Power transmission line defect hidden danger identification method and device, electronic equipment and storage medium

Abstract

The invention discloses a power transmission line defect hidden danger identification method and device, electronic equipment and a storage medium, and the method comprises the steps: extracting defect hidden danger data from the historical operation data of a power transmission line, the defect hidden danger data comprising the defect hidden danger type of the power transmission line and feature data corresponding to the defect hidden danger type; performing model training based on the defect hidden danger data to obtain a trained defect hidden danger detection model; acquiring real-time operation data of the power transmission line; and inputting the real-time operation data into the defect hidden danger detection model so as to identify the defect hidden danger type existing in the operation of the power transmission line. According to the embodiment of the invention, the defect hidden danger detection model is established by extracting the defect hidden danger data, data such as panoramic pictures of a large number of power transmission lines can be acquired and analyzed one by one, the comprehensiveness and objectivity of power transmission line detection analysis are realized, and the reference and accuracy of an analysis result are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid maintenance, and in particular to a method, device, electronic equipment and storage medium for identifying defects and hidden dangers of power transmission lines. Background Art

[0002] The potential safety hazards between the installed gas pipelines and power transmission lines, as well as the potential safety hazards of defects in the power transmission lines are worrying.

[0003] In the prior art, data is collected from the power transmission line mainly by using a remote data collection terminal that is connected to the monitoring terminal, and the data is sent to a manual terminal for identification and observation, so as to timely discover abnormal information and safety hazards of the line.

[0004] However, due to the huge number of transmission lines, it is difficult to collect and analyze data such as panoramic pictures of the transmission lines one by one, and thus it is impossible to understand the actual situation of the current transmission lines more accurately. At the same time, it is also impossible to guarantee the comprehensiveness and authenticity of manual identification and observation in the process of transmission line detection and analysis, and thus it is impossible to guarantee the referenceability and accuracy of the analysis results. Summary of the invention

[0005] The present invention provides a method for identifying defects and hidden dangers of a power transmission line, so as to solve the problem that the referenceability and accuracy of the analysis results cannot be guaranteed in the existing process of identifying defects and hidden dangers of a power transmission line.

[0006] In a first aspect, the present invention provides a method for identifying defects and hidden dangers of a power transmission line, comprising:

[0007] Extracting defect hidden danger data from historical operation data of the transmission line, wherein the defect hidden danger data includes defect hidden danger types of the transmission line and characteristic data corresponding to the defect hidden danger types;

[0008] Performing model training based on the defect hidden danger data to obtain a trained defect hidden danger detection model;

[0009] Obtain real-time operation data of transmission lines;

[0010] The real-time operation data is input into the defect hidden danger detection model to identify the defect hidden danger types existing during the operation of the transmission line.

[0011] In a second aspect, the present invention provides a device for identifying defects and hidden dangers of a power transmission line, comprising:

[0012] A defect hidden danger data acquisition module is used to extract defect hidden danger data from the historical operation data of the transmission line, wherein the defect hidden danger data includes the defect hidden danger type of the transmission line and the characteristic data corresponding to the defect hidden danger type;

[0013] A model training module, used to perform model training based on the defect hidden danger data to obtain a trained defect hidden danger detection model;

[0014] A real-time operation data acquisition module is used to obtain real-time operation data of the transmission line;

[0015] A defect hidden danger type identification module is used to input the real-time operation data into the defect hidden danger detection model to identify the defect hidden danger type existing during the operation of the transmission line.

[0016] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for identifying defects and hidden dangers of transmission lines described in the first aspect of the present invention.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a processor to implement the method for identifying defects and hidden dangers of transmission lines described in the first aspect of the present invention when executed.

[0021] The embodiment of the present invention provides a method for identifying defects and hidden dangers of a power transmission line, including: extracting defect and hidden danger data from the historical operation data of the power transmission line, the defect and hidden danger data including the defect and hidden danger type of the power transmission line and the characteristic data corresponding to the defect and hidden danger type, performing model training based on the defect and hidden danger data to obtain a trained defect and hidden danger detection model; acquiring the real-time operation data of the power transmission line; inputting the real-time operation data into the defect and hidden danger detection model to identify the defect and hidden danger type existing when the power transmission line is in operation. The embodiment of the present invention extracts defect and hidden danger data to build a defect and hidden danger detection model, and can collect and analyze a large number of data such as panoramic pictures of the power transmission line one by one, thereby achieving the comprehensiveness and objectivity of the power transmission line detection and analysis, thereby ensuring the referenceability and accuracy of the analysis results.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a method for identifying defects and hidden dangers of a power transmission line provided by an embodiment of the present invention;

[0025] Figure 2 It is a flow chart of a method for obtaining defect hidden danger data provided by an embodiment of the present invention;

[0026] Figure 3 It is a structural schematic diagram of a device for identifying defects and hidden dangers of a power transmission line provided by an embodiment of the present invention;

[0027] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] Figure 1 This is a flow chart of a method for identifying defects and hidden dangers in a power transmission line provided by an embodiment of the present invention. This embodiment is applicable to the case of identifying defects and hidden dangers in a power transmission line. The method can be executed by a device for identifying defects and hidden dangers in a power transmission line. The device for identifying defects and hidden dangers in a power transmission line can be implemented in the form of hardware and / or software. The device for identifying defects and hidden dangers in a power transmission line can be configured in an electronic device. Figure 1 As shown, the method for identifying defects and hidden dangers of transmission lines includes:

[0030] S11. Extract defect hidden danger data from the historical operation data of the transmission line.

[0031] Information collection equipment and a gateway connected to the information collection equipment are provided along the transmission line. Specifically, the information collection equipment may be an image collection device or an electrical signal collection device. The information collection equipment collects operating data of the transmission line and sends it to the gateway. The gateway may be directly or indirectly connected to the transmission line defect and hidden danger identification device in this embodiment, that is, the transmission line defect and hidden danger identification device may directly or indirectly obtain the operating data of the transmission line.

[0032] The defect hidden danger data includes the defect hidden danger type of the transmission line and the characteristic data corresponding to the defect hidden danger type. The characteristic data can be expressed in the form of pictures or electrical signals. In addition, it can also be data obtained based on the analysis of pictures or electrical signals. For example, the area, volume and texture of an object can be obtained by analyzing the picture.

[0033] In an optional embodiment, the historical operation data includes multiple parameter groups, and the defect hidden danger data is extracted from the historical operation data of the transmission line, including: preprocessing the historical operation data of the transmission line to obtain spare data; and extracting and classifying features of the parameter groups in the spare data to obtain the defect hidden danger data.

[0034] Preprocessing includes data cleaning, data conversion, data integration and data normalization. Data cleaning: remove duplicate data, missing values ​​and outliers, correct erroneous data, etc. to ensure the integrity and accuracy of the data; data conversion: standardize the data to make it conform to the specified data format and unit for subsequent analysis; data integration: integrate data from multiple data sources, eliminate redundant information, and obtain a complete data set; data normalization: normalize the data so that the values ​​of different attributes have the same dimension to avoid the impact of data magnitude.

[0035] The historical operation data includes normal data and defect hidden danger data. The defect hidden danger data is needed when training the defect hidden danger detection model, so the defect hidden danger data needs to be extracted from the historical operation data. Optionally, the defect hidden danger data can be processed by clustering method. Exemplarily, the historical operation data is divided into k groups using the k-means clustering algorithm. Each time a sample is assigned, the cluster center of the cluster is recalculated according to the existing objects in the cluster. This process will be repeated until a certain termination condition is met. The termination condition can be that there is no (or a minimum number of) cluster centers that change again, and the error sum of squares is locally minimized.

[0036] Figure 2 FIG. 1 is a flow chart of a method for obtaining defect hidden danger data. In an optional embodiment, feature extraction and classification are performed on parameter groups in the spare data to obtain defect hidden danger data, such as Figure 2 As shown, the following steps are included:

[0037] S11A, each parameter group in the backup data is recorded as A i .

[0038] Here, i represents the number corresponding to each parameter group, i=1, 2, ..., n.

[0039] S11B, record the types of defects and hidden dangers of the transmission line as B j .

[0040] j represents the number corresponding to each defect hidden danger type, j=1, 2,…, m.

[0041] S11C, the joint probability distribution between each parameter group and each defect hidden danger type is recorded as P(A i , B j ), the marginal rate distribution function of each parameter group and each defect hidden danger type is recorded as P(A i ) and P(B j );

[0042] S11D, according to the joint probability distribution P(A i , B j ), marginal rate distribution function P(A i ) and P(B j ) Calculate the mutual information value between each parameter group and each defect hidden danger type.

[0043] The mutual information value is a useful information measure in information theory. It can be viewed as the amount of information contained in a random variable about another random variable, or the uncertainty of a random variable reduced due to the knowledge of another random variable. Therefore, the mutual information value can be used as a measure between parameter groups and defect potential risk categories.

[0044] The calculation formula of mutual information value is as follows:

[0045]

[0046] Among them, β ij , P(A i , B j ) are the mutual information value and joint probability distribution of the i-th parameter group and the j-th defect hidden danger type, P(A i ) and P(B j ) are the marginal rate distribution functions of the i-th parameter group and the j-th defect hidden danger type respectively.

[0047] S11E. Determine characteristic data corresponding to each defect hidden danger type based on the mutual information value between each parameter group and each defect hidden danger type.

[0048] Mutual information is a measure between feature data and defect hidden danger types. If the feature data belongs to the defect hidden danger type, their mutual information value is large. Therefore, each mutual information value can be compared with the information threshold in the database; when the mutual information value is greater than or equal to the information threshold, the parameter group corresponding to the mutual information value is recorded as the feature data of the defect hidden danger type corresponding to the mutual information value, wherein the information threshold can be set based on actual needs. When the information threshold is large, the correlation between the defect hidden danger types corresponding to the mutual information value is greater. Furthermore, when a parameter group corresponds to multiple defect hidden danger types, the defect hidden danger type corresponding to the maximum mutual information value is used as the only defect hidden danger type corresponding to the parameter group, making the data more accurate. The subsequent defect hidden danger detection model is trained based on the feature data and the corresponding defect hidden danger type, which reduces the time wasted on data analysis in the early stage of model training to a certain extent, ensures the accuracy of the model's analysis results, and can improve the model's prediction ability, that is, improve the recognition accuracy of defect hidden danger types.

[0049] Optionally, each characteristic data includes at least one of the distance between the transmission line and the gas pipeline, abnormal hot spot value, temperature mutation area, insulator crack value, connector looseness value, current value, voltage value, impedance value and resistance value. These data are important parameters for analyzing whether there are defects and hidden dangers in the transmission line. Multi-dimensional parameters make the analysis results more comprehensive. The lack of them will reduce the accuracy of the analysis results, and the authenticity of the analysis results cannot be guaranteed, which will reduce the use effect of the defect and hidden danger detection model to a certain extent. Among them, the distance between the transmission line and the gas pipeline has not been used in the prior art, but the distance between the transmission line and the gas pipeline is also an important parameter for the occurrence of defects and hidden dangers in the transmission line. When the distance is too short, it is easy to cause danger. Therefore, this embodiment takes this parameter into consideration, which can improve the defect and hidden danger detection effect of the transmission line and further ensure the safety of the transmission line.

[0050] Among them, the distance between the transmission line and the gas pipeline can be obtained based on the picture. The specific method is: measurement reference marks are set on the transmission line and the gas pipeline. The measurement reference marks can be set along the surface of the transmission line and the gas pipeline. After the on-site picture is collected, the relationship between the first distance parameter of the measurement reference mark in the picture and the actual distance parameter is used as a reference relationship, and then the distance between the transmission line and the gas pipeline in the picture is obtained as the second distance parameter. Based on the reference relationship and the second distance parameter, the distance between the transmission line and the gas pipeline can be accurately measured to avoid errors and spatial distortion effects caused by the image acquisition device.

[0051] S11F. Take each defect hidden danger type and a set of characteristic data corresponding to each defect hidden danger type as defect hidden danger data.

[0052] In the above steps, n represents the total number of parameter groups; m represents the total number of defect potential types, and both n and m are positive integers greater than 2; generally speaking, n<m.

[0053] S12. Perform model training based on the defect and hidden danger data to obtain a trained defect and hidden danger detection model.

[0054] In the first step, the characteristic data of each defect hidden danger type can be labeled and divided, and then the training set and the verification set of the operation data can be obtained. The specific labeling process is as follows:

[0055] The characteristic data of each defect hidden danger type is used as defect hidden danger data and marked as 0, and the normal data is marked as 1; the defect hidden danger data and the normal data are mixed to obtain an operating data set, and then the operating data set is divided.

[0056] Optionally, the operating data set includes normal data 1 and defect hidden danger data 0, normal data 1 includes the distance between the transmission line and the gas pipeline, abnormal hot spot value, temperature value mutation area, insulator crack value, connector looseness value, current value, voltage value, impedance value and resistance value; defect hidden danger data 0 includes the defect hidden danger type, and also includes the distance between the transmission line and the gas pipeline, abnormal hot spot value, temperature value mutation area, insulator crack value, connector looseness value, current value, voltage value, impedance value and resistance value corresponding to the defect hidden danger type.

[0057] Optionally, the running data set is divided. The specific division process is as follows:

[0058] The running data set is divided into w subsets, one subset is extracted as the validation set of the running data, the remaining w-1 subsets are used as the training set of the running data, and the w-1 subsets are rotated one by one as the validation set of the running data until all w subsets have been used as the validation set. In this way, w performance indicators can be obtained, and the average value of the w performance indicators can be calculated as the estimated parameter of the model performance. It should be noted that the subsets are rotated one by one as the validation set of the running data, which means that the wth subset is used as the validation set in the first iteration, and any subset other than the wth subset is used as the validation set of the data in the second iteration, and any subset other than the first and second subsets is used as the validation set of the data in the third iteration, and so on.

[0059] In the second step, the training set and the validation set in the operation data set are extracted to train the initial model to obtain a pre-trained large model, and then the fine-tuning operation data set is used to fine-tune the obtained pre-trained large model by SFT (Supervised Fine-Tun-ing) to obtain a defect hidden danger detection model for the transmission line. Optionally, the fine-tuning operation data set includes fine-tuning operation input data and fine-tuning operation output data.

[0060] The specific training process is as follows:

[0061] The model is repeatedly trained using the training set and the operation data validation set to obtain a pre-trained large model, and the fine-tuning operation data set is extracted from the database. Then, the fine-tuning operation data set is used to fine-tune each setting layer of the pre-trained large model through SFT supervised fine-tuning, so as to optimize the pre-trained large model through the back propagation algorithm to obtain a defect hidden danger detection model for transmission lines. It should be noted that each setting layer is the last several layers, and if adjustment is required, it can also be set to the middle several layers.

[0062] S13. Obtain real-time operation data of the transmission line.

[0063] The operation data of the transmission line is detected in real time and recorded as the real-time operation data of the transmission line.

[0064] S14. Input the real-time operation data into the defect hidden danger detection model to identify the defect hidden danger types existing during the operation of the transmission line.

[0065] The data are transmitted to the defect hidden danger detection model of the transmission line, and then the defect hidden danger analysis results of the transmission line are output. When the defect hidden danger detection model analyzes that the transmission line is operating normally, 1 is output. When the defect hidden danger detection model analyzes that a defect hidden danger occurs in the transmission line, 0 is output. The defect hidden danger types in the defect hidden danger data are displayed in the form of a chart, including the distance between the transmission line and the gas pipeline, abnormal hot spot value, temperature value mutation area, insulator crack value, loose connection value, current value, voltage value, impedance value and resistance value corresponding to the defect hidden danger type. In addition, the corresponding normal data range can be marked for each defect hidden danger type in the defect hidden danger analysis result, and an early warning prompt can be given at the same time.

[0066] The embodiment of the present invention provides a method for identifying defects and hidden dangers of a power transmission line, including: extracting defect and hidden danger data from the historical operation data of the power transmission line, the defect and hidden danger data including the defect and hidden danger type of the power transmission line and the characteristic data corresponding to the defect and hidden danger type, performing model training based on the defect and hidden danger data to obtain a trained defect and hidden danger detection model; acquiring the real-time operation data of the power transmission line; inputting the real-time operation data into the defect and hidden danger detection model to identify the defect and hidden danger type existing when the power transmission line is in operation. The embodiment of the present invention extracts defect and hidden danger data to build a defect and hidden danger detection model, and can collect and analyze a large number of data such as panoramic pictures of the power transmission line one by one, thereby achieving the comprehensiveness and objectivity of the power transmission line detection and analysis, thereby ensuring the referenceability and accuracy of the analysis results.

[0067] In one embodiment of the present invention, a device for identifying defects and hidden dangers of a power transmission line is provided. Figure 3 As shown, Figure 3The present invention is a schematic diagram of a structure of a device for identifying defects and hidden dangers of a power transmission line, and the device for identifying defects and hidden dangers of a power transmission line comprises:

[0068] The defect hidden danger data acquisition module 301 is used to extract defect hidden danger data from the historical operation data of the transmission line, wherein the defect hidden danger data includes the defect hidden danger type of the transmission line and the characteristic data corresponding to the defect hidden danger type;

[0069] A model training module 302 is used to perform model training based on the defect hidden danger data to obtain a trained defect hidden danger detection model;

[0070] A real-time operation data acquisition module 303 is used to acquire real-time operation data of the transmission line;

[0071] The defect hidden danger type identification module 304 is used to input the real-time operation data into the defect hidden danger detection model to identify the defect hidden danger type existing during the operation of the transmission line.

[0072] Optionally, the historical operation data includes multiple parameter groups, and the defect hidden danger data acquisition module 301 includes:

[0073] A backup data acquisition submodule is used to pre-process the historical operation data of the transmission line to obtain backup data;

[0074] The defect hidden danger data acquisition submodule is used to extract features and classify the parameter groups in the backup data to obtain defect hidden danger data.

[0075] Optionally, the defect hidden danger data acquisition submodule includes:

[0076] A parameter group marking unit, used to mark each parameter group in the backup data as A i , where i represents the number corresponding to each parameter group, i = 1, 2, ..., n;

[0077] Defect hidden danger type marking unit, used to mark each defect hidden danger type of the transmission line as B j , j represents the number corresponding to each defect hidden danger type, j = 1, 2, ..., m;

[0078] The distribution and distribution function marking unit is used to record the joint probability distribution between each parameter group and each defect hidden danger type as P(A i , B j ), the marginal rate distribution function of each parameter group and each defect hidden danger type is recorded as P(A i ) and P(B j );

[0079] A mutual information value calculation unit is used to calculate the mutual information value according to the joint probability distribution P(Ai , B j ), the edge rate distribution function P(A i ) and P(B j ) calculate the mutual information value between each parameter group and each defect hidden danger type;

[0080] A feature data extraction unit, used to determine feature data corresponding to each defect hidden danger type based on the mutual information value between each parameter group and each defect hidden danger type;

[0081] The hidden danger data obtaining unit is used to take each defect hidden danger type and a set of characteristic data corresponding to each defect hidden danger type as defect hidden danger data.

[0082] Optionally, the mutual information value is calculated as follows:

[0083]

[0084] Among them, β ij , P(A i , B j ) are the mutual information value and joint probability distribution of the i-th parameter group and the j-th defect hidden danger type, P(A i ) and P(B j ) are the marginal rate distribution functions of the i-th parameter group and the j-th defect hidden danger type respectively.

[0085] Optionally, the feature data extraction unit includes:

[0086] A comparison subunit, used to compare each of the mutual information values ​​with an information threshold in a database;

[0087] The feature data extraction subunit is used to record the parameter group corresponding to the mutual information value as the feature data of the defect hidden danger type corresponding to the mutual information value when the mutual information value is greater than or equal to the information threshold.

[0088] Optionally, the defect hidden danger type identification module 304 includes:

[0089] An analysis result acquisition submodule, used for inputting the real-time operation data into the defect hidden danger detection model to output the defect hidden danger analysis result of the transmission line;

[0090] The defect hidden danger type warning submodule is used to display the defect hidden danger type corresponding to the real-time operation data, mark the corresponding normal data range and issue a warning when a defect hidden danger is detected in the transmission line.

[0091] Optionally, each of the characteristic data includes at least one of the distance between the transmission line and the gas pipeline, abnormal hot spot value, temperature change area, insulator crack value, connector looseness value, current value, voltage value, impedance value and resistance value.

[0092] The device for identifying defects and hidden dangers of a power transmission line provided in an embodiment of the present invention can execute the method for identifying defects and hidden dangers of a power transmission line provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0093] In one embodiment of the present invention, Figure 4 As shown, an electronic device 40 that can be used to implement an embodiment of the present invention is provided. Figure 4 4 is a schematic diagram of the structure of an electronic device 40. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0094] like Figure 4 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0095] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0096] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as a method for identifying hidden dangers of power transmission line defects.

[0097] In some embodiments, the method for identifying defects and hidden dangers of a transmission line may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the method for identifying defects and hidden dangers of a transmission line described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the method for identifying defects and hidden dangers of a transmission line by any other appropriate means (e.g., by means of firmware).

[0098] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0100] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0101] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0102] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0103] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0104] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0105] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying defects and hidden dangers of power transmission lines, characterized in that: include: Extracting defect hidden danger data from historical operation data of the power transmission line, wherein the defect hidden danger data includes defect hidden danger types of the power transmission line and characteristic data corresponding to the defect hidden danger types; Performing model training based on the defect hidden danger data to obtain a trained defect hidden danger detection model; Obtain real-time operation data of transmission lines; The real-time operation data is input into the defect hidden danger detection model to identify the defect hidden danger types existing during the operation of the transmission line.

2. The method according to claim 1, characterized in that The historical operation data includes a plurality of parameter groups, and the step of extracting defect hidden danger data from the historical operation data of the power transmission line includes: Preprocess the historical operation data of the transmission line to obtain backup data; Feature extraction and classification are performed on the parameter groups in the spare data to obtain defect hidden danger data.

3. The method according to claim 2, characterized in that The feature extraction and classification of the parameter groups in the spare data to obtain defect hidden danger data includes: Each parameter group in the backup data is recorded as A i , where i represents the number corresponding to each parameter group, i = 1, 2, ..., n; The types of defects and hidden dangers of transmission lines are recorded as B j , j represents the number corresponding to each defect hidden danger type, j = 1, 2, ..., m; The joint probability distribution between each parameter group and each defect hidden danger type is denoted as P(A i , B j ), the marginal rate distribution function of each parameter group and each defect hidden danger type is recorded as P(A i ) and P(B j ); According to the joint probability distribution P(A i , B j ), the edge rate distribution function P(A i ) and P(B j ) calculate the mutual information value between each parameter group and each defect hidden danger type; Determine the characteristic data corresponding to each defect hidden danger type based on the mutual information value between each parameter group and each defect hidden danger type; A collection of each defect hidden danger type and the characteristic data corresponding to each defect hidden danger type is used as defect hidden danger data.

4. The method according to claim 3, characterized in that The calculation formula of the mutual information value is as follows: Among them, β ij , P(A i , B j ) are the mutual information value and joint probability distribution of the i-th parameter group and the j-th defect hidden danger type, P(A i ) and P(B j ) are the marginal rate distribution functions of the i-th parameter group and the j-th defect hidden danger type respectively.

5. The method according to claim 3, characterized in that The determining of the characteristic data corresponding to each defect hidden danger type based on the mutual information value between each parameter group and each defect hidden danger type includes: Comparing each of the mutual information values ​​with an information threshold in a database respectively; When the mutual information value is greater than or equal to the information threshold, the parameter group corresponding to the mutual information value is recorded as characteristic data of the defect hidden danger type corresponding to the mutual information value.

6. The method according to any one of claims 1 to 5, characterized in that: The step of inputting the real-time operation data into the defect hidden danger detection model to identify the defect hidden danger types existing in the operation of the transmission line includes: Inputting the real-time operation data into the defect hidden danger detection model to output the defect hidden danger analysis result of the transmission line; When defects and hidden dangers are detected in the transmission line, the defect and hidden danger type corresponding to the real-time operation data is displayed, and the corresponding normal data range is marked and an early warning is issued.

7. The method according to any one of claims 1 to 5, characterized in that: Each of the characteristic data includes at least one of the distance between the power transmission line and the gas pipeline, abnormal hot spot value, temperature change area, insulator crack value, connector looseness value, current value, voltage value, impedance value and resistance value.

8. A device for identifying defects and hidden dangers of power transmission lines, characterized in that: include: A defect hidden danger data acquisition module is used to extract defect hidden danger data from the historical operation data of the transmission line, wherein the defect hidden danger data includes the defect hidden danger type of the transmission line and the characteristic data corresponding to the defect hidden danger type; A model training module, used to perform model training based on the defect hidden danger data to obtain a trained defect hidden danger detection model; A real-time operation data acquisition module is used to obtain real-time operation data of the transmission line; The defect hidden danger type identification module is used to input the real-time operation data into the defect hidden danger detection model to identify the defect hidden danger type existing during the operation of the transmission line.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for identifying defects and hidden dangers of a power transmission line according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for identifying defects and hidden dangers of a power transmission line according to any one of claims 1 to 7 when executed.

Images