted multiple times in the virtual model to obtain multiple simulated detection data. After obtaining the multiple simulated detection data, the above-mentioned multiple simulated detection data and the above-mentioned target detection data are used as the input of the above-mentioned comparison model and input into the above-mentioned comparison model to output the target simulated detection data among the above-mentioned multiple simulated detection data. After determining the above-mentioned target simulated detection data, the target operating parameters corresponding to the above-mentioned target simulated detection data are determined, and the fault model corresponding to the target operating parameters is determined from the virtual model. After determining the above-mentioned fault model, the operating risk of the above-mentioned substation is analyzed in the above-mentioned virtual model according to the above-mentioned fault model, and then the above-mentioned prediction data is determined.

[0098] In the present application, the operating parameters of the target device and the associated device are adjusted multiple times through the target historical detection data to obtain a relatively comprehensive set of multiple simulated detection data. The target detection data and the multiple simulated detection data are compared to determine a relatively accurate target simulated detection data. Furthermore, the fault type corresponding to the relatively accurate target operating parameters is obtained, and then relatively accurate prediction data is obtained, effectively improving the accuracy of obtaining prediction data, and thus effectively improving the accuracy of substation inspection and enhancing the user experience.

[0099] Optionally, comparing the target detection data with multiple simulated detection data to determine the target simulated detection data among the multiple simulated detection data includes: constructing a target data set based on the target detection data, the target time data corresponding to the target detection data, the device information of the target device, and other detection data of the target device; constructing multiple simulated data sets based on different simulated detection data, the target time data, the device information, and other simulated detection data of the target device; determining the deviation values between the target data set and different simulated data sets; and when the deviation value corresponding to any one of the simulated data sets is greater than a second threshold, determining the simulated detection data corresponding to the simulated data set as the target simulated detection data.

[0100] The above-mentioned second threshold refers to the threshold used to limit the deviation values corresponding to the multiple simulated data sets. In this application, the simulated detection data is screened by the above-mentioned second threshold to determine the simulated detection data corresponding to the simulated data set as the target simulated detection data. When the deviation value corresponding to the simulated data set is greater than the second threshold, the simulated detection data corresponding to the simulated data set is determined as the target detection data.

[0101] The above-mentioned other detection data refers to other detection data of the target device in the above-mentioned substation except the target detection data. In this application, the above-mentioned other detection data can be obtained by sensors. By obtaining the above-mentioned other detection data, the target data set can be constructed more comprehensively, and then the above-mentioned target simulated detection data can be determined more comprehensively. Among them, the above-mentioned other detection data includes but is not limited to: leakage current, response time, system performance index, size, weight, material property, or noise level, etc.

[0102] In an optional embodiment, after obtaining the above-mentioned target detection data and the above-mentioned multiple simulated detection data, the user can construct a target data set according to the target detection data, the target time data corresponding to the target detection data, the device information of the target device, and other detection data of the target device; and construct multiple simulated data sets according to different simulated detection data, the target time data, the device information, and other simulated detection data of the target device. After determining the above-mentioned target data set and the above-mentioned multiple simulated data sets, the user can calculate to obtain the deviation values between the above-mentioned target data set and the above-mentioned different simulated data sets. Among them, the calculation formula of the above-mentioned deviation value is as follows:

[0103]

[0104] Among them, Deviation is the deviation value; α is the weight value corresponding to the target detection data; R * is the target detection data; is the i-th simulated detection data (i = 1, 2, 3,..., m), where m is the total number of multiple simulated detection data, R′ (k) is other detection data; R i (k) is the i-th other simulated detection data; β(k) is the weight corresponding to the other detection data; where

[0105] After calculating the deviation value, compare the above deviation value with the above second threshold. In response to the deviation value corresponding to any one of the simulated data sets being greater than the second threshold, determine the simulated detection data corresponding to the simulated data set as the target simulated detection data.

[0106] In another alternative embodiment, a deviation value determination model and a determination model can be established in advance. After obtaining the target detection data, target time data, device information of the target device, other detection data, different simulated detection data, and other simulated detection data, use the target detection data, target time data, device information of the target device, other detection data, different simulated detection data, and other simulated detection data as the input of the above deviation value determination model, input it into the above deviation value determination model, and output the deviation value between the target data set and different simulated data sets; the above deviation value can be used as the input of the above determination model, input it into the above determination model, and the determination model determines the simulated detection data corresponding to the simulated data set as the target simulated detection data according to the above deviation value, and outputs the target simulated detection data.

[0107] In this application, by calculating the deviation value between the target data set and different simulated data sets, and by setting the second threshold to quickly determine the relationship between the deviation value and the second threshold, and then quickly determine the target simulated detection data, thereby effectively improving the rate of obtaining the target simulated detection data, and further effectively improving the rate of substation inspection and enhancing the user experience.

[0108] Optionally, generating an inspection path and an inspection plan based on the prediction data includes: obtaining historical detection data corresponding to the prediction data; classifying the substation based on the prediction data and the historical detection data to obtain the defect level of the substation; generating an inspection path and an inspection plan based on the defect level.

[0109] In an alternative embodiment, after obtaining the prediction data, historical detection data corresponding to the above prediction data can be obtained. The user can manually classify the substation according to the prediction data and the historical detection data to obtain the defect level of the substation, and generate an inspection path and an inspection plan according to the defect level. Among them, the above classification can be determined according to the user's needs.

[0110] In another alternative embodiment, an inspection warning model can be established in advance. After obtaining the prediction data, the prediction data and the historical detection data can be used as the input of the above inspection warning model and input into the above inspection warning model to obtain the defect level of the substation. After obtaining the above defect level, the user can generate an inspection path and an inspection plan according to the above defect level.

[0111] Exemplarily, the user can classify the defect levels according to requirements into: general defects, serious defects, and urgent defects; when the defect level is a general defect, there are abnormalities in the detection data of the equipment, and the change gradient of the detection data is weak, and the defect will not cause an accident. At this time, maintenance can be carried out during the power outage interval, and at the same time, the infrared temperature measurement frequency can be increased to pay attention to the development of the defect; when the defect level is a serious defect, there are abnormalities in the detection data of the equipment, and the degree is relatively serious, and the change gradient of the detection data is large, and the defect may cause an equipment accident. At this time, arrange maintenance as soon as possible. For the current-induced heating type temperature rise phenomenon, reduce its load current. If it is a voltage-induced heating type temperature rise, use a composite method to confirm the cause of the defect and arrange maintenance immediately after determination; when the defect level is an urgent defect, there are abnormalities in the detection data of the equipment, and the abnormality of the detection data exceeds the national standard. At this time, arrange maintenance and handling immediately. If it is a current-induced heating type temperature rise, immediately withdraw its load and carry out maintenance. For a voltage-induced heating type temperature rise, immediately stop the equipment operation and carry out maintenance.

[0112] In this application, the above substation is classified through the prediction data and the historical detection data to determine the defect level of the substation, and then an inspection path and an inspection plan are generated according to the defect level, effectively improving the rate of obtaining the above inspection path and the above inspection plan, and further improving the inspection rate of the above substation, and further improving the user experience.

[0113] Optionally, based on the prediction data and the historical detection data, the substation is classified to obtain the defect level of the substation, including: inputting the prediction data and the historical detection data into the inspection warning model, and using the inspection warning model to classify the substation to obtain the defect level of the substation.

[0114] The above inspection warning model refers to a model established in advance for classifying the substation to obtain the defect level of the substation. In this application, through the above inspection warning model, the defect level of the substation corresponding to the current prediction data can be determined according to the prediction data and the historical detection data, and then the inspection path and the inspection plan of the substation can be determined.

[0115] In an alternative embodiment, after obtaining the prediction data and the historical detection data, the prediction data and the historical detection data are used as the input of the above-mentioned patrol warning model and input into the above-mentioned patrol warning model. The patrol warning model preprocesses the historical detection data, including but not limited to: removing duplicates from the historical detection data, deleting the error data in the historical detection data, and filling the missing values in the historical detection data to obtain the standardized historical detection data. After obtaining the standardized historical detection data, eigenvalue is extracted from the standardized historical detection data. The eigenvalue includes but not limited to: the faulty equipment of the substation, the fault occurrence time of the substation, the environmental data at the time of the substation fault, the fault type of the substation, and the fault occurrence location of the substation, etc. After obtaining the eigenvalue in the historical detection data, the patrol warning model combines the prediction data to determine the defect level of the substation.

[0116] In the present application, through the above-mentioned patrol warning model, the user can input the prediction data and the historical detection data into the above-mentioned patrol warning model to quickly obtain the patrol path and the patrol plan of the substation, effectively improving the efficiency of obtaining the patrol path and the patrol plan, improving the efficiency of patrolling the substation, and thus effectively improving the user experience.

[0117] According to an embodiment of the present invention, an embodiment of a substation patrol system is provided. It should be noted that the system can be used to execute the above-mentioned substation patrol method. Figure 2 is a schematic structural diagram of an alternative substation patrol system according to an embodiment of the present invention, as Figure 2 shown, the system includes: a device perception layer 20, a patrol control layer 22, an information interaction layer 24, and a patrol device 26; the device perception layer 20 is arranged in the physical space of the substation and is used to obtain the detection data of the substation. The detection data includes: the environmental data of the environment where the substation is located, the state data of the primary equipment in the substation, and the operation data of the secondary equipment in the substation; the information interaction layer 22 is respectively connected to the device perception layer 20 and the patrol control layer 24 and is used to receive the detection data and map the detection data to the virtual model of the substation in the patrol control layer 24; the patrol control layer 24 is used to simulate and predict the working process of the substation by using the virtual model to obtain the prediction data of the substation, and generate a patrol path and a patrol plan based on the prediction data, where the prediction data is used to represent the fault data of the substation; the patrol device 26 is used to patrol the substation based on the patrol path and the patrol plan.

[0118] In an alternative embodiment, as Figure 2As shown in the figure, the device perception layer 20 includes that of the substation. The device perception layer 20 is connected to the information interaction layer 22. The device perception layer 20 includes temperature, current, voltage sensors 201, partial discharge sensors 202 and environmental detection unit 203. The information interaction layer 22 includes a data transmission mapping unit 221 and a database 222. The information interaction layer 22 is also connected to the inspection control layer 24. The inspection control layer 24 includes a virtual model unit 241 and an inspection warning model unit 242. The inspection control layer 24 is connected to the inspection device 26. The device perception layer 20 is used to obtain the detection data of the substation. Among them, the detection data includes: environmental data of the environment where the substation is located, status data of primary equipment in the substation, and operation data of secondary equipment in the substation. Temperature, current, voltage sensors 201, partial discharge sensors 202 and environmental detection unit 203 are arranged in the device perception layer 20. The status data of the primary equipment and the operation data of the secondary equipment are obtained through the temperature, current, voltage sensors 201 and the partial discharge sensors 202. The environmental data of the environment where the substation is located is obtained through the environmental detection unit 203. After the device perception layer 20 obtains the detection data, it transmits the above detection data to the information interaction layer 22. The database 222 in the information interaction layer 22 stores the above detection data. The above transmission mapping unit 221 is used to map the detection data into the virtual model unit 241 of the substation in the inspection control layer 24. After the virtual model unit 241 of the substation in the inspection control layer 24 receives the above detection data, it uses the virtual model in the virtual model unit 241 of the substation to simulate and predict the working process of the substation, obtains the prediction data of the substation, and obtains the inspection path and inspection plan through the inspection warning model unit 242 in the inspection control layer 24. After obtaining the above inspection path and the above inspection plan, the above inspection path and the above inspection plan are sent to the above inspection device 26 to inspect the above substation through the inspection path and inspection plan.

[0119] Optionally, the virtual model includes a visualization interface, and the operation status data of the substation is displayed in the visualization interface.

[0120] In an alternative embodiment, the virtual model in the virtual model unit includes a visualization interface, and the operation status data of the above substation is displayed in the above visualization interface. The user can determine the operation status of the substation in the above virtual model according to the operation status data of the substation in the above virtual model displayed in the above visualization interface.

[0121] Optionally, the system further includes: an alarm module, which is used to output an alarm message when the working process of the substation is simulated and predicted by using the virtual model.

[0122] In an alternative embodiment, the system further includes an alarm module, which is configured to output an alarm message during the simulation and prediction of the operation process of the substation using the virtual model, so as to prompt the user in a timely manner that a fault or abnormality has occurred in the substation.

[0123] According to an embodiment of the present invention, an embodiment of a substation inspection device is provided. It should be noted that this device can be used to execute the above-mentioned substation inspection method. Figure 3 FIG. is a schematic structural diagram of another alternative substation inspection device according to an embodiment of the present invention, as Figure 3 shown, the device includes: an acquisition module 30, configured to acquire detection data of the substation, where the detection data includes: environmental data of the environment where the substation is located, status data of primary equipment in the substation, and operation data of secondary equipment in the substation; a mapping module 32, configured to map the detection data to a virtual model of the substation, and simulate and predict the operation process of the substation using the virtual model to obtain prediction data of the substation, where the prediction data is used to characterize fault data indicating that a fault has occurred in the substation; a generation module 34, configured to generate an inspection path and an inspection plan based on the prediction data; and an inspection module 36, configured to inspect the substation based on the inspection path and the inspection plan.

[0124] Optionally, the mapping module includes: a determination unit, configured to determine target detection data that meets a preset condition from the detection data; a first acquisition unit, configured to acquire target historical detection data of a target device, where the target device is a power device corresponding to the target detection data; and a mapping unit, configured to map the target historical detection data and the target detection data to the virtual model, and simulate and predict the operation process of the substation using the virtual model to obtain prediction data.

[0125] Optionally, the determination unit includes: an acquisition subunit, configured to acquire multiple historical detection data corresponding to any one detection data; a prediction subunit, configured to predict speculative data corresponding to the detection data based on the multiple historical detection data; a first determination subunit, configured to determine a one-way change gradient of the detection data based on the detection data and the speculative data; and a second determination subunit, configured to determine the detection data as target detection data when the one-way change gradient is greater than a first threshold.

[0126] Optionally, the prediction subunit is further configured to sort the multiple historical detection data in chronological order to obtain a historical detection data sequence; superimpose the historical detection data sequence to obtain multiple superimposed sequences; fit the multiple superimposed sequences to obtain a fitting function; and determine the speculative data corresponding to the detection data based on the fitting function.

[0127] Optionally, the predictor subunit is further configured to construct an initial fitting function, where the initial fitting function includes initial values of at least one parameter; solve the initial fitting function based on multiple superimposed sequences to obtain target values of at least one parameter; and replace the initial values of at least one parameter in the initial fitting function with the target values of at least one parameter to obtain a fitting function.

[0128] Optionally, the mapping unit includes: an adjustment subunit, configured to perform multiple adjustments on the operating parameters of the target device and the associated device in the virtual model based on the target historical detection data to obtain multiple simulated detection data, where the associated device is used to characterize a power device having an association relationship with the target device; a comparison subunit, configured to compare the target detection data with the multiple simulated detection data to determine the target simulated detection data among the multiple simulated detection data; a third determination subunit, configured to determine a fault model corresponding to the target operating parameter from the virtual model based on the target operating parameter corresponding to the target simulated detection data; and an analysis subunit, configured to analyze the operation risk of the substation in the virtual model based on the fault model to obtain prediction data.

[0129] Optionally, the third determination subunit is further configured to construct a target data set based on the target detection data, the target time data corresponding to the target detection data, the device information of the target device, and other detection data of the target device; construct multiple simulated data sets based on different simulated detection data, target time data, device information, and other simulated detection data of the target device; determine the deviation values between the target data set and the different simulated data sets; and determine the simulated detection data corresponding to the simulated data set as the target simulated detection data when the deviation value corresponding to any one simulated data set is greater than the second threshold.

[0130] Optionally, the inspection module includes: a second acquisition unit, configured to acquire historical detection data corresponding to the prediction data; a grading unit, configured to grade the substation based on the prediction data and the historical detection data to obtain the defect level of the substation; and a generation unit, configured to generate an inspection path and an inspection plan based on the defect level.

[0131] Optionally, the grading unit includes: a grading subunit, configured to input the prediction data and the historical detection data into an inspection warning model, and use the inspection warning model to grade the substation to obtain the defect level of the substation.

[0132] An embodiment of the present application further provides an electronic device, Figure 4 which is a schematic structural diagram of an optional electronic device according to an embodiment of the present invention, as Figure 4 shown. The electronic device 40 includes: a memory 401, storing an executable computer program; and a processor 402, configured to run the computer program, where the computer program executes the methods in the various embodiments of the present invention when running.

[0133] An embodiment of the present application further provides a computer-readable storage medium. The computer-readable storage medium includes an executable program stored therein. When the executable program runs, it controls the device where the computer-readable storage medium is located to execute the methods in various embodiments of the present invention.

[0134] An embodiment of the present application further provides a computer program product, including a computer program which, when executed by a processor, implements the methods in various embodiments of the present invention.

[0135] An embodiment of the present application further provides a computer program which, when executed by a processor, implements the methods in the above-mentioned various embodiments of the present invention.

[0136] In the above embodiments of the present invention, the descriptions of the various embodiments have their own emphases. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0137] In the several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0138] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, the functional units in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0140] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs.

[0141] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A substation inspection method, characterized in that: include: Acquire detection data of the substation, wherein the detection data includes: environmental data of the environment in which the substation is located, status data of primary equipment in the substation, and operation data of secondary equipment in the substation; Mapping the detection data to a virtual model of the substation, using the virtual model to simulate and predict the working process of the substation to obtain prediction data of the substation, wherein the prediction data is used to characterize fault data of a fault in the substation; Generate an inspection path and an inspection plan based on the prediction data; The substation is inspected based on the inspection path and the inspection plan.

2. The method according to claim 1, characterized in that The step of mapping the detection data to the virtual model of the substation, and using the virtual model to simulate and predict the working process of the substation to obtain the prediction data of the substation includes: Determining target detection data that meets preset conditions from the detection data; Acquire target historical detection data of a target device, wherein the target device is an electric power device corresponding to the target detection data; The target historical detection data and the target detection data are mapped to the virtual model, and the working process of the substation is simulated and predicted using the virtual model to obtain the prediction data.

3. The method according to claim 2, characterized in that The step of determining target detection data satisfying a preset condition from the detection data includes: Obtain multiple historical test data corresponding to any test data; Based on the plurality of historical detection data, predicting inferred data corresponding to the detection data; Determining a unidirectional change gradient of the detection data based on the detection data and the inferred data; When the unidirectional change gradient is greater than a first threshold, the detection data is determined to be the target detection data.

4. The method according to claim 3, characterized in that The predicting of inferred data corresponding to the detection data based on the plurality of historical detection data includes: Sorting the plurality of historical detection data in chronological order to obtain a historical detection data sequence; Superimposing the historical detection data sequences to obtain multiple superimposed sequences; Fitting the multiple superposition sequences to obtain a fitting function; Determine inferred data corresponding to the detection data based on the fitting function.

5. The method according to claim 4, characterized in that The step of fitting the multiple superposition sequences to obtain a fitting function comprises: Constructing an initial fitting function, wherein the initial fitting function includes an initial value of at least one parameter; Solving the initial fitting function based on the multiple superposition sequences to obtain a target value of the at least one parameter; The fitting function is obtained by replacing an initial value of at least one parameter in the initial fitting function with a target value of the at least one parameter.

6. The method according to claim 2, characterized in that The step of mapping the target historical detection data and the target detection data to the virtual model, and using the virtual model to simulate and predict the working process of the substation to obtain the prediction data includes: Based on the target historical detection data, the operating parameters of the target device and the associated devices are adjusted multiple times in the virtual model to obtain multiple simulated detection data, wherein the associated devices are used to characterize the power devices that have an associated relationship with the target device; Comparing the target detection data with the plurality of simulation detection data to determine the target simulation detection data among the plurality of simulation detection data; Based on the target operating parameters corresponding to the target simulation detection data, determining a fault model corresponding to the target operating parameters from the virtual model; The operation risk of the substation is analyzed in the virtual model based on the fault model to obtain the prediction data.

7. The method according to claim 6, characterized in that The step of comparing the target detection data with the plurality of simulation detection data to determine the target simulation detection data among the plurality of simulation detection data comprises: constructing a target data set based on the target detection data, target time data corresponding to the target detection data, device information of the target device, and other detection data of the target device; constructing a plurality of simulation data sets based on different simulation detection data, the target time data, the device information and other simulation detection data of the target device; Determining deviation values ​​between the target data set and different simulated data sets; When the deviation value corresponding to any one of the simulated data sets is greater than the second threshold, the simulated detection data corresponding to the simulated data set is determined to be the target simulated detection data.

8. The method according to claim 1, characterized in that The generating of the inspection path and the inspection plan based on the prediction data comprises: Acquiring historical detection data corresponding to the predicted data; Based on the prediction data and the historical detection data, the substation is graded to obtain a defect grade of the substation; Based on the defect level, the inspection path and the inspection plan are generated.

9. The method according to claim 8, characterized in that The step of grading the substation based on the prediction data and the historical detection data to obtain the defect level of the substation includes: The prediction data and the historical detection data are input into the inspection and early warning model, and the substation is graded using the inspection and early warning model to obtain the defect grade of the substation.

10. A substation inspection system, characterized in that: Used to execute the substation inspection method according to any one of claims 1 to 9, the system comprises: a device perception layer, an inspection control layer, an information interaction layer and an inspection device; The device perception layer is arranged in the physical space of the substation, and is used to obtain detection data of the substation, wherein the detection data includes: environmental data of the environment in which the substation is located, status data of primary equipment in the substation, and operation data of secondary equipment in the substation; The information interaction layer is connected to the device perception layer and the inspection control layer respectively, and is used to receive the detection data and map the detection data to the virtual model of the substation in the inspection control layer; The inspection control layer is used to simulate and predict the working process of the substation using the virtual model to obtain prediction data of the substation, and generate an inspection path and an inspection plan based on the prediction data, wherein the prediction data is used to characterize fault data of a fault in the substation; The inspection device is used to inspect the substation based on the inspection path and the inspection plan.

11. The system according to claim 10, characterized in that The virtual model includes a visualization interface, and the operation status data of the substation is displayed in the visualization interface.

12. The system according to claim 10, characterized in that The system further comprises: The alarm module is used to output alarm information when the virtual model is used to simulate and predict the working process of the substation.

13. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 9 when running.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 9.

15. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images