CN111090747A - Power communication fault emergency disposal method based on neural network classification - Google Patents
Power communication fault emergency disposal method based on neural network classification Download PDFInfo
- Publication number
- CN111090747A CN111090747A CN201911217782.3A CN201911217782A CN111090747A CN 111090747 A CN111090747 A CN 111090747A CN 201911217782 A CN201911217782 A CN 201911217782A CN 111090747 A CN111090747 A CN 111090747A
- Authority
- CN
- China
- Prior art keywords
- network management
- neural network
- power communication
- alarm
- fault
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 46
- 238000004891 communication Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 230000011218 segmentation Effects 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000013145 classification model Methods 0.000 abstract description 2
- 230000004044 response Effects 0.000 abstract description 2
- 230000000306 recurrent effect Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000001537 neural effect Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a neural network classification-based power communication fault emergency disposal method. Obtaining a network management warning text through a power communication network management system, and preprocessing the network management warning text through text word segmentation and character feature extraction so as to extract each piece of network management warning information; obtaining the mark fault type of each alarm by a manual marking method, and dividing the network management alarm information into a network management alarm training set and a network management alarm testing set; taking a network management alarm training set as the input of a neural network, training the neural network by combining with a labeled fault type, and obtaining the trained neural network through training; and applying the trained neural network to a power communication network management system, and providing a corresponding emergency disposal scheme according to the predicted fault type. According to the invention, by introducing the neural network classification model, the power communication fault disposal efficiency is improved, and the emergency response time is reduced.
Description
Technical Field
The invention belongs to the technical field of power communication, and particularly relates to a power communication fault emergency disposal method based on neural network classification.
Background
With the rapid development of the ubiquitous power internet of things in the power grid of China, the service borne by the traditional power communication network and the network coverage range rapidly increase, and the role of the power communication network in the ubiquitous power internet of things is increasingly prominent. In the high-speed development process of the power communication network, the power communication fault events are gradually increased, and great difficulty is caused to the operation and maintenance of the power communication network. The existing power communication fault disposal method is to manually search the alarm message in the power communication network management system, further analyze the fault type by combining the alarm message, and further give an emergency disposal scheme by combining the fault type.
However, the number of alarm messages in the existing power communication network management system is huge, and especially when a power communication fault occurs, the number of alarm messages is rapidly increased in a short time, and the huge alarm messages further affect the efficiency of fault classification, reduce the efficiency of emergency treatment, and further hinder the development of the ubiquitous power internet of things.
Disclosure of Invention
In order to solve the technical problem, the invention provides a power communication fault emergency disposal method based on neural network classification.
The technical scheme of the invention is a method for emergency disposal of power communication faults based on neural network classification, which is characterized by comprising the following steps:
step 1: obtaining a network management warning text through a power communication network management system, and preprocessing the network management warning text through text word segmentation and character feature extraction so as to extract each piece of network management warning information;
step 2: obtaining the mark fault type of each alarm by a manual marking method, and dividing the network management alarm information into a network management alarm training set and a network management alarm testing set;
and step 3: taking a network management alarm training set as the input of a neural network, training the neural network by combining with a labeled fault type, and obtaining the trained neural network through training;
and 4, step 4: and applying the trained neural network to a power communication network management system, and providing a corresponding emergency disposal scheme according to the predicted fault type.
Preferably, the network management warning text in step 1 is composed of a plurality of network management warning message texts;
in step 1, the text word segmentation divides the network management alarm text into a plurality of network management alarm message texts through a text word segmentation algorithm;
the character feature extraction in the step 1 carries out feature extraction on the network management alarm characters in each network management alarm message text, thereby extracting each network management alarm message;
preferably, the step 2 of dividing the network management alarm information into a network management alarm training set and a network management alarm test set is to divide the network management alarm information into the network management alarm training set and the network management alarm test set according to a certain proportion;
the network management warning training set consists of a plurality of pieces of network management warning information;
the network management alarm test set consists of a plurality of network management alarm messages;
preferably, the step 3 of training the neural network in combination with the labeled fault types specifically includes:
constructing a neural network model;
and predicting the fault type according to the marked fault type and the built neural network model, combining a loss model of the neural network, and optimizing by using the aim of minimizing the error between the marked fault type and the predicted fault type of the neural network, thereby obtaining the optimized neural network model.
Preferably, the applying the trained neural network to the power communication network management system in step 4 specifically includes:
according to the real-time network management warning message in the power communication network management system, carrying out real-time fault classification on the real-time network management warning message through a trained neural network to obtain a predicted fault type, and according to an emergency disposal scheme corresponding to the predicted fault type, providing an emergency disposal scheme corresponding to the predicted fault type;
and the fault disposal scheme corresponding to the predicted fault type is an emergency disposal scheme corresponding to the fault type association and stored in the power communication network management system according to the power communication fault disposal procedure.
According to the invention, by introducing the neural network classification model, the power communication fault disposal and emergency disposal efficiency is improved, and the emergency response time is reduced.
Description of the drawings:
FIG. 1 is a flow chart of a method of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The following describes in detail a specific embodiment of the present invention, which is a method for emergency handling of power communication fault based on neural network classification, with reference to the accompanying drawings, and includes the following steps:
the invention selects a 10G network in the area of Hubei as a power communication network, and develops a specific implementation mode of the invention on a 10G network management system.
Step 1: obtaining a network management warning text through a power communication network management system, and preprocessing the network management warning text through text word segmentation and character feature extraction so as to extract each piece of network management warning information;
the network management warning text in the step 1 consists of a plurality of network management warning message texts;
in the step 1, the text segmentation divides the network management alarm text into a plurality of network management alarm message texts through a text segmentation algorithm, wherein the text segmentation algorithm is a text segmentation algorithm based on a hidden Markov model;
the character feature extraction in the step 1 is to perform feature extraction on the network management alarm characters in each network management alarm message text so as to extract each network management alarm message, and the character feature extraction method is a word frequency reverse file frequency algorithm;
step 2: obtaining the mark fault type of each alarm by a manual marking method, and dividing the network management alarm information into a network management alarm training set and a network management alarm testing set;
dividing the network management alarm information into a network management alarm training set and a network management alarm test set, wherein the network management alarm information is divided into the network management alarm training set and the network management alarm test set according to a certain proportion, and the certain proportion is 4:1, namely 80% of the network management alarm information is used as the network management alarm training set, and 20% of the network management alarm information is used as the network management alarm test set;
the network management warning information is defined as:
messagejj∈[1,N]
wherein, N is the number of network management alarm information, messagejFor jth net management alarm information, messagejManually marking the type of failure as yj;
The network management alarm training set is composed of a plurality of pieces of network management alarm information in a messagejj∈[1,N]Randomly selecting network management alarm information with the quantity of 0.8N as a network management alarm training set, wherein the network management alarm training set comprises the following steps:
trainii∈[1,0.8N]
the network management alarm test set is composed of a plurality of network management alarm messages in a messageii∈[1,N]Randomly selecting network management alarm information with the quantity of 0.2N as a network management alarm test set, wherein the network management alarm test set comprises the following steps:
testkk∈[1,0.2N]
and step 3: taking a network management alarm training set as the input of a neural network, training the neural network by combining with a labeled fault type, and obtaining the trained neural network through training;
the training of the neural network obtained in the step 3 is specifically as follows:
constructing a neural network model through a recurrent neural network;
determining a specific structure of a recurrent neural model, and constructing a recurrent neural network model;
the constructed recurrent neural model adopts 1 input layer, 3 hidden layers and 1 output layer;
the input layer input is the ith sample train in the training setiAnd the output of the output layer is recorded as the type of the predicted fault
Randomly initializing a weight matrix U, W, V and bias matrices b and c of the recurrent neural model;
the ith sample train in the training setiThe hidden state of the recurrent neural network model is recorded as hiThe predicted value of the model, i.e. the type of the predicted fault, is recorded
Activation function f (x) is typically tanh, b is a bias in a linear relationship, and activation function g (x) is typically a Softmax function;
the recurrent neural network model is as follows:
selecting a cross entropy function Loss as a Loss function, recording the Loss function as L, and expressing the Loss function L as follows:
through the back propagation training, specifically:
selecting a cross entropy function Loss as an optimization target, and taking a model parameter weight matrix U, W, V and bias matrixes b and c as optimization objects;
comparison of predicted valuesWith the true value yiThe model parameters are optimized by iteration through a gradient descent method, so that an optimized cyclic neural network, namely a trained neural network, is obtained;
and 4, step 4: and applying the trained neural network to a power communication network management system, and providing a corresponding emergency disposal scheme according to the predicted fault type.
The step 4 of applying the trained neural network to the power communication network management system specifically comprises the following steps:
according to the real-time network management alarm message in the power communication network management system, carrying out real-time fault classification on the real-time network management alarm message through the trained neural network in the step 3 to obtain a predicted fault type, and according to an emergency disposal scheme corresponding to the predicted fault type, providing an emergency disposal scheme corresponding to the predicted fault type;
and the fault disposal scheme corresponding to the predicted fault type is an emergency disposal scheme corresponding to the fault type association and stored in the power communication network management system according to the power communication fault disposal procedure.
It should be understood that parts of the specification not set forth in detail are well within the prior art.
It should be understood that the above-mentioned preferred embodiments are described in some detail, and not intended to limit the scope of the invention, and those skilled in the art will be able to make alterations and modifications without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. A power communication fault emergency disposal method based on neural network classification is characterized by comprising the following steps:
step 1: obtaining a network management warning text through a power communication network management system, and preprocessing the network management warning text through text word segmentation and character feature extraction so as to extract each piece of network management warning information;
step 2: obtaining the mark fault type of each alarm by a manual marking method, and dividing the network management alarm information into a network management alarm training set and a network management alarm testing set;
and step 3: taking a network management alarm training set as the input of a neural network, training the neural network by combining with a labeled fault type, and obtaining the trained neural network through training;
and 4, step 4: and applying the trained neural network to a power communication network management system, and providing a corresponding emergency disposal scheme according to the predicted fault type.
2. The neural network classification-based power communication fault emergency handling method according to claim 1, wherein: the network management warning text in the step 1 consists of a plurality of network management warning message texts;
in step 1, the text word segmentation divides the network management alarm text into a plurality of network management alarm message texts through a text word segmentation algorithm;
in the step 1, the character feature extraction carries out feature extraction on the network management alarm characters in each network management alarm message text, thereby extracting each network management alarm message.
3. The neural network classification-based power communication fault emergency handling method according to claim 1, wherein:
in step 2, the network management warning information is divided into a network management warning training set and a network management warning test set according to a certain proportion;
the network management warning training set consists of a plurality of pieces of network management warning information;
the network management alarm test set is composed of a plurality of network management alarm messages.
4. The neural network classification-based power communication fault emergency handling method according to claim 1, wherein: the step 3 of training the neural network by combining the labeled fault types specifically comprises the following steps:
constructing a neural network model;
and predicting the fault type according to the marked fault type and the built neural network model, combining a loss model of the neural network, and optimizing by using the aim of minimizing the error between the marked fault type and the predicted fault type of the neural network, thereby obtaining the optimized neural network model.
5. The neural network classification-based power communication fault emergency handling method according to claim 1, wherein:
the step 4 of applying the trained neural network to the power communication network management system specifically comprises the following steps:
according to the real-time network management warning message in the power communication network management system, carrying out real-time fault classification on the real-time network management warning message through a trained neural network to obtain a predicted fault type, and according to an emergency disposal scheme corresponding to the predicted fault type, providing an emergency disposal scheme corresponding to the predicted fault type;
and the fault disposal scheme corresponding to the predicted fault type is an emergency disposal scheme corresponding to the fault type association and stored in the power communication network management system according to the power communication fault disposal procedure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911217782.3A CN111090747A (en) | 2019-12-03 | 2019-12-03 | Power communication fault emergency disposal method based on neural network classification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911217782.3A CN111090747A (en) | 2019-12-03 | 2019-12-03 | Power communication fault emergency disposal method based on neural network classification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111090747A true CN111090747A (en) | 2020-05-01 |
Family
ID=70393933
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911217782.3A Pending CN111090747A (en) | 2019-12-03 | 2019-12-03 | Power communication fault emergency disposal method based on neural network classification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111090747A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111538643A (en) * | 2020-07-07 | 2020-08-14 | 宝信软件(成都)有限公司 | Alarm information filtering method and system for monitoring system |
CN113821408A (en) * | 2021-09-23 | 2021-12-21 | 中国建设银行股份有限公司 | Server alarm processing method and related equipment |
CN115409431A (en) * | 2022-10-31 | 2022-11-29 | 国网湖北省电力有限公司信息通信公司 | Distributed power resource scheduling method based on neural network |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100228854A1 (en) * | 2009-03-09 | 2010-09-09 | At&T Mobility Ii Llc | Network operation management |
CN105447568A (en) * | 2015-11-09 | 2016-03-30 | 广州供电局有限公司 | BP neural network-based power communication fault analysis method |
CN108664374A (en) * | 2018-05-17 | 2018-10-16 | 腾讯科技(深圳)有限公司 | Fault warning model creation method, apparatus, fault alarming method and device |
CN110263172A (en) * | 2019-06-26 | 2019-09-20 | 国网江苏省电力有限公司南京供电分公司 | A kind of evented autonomous classification method of power system monitor warning information |
CN110321555A (en) * | 2019-06-11 | 2019-10-11 | 国网江苏省电力有限公司南京供电分公司 | A kind of power network signal classification method based on Recognition with Recurrent Neural Network model |
CN110334756A (en) * | 2019-06-26 | 2019-10-15 | 国网江苏省电力有限公司 | Power system monitor alarm event knows method for distinguishing, terminal installation, equipment and medium |
CN110329249A (en) * | 2019-07-02 | 2019-10-15 | 武汉理工大学 | To anti-collision warning control system and method before a kind of automobile of Recognition with Recurrent Neural Network |
-
2019
- 2019-12-03 CN CN201911217782.3A patent/CN111090747A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100228854A1 (en) * | 2009-03-09 | 2010-09-09 | At&T Mobility Ii Llc | Network operation management |
CN105447568A (en) * | 2015-11-09 | 2016-03-30 | 广州供电局有限公司 | BP neural network-based power communication fault analysis method |
CN108664374A (en) * | 2018-05-17 | 2018-10-16 | 腾讯科技(深圳)有限公司 | Fault warning model creation method, apparatus, fault alarming method and device |
CN110321555A (en) * | 2019-06-11 | 2019-10-11 | 国网江苏省电力有限公司南京供电分公司 | A kind of power network signal classification method based on Recognition with Recurrent Neural Network model |
CN110263172A (en) * | 2019-06-26 | 2019-09-20 | 国网江苏省电力有限公司南京供电分公司 | A kind of evented autonomous classification method of power system monitor warning information |
CN110334756A (en) * | 2019-06-26 | 2019-10-15 | 国网江苏省电力有限公司 | Power system monitor alarm event knows method for distinguishing, terminal installation, equipment and medium |
CN110329249A (en) * | 2019-07-02 | 2019-10-15 | 武汉理工大学 | To anti-collision warning control system and method before a kind of automobile of Recognition with Recurrent Neural Network |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111538643A (en) * | 2020-07-07 | 2020-08-14 | 宝信软件(成都)有限公司 | Alarm information filtering method and system for monitoring system |
CN111538643B (en) * | 2020-07-07 | 2020-10-16 | 宝信软件(成都)有限公司 | Alarm information filtering method and system for monitoring system |
CN113821408A (en) * | 2021-09-23 | 2021-12-21 | 中国建设银行股份有限公司 | Server alarm processing method and related equipment |
CN115409431A (en) * | 2022-10-31 | 2022-11-29 | 国网湖北省电力有限公司信息通信公司 | Distributed power resource scheduling method based on neural network |
CN115409431B (en) * | 2022-10-31 | 2023-01-24 | 国网湖北省电力有限公司信息通信公司 | Distributed power resource scheduling method based on neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112149316A (en) | Aero-engine residual life prediction method based on improved CNN model | |
CN111090747A (en) | Power communication fault emergency disposal method based on neural network classification | |
CN110232188A (en) | The Automatic document classification method of power grid user troublshooting work order | |
CN111709244B (en) | Deep learning method for identifying cause and effect relationship of contradictory dispute | |
CN108470022A (en) | A kind of intelligent work order quality detecting method based on operation management | |
CN110689069A (en) | Transformer fault type diagnosis method based on semi-supervised BP network | |
CN110895565A (en) | Method and system for classifying fault defect texts of power equipment | |
CN112419096A (en) | Automatic user power demand worksheet transferring method based on NLP information extraction and few-sample self-learning | |
CN115758255B (en) | Power consumption abnormal behavior analysis method and device under fusion model | |
CN108447475A (en) | A kind of method for building up of the speech recognition modeling based on electric power dispatching system | |
CN110889565B (en) | Distribution network routing inspection period calculation method based on multi-dimensional matrix decision | |
CN116187508A (en) | Wind turbine generator system fault prediction method integrating knowledge graph and deep learning | |
CN110728186B (en) | Fire detection method based on multi-network fusion | |
CN112035345A (en) | Mixed depth defect prediction method based on code segment analysis | |
CN108804743A (en) | A kind of nuclear accident Source Term Inversion method | |
CN114841268A (en) | Abnormal power customer identification method based on Transformer and LSTM fusion algorithm | |
CN105354764A (en) | Method for evaluating power grid maintenance scheme | |
CN106484913A (en) | Method and server that a kind of Target Photo determines | |
CN113128769A (en) | Intelligent flight delay prediction method based on deep learning | |
CN117150409A (en) | Power consumption abnormality detection method | |
CN109978013B (en) | Deep clustering method for character action recognition | |
CN111091141B (en) | Photovoltaic backboard fault diagnosis method based on layered Softmax | |
CN117172413A (en) | Power grid equipment operation state monitoring method based on multi-mode data joint characterization and dynamic weight learning | |
CN116663499A (en) | Intelligent industrial data processing method and system | |
CN117236154A (en) | Flood disaster condition assessment method |
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 |