CN114414935A - Automatic positioning method and system for feeder fault area of power distribution network based on big data - Google Patents
Automatic positioning method and system for feeder fault area of power distribution network based on big data Download PDFInfo
- Publication number
- CN114414935A CN114414935A CN202111531499.5A CN202111531499A CN114414935A CN 114414935 A CN114414935 A CN 114414935A CN 202111531499 A CN202111531499 A CN 202111531499A CN 114414935 A CN114414935 A CN 114414935A
- Authority
- CN
- China
- Prior art keywords
- information
- preset
- risk
- generating
- node address
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of power grid detection, and particularly discloses a power distribution network feeder fault area automatic positioning method based on big data, which comprises the steps of obtaining input signals of all nodes and generating prediction signals; acquiring output signals of all nodes, and calculating the offset rate of the output signals and the predicted signals; inputting the determined offset rate and the corresponding node address into a trained risk analysis model to obtain risk information containing the node address; and when the risk information reaches a preset risk threshold value, acquiring a line of information of the corresponding node according to the node address, and generating a dangerous case plan according to the line of information. According to the invention, the output signal is acquired and compared with the prediction signal to generate a preliminary judgment result, and then first-line information is acquired to further detect the corresponding node.
Description
Technical Field
The invention relates to the technical field of power grid detection, in particular to a method and a system for automatically positioning a fault area of a feeder line of a power distribution network based on big data.
Background
In the distribution network, the fault positioning system can monitor the fault and can quickly position the fault after the fault occurs, thereby shortening the fault isolation and recovery time and greatly reducing the power failure loss. The existing fault detection mode is mostly based on some circuit measuring meters, at most, some information transmission functions are added in the circuit measuring meters, in order to enable the detection process to be more accurate, workers need to detect the circuit measuring meters at regular high frequency, and once the circuit measuring meters have problems, the measurement errors can be possibly caused. Therefore, how to reduce the dependency on the circuit measuring meter and enable a worker to perform low-frequency detection on the circuit measuring meter so as to reduce the labor cost is a technical problem to be solved by the technical scheme of the invention.
Disclosure of Invention
The invention aims to provide a method and a system for automatically positioning a feeder fault area of a power distribution network based on big data, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a big data-based automatic positioning method for a feeder fault area of a power distribution network comprises the following steps:
acquiring input signals of all nodes according to a preset node address table, and generating prediction signals according to the input signals;
acquiring output signals of all nodes according to a preset node address table, and calculating the offset rates of the output signals and the prediction signals;
inputting the determined offset rate and the corresponding node address into a trained risk analysis model to obtain risk information containing the node address; the nodes are signal points with a plurality of data transmission directions in the power distribution process; the risk information is the probability of different fault types of the power distribution network feed money;
and when the risk information reaches a preset risk threshold value, acquiring a line of information of the corresponding node according to the node address, and generating a dangerous case plan according to the line of information.
As a further scheme of the invention: when the risk information reaches a preset risk threshold value, acquiring a line of information of a corresponding node according to the node address, and generating a dangerous case plan according to the line of information comprises the following steps:
when the risk information reaches a preset risk threshold value, sending an image acquisition instruction to a corresponding acquisition end according to a node address;
receiving image information acquired by an acquisition end, randomly acquiring pixel points in a preset proportion in the image information, and generating a feature point set; the number of the pixel points is the sum of the pixel points of the image information multiplied by a preset proportion;
sequentially converting pixel points in the feature point set into feature values according to a preset conversion formula to obtain a feature array, and generating a representative value based on the feature array, wherein the representative value and the image information are in a mapping relation;
and when the representative value exceeds a preset range, performing content identification on the image information, and generating an emergency plan according to a content identification result.
As a further scheme of the invention: when the representative value exceeds a preset range, the step of identifying the content of the image information and generating the dangerous case plan according to the content identification result comprises the following steps:
comparing the representative value with a boundary value of a preset range, and judging whether the representative value exceeds the preset range;
when the representative value exceeds a preset range, sequentially carrying out logic AND operation on different image information to generate a binary matrix;
calculating the mean value of each element in the binary matrix, and determining corresponding time information when the mean value reaches a preset mean value threshold;
and reading target image information according to the time information, comparing the target image information with a preset reference image, and generating a dangerous case plan according to a comparison result.
As a further scheme of the invention: the steps of reading target image information according to the time information, comparing the target image information with a preset reference image, and generating a dangerous case plan according to a comparison result comprise:
extracting acquisition time in the image information, comparing the acquisition time with the time information, and marking the corresponding image information as target image information after the acquisition time is in the time information;
determining a convolution kernel containing an dangerous case type according to a reference image, performing convolution operation on the target image information according to the convolution kernel, and determining the dangerous case type; wherein the dangerous case type comprises at least one fault type and corresponding probability;
according to the occurrence probability of different faults, performing descending order arrangement on the different faults, and reading the fault type with higher fault rate;
and establishing a connection channel with the record database, reading emergency records in the record database according to the fault type with higher fault rate, and determining the dangerous case record.
As a further scheme of the invention: the step of determining the dangerous case type by determining a convolution kernel containing the dangerous case type according to the reference image and performing convolution operation on the target image information according to the convolution kernel comprises the following steps:
reading the convolution kernel, determining a step length, and performing convolution operation on the target image according to the convolution kernel and the step length to obtain a feature map;
performing feature classification on the feature map according to a preset nonlinear activation function to obtain an activation map;
performing pooling operation on the activated image according to a preset pooling size to obtain a compression map corresponding to the activated image;
and determining the dangerous case type according to the compressed image.
As a further scheme of the invention: the step of determining the type of dangerous case from the compressed image comprises:
inputting the compressed image into a trained numerical matching model to obtain a matching degree;
comparing the matching degree with a preset matching threshold, and marking a corresponding convolution kernel when the matching degree is greater than the preset matching threshold;
and counting the marked convolution kernels, and reading the dangerous case types in the convolution kernels.
As a further scheme of the invention: when the risk information reaches a preset risk threshold value, acquiring a line of information of a corresponding node according to the node address, and generating a dangerous case plan according to the line of information comprises the following steps:
when the risk information reaches a preset risk threshold value, sending a temperature acquisition instruction and an environment information acquisition instruction to a corresponding acquisition end according to the node address; wherein the environmental information includes at least temperature, wind direction, and wind speed;
receiving environmental information acquired by an acquisition end, and generating a predicted temperature map according to the environmental information;
receiving a temperature information graph acquired by an acquisition end, and comparing the temperature information graph with the predicted temperature graph to obtain a risk probability;
and generating an dangerous case plan according to the risk probability.
The technical scheme of the invention also provides a power distribution network feeder line fault area automatic positioning system based on big data, which comprises the following steps:
the prediction signal generation module is used for acquiring input signals of all nodes according to a preset node address table and generating prediction signals according to the input signals;
the offset rate calculation module is used for acquiring the output signal of each node according to a preset node address table and calculating the offset rate of the output signal and the predicted signal;
the risk analysis module is used for inputting the deviation rate determination and the corresponding node address into a trained risk analysis model to obtain risk information containing the node address; the nodes are signal points with a plurality of data transmission directions in the power distribution process; the risk information is the probability of different fault types of the power distribution network feed money;
and the plan generating module is used for acquiring a line of information of the corresponding node according to the node address when the risk information reaches a preset risk threshold value, and generating a dangerous case plan according to the line of information.
As a further scheme of the invention: the plan generating module comprises:
the image acquisition unit is used for sending an image acquisition instruction to a corresponding acquisition end according to the node address when the risk information reaches a preset risk threshold;
the point set generating unit is used for receiving the image information acquired by the acquisition end, randomly acquiring pixel points with a preset proportion in the image information and generating a characteristic point set; the number of the pixel points is the sum of the pixel points of the image information multiplied by a preset proportion;
the characteristic value generating unit is used for sequentially converting the pixel points in the characteristic point set into characteristic values according to a preset conversion formula to obtain a characteristic array, and generating a representative value based on the characteristic array, wherein the representative value and the image information are in a mapping relation;
and the content identification unit is used for identifying the content of the image information when the representative value exceeds a preset range and generating the dangerous case plan according to the content identification result.
As a further scheme of the invention: the plan generating module comprises:
the instruction sending unit is used for sending a temperature acquisition instruction and an environmental information acquisition instruction to the corresponding acquisition end according to the node address when the risk information reaches a preset risk threshold; wherein the environmental information includes at least temperature, wind direction, and wind speed;
the prediction graph generating unit is used for receiving the environmental information acquired by the acquisition end and generating a prediction temperature graph according to the environmental information;
the probability generation unit is used for receiving the temperature information graph obtained by the acquisition end, and comparing the temperature information graph with the predicted temperature graph to obtain a risk probability;
and the processing execution unit is used for generating the dangerous case plan according to the risk probability.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the output signal is acquired and compared with the prediction signal to generate a preliminary judgment result, and then first-line information is acquired to further detect the corresponding node. In addition, the multi-stage detection mode can reduce the dependency on the circuit measuring meter and lighten the detection work of workers.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 shows a flow chart of a big data-based automatic positioning method for a feeder fault area of a power distribution network.
Fig. 2 shows a first sub-flow block diagram of a big data-based power distribution network feeder fault area automatic positioning method.
Fig. 3 shows a second sub-flow block diagram of a big data-based power distribution network feeder fault area automatic positioning method.
Fig. 4 shows a third sub-flow block diagram of a big data-based power distribution network feeder fault area automatic positioning method.
Fig. 5 shows a block diagram of a component structure of a big data-based automatic positioning system for a feeder fault area of a power distribution network.
Fig. 6 shows a first component structure block diagram of a plan generation module in a big data-based automatic positioning system for feeder fault areas of a power distribution network.
Fig. 7 shows a second component structure block diagram of a plan generation module in the big data-based automatic positioning system for the feeder fault area of the power distribution network.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
Fig. 1 shows a flow chart of a method for automatically positioning a feeder fault area of a power distribution network based on big data, and in an embodiment of the present invention, the method for automatically positioning a feeder fault area of a power distribution network based on big data includes steps S100 to S200:
step S100: acquiring input signals of all nodes according to a preset node address table, and generating prediction signals according to the input signals;
step S200: acquiring output signals of all nodes according to a preset node address table, and calculating the offset rates of the output signals and the prediction signals;
the function of steps S100 to S200 is to generate a prediction signal, compare the prediction signal with the output signal, and determine whether the output signal has a problem according to the comparison process, wherein the prediction process uses a theoretical model, the obtained value is also a theoretical value, and the theoretical value has a certain deviation from the actual output signal, but the deviation should be within a certain range.
Step S300: inputting the determined offset rate and the corresponding node address into a trained risk analysis model to obtain risk information containing the node address; the nodes are signal points with a plurality of data transmission directions in the power distribution process; the risk information is the probability of different fault types of the power distribution network feed money;
step S400: and when the risk information reaches a preset risk threshold value, acquiring a line of information of the corresponding node according to the node address, and generating a dangerous case plan according to the line of information.
The function of steps S300 to S400 is to determine risk information according to the offset rate, for the offset rate, the offsets in different directions and the offset amplitudes cannot exactly obtain specific fault types, so that there are many fault types of the offsets, and for the same offset rate, the corresponding fault type may not be unique, but there is a probability, and the larger the probability, the more likely the meaning is what kind of fault.
Fig. 2 shows a first sub-flow block diagram of a power distribution network feeder fault area automatic positioning method based on big data, where the step of obtaining a line information of a corresponding node according to the node address when the risk information reaches a preset risk threshold, and generating a dangerous case scenario plan according to the line information includes steps S401 to S404:
step S401: when the risk information reaches a preset risk threshold value, sending an image acquisition instruction to a corresponding acquisition end according to a node address;
step S402: receiving image information acquired by an acquisition end, randomly acquiring pixel points in a preset proportion in the image information, and generating a feature point set; the number of the pixel points is the sum of the pixel points of the image information multiplied by a preset proportion;
step S403: sequentially converting pixel points in the feature point set into feature values according to a preset conversion formula to obtain a feature array, and generating a representative value based on the feature array, wherein the representative value and the image information are in a mapping relation;
step S404: and when the representative value exceeds a preset range, performing content identification on the image information, and generating an emergency plan according to a content identification result.
Step S401 to step S404 refine the generation process of the dangerous case plan, firstly, when it is clear that a certain node possibly has problems, the image information of the node area is obtained through the acquisition end, and then the risk probability is further determined based on the image information; the specific process comprises the following steps: in the process of softening the image information, that is, in the process of extracting the pixel points, a representative value is generated according to the softened image information, and the representative value is determined.
Fig. 3 shows a second sub-flow block diagram of a method for automatically positioning a feeder fault area of a power distribution network based on big data, where the step of performing content identification on the image information and generating a dangerous case scenario according to a content identification result when the representative value exceeds a preset range includes steps S4041 to S4044:
step S4041: comparing the representative value with a boundary value of a preset range, and judging whether the representative value exceeds the preset range;
step S4042: when the representative value exceeds a preset range, sequentially carrying out logic AND operation on different image information to generate a binary matrix;
step S4043: calculating the mean value of each element in the binary matrix, and determining corresponding time information when the mean value reaches a preset mean value threshold;
step S4044: and reading target image information according to the time information, comparing the target image information with a preset reference image, and generating a dangerous case plan according to a comparison result.
The acquired image information is actually an image data stream and is an image containing time information, and the common points of the images are many, so that by sequentially carrying out logic and operation, only one memory is needed to extract key information of a plurality of images, the value of the same pixel point is one, the value of different pixel points is zero, and finally a binary matrix is obtained.
Fig. 4 shows a third sub-flow block diagram of a power distribution network feeder fault area automatic positioning method based on big data, where the step of reading target image information according to the time information, comparing the target image information with a preset reference image, and generating a dangerous case plan according to a comparison result includes steps S40441 to S40444:
step S40441: extracting acquisition time in the image information, comparing the acquisition time with the time information, and marking the corresponding image information as target image information after the acquisition time is in the time information;
step S40442: determining a convolution kernel containing an dangerous case type according to a reference image, performing convolution operation on the target image information according to the convolution kernel, and determining the dangerous case type; wherein the dangerous case type comprises at least one fault type and corresponding probability;
step S40443: according to the occurrence probability of different faults, performing descending order arrangement on the different faults, and reading the fault type with higher fault rate;
step S40444: and establishing a connection channel with the record database, reading emergency records in the record database according to the fault type with higher fault rate, and determining the dangerous case record.
Steps S40441 to S40444 are specific comparison processes, in which, the two parties of comparison are the actual image and the reference image, convolution kernels are generated according to the reference image, the convolution kernels represent features, and the actual image is traversed and detected through the convolution kernels, so that the comparison process can be realized. After the fault type is determined, the step of determining the dangerous case plan according to the fault type is a simple database reading operation.
Further, the determining a convolution kernel containing an emergency type according to the reference image, and performing convolution operation on the target image information according to the convolution kernel, wherein the determining an emergency type includes:
reading the convolution kernel, determining a step length, and performing convolution operation on the target image according to the convolution kernel and the step length to obtain a feature map;
performing feature classification on the feature map according to a preset nonlinear activation function to obtain an activation map;
performing pooling operation on the activated image according to a preset pooling size to obtain a compression map corresponding to the activated image;
and determining the dangerous case type according to the compressed image.
Specifically, the step of determining the dangerous case type according to the compressed image comprises:
inputting the compressed image into a trained numerical matching model to obtain a matching degree;
comparing the matching degree with a preset matching threshold, and marking a corresponding convolution kernel when the matching degree is greater than the preset matching threshold;
and counting the marked convolution kernels, and reading the dangerous case types in the convolution kernels.
The above is a specific image detection process based on convolution kernel, where the convolution kernel represents some small feature region, generally 3X3 or 5X5, and the step size is the moving step size of the feature region when performing convolution operation, generally 1, which represents shifting by one pixel to the right for each detection; after convolution operation, a convolution layer, namely the characteristic diagram is obtained;
the convolution layer performs multiple convolution operations on the original image to generate a set of linear activation responses, and the nonlinear activation layer performs a nonlinear activation response on the previous result. The most nonlinear activation function is the Relu function, whose formula is defined as: (x) = max (0, x), that is, a value of 0 or more is retained, and all the remaining values less than 0 are directly rewritten to 0; this process is not difficult.
After the nonlinear activation, although the data amount is much smaller than that of the original image, the data amount is still too large (hundreds of thousands of training pictures are obtained by relatively deep learning), so that the subsequent pooling operation can play a role, and the biggest goal is to reduce the data amount. The Pooling is divided into two types, Max Pooling maximum Pooling and Average Pooling Average Pooling. As the name implies, maximal pooling is taken as the maximum value, and average pooling is taken as the average value. Typically, max pooling is used, since it preserves the maximum value within each tile, it is equivalent to preserving the best match result for this tile (since a value closer to 1 indicates a better match). This means that it does not focus specifically on exactly where within the window matches, but only on whether there is a place to match.
As a preferred embodiment of the technical solution of the present invention, when the risk information reaches a preset risk threshold, the step of obtaining a line of information of a corresponding node according to the node address, and generating a dangerous case scenario according to the line of information includes:
when the risk information reaches a preset risk threshold value, sending a temperature acquisition instruction and an environment information acquisition instruction to a corresponding acquisition end according to the node address; wherein the environmental information includes at least temperature, wind direction, and wind speed;
receiving environmental information acquired by an acquisition end, and generating a predicted temperature map according to the environmental information;
receiving a temperature information graph acquired by an acquisition end, and comparing the temperature information graph with the predicted temperature graph to obtain a risk probability;
and generating an dangerous case plan according to the risk probability.
In a preferred embodiment of the technical solution of the present invention, the temperature information is detected, when a problem occurs in the temperature of a certain node area, it is likely that some fault occurs, and the temperature is an important parameter for the power element.
Example 2
Fig. 5 is a block diagram illustrating a configuration of a big data-based automatic positioning system for a feeder fault area of a power distribution network, in an embodiment of the present invention, the big data-based automatic positioning system for a feeder fault area of a power distribution network includes:
the prediction signal generation module 11 is configured to obtain an input signal of each node according to a preset node address table, and generate a prediction signal according to the input signal;
an offset rate calculation module 12, configured to obtain an output signal of each node according to a preset node address table, and calculate an offset rate of the output signal and the predicted signal;
a risk analysis module 13, configured to input the offset rate determination and the corresponding node address into a trained risk analysis model to obtain risk information including the node address; the nodes are signal points with a plurality of data transmission directions in the power distribution process; the risk information is the probability of different fault types of the power distribution network feed money;
and the plan generating module 14 is configured to, when the risk information reaches a preset risk threshold, obtain a line of information of a corresponding node according to the node address, and generate a dangerous case plan according to the line of information.
Fig. 6 shows a first constitutional block diagram of a plan generating module in a big data-based automatic positioning system for feeder fault areas of a power distribution network, wherein the plan generating module 14 comprises:
the image acquisition unit 141 is configured to send an image acquisition instruction to a corresponding acquisition end according to a node address when the risk information reaches a preset risk threshold;
the point set generating unit 142 is configured to receive the image information acquired by the acquisition end, randomly acquire pixel points in the image information at a predetermined ratio, and generate a feature point set; the number of the pixel points is the sum of the pixel points of the image information multiplied by a preset proportion;
the feature value generating unit 143 is configured to sequentially convert the pixel points in the feature point set into feature values according to a preset conversion formula to obtain a feature array, and generate a representative value based on the feature array, where the representative value and the image information are in a mapping relationship;
and a content identification unit 144 configured to perform content identification on the image information when the representative value is out of a preset range, and generate a dangerous case scenario according to a content identification result.
Fig. 7 shows a second constitutional block diagram of a plan generating module in the big data-based automatic positioning system for feeder fault areas of the power distribution network, wherein the plan generating module 14 comprises:
the instruction sending unit 145 is configured to send a temperature obtaining instruction and an environmental information obtaining instruction to corresponding collection terminals according to the node address when the risk information reaches a preset risk threshold; wherein the environmental information includes at least temperature, wind direction, and wind speed;
the prediction graph generating unit 146 is configured to receive the environment information acquired by the acquisition end, and generate a prediction temperature graph according to the environment information;
a probability generating unit 147, configured to receive the temperature information map obtained by the acquisition end, and compare the temperature information map with the predicted temperature map to obtain a risk probability;
and the processing execution unit 148 is used for generating an emergency plan according to the risk probability.
The functions which can be realized by the big data based distribution network feeder line fault area automatic positioning method are all completed by a computer device, the computer device comprises one or more processors and one or more memories, and at least one program code is stored in the one or more memories and is loaded and executed by the one or more processors to realize the functions of the big data based distribution network feeder line fault area automatic positioning method.
The processor fetches instructions and analyzes the instructions one by one from the memory, then completes corresponding operations according to the instruction requirements, generates a series of control commands, enables all parts of the computer to automatically, continuously and coordinately act to form an organic whole, realizes the input of programs, the input of data, the operation and the output of results, and the arithmetic operation or the logic operation generated in the process is completed by the arithmetic unit; the Memory comprises a Read-Only Memory (ROM) for storing a computer program, and a protection device is arranged outside the Memory.
Illustratively, a computer program can be partitioned into one or more modules, which are stored in memory and executed by a processor to implement the present invention. One or more of the modules may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the terminal device.
Those skilled in the art will appreciate that the above description of the service device is merely exemplary and not limiting of the terminal device, and may include more or less components than those described, or combine certain components, or different components, such as may include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal equipment and connects the various parts of the entire user terminal using various interfaces and lines.
The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the terminal device by operating or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory mainly comprises a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs (such as an information acquisition template display function, a product information publishing function and the like) required by at least one function and the like; the storage data area may store data created according to the use of the berth-state display system (e.g., product information acquisition templates corresponding to different product types, product information that needs to be issued by different product providers, etc.), and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The terminal device integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the modules/units in the system according to the above embodiment may be implemented by a computer program, which may be stored in a computer-readable storage medium and used by a processor to implement the functions of the embodiments of the system. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A big data-based automatic positioning method for a feeder fault area of a power distribution network is characterized by comprising the following steps:
acquiring input signals of all nodes according to a preset node address table, and generating prediction signals according to the input signals;
acquiring output signals of all nodes according to a preset node address table, and calculating the offset rates of the output signals and the prediction signals;
inputting the determined offset rate and the corresponding node address into a trained risk analysis model to obtain risk information containing the node address; the nodes are signal points with a plurality of data transmission directions in the power distribution process; the risk information is the probability of different fault types of the power distribution network feed money;
and when the risk information reaches a preset risk threshold value, acquiring a line of information of the corresponding node according to the node address, and generating a dangerous case plan according to the line of information.
2. The method for automatically positioning the fault area of the feeder line of the power distribution network based on the big data as claimed in claim 1, wherein the step of obtaining a line of information of a corresponding node according to the node address when the risk information reaches a preset risk threshold value, and generating a dangerous case plan according to the line of information comprises:
when the risk information reaches a preset risk threshold value, sending an image acquisition instruction to a corresponding acquisition end according to a node address;
receiving image information acquired by an acquisition end, randomly acquiring pixel points in a preset proportion in the image information, and generating a feature point set; the number of the pixel points is the sum of the pixel points of the image information multiplied by a preset proportion;
sequentially converting pixel points in the feature point set into feature values according to a preset conversion formula to obtain a feature array, and generating a representative value based on the feature array, wherein the representative value and the image information are in a mapping relation;
and when the representative value exceeds a preset range, performing content identification on the image information, and generating an emergency plan according to a content identification result.
3. The method for automatically positioning the fault area of the feeder line of the power distribution network based on the big data as claimed in claim 2, wherein the step of performing content identification on the image information when the representative value exceeds a preset range and generating a dangerous case plan according to a content identification result comprises:
comparing the representative value with a boundary value of a preset range, and judging whether the representative value exceeds the preset range;
when the representative value exceeds a preset range, sequentially carrying out logic AND operation on different image information to generate a binary matrix;
calculating the mean value of each element in the binary matrix, and determining corresponding time information when the mean value reaches a preset mean value threshold;
and reading target image information according to the time information, comparing the target image information with a preset reference image, and generating a dangerous case plan according to a comparison result.
4. The automatic positioning method for the feeder fault areas of the power distribution network based on the big data as claimed in claim 3, wherein the step of reading target image information according to the time information, comparing the target image information with a preset reference image, and generating a dangerous case plan according to a comparison result comprises:
extracting acquisition time in the image information, comparing the acquisition time with the time information, and marking the corresponding image information as target image information after the acquisition time is in the time information;
determining a convolution kernel containing an dangerous case type according to a reference image, performing convolution operation on the target image information according to the convolution kernel, and determining the dangerous case type; wherein the dangerous case type comprises at least one fault type and corresponding probability;
according to the occurrence probability of different faults, performing descending order arrangement on the different faults, and reading the fault type with higher fault rate;
and establishing a connection channel with the record database, reading emergency records in the record database according to the fault type with higher fault rate, and determining the dangerous case record.
5. The automatic positioning method for the feeder fault areas of the power distribution network based on the big data as claimed in claim 4, wherein the step of determining a convolution kernel containing a dangerous case type according to a reference image, and performing convolution operation on the target image information according to the convolution kernel, wherein the step of determining the dangerous case type comprises:
reading the convolution kernel, determining a step length, and performing convolution operation on the target image according to the convolution kernel and the step length to obtain a feature map;
performing feature classification on the feature map according to a preset nonlinear activation function to obtain an activation map;
performing pooling operation on the activated image according to a preset pooling size to obtain a compression map corresponding to the activated image;
and determining the dangerous case type according to the compressed image.
6. The method for automatically positioning the fault area of the feeder line of the power distribution network based on the big data as claimed in claim 5, wherein the step of determining the type of the dangerous case according to the compressed image comprises:
inputting the compressed image into a trained numerical matching model to obtain a matching degree;
comparing the matching degree with a preset matching threshold, and marking a corresponding convolution kernel when the matching degree is greater than the preset matching threshold;
and counting the marked convolution kernels, and reading the dangerous case types in the convolution kernels.
7. The method for automatically positioning the fault area of the feeder line of the power distribution network based on the big data as claimed in claim 1, wherein the step of obtaining a line of information of a corresponding node according to the node address when the risk information reaches a preset risk threshold value, and generating a dangerous case plan according to the line of information comprises:
when the risk information reaches a preset risk threshold value, sending a temperature acquisition instruction and an environment information acquisition instruction to a corresponding acquisition end according to the node address; wherein the environmental information includes at least temperature, wind direction, and wind speed;
receiving environmental information acquired by an acquisition end, and generating a predicted temperature map according to the environmental information;
receiving a temperature information graph acquired by an acquisition end, and comparing the temperature information graph with the predicted temperature graph to obtain a risk probability;
and generating an dangerous case plan according to the risk probability.
8. A big data-based automatic positioning system for a feeder fault area of a power distribution network is characterized in that:
the prediction signal generation module is used for acquiring input signals of all nodes according to a preset node address table and generating prediction signals according to the input signals;
the offset rate calculation module is used for acquiring the output signal of each node according to a preset node address table and calculating the offset rate of the output signal and the predicted signal;
the risk analysis module is used for inputting the deviation rate determination and the corresponding node address into a trained risk analysis model to obtain risk information containing the node address; the nodes are signal points with a plurality of data transmission directions in the power distribution process; the risk information is the probability of different fault types of the power distribution network feed money;
and the plan generating module is used for acquiring a line of information of the corresponding node according to the node address when the risk information reaches a preset risk threshold value, and generating a dangerous case plan according to the line of information.
9. The big data based distribution network feeder fault area automated positioning system of claim 8, wherein the plan generation module comprises:
the image acquisition unit is used for sending an image acquisition instruction to a corresponding acquisition end according to the node address when the risk information reaches a preset risk threshold;
the point set generating unit is used for receiving the image information acquired by the acquisition end, randomly acquiring pixel points with a preset proportion in the image information and generating a characteristic point set; the number of the pixel points is the sum of the pixel points of the image information multiplied by a preset proportion;
the characteristic value generating unit is used for sequentially converting the pixel points in the characteristic point set into characteristic values according to a preset conversion formula to obtain a characteristic array, and generating a representative value based on the characteristic array, wherein the representative value and the image information are in a mapping relation;
and the content identification unit is used for identifying the content of the image information when the representative value exceeds a preset range and generating the dangerous case plan according to the content identification result.
10. The big data based distribution network feeder fault area automated positioning system of claim 8, wherein the plan generation module comprises:
the instruction sending unit is used for sending a temperature acquisition instruction and an environmental information acquisition instruction to the corresponding acquisition end according to the node address when the risk information reaches a preset risk threshold; wherein the environmental information includes at least temperature, wind direction, and wind speed;
the prediction graph generating unit is used for receiving the environmental information acquired by the acquisition end and generating a prediction temperature graph according to the environmental information;
the probability generation unit is used for receiving the temperature information graph obtained by the acquisition end, and comparing the temperature information graph with the predicted temperature graph to obtain a risk probability;
and the processing execution unit is used for generating the dangerous case plan according to the risk probability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111531499.5A CN114414935A (en) | 2021-12-15 | 2021-12-15 | Automatic positioning method and system for feeder fault area of power distribution network based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111531499.5A CN114414935A (en) | 2021-12-15 | 2021-12-15 | Automatic positioning method and system for feeder fault area of power distribution network based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114414935A true CN114414935A (en) | 2022-04-29 |
Family
ID=81267725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111531499.5A Pending CN114414935A (en) | 2021-12-15 | 2021-12-15 | Automatic positioning method and system for feeder fault area of power distribution network based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114414935A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114912636A (en) * | 2022-05-09 | 2022-08-16 | 安徽继远检验检测技术有限公司 | Intelligent target power grid equipment detection method and system based on handheld terminal |
| CN115526215A (en) * | 2022-11-24 | 2022-12-27 | 光微半导体(吉林)有限公司 | Method and system for diagnosing, maintaining, analyzing and optimizing rubber pump fault |
| CN115549313A (en) * | 2022-11-09 | 2022-12-30 | 国网江苏省电力有限公司徐州供电分公司 | Electricity utilization monitoring method and system based on artificial intelligence |
| CN115936680A (en) * | 2023-02-06 | 2023-04-07 | 北京安录国际技术有限公司 | Intelligent order dispatching method and system for equipment operation and maintenance |
| CN116939159A (en) * | 2023-06-16 | 2023-10-24 | 北京佳格天地科技有限公司 | Farmland disaster early warning method and system |
| CN117783769A (en) * | 2024-02-28 | 2024-03-29 | 国网山西省电力公司太原供电公司 | Power distribution network fault positioning method, system, equipment and storage medium based on visual platform |
-
2021
- 2021-12-15 CN CN202111531499.5A patent/CN114414935A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114912636A (en) * | 2022-05-09 | 2022-08-16 | 安徽继远检验检测技术有限公司 | Intelligent target power grid equipment detection method and system based on handheld terminal |
| CN115549313A (en) * | 2022-11-09 | 2022-12-30 | 国网江苏省电力有限公司徐州供电分公司 | Electricity utilization monitoring method and system based on artificial intelligence |
| CN115549313B (en) * | 2022-11-09 | 2024-03-08 | 国网江苏省电力有限公司徐州供电分公司 | Power consumption monitoring method and system based on artificial intelligence |
| CN115526215A (en) * | 2022-11-24 | 2022-12-27 | 光微半导体(吉林)有限公司 | Method and system for diagnosing, maintaining, analyzing and optimizing rubber pump fault |
| CN115526215B (en) * | 2022-11-24 | 2023-04-07 | 光微半导体(吉林)有限公司 | Method and system for diagnosing, maintaining, analyzing and optimizing rubber pump fault |
| CN115936680A (en) * | 2023-02-06 | 2023-04-07 | 北京安录国际技术有限公司 | Intelligent order dispatching method and system for equipment operation and maintenance |
| CN116939159A (en) * | 2023-06-16 | 2023-10-24 | 北京佳格天地科技有限公司 | Farmland disaster early warning method and system |
| CN116939159B (en) * | 2023-06-16 | 2024-03-22 | 北京佳格天地科技有限公司 | Farmland disaster early warning method and system |
| CN117783769A (en) * | 2024-02-28 | 2024-03-29 | 国网山西省电力公司太原供电公司 | Power distribution network fault positioning method, system, equipment and storage medium based on visual platform |
| CN117783769B (en) * | 2024-02-28 | 2024-05-10 | 国网山西省电力公司太原供电公司 | Power distribution network fault positioning method, system, equipment and storage medium based on visual platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114414935A (en) | Automatic positioning method and system for feeder fault area of power distribution network based on big data | |
| CN109858740B (en) | Enterprise risk assessment method and device, computer equipment and storage medium | |
| CN109886928B (en) | Target cell marking method, device, storage medium and terminal equipment | |
| CN110764993A (en) | Automatic testing method and terminal equipment | |
| CN113239314A (en) | Method, device, terminal and computer-readable storage medium for carbon emission prediction | |
| CN113963033B (en) | Power equipment abnormality detection method and system based on artificial intelligence | |
| CN113888480A (en) | MES-based quality tracing method and system | |
| CN113901647B (en) | Part technical specification compiling method and device, storage medium and electronic equipment | |
| CN114581442B (en) | Product detection method and device for MES system | |
| CN113449703B (en) | Quality control method and device for environment online monitoring data, storage medium and equipment | |
| CN113435305A (en) | Precision detection method, device and equipment of target object identification algorithm and storage medium | |
| CN113723467A (en) | Sample collection method, device and equipment for defect detection | |
| CN114143049A (en) | Abnormal flow detection method, abnormal flow detection device, storage medium and electronic equipment | |
| CN111124863A (en) | Intelligent equipment performance testing method and device and intelligent equipment | |
| CN115098589A (en) | Industrial energy consumption data monitoring method and device based on Internet of things | |
| CN114565196A (en) | Multi-event trend prejudging method, device, equipment and medium based on government affair hotline | |
| CN114782060A (en) | Interactive product detection method and system | |
| CN115086343B (en) | Internet of things data interaction method and system based on artificial intelligence | |
| CN109326324B (en) | Antigen epitope detection method, system and terminal equipment | |
| CN116342111A (en) | Intelligent transaction method and system for automobile parts based on big data | |
| CN115734072A (en) | Internet of things centralized monitoring method and device for industrial automation equipment | |
| CN112149546B (en) | Information processing method, device, electronic equipment and storage medium | |
| CN113989632A (en) | Bridge detection method and device for remote sensing image, electronic equipment and storage medium | |
| CN114882242A (en) | Violation image identification method and system based on computer vision | |
| CN114077545A (en) | Method, device and equipment for acquiring verification data and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |