Low-voltage distribution network fault analysis method, system, equipment and medium

Abstract

The invention relates to the technical field of low-voltage distribution network fault detection, in particular to a low-voltage distribution network fault analysis method, system and device and a medium. The method comprises the following steps: firstly, preprocessing to obtain power data from a low-voltage distribution network, and extracting to obtain electrical quantity characteristics; constructing a fault analysis model to obtain a fault type; and finally, analyzing a fault type according to a low-voltage distribution network GIS topological structure, generating a fault work order and issuing the fault work order. The low-voltage distribution network data is mined and analyzed based on the big data technology, the reason and the position of the fault are quickly and accurately analyzed, and the efficiency and the accuracy of fault analysis are improved; the state of the low-voltage distribution network is monitored in real time by issuing a fault work order, abnormity and faults are found in time, damage to power equipment and power failure accidents are avoided, resource configuration of a power system is optimized, operation cost is reduced, and safe and stable operation of the power system is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of low-voltage distribution network fault detection, and in particular to a low-voltage distribution network fault analysis method, system, equipment and medium. Background Art

[0002] In the context of advocating the construction of a new power system, State Grid Corporation of China proposed a framework for the digital technology support system of the new power system, and clarified the overall digital architecture of three zones and four layers, among which equipment data collection and in-depth application are important contents. State Grid Sichuan Electric Power Company is also accelerating the top-level layout and promotion in the field of smart grids. All digital construction of power grids is to meet people's yearning for a better life, and the low-voltage distribution network is closest to users and can best reflect the company's service level and service quality. However, although some equipment has been developed in the field of intelligence in the current low-voltage distribution network, in-depth research has not yet been carried out on how to use and make good use of data.

[0003] With the continuous advancement of science and technology, big data technology has gradually penetrated into all walks of life, bringing many conveniences to modern society. In the power industry, big data technology has also shown great potential. In particular, the application of big data technology is expected to bring revolutionary breakthroughs in the intelligent analysis of low-voltage distribution network faults. At present, there are many types of distribution network faults, complex fault modes, and it is difficult to analyze and locate faults. Traditional low-voltage distribution network fault diagnosis methods mainly rely on manual experience and rules, and the analysis efficiency and accuracy are low. Summary of the invention

[0004] Aiming at the problems that the current distribution network has many types of faults, complex fault modes, difficult fault analysis and positioning, and low analysis efficiency and accuracy, the present invention proposes a low-voltage distribution network fault analysis method, system, equipment and medium; the method first pre-processes the power data obtained from the low-voltage distribution network and extracts the electrical quantity characteristics; then builds a fault analysis model to obtain the fault type; finally, analyzes the fault type according to the low-voltage distribution network GIS topological structure, generates and publishes a fault work order; quickly and accurately identifies, locates and diagnoses faults, greatly improves the efficiency and accuracy of fault handling, and ensures the safe and stable operation of the power system.

[0005] The specific implementation contents of the present invention are as follows: A low voltage distribution network fault analysis method specifically comprises the following steps: Step S1: pre-processing to obtain power data from the low voltage distribution network; Step S2: extracting the preprocessed power data to obtain electrical quantity characteristics; Step S3: constructing a fault analysis model according to the power characteristics; Step S4: inputting the power data into the constructed fault analysis model to obtain the fault type; Step S5: Analyze the fault type according to the low-voltage distribution network GIS topology structure, generate a fault work order and publish it.

[0006] In order to better implement the present invention, further, the step S2 specifically includes the following steps: Step S21: extracting electrical quantity characteristics according to the preprocessed power data; the electrical quantity characteristics include current characteristics, voltage characteristics, and power characteristics; Step S22: Perform time domain analysis and frequency domain transformation according to the electrical quantity characteristics to obtain time domain characteristics and frequency domain characteristics.

[0007] In order to better implement the present invention, further, the step S3 specifically includes the following steps: Step S31: Based on the time domain features and the frequency domain features, a deep learning model is called to build a fault analysis model; Step S32: Convert the electrical quantity data into image data to train the fault analysis model to obtain a trained fault analysis model.

[0008] In order to better implement the present invention, further, the step S4 specifically includes the following steps: Step S41: input the newly acquired power data into the trained fault analysis model, and output fault information if a fault exists; Step S42: calling an integrated learning method to fuse multiple output fault information to obtain fused information; Step S43: Analyze and obtain the fault type based on the fusion information.

[0009] In order to better implement the present invention, further, step S5 specifically includes the following steps: Step S51: classify the fault type according to the acquired low-voltage distribution network line information and SOE signal; Step S52: Obtain the fault location based on the acquired terminal online status information, power-off alarm time, instantaneous quantity data, and classified fault type in combination with the low-voltage distribution network GIS topology structure; Step S53: Generate and publish a fault work order based on the fault location.

[0010] In order to better implement the present invention, further, the step S1 specifically includes the following steps: Step S11: acquiring power data from the low voltage distribution network and cleaning it to obtain cleaned power data; Step S12: calling a statistical method to calculate abnormal values ​​of the cleaned power data; Step S13: removing abnormal power data according to the abnormal value to obtain the power data after removal; Step S14: normalize the removed power data to obtain pre-processed power data.

[0011] In order to better implement the present invention, further, a low-voltage distribution network fault analysis system is proposed, which is used for the above-mentioned low-voltage distribution network fault analysis method; it includes a preprocessing unit, an extraction unit, a construction unit, an analysis unit, and a publishing unit; The preprocessing unit is used to preprocess the power data obtained from the low voltage distribution network; The extraction unit is used to extract the pre-processed power data to obtain the electrical quantity characteristics; The construction unit is used to construct a fault analysis model according to the power characteristics; The extraction unit is used to input the power data into the constructed fault analysis model to obtain the fault type; The publishing unit is used to analyze the fault type according to the low-voltage distribution network GIS topology structure, generate a fault work order and publish it.

[0012] In order to better implement the present invention, further, an electronic device is proposed, including a memory and a processor; a computer program is stored in the memory; when the computer program is executed on the processor, the above-mentioned low-voltage distribution network fault analysis method is executed.

[0013] In order to better implement the present invention, further, a computer-readable storage medium is proposed, on which computer instructions are stored; when the computer instructions are executed on the above-mentioned electronic device, the above-mentioned low-voltage distribution network fault analysis method is implemented.

[0014] The present invention has the following beneficial effects: (1) The present invention mines and analyzes low-voltage distribution network data based on big data technology, quickly and accurately analyzes the cause and location of the fault, and improves the efficiency and accuracy of fault analysis.

[0015] (2) The present invention monitors the status of the low-voltage distribution network in real time by issuing fault work orders, promptly discovers anomalies and faults, avoids damage to power equipment and power outages, optimizes the resource allocation of the power system, reduces operating costs, and ensures the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic block diagram of the process provided by the present invention. DETAILED DESCRIPTION

[0017] In order to more clearly illustrate the technical solutions of the embodiments 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 drawings in the embodiments of the present invention. It should be understood that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments, and therefore should not be regarded as limiting the scope of protection. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technical personnel in this field without making creative work are within the scope of protection of the present invention.

[0018] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "disposed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0019] Embodiment 1: This embodiment provides a low voltage distribution network fault analysis method, which specifically includes the following steps: Step S1: Preprocessing to obtain power data from the low voltage distribution network.

[0020] The step S1 specifically includes the following steps: Step S11: acquiring power data from the low voltage distribution network and cleaning it to obtain cleaned power data; Step S12: calling a statistical method to calculate abnormal values ​​of the cleaned power data; Step S13: removing abnormal power data according to the abnormal value to obtain the power data after removal; Step S14: normalize the removed power data to obtain pre-processed power data.

[0021] Step S2: extract the preprocessed power data to obtain electrical quantity characteristics.

[0022] Furthermore, the step S2 specifically includes the following steps: Step S21: extracting electrical quantity characteristics according to the preprocessed power data; the electrical quantity characteristics include current characteristics, voltage characteristics, and power characteristics; Step S22: Perform time domain analysis and frequency domain transformation according to the electrical quantity characteristics to obtain time domain characteristics and frequency domain characteristics.

[0023] Step S3: constructing a fault analysis model according to the power characteristics.

[0024] Furthermore, the step S3 specifically includes the following steps: Step S31: Based on the time domain features and the frequency domain features, a deep learning model is called to build a fault analysis model; Step S32: Convert the electrical quantity data into image data to train the fault analysis model to obtain a trained fault analysis model.

[0025] Step S4: Input the power data into the constructed fault analysis model to obtain the fault type.

[0026] Furthermore, the step S4 specifically includes the following steps: Step S41: input the newly acquired power data into the trained fault analysis model, and output fault information if a fault exists; Step S42: calling an integrated learning method to fuse multiple output fault information to obtain fused information; Step S43: Analyze and obtain the fault type based on the fusion information.

[0027] Step S5: Analyze the fault type according to the low-voltage distribution network GIS topology structure, generate a fault work order and publish it.

[0028] Furthermore, the step S5 specifically includes the following steps: Step S51: classify the fault type according to the acquired low-voltage distribution network line information and SOE signal; Step S52: Obtain the fault location based on the acquired terminal online status information, power-off alarm time, instantaneous quantity data, and classified fault type in combination with the low-voltage distribution network GIS topology structure; Step S53: Generate and publish a fault work order based on the fault location.

[0029] Working principle: This embodiment first pre-processes the power data obtained from the low-voltage distribution network and extracts the electrical quantity characteristics; then builds a fault analysis model to obtain the fault type; finally, analyzes the fault type according to the low-voltage distribution network GIS topology structure, generates and publishes a fault work order; quickly and accurately identifies, locates and diagnoses faults, greatly improving the efficiency and accuracy of fault handling and ensuring the safe and stable operation of the power system.

[0030] Embodiment 2: This embodiment is described in detail with a specific embodiment based on the above embodiment 1.

[0031] Step S1: Preprocessing to obtain power data from the low voltage distribution network.

[0032] In the power system, the low-voltage distribution network generates a large amount of power data every day. The generated power data contains noise and outliers due to various reasons. Therefore, the power data is first obtained from the low-voltage distribution network of the power system and cleaned to obtain the cleaned power data. Cleaning is the core process of the preprocessing link. Identifying and removing duplicate, missing or irrelevant power data can ensure the consistency and accuracy of the acquired power data.

[0033] After the initial cleaning, there are still power data points that obviously deviate from the normal range, namely power abnormal data, which also need to be processed; these power abnormal data may be caused by power fluctuations, equipment failure or other unknown reasons, so statistical methods are called to calculate the abnormal values, and the power abnormal data are removed according to the abnormal values ​​to obtain the power data after removal.

[0034] After removing abnormal data, data normalization is also an important part of data preprocessing. Since different data types lead to differences between data, the power data after normalization or standardization is removed to make it on the same dimension to obtain the final preprocessed power data.

[0035] Step S2: extract the preprocessed power data to obtain electrical quantity characteristics.

[0036] Although the power data preprocessed in step S1 is more uniform than the original power data, it is difficult to obtain accurate analysis results by directly inputting the preprocessed power data into the deep learning neural network model. Therefore, it is necessary to extract fault-related features from the preprocessed power data. Based on the preprocessed power data, electrical quantity features are extracted. Electrical quantity features are one of the commonly used features in low-voltage distribution network fault analysis. The electrical quantity features include current features, voltage features, and power features, which can reflect the operating status of low-voltage distribution network equipment; and time domain analysis and frequency domain transformation are performed based on the electrical quantity features to obtain time domain features and frequency domain features, which provide rich information for subsequent model construction.

[0037] Step S3: constructing a fault analysis model according to the power characteristics.

[0038] The deep learning neural network model has significant advantages in dealing with complex and nonlinear problems; according to the time domain characteristics and the frequency domain characteristics, the deep learning neural network model is called to build a fault analysis model. The deep learning neural network model includes a convolutional neural network model and a recurrent neural network model; the convolutional neural network is good at processing data with spatial correlation such as image data, converting electrical quantity data into image data such as spectrum diagrams and wavelet transform diagrams, and capturing the time correlation series of electrical quantity data according to the recurrent neural network; then training and learning are performed to obtain the trained fault analysis model.

[0039] Step S4: Input the power data into the constructed fault analysis model to obtain the fault type.

[0040] After the fault analysis model training is completed, the newly acquired power data is input into the fault analysis model for fault analysis to determine whether the current power system state is normal or faulty. If a fault exists, the fault information is output, and the integrated learning method is called to fuse multiple output fault information to obtain the fused information analysis to obtain the fault type. The fusion operation further improves the stability and accuracy of the diagnosis.

[0041] Step S5: Analyze the fault type according to the low-voltage distribution network GIS topology structure, generate a fault work order and publish it.

[0042] Obtain low-voltage distribution network line information and SOE signals, and automatically merge and classify fault types through the obtained low-voltage distribution network line information and SOE events, such as classifying actions, states or operations on the same line into one category; obtain terminal online status information, power-off alarm time, and instantaneous quantity data, and obtain the fault location such as the tripping location based on the classified fault type and the low-voltage distribution network GIS topology structure. Finally, generate a fault work order based on the fault location and publish it to the fault repair platform in real time, and forward it to relevant repair personnel in real time, which improves processing efficiency and can further prevent the expansion of faults.

[0043] The other parts of this embodiment are the same as those of the above-mentioned embodiment 1, and thus will not be described in detail.

[0044] Embodiment 3: This embodiment, based on any one of the above-mentioned embodiments 1-2, proposes a low-voltage distribution network fault analysis system for the above-mentioned low-voltage distribution network fault analysis method; including a preprocessing unit, an extraction unit, a construction unit, an analysis unit, and a publishing unit; The preprocessing unit is used to preprocess the power data obtained from the low voltage distribution network; The extraction unit is used to extract the pre-processed power data to obtain the electrical quantity characteristics; The construction unit is used to construct a fault analysis model according to the power characteristics; The extraction unit is used to input the power data into the constructed fault analysis model to obtain the fault type; The publishing unit is used to analyze the fault type according to the low-voltage distribution network GIS topology structure, generate a fault work order and publish it.

[0045] This embodiment further proposes an electronic device, including a memory and a processor; a computer program is stored in the memory; when the computer program is executed on the processor, the above-mentioned low-voltage distribution network fault analysis method is executed.

[0046] This embodiment further proposes a computer-readable storage medium, on which computer instructions are stored; when the computer instructions are executed on the above-mentioned electronic device, the above-mentioned low-voltage distribution network fault analysis method is implemented.

[0047] The other parts of this embodiment are the same as any one of the above-mentioned embodiments 1-2, so they will not be repeated here.

[0048] The processor involved in the embodiments of the present application may be a chip. For example, it may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0049] The memory involved in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0050] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0051] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0052] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0053] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0054] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one device or distributed on multiple devices. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0055] In addition, each functional module in each embodiment of the present application may be integrated into one device, or each module may exist physically separately, or two or more modules may be integrated into one device.

[0056] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or may include one or more servers, data centers and other data storage devices that can be integrated with the medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0057] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A low voltage distribution network fault analysis method, characterized in that: The specific steps include: Step S1: pre-processing to obtain power data from the low voltage distribution network; Step S2: extracting the preprocessed power data to obtain electrical quantity characteristics; Step S3: constructing a fault analysis model according to the power characteristics; Step S4: inputting the power data into the constructed fault analysis model to obtain the fault type; Step S5: Analyze the fault type according to the low-voltage distribution network GIS topology structure, generate a fault work order and publish it.

2. A low voltage distribution network fault analysis method according to claim 1, characterized in that: The step S2 specifically includes the following steps: Step S21: extracting electrical quantity characteristics according to the preprocessed power data; the electrical quantity characteristics include current characteristics, voltage characteristics, and power characteristics; Step S22: Perform time domain analysis and frequency domain transformation according to the electrical quantity characteristics to obtain time domain characteristics and frequency domain characteristics.

3. A low voltage distribution network fault analysis method according to claim 2, characterized in that: The step S3 specifically comprises the following steps: Step S31: Based on the time domain features and the frequency domain features, a deep learning model is called to build a fault analysis model; Step S32: Convert the electrical quantity data into image data to train the fault analysis model to obtain a trained fault analysis model.

4. A low voltage distribution network fault analysis method according to claim 3, characterized in that: The step S4 specifically comprises the following steps: Step S41: input the newly acquired power data into the trained fault analysis model, and output fault information if a fault exists; Step S42: calling an integrated learning method to fuse multiple output fault information to obtain fused information; Step S43: Analyze and obtain the fault type based on the fusion information.

5. A low voltage distribution network fault analysis method according to claim 4, characterized in that: The step S5 specifically comprises the following steps: Step S51: classify the fault type according to the acquired low-voltage distribution network line information and SOE signal; Step S52: Obtain the fault location based on the acquired terminal online status information, power-off alarm time, instantaneous quantity data, and classified fault type in combination with the low-voltage distribution network GIS topology structure; Step S53: Generate and publish a fault work order based on the fault location.

6. A low voltage distribution network fault analysis method according to claim 1, characterized in that: The step S1 specifically includes the following steps: Step S11: acquiring power data from the low voltage distribution network and cleaning it to obtain cleaned power data; Step S12: calling a statistical method to calculate abnormal values ​​of the cleaned power data; Step S13: removing abnormal power data according to the abnormal value to obtain the power data after removal; Step S14: normalize the removed power data to obtain pre-processed power data.

7. A low voltage distribution network fault analysis system, used to implement the low voltage distribution network fault analysis method according to claim 1; characterized in that: It includes pre-processing unit, extraction unit, construction unit, analysis unit and publishing unit; The preprocessing unit is used to preprocess the power data obtained from the low voltage distribution network; The extraction unit is used to extract the pre-processed power data to obtain the electrical quantity characteristics; The construction unit is used to construct a fault analysis model according to the power characteristics; The extraction unit is used to input the power data into the constructed fault analysis model to obtain the fault type; The publishing unit is used to analyze the fault type according to the low-voltage distribution network GIS topology structure, generate a fault work order and publish it.

8. An electronic device, characterized in that: It comprises a memory and a processor; the memory stores a computer program; when the computer program is executed on the processor, the low-voltage distribution network fault analysis method as described in any one of claims 1-6 is executed.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions; when the computer instructions are executed on the electronic device as claimed in claim 8, the low-voltage distribution network fault analysis method as claimed in any one of claims 1-6 is implemented.

Images