CN118137414A

CN118137414A - Line tripping fixed value determining method, determining device and electronic equipment

Info

Publication number: CN118137414A
Application number: CN202410315462.6A
Authority: CN
Inventors: 刘小林; 詹泽宇; 潘健敏; 吴树钊; 冼海炎; 麦立昀; 王彬; 徐龙彬; 李春辉; 袁艺文; 蔡思华; 罗雨豪; 李嘉莹; 彭丹; 陈若兰; 林浦曦; 邓亦彤; 张宁恺; 李恒弛; 姚锋
Original assignee: Guangdong Power Grid Co Ltd; Foshan Power Supply Bureau of Guangdong Power Grid Corp
Current assignee: Guangdong Power Grid Co Ltd; Foshan Power Supply Bureau of Guangdong Power Grid Corp
Priority date: 2024-03-19
Filing date: 2024-03-19
Publication date: 2024-06-04

Abstract

The application provides a method and a device for determining a circuit tripping fixed value and electronic equipment. The method comprises the following steps: acquiring load data of each circuit breaker in a line, and forming a node load data array according to the load data of each circuit breaker; analyzing the node load data array through a neural network model to obtain a node trip data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: a node load data array and a node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes; and determining a circuit breaker corresponding to a tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node, and determining a tripping fixed value of the tripping node. The application solves the problem of higher error rate of manually calculating the trip node and the corresponding fixed value list in the prior art.

Description

Line tripping fixed value determining method, determining device and electronic equipment

Technical Field

The present application relates to the technical field of power systems, and in particular, to a method for determining a line trip determination value, a device for determining a line trip determination value, a computer-readable storage medium, and an electronic device.

Background

The 10kV distribution network system adopts an open-loop operation mode, so that the circuit topology is simple, and in practical application, only simple overcurrent relay protection is usually used. The constant value cooperation of the overcurrent relay protection of the distribution network system is usually not more than two stages, and the constant value set values of the power grids in the same region are the same, so that the constant value setting of the circuit is basically completed as long as the constant value tripping point of the circuit is correctly set. The constant value planning of the current 10kV distribution network line is completed manually. Because the distribution network has multiple branches, the types of the switching equipment are various, the line updating is fast, the current method for manually identifying the graph and setting the line fixed value is slow, and a large amount of fixed value setting personnel are required to be input. The manual calculation consumes a lot of manpower, and is low in efficiency and high in error rate.

Thus, there is a need for a method of automatically calculating the trip nodes of a line and setting corresponding constant value bill data.

Disclosure of Invention

The application mainly aims to provide a method for determining a line tripping fixed value, a device for determining the line tripping fixed value, a computer readable storage medium and electronic equipment, so as to at least solve the problem of high error rate of manually calculating a tripping point in the prior art.

To achieve the above object, according to one aspect of the present application, there is provided a method for determining a line trip determination value, including: acquiring load data of each circuit breaker in a circuit, and forming a node load data array according to the load data of each circuit breaker, wherein the circuit breaker at least comprises a transformer substation outlet circuit breaker and a circuit breaker, and elements in the node load data array represent total load sizes of all branches in a preset direction of a node corresponding to the circuit breaker, and the preset direction is a direction from the transformer substation outlet circuit breaker to the circuit breaker; analyzing the node load data array through a neural network model to obtain a node trip data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes; and determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node, and determining a tripping fixed value of the tripping node, wherein the tripping fixed value is a fixed value for tripping the circuit breaker.

Optionally, obtaining load data of each circuit breaker in the line includes: the method for acquiring the load data of each circuit breaker in the circuit comprises the following steps: acquiring an original circuit diagram, and representing the circuit breaker in the original circuit diagram by using nodes to obtain a simplified circuit diagram of the original circuit diagram; and adding the loads of all branches of the circuit breaker in the preset direction in the simplified circuit diagram to obtain the load data corresponding to the nodes of the circuit breaker.

Optionally, forming a node load data array according to the load data of each circuit breaker includes: filling the load data into the nodes of the corresponding circuit breakers in the simplified circuit diagram; representing the simplified circuit diagram by adopting a binary tree structure to obtain a binary tree circuit diagram, wherein each node in the binary tree circuit diagram has at most two child nodes; and sequentially storing the binary tree circuit diagram into an array with a preset size to obtain the node load data array, wherein the preset size is determined by the maximum depth value of the binary tree circuit diagram.

Optionally, before analyzing the node load data array through the neural network model to obtain a node trip data array, the method further includes: acquiring initial load data, adjusting the size of the initial load data to obtain a plurality of historical load data, and generating a historical node load data set according to the plurality of historical load data, wherein the adjustment range of the initial load data is smaller than a preset multiple of the initial load data; and acquiring a historical node tripping data array corresponding to each historical node load data set, and training an initial neural network model by adopting the historical node load data sets and the historical node tripping data arrays to obtain the neural network model.

Optionally, training an initial neural network model using the historical node load data set and the historical node trip data set includes: determining neurons of the initial neural network model asWherein x _j represents an element in the historical node load data set, ω _j represents a weight of the neuron, b is a bias of the neuron, σ represents a value of the neuron; determining a cost function of the initial neural network model as/>Wherein a _j represents the actual output of the initial neural network model, y _j represents the expectation of the initial neural network model, k represents the number of neurons, and C represents the value of the cost function; the initial neural network model is updated using a gradient descent method.

Optionally, updating the initial neural network model using a gradient descent method includes: determining the updated formula of the weight asWherein ω _old is the weight before the present training, η is the learning rate, ω _new is the weight after the present training; determining the updated formula of the bias as/>Wherein b _old is the bias before the current training, and b _new is the bias after the current training.

Optionally, determining the circuit breaker corresponding to the trip expected value greater than a preset threshold in the node trip data array as a trip node, and determining a trip constant value of the trip node includes: determining the trip node as a first level trip node in the event that there are no remaining of the trip nodes in the substation outlet circuit breaker to the line circuit breaker; sequentially determining each level of trip nodes according to the preset direction under the condition that the rest of trip nodes exist from the transformer substation outlet circuit breaker to the line circuit breaker; determining the trip constant value of the trip node for each stage, wherein the trip constant value is different for each stage.

According to another aspect of the present application, there is provided a line trip constant value determining apparatus, comprising: the first determining unit is used for obtaining load data of each circuit breaker in a circuit and forming a node load data array according to the load data of each circuit breaker, wherein the circuit breaker at least comprises a transformer substation outlet circuit breaker and a circuit breaker, elements in the node load data array represent total load sizes of all branches in a preset direction of a node corresponding to the circuit breaker, and the preset direction is a direction from the transformer substation outlet circuit breaker to the circuit breaker; the analysis unit is used for analyzing the node load data array through a neural network model to obtain a node tripping data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes; and the second determining unit is used for determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node and determining a tripping fixed value of the tripping node, wherein the tripping fixed value is a fixed value for tripping the circuit breaker.

According to still another aspect of the present application, there is provided a computer-readable storage medium including a stored program, wherein the program, when executed, controls a device in which the computer-readable storage medium is located to execute any one of the determination methods.

According to still another aspect of the present application, there is provided an electronic apparatus including: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any one of the determining methods.

By applying the technical scheme of the application, the load data of each circuit breaker in a circuit is obtained, and a node load data array is formed according to the load data of each circuit breaker; and then analyzing the node load data array through a neural network model to obtain a node tripping data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes; and determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node, and determining a tripping fixed value of the tripping node. Compared with the method that more manpower and higher error rate are wasted through manual calculation of the tripping nodes and the corresponding fixed values in the prior art, the method can automatically determine the tripping nodes and the corresponding tripping fixed values through the neural network model, and the problems of manpower waste and high error rate caused by manual calculation are avoided. Therefore, the problem that the error rate of manually calculating the trip node and the corresponding fixed value list in the prior art is high can be solved, and the effects of saving manpower and reducing the error rate are achieved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

Fig. 1 is a block diagram showing a hardware configuration of a mobile terminal for performing a method for determining a line trip decision value according to an embodiment of the present application;

Fig. 2 is a flow chart illustrating a method for determining a line trip determination according to an embodiment of the present application;

Fig. 3 is a flow chart illustrating a specific method for determining a line trip constant value according to an embodiment of the present application;

FIG. 4 shows a simplified single line diagram of a 10kV line provided by an embodiment of the application;

FIG. 5 illustrates a process for transforming a binary tree of virtual nodes when the number of sub-nodes is 5, provided by an embodiment of the present application;

Fig. 6 is a block diagram showing a configuration of a circuit trip constant value determining apparatus according to an embodiment of the present application.

Wherein the above figures include the following reference numerals:

102. A processor; 104. a memory; 106. a transmission device; 108. and an input/output device.

Detailed Description

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

As described in the background art, in order to solve the problem that the error rate of manually calculating the trip fixed value point is high in the prior art, the embodiment of the application provides a method for determining the circuit trip fixed value, a device for determining the circuit trip fixed value, a computer-readable storage medium and electronic equipment.

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

The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of the mobile terminal according to a method for determining a line trip constant according to an embodiment of the present application. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a method for determining a line trip constant value in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, to implement the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as a NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.

In the present embodiment, a method of determining a line trip value operating on a mobile terminal, a computer terminal, or a similar computing device is provided, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and although a logical sequence is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in a different order than that illustrated herein.

Fig. 2 is a flowchart of a method of determining a line trip constant according to an embodiment of the present application. As shown in fig. 2, the method comprises the steps of:

Step S201, obtaining load data of each circuit breaker in a circuit, and forming a node load data array according to the load data of each circuit breaker, wherein the circuit breaker at least comprises a transformer substation outlet circuit breaker and a circuit breaker, elements in the node load data array represent total load sizes of all branches in a preset direction of a node corresponding to the circuit breaker, and the preset direction is a direction from the transformer substation outlet circuit breaker to the circuit breaker;

Specifically, the application is applied to a 10KV distribution network system, and can also be applied to distribution network systems with other voltage levels. Firstly, simplifying a circuit, hiding a non-breaker switch in a single line diagram of a 10kV circuit, changing the breaker switch into a node representation, and only including a breaker node and the rear end load of the node in the simplified circuit diagram. In general, the circuit comprises devices such as a transformer substation outlet, a load switch, a disconnecting switch, a circuit breaker, a fuse and the like, elements such as the load switch, the disconnecting switch, the fuse and the like are hidden in a simplified circuit diagram, the circuit only comprises a circuit breaker node, and the number in the node represents the load size of the rear end of the node. And obtaining load data of the line after simplification, and forming the load data into a node load data array to represent the load condition in the line.

Step S202, analyzing the node load data array through a neural network model to obtain a node trip data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes;

Specifically, the node load data array is analyzed by adopting a neural network model, so that a node trip data array can be obtained, and if the node load data array is a one-dimensional array X of 1× (2 ⁿ -1), the output node trip data array is also a one-dimensional array of 1× (2 ⁿ -1) and can be marked as Y.

And step S203, determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node, and determining a tripping fixed value of the tripping node, wherein the tripping fixed value is a fixed value for tripping the circuit breaker.

Specifically, a preset threshold value K of the trip point is set, and a node with a number greater than K in the array Y is set as the line trip node. The K value interval is (0.5, 1), and is usually 0.8.

According to the embodiment, load data of each circuit breaker in a line are obtained, and a node load data array is formed according to the load data of each circuit breaker; and then analyzing the node load data array through a neural network model to obtain a node trip data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes; and determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node, and determining the tripping fixed value of the tripping node. Compared with the method that more manpower and higher error rate are wasted through manual calculation of the tripping nodes and the corresponding fixed values in the prior art, the method can automatically determine the tripping nodes and the corresponding tripping fixed values through the neural network model, and the problems of manpower waste and high error rate caused by manual calculation are avoided. Therefore, the problem that the error rate of manually calculating the trip node and the corresponding fixed value list in the prior art is high can be solved, and the effects of saving manpower and reducing the error rate are achieved.

In a specific implementation process, the step S201 of obtaining the load data of each circuit breaker in the line may be implemented by the following steps: the method for acquiring the load data of each circuit breaker in the circuit comprises the following steps: acquiring an original circuit diagram, and representing the circuit breaker in the original circuit diagram by using nodes to obtain a simplified circuit diagram of the original circuit diagram; in the simplified circuit diagram, loads of all branches of the circuit breaker in the predetermined direction are added to obtain the load data corresponding to the node of the circuit breaker. The method simplifies the original circuit diagram and marks the nodes through the steps, so that the load data of each node can be calculated conveniently.

In particular, as mentioned above, the lines to be processed are simplified. And hiding a non-breaker switch in a single line diagram of the 10kV line, wherein the breaker switch is changed into a node representation, and the simplified line diagram only comprises a breaker node and the load size of the rear end of the node, and the number in the node represents the load size of the rear end of the node.

In some alternative embodiments, the step S201 may form a node load data array according to the load data of each circuit breaker, which may be implemented by: filling the load data into the nodes of the corresponding circuit breaker in the simplified circuit diagram; representing the simplified circuit diagram by adopting a binary tree structure to obtain a binary tree circuit diagram, wherein each node in the binary tree circuit diagram is provided with at most two child nodes; and sequentially storing the binary tree circuit diagram into an array with a preset size to obtain the node load data array, wherein the preset size is determined by the maximum depth value of the binary tree circuit diagram. The method adopts a binary tree to represent the simplified circuit diagram, so that the node load data array can be determined through the binary tree.

Specifically, the simplified line is represented by a binary tree structure. The binary tree requires that each node only has 2 sub-nodes at most, so when the number of the sub-nodes of a certain node of the line is more than 2, virtual nodes are needed to be added between the node and the sub-nodes, and the number in the virtual nodes is the sum of the number of the sub-nodes of the lower level. And adding virtual nodes of the line until the number of child nodes of all nodes in the line does not exceed 2, wherein the line at the moment is in a binary tree form. Typically the number of sub-nodes in the line will not be greater than 6. Virtual nodes are not true nodes, and have no true meaning in real lines.

In order to train to obtain the neural network model, before analyzing the node load data array through the neural network model to obtain the node trip data array, the method further comprises the following steps: acquiring initial load data, adjusting the size of the load data in the initial load data to obtain a plurality of historical load data, and generating a historical node load data set according to the plurality of historical load data, wherein the adjustment range of the initial load data is smaller than a preset multiple of the initial load data; and acquiring a historical node tripping data array corresponding to each historical node load data set, and training an initial neural network model by adopting the historical node load data sets and the historical node tripping data arrays to obtain the neural network model. According to the method, the neural network model is trained through the steps, so that the accurate neural network model can be obtained through training.

In a specific implementation process, training of the neural network system is as follows: a large number of single line diagrams of the 10kV line with constant value are obtained. The single line patterns are data-augmented to increase the number of single line patterns. The specific method is to randomly adjust the load in the circuit, the adjustment range is not more than 5%, and the tripping position of the circuit is unchanged. Performing the above operation on all the single line diagram data to obtain binary tree load data of all the single line diagrams, which are defined as input data X ₁,X₂,...,X_M of the neural network; binary tree trip node data of all the single line patterns are obtained and defined as target output data Y ₁,Y₂,...,Y_M of the neural network, wherein M is the number of all the single line patterns, and binary tree load data and binary tree trip node data of each single line pattern are one-dimensional arrays with the format of 1× (2 ⁿ -1). The input data and the output data of the neural network are divided into a training set and a testing set.

In some alternative embodiments, training the initial neural network model using the historical node load data set and the historical node trip data set may be achieved by: determining the neuron of the initial neural network model asWherein x _j represents an element in the history node load data set, ω _j represents a weight of the neuron, b is a bias of the neuron, and σ represents a value of the neuron; determining the cost function of the initial neural network model as/>Wherein a _j represents an actual output of the initial neural network model, y _j represents an expectation of the initial neural network model, k represents the number of neurons, and C represents a value of the cost function; and updating the initial neural network model by using a gradient descent method. The method determines the neuron and the cost function of the neural network model through the steps, so that the initial neural network model can be accurately trained.

Specifically, the neural network system adopts S-shaped neurons with the expression ofThe weights and bias initial values of the neurons are set to be random numbers with the mean value of 0 and the variance of 1. The cost function of the neural network is set toWherein a1, a 2.

In the specific implementation process, the initial neural network model is updated by using a gradient descent method, and the method can be realized by the following steps: determining the update formula of the weight asWherein ω _old is the weight before the present training, η is the learning rate, ω _new is the weight after the present training; determining the updated formula of the bias asWherein b _old is the bias before the present training, and b _new is the bias after the present training. The method can update the weight and the bias in time through the steps so as to accurately train and obtain the neural network model.

Specifically, the neural network training update is performed by using a gradient descent method, and the update formula of the neuron weights and the bias is shown in the above formula. The value range of each parameter can be set to be between 0 and 0.01. The training set is used for deep neural network learning, so that the trained deep neural network model can calculate the correct trip point position of the line, and meanwhile, the data of the verification set is used for evaluating the performance of the neural network model. After training, the parameters of the trained neural network model are saved and used for calculating the trip point positions of the circuit.

In some optional embodiments, the step S203 may be implemented by determining the circuit breaker corresponding to the trip expected value greater than a preset threshold in the node trip data array as a trip node, and determining a trip constant of the trip node, by: determining the trip node as a first level trip node if there are no remaining trip nodes in the substation outlet circuit breaker to the line circuit breaker; sequentially determining each level of trip nodes according to the predetermined direction when the remaining trip nodes exist from the substation outlet breaker to the line breaker; determining the trip constant value of the trip node for each stage, wherein the trip constant values are different for each stage. According to the method, the trip nodes of different levels are set through the steps, so that different trip constant values can be set for the trip nodes of different levels.

In a specific implementation, after determining the trip node, a trip constant is set at the trip node. If no other tripping nodes exist between the outlet of the transformer substation and the tripping node, the node is a first-stage tripping node; if a trip node is included between the substation and the trip node, the trip node is a second stage trip node. And then setting a trip constant value on the circuit breaker equipment actually corresponding to the trip node in the circuit, wherein the first-stage trip node sets a first-stage trip constant value, the second-stage trip node sets a second-stage constant value, and so on. The specific fixed value data is determined by the matching of the upper and lower level circuits of the circuit.

In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for determining a line trip constant of the present application will be described in detail with reference to specific embodiments.

The embodiment relates to a specific method for determining a line tripping fixed value, as shown in fig. 3, comprising the following steps:

Step S1: and (3) line simplification: and hiding a non-breaker switch in a single line diagram of the 10kV line, wherein the breaker switch is changed into a node representation, and the simplified line diagram only comprises a breaker node and the rear end load of the node. Fig. 4 presents a simplified schematic diagram of a single line diagram of a 10kV line. The elements such as a load switch, an isolating switch, a fuse and the like in the simplified circuit diagram are hidden, the circuit only comprises a breaker node, and the number in the node represents the load size of the rear end of the node; the original circuit diagram comprises a transformer substation outlet, load switches S1, S2 and S3, a disconnecting switch Q1, circuit breakers CB1, CB2, CB3, CB4 and 315KVA loads, 630KVA loads and two 315KVA loads; after simplification, the obtained simplified circuit diagram only comprises a circuit breaker CB1 and a load 1260 in a circuit at the rear end of the circuit breaker, then a circuit breaker CB2 and a circuit breaker CB3, the loads of the circuit after the circuit breaker CB2 and the circuit breaker CB3 are 630KVA, the circuit breaker CB4 is arranged after the circuit breaker CB2, and the load of a branch circuit after the circuit breaker CB4 is 315KVA;

Step S2: conversion into a binary tree: fig. 5 shows a virtual node conversion process when the number of child nodes of a certain node is 5, m1 has two child nodes m2 and m3, m2 has five child nodes m4, m5, m6, m7 and m8, first two virtual nodes m9 and m10 are added to the node m2, the m9 virtual node has two child nodes m4 and m5, the m10 virtual node has two child nodes m6 and m7, so far the child node of the node m2 has been converted into 3, the conversion needs to be continued, one virtual node m11 is added, the virtual node m11 has two nodes m9 and m10, and all the nodes are converted into two child nodes, wherein the relationship between the nodes is m9=m4+m5, m10=m6+m7 and m11=m9+m10;

step S3: data conversion: storing load data of the binary tree into a1× (2 n-1) one-dimensional array X in a sequential storage mode, wherein the data at blank nodes are represented by 0 in the one-dimensional array, and n is the maximum depth value in all binary trees;

Step S4: neural network training obtains trip nodes: the array X is put into a trained neural network, and the output of the neural network is also a one-dimensional array of 1× (2 ⁿ -1), defined as Y. And setting a tripping node preset threshold value K, wherein in the array Y, the node with the number larger than K is set as the circuit tripping node. The range of the K value interval is (0.5, 1), and is usually set to be 0.8;

Step S5: setting a trip node constant value: a trip constant is set at the trip node. If no tripping node exists between the outlet of the transformer substation and the tripping node, the node is a first-stage tripping node; if a trip node is included between the substation and the trip node, the trip node is a second stage trip node. And then setting a tripping fixed value for the tripping node on the circuit breaker equipment actually corresponding to the circuit, wherein the first-stage tripping fixed value is set for the first-stage tripping point, the second-stage tripping point is set for the second-stage fixed value, and the specific fixed value data is automatically determined according to the matching of the upper and lower-stage circuits of the circuit.

The embodiment of the application also provides a device for determining the line tripping fixed value, and the device for determining the line tripping fixed value can be used for executing the method for determining the line tripping fixed value. The device is used for realizing the above embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

The following describes a device for determining a line trip constant value provided by an embodiment of the present application.

Fig. 6 is a schematic diagram of a line trip constant value determining apparatus according to an embodiment of the present application. As shown in fig. 6, the apparatus includes:

a first determining unit 10, configured to obtain load data of each circuit breaker in a line, and form a node load data array according to the load data of each circuit breaker, where the circuit breaker at least includes a substation outlet circuit breaker and a line circuit breaker, and elements in the node load data array represent total load sizes of all branches in a predetermined direction of a node corresponding to the circuit breaker, where the predetermined direction is a direction from the substation outlet circuit breaker to the line circuit breaker;

An analysis unit 20, configured to analyze the node load data array through a neural network model to obtain a node trip data array, where the neural network model is obtained by training multiple sets of data through machine learning, and each set of data in the multiple sets of data includes: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes;

Specifically, the node load data array is analyzed by adopting a neural network model, so that a node trip data array can be obtained, and if the node load data array is a one-dimensional array X of 1× (2 n-1), the output node trip data array is also a one-dimensional array of 1× (2 n-1) and can be marked as Y.

And a second determining unit 30, configured to determine the circuit breaker corresponding to the trip expected value greater than a preset threshold in the node trip data array as a trip node, and determine a trip constant value of the trip node, where the trip constant value is a constant value for tripping the circuit breaker.

According to the embodiment, load data of each circuit breaker in a line are obtained, and a node load data array is formed according to the load data of each circuit breaker; and then analyzing the node load data array through a neural network model to obtain a node trip data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes; and determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node, and determining the tripping fixed value of the tripping node. Compared with the prior art, the tripping node and the corresponding tripping fixed value can be automatically determined through the neural network model by manually calculating the tripping node and the corresponding fixed value list, so that the problems of labor waste and high error rate caused by manual calculation are avoided. Therefore, the problem that the error rate of manually calculating the trip node and the corresponding fixed value list in the prior art is high can be solved, and the effects of saving manpower and reducing the error rate are achieved.

In a specific implementation process, the first determining unit comprises an obtaining module and an adding module, wherein the obtaining module is used for obtaining an original circuit diagram, and the circuit breaker in the original circuit diagram is represented by a node to obtain a simplified circuit diagram of the original circuit diagram; and the adding module is used for adding the loads of all the branches of the circuit breaker in the preset direction in the simplified circuit diagram to obtain the load data corresponding to the nodes of the circuit breaker. The device simplifies the original circuit diagram and marks the nodes through the steps, thus facilitating the calculation of the load data of each node.

In some optional embodiments, the first determining unit further includes a filling module, a representation module, and a storage module, where the filling module is configured to fill the load data into the nodes of the circuit breaker corresponding to the simplified circuit diagram; the representation module is used for representing the simplified circuit diagram by adopting a binary tree structure to obtain a binary tree circuit diagram, wherein each node in the binary tree circuit diagram is provided with at most two child nodes; the storage module is used for sequentially storing the binary tree circuit diagram into an array with a preset size to obtain the node load data array, wherein the preset size is determined by the maximum depth value of the binary tree circuit diagram. The device adopts a binary tree to represent the simplified circuit diagram, so that the node load data array can be determined through the binary tree.

In order to train to get the neural network model, before analyzing the above-mentioned node load data array through the neural network model, get node trip data array, the above-mentioned apparatus also includes adjusting unit and training unit, the adjusting unit is used for obtaining the initial load data, adjust the size of the above-mentioned load data in the above-mentioned initial load data, get a plurality of historical load data, and produce the historical node load data array according to a plurality of above-mentioned historical load data, wherein, the adjustment scope of the above-mentioned initial load data is smaller than the predetermined multiple of the above-mentioned initial load data; the training unit is used for acquiring a historical node tripping data array corresponding to each historical node load data set, and training an initial neural network model by adopting the historical node load data sets and the historical node tripping data arrays to obtain the neural network model. The device trains the neural network model through the steps so as to obtain an accurate neural network model through training.

In a specific implementation process, training of the neural network system is as follows: a large number of single line diagrams of the 10kV line with constant value are obtained. The single line patterns are data-augmented to increase the number of single line patterns. The specific device is to randomly adjust the load in the circuit, the adjustment range is not more than 5%, and the tripping position of the circuit is unchanged. Performing the above operation on all the single line diagram data to obtain binary tree load data of all the single line diagrams, which are defined as input data X ₁,X₂,...,X_M of the neural network; binary tree trip node data of all the single line patterns are obtained and defined as target output data Y ₁,Y₂,...,Y_M of the neural network, wherein M is the number of all the single line patterns, and binary tree load data and binary tree trip node data of each single line pattern are one-dimensional arrays with the format of 1× (2 ⁿ -1). The input data and the output data of the neural network are divided into a training set and a testing set.

In some optional embodiments, the training unit includes a first determining module, a second determining module, and an updating module, where the first determining module is configured to determine that the neurons of the initial neural network model areWherein x _j represents an element in the history node load data set, ω _j represents a weight of the neuron, b is a bias of the neuron, and σ represents a value of the neuron; the second determining module is used for determining that the cost function of the initial neural network model is/>Wherein a _j represents an actual output of the initial neural network model, y _j represents an expectation of the initial neural network model, k represents the number of neurons, and C represents a value of the cost function; and updating the initial neural network model by using a gradient descent method. The device determines the neuron and the cost function of the neural network model through the steps, so that the initial neural network model can be accurately trained. /(I)

In a specific implementation process, the updating module comprises a first determining submodule and a second determining submodule, wherein the first determining submodule is used for determining that an updating formula of the weight is thatWherein ω _old is the weight before the present training, η is the learning rate, ω _new is the weight after the present training; the second determination submodule is used for determining that the update formula of the bias is/>Wherein b _old is the bias before the present training, and b _new is the bias after the present training. The device can update the weight and the bias in time through the steps so as to accurately train and obtain the neural network model.

In some optional embodiments, the second determining unit includes a third determining module, a fourth determining module, and a fifth determining module, where the third determining module is configured to determine the trip node as a first-stage trip node if there are no remaining trip nodes in the substation outlet circuit breaker to the line circuit breaker; the fourth determining module is used for sequentially determining the tripping nodes of each stage according to the preset direction under the condition that the outlet circuit breaker of the transformer substation has the rest tripping nodes in the circuit breaker; and a fifth determining module for determining the trip constant value of the trip nodes of each stage, wherein the trip constant value of each stage is different. The device sets the tripping nodes of different levels through the steps, so that different tripping fixed values can be set for the tripping nodes of different levels.

The device for determining the line tripping determination value comprises a processor and a memory, wherein the first determination unit, the analysis unit, the second determination unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions. The modules are all located in the same processor; or the above modules may be located in different processors in any combination.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the problem of high error rate of manually calculating the trip node and the corresponding fixed value list is solved by adjusting the kernel parameters.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the invention provides a computer readable storage medium, which comprises a stored program, wherein the program is controlled to control equipment where the computer readable storage medium is located to execute the method for determining the line tripping fixed value.

Specifically, the method for determining the line tripping fixed value comprises the following steps:

Optionally, obtaining load data of each circuit breaker in the line includes: the method for acquiring the load data of each circuit breaker in the circuit comprises the following steps: acquiring an original circuit diagram, and representing the circuit breaker in the original circuit diagram by using nodes to obtain a simplified circuit diagram of the original circuit diagram; in the simplified circuit diagram, loads of all branches of the circuit breaker in the predetermined direction are added to obtain the load data corresponding to the node of the circuit breaker.

Optionally, forming a node load data array according to the load data of each circuit breaker, including: filling the load data into the nodes of the corresponding circuit breaker in the simplified circuit diagram; representing the simplified circuit diagram by adopting a binary tree structure to obtain a binary tree circuit diagram, wherein each node in the binary tree circuit diagram is provided with at most two child nodes; and sequentially storing the binary tree circuit diagram into an array with a preset size to obtain the node load data array, wherein the preset size is determined by the maximum depth value of the binary tree circuit diagram.

Optionally, before analyzing the node load data array through the neural network model to obtain the node trip data array, the method further includes: acquiring initial load data, adjusting the size of the load data in the initial load data to obtain a plurality of historical load data, and generating a historical node load data set according to the plurality of historical load data, wherein the adjustment range of the initial load data is smaller than a preset multiple of the initial load data; and acquiring a historical node tripping data array corresponding to each historical node load data set, and training an initial neural network model by adopting the historical node load data sets and the historical node tripping data arrays to obtain the neural network model.

Optionally, training the initial neural network model using the historical node load data set and the historical node trip data set includes: determining the neuron of the initial neural network model asWherein x _j represents an element in the history node load data set, ω _j represents a weight of the neuron, b is a bias of the neuron, and σ represents a value of the neuron; determining the cost function of the initial neural network model as/>Wherein a _j represents an actual output of the initial neural network model, y _j represents an expectation of the initial neural network model, k represents the number of neurons, and C represents a value of the cost function; and updating the initial neural network model by using a gradient descent method.

Optionally, updating the initial neural network model by using a gradient descent method includes: determining the update formula of the weight asWherein ω _old is the weight before the present training, η is the learning rate, ω _new is the weight after the present training; determining the updated formula of the bias as/>Wherein b _old is the bias before the present training, and b _new is the bias after the present training.

Optionally, determining the circuit breaker corresponding to the trip expected value greater than a preset threshold in the node trip data array as a trip node, and determining a trip constant value of the trip node includes: determining the trip node as a first level trip node if there are no remaining trip nodes in the substation outlet circuit breaker to the line circuit breaker; sequentially determining each level of trip nodes according to the predetermined direction when the remaining trip nodes exist from the substation outlet breaker to the line breaker; determining the trip constant value of the trip node for each stage, wherein the trip constant values are different for each stage.

The embodiment of the invention provides an electronic device, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the processor realizes at least the following steps when executing the program:

The device herein may be a server, PC, PAD, cell phone, etc.

Optionally, before analyzing the node load data array through the neural network model to obtain the node trip data array, the method further includes: acquiring initial load data, adjusting the size of the load data in the initial load data to obtain a plurality of historical load data, and generating a historical node load data set according to the plurality of historical load data, wherein the adjustment range of the initial load data is smaller than a preset multiple of the initial load data; and acquiring a historical node tripping data array corresponding to each historical node load data set, and training an initial neural network model by adopting the initial load data and the historical node tripping data array to obtain the neural network model.

The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the above method of the various embodiments of the application:

It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

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

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

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

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

1) In the method for determining the circuit trip constant value, load data of each circuit breaker in a circuit is obtained, and a node load data array is formed according to the load data of each circuit breaker; and then analyzing the node load data array through a neural network model to obtain a node trip data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes; and determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node, and determining the tripping fixed value of the tripping node. Compared with the method that more manpower and higher error rate are wasted through manual calculation of the tripping nodes and the corresponding fixed values in the prior art, the method can automatically determine the tripping nodes and the corresponding tripping fixed values through the neural network model, and the problems of manpower waste and high error rate caused by manual calculation are avoided. Therefore, the problem that the error rate of manually calculating the trip node and the corresponding fixed value list in the prior art is high can be solved, and the effects of saving manpower and reducing the error rate are achieved.

2) In the circuit trip constant value determining device, load data of each circuit breaker in a circuit are obtained, and a node load data array is formed according to the load data of each circuit breaker; and then analyzing the node load data array through a neural network model to obtain a node trip data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes; and determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node, and determining the tripping fixed value of the tripping node. Compared with the prior art, the tripping node and the corresponding tripping fixed value can be automatically determined through the neural network model by manually calculating the tripping node and the corresponding fixed value list, so that the problems of labor waste and high error rate caused by manual calculation are avoided. Therefore, the problem that the error rate of manually calculating the trip node and the corresponding fixed value list in the prior art is high can be solved, and the effects of saving manpower and reducing the error rate are achieved.

The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method of determining a line trip decision, comprising:

Acquiring load data of each circuit breaker in a circuit, and forming a node load data array according to the load data of each circuit breaker, wherein the circuit breaker at least comprises a transformer substation outlet circuit breaker and a circuit breaker, and elements in the node load data array represent total load sizes of all branches in a preset direction of a node corresponding to the circuit breaker, and the preset direction is a direction from the transformer substation outlet circuit breaker to the circuit breaker;

analyzing the node load data array through a neural network model to obtain a node trip data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes;

And determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node, and determining a tripping fixed value of the tripping node, wherein the tripping fixed value is a fixed value for tripping the circuit breaker.

2. The method of determining of claim 1, wherein obtaining load data for each circuit breaker in the line comprises:

Acquiring an original circuit diagram, and representing the circuit breaker in the original circuit diagram by using nodes to obtain a simplified circuit diagram of the original circuit diagram;

and adding the loads of all branches of the circuit breaker in the preset direction in the simplified circuit diagram to obtain the load data corresponding to the nodes of the circuit breaker.

3. The method of determining of claim 2, wherein forming a node load data array from the load data of each of the circuit breakers comprises:

Filling the load data into the nodes of the corresponding circuit breakers in the simplified circuit diagram;

representing the simplified circuit diagram by adopting a binary tree structure to obtain a binary tree circuit diagram, wherein each node in the binary tree circuit diagram has at most two child nodes;

and sequentially storing the binary tree circuit diagram into an array with a preset size to obtain the node load data array, wherein the preset size is determined by the maximum depth value of the binary tree circuit diagram.

4. The method of determining of claim 1, wherein prior to analyzing the node load data array by a neural network model to obtain a node trip data array, the method further comprises:

Acquiring initial load data, adjusting the size of the initial load data to obtain a plurality of historical load data, and generating a historical node load data set according to the plurality of historical load data, wherein the adjustment range of the initial load data is smaller than a preset multiple of the initial load data;

And acquiring a historical node tripping data array corresponding to each historical node load data set, and training an initial neural network model by adopting the historical node load data sets and the historical node tripping data arrays to obtain the neural network model.

5. The method of determining of claim 4, wherein training an initial neural network model using the historical node load data set and the historical node trip data set comprises:

Determining neurons of the initial neural network model as Wherein x _j represents an element in the historical node load data set, ω _j represents a weight of the neuron, b is a bias of the neuron, σ represents a value of the neuron;

determining a cost function of the initial neural network model as Wherein a _j represents the actual output of the initial neural network model, y _j represents the expectation of the initial neural network model, k represents the number of neurons, and C represents the value of the cost function;

The initial neural network model is updated using a gradient descent method.

6. The method of determining of claim 5, wherein updating the initial neural network model using a gradient descent method comprises:

determining the updated formula of the weight as Wherein ω _old is the weight before the present training, η is the learning rate, ω _new is the weight after the present training;

Determining an updated formula for the bias as Wherein b _old is the bias before the current training, and b _new is the bias after the current training.

7. The determining method according to claim 1, wherein determining the circuit breaker corresponding to the trip expected value greater than a preset threshold in the node trip data array as a trip node, and determining a trip fixed value of the trip node, comprises:

Determining the trip node as a first level trip node in the event that there are no remaining of the trip nodes in the substation outlet circuit breaker to the line circuit breaker;

sequentially determining each level of trip nodes according to the preset direction under the condition that the rest of trip nodes exist from the transformer substation outlet circuit breaker to the line circuit breaker;

Determining the trip constant value of the trip node for each stage, wherein the trip constant value is different for each stage.

8. A line trip decision device, comprising:

The first determining unit is used for obtaining load data of each circuit breaker in a circuit and forming a node load data array according to the load data of each circuit breaker, wherein the circuit breaker at least comprises a transformer substation outlet circuit breaker and a circuit breaker, elements in the node load data array represent total load sizes of all branches in a preset direction of a node corresponding to the circuit breaker, and the preset direction is a direction from the transformer substation outlet circuit breaker to the circuit breaker;

The analysis unit is used for analyzing the node load data array through a neural network model to obtain a node tripping data array, wherein the neural network model is obtained by training a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises: the node load data array and the node trip data array, wherein elements in the node trip data array represent trip expected values corresponding to the nodes;

And the second determining unit is used for determining the circuit breaker corresponding to the tripping expected value larger than a preset threshold value in the node tripping data array as a tripping node and determining a tripping fixed value of the tripping node, wherein the tripping fixed value is a fixed value for tripping the circuit breaker.

9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the program, when run, controls a device in which the computer-readable storage medium is located to perform the determination method of any one of claims 1 to 7.

10. An electronic device, comprising: one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing the determining method of any of claims 1-7.