CN111639815A - Method and system for predicting power grid defect materials through multi-model fusion - Google Patents
Method and system for predicting power grid defect materials through multi-model fusion Download PDFInfo
- Publication number
- CN111639815A CN111639815A CN202010490388.3A CN202010490388A CN111639815A CN 111639815 A CN111639815 A CN 111639815A CN 202010490388 A CN202010490388 A CN 202010490388A CN 111639815 A CN111639815 A CN 111639815A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- materials
- prediction
- defect
- 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.)
- Granted
Links
- 239000000463 material Substances 0.000 title claims abstract description 95
- 230000007547 defect Effects 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000004927 fusion Effects 0.000 title claims abstract description 55
- 230000002950 deficient Effects 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000003062 neural network model Methods 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims description 17
- 238000012795 verification Methods 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims 4
- 239000002994 raw material Substances 0.000 claims 4
- 238000003860 storage Methods 0.000 abstract description 14
- 238000007726 management method Methods 0.000 abstract description 9
- 230000008439 repair process Effects 0.000 abstract description 2
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 238000007796 conventional method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241001122767 Theaceae Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000010801 machine learning 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
- 230000006855 networking Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06Q50/06—Energy or water supply
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for predicting defective materials of a power grid through multi-model fusion, wherein the method comprises the steps of sequentially constructing a regression model, a negative feedback neural network model, a gradient lifting tree GBDT model and an XgBoost model based on fault probability strategies of different regions, time and equipment; uniformly inputting the collected defect material data and the corresponding meteorological data into the regression model, the negative feedback neural network model, the gradient lifting tree GBDT model and the XgBoost model for training; respectively outputting the prediction results corresponding to the models; and forming a prediction model by fusing the trained models by using a multi-model fusion strategy, and solving the average value of the prediction results to obtain the final fusion prediction result. The method and the system realize the advanced storage of the types, scales and places of emergency repair materials, improve the forward-looking planning capability of the material management of a power grid company, and reduce the cost of the operation materials of a power grid enterprise while enhancing the operation reliability of the power grid.
Description
Technical Field
The invention relates to the technical field of power grid electric power material information processing, in particular to a method and a system for predicting power grid defect materials through multi-model fusion.
Background
In the operation process of a power grid, a plurality of devices can break down due to various reasons, such as operation load, thunderstorm weather, snowy weather, landslide and the like, some faults cannot be solved through maintenance, so that materials need to be stored, and the traditional material storage is low in efficiency, namely, the supply of the materials is ensured through some simple analysis and strategies.
Along with the development and transformation of power grid enterprises, the efficiency problem of storage and scheduling receives attention, and along with the development of technologies such as big data, thing networking, artificial intelligence, the acquisition and the utilization of data become very convenient, make full use of historical defect data, excavate effective characteristic, realize the accurate prediction of defect goods and materials, can promote the storage and the scheduling efficiency of power grid, become the important tongs that reduce the operation cost of enterprise.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides a method and a system for predicting power grid defect materials through multi-model fusion, which can solve the problems of low efficiency of power grid storage and scheduling, prediction analysis of the defect materials and cost of power grid enterprise operation materials.
In order to solve the technical problems, the invention provides the following technical scheme: sequentially constructing a regression model, a negative feedback neural network model, a gradient lifting tree GBDT model and an XgBoost model based on fault probability strategies of different regions, time and equipment; uniformly inputting the collected defect material data and the corresponding meteorological data into the regression model, the negative feedback neural network model, the gradient lifting tree GBDT model and the XgBoost model for training; respectively outputting the prediction results corresponding to the models; and forming a prediction model by fusing the trained models by using a multi-model fusion strategy, and solving the average value of the prediction results to obtain the final fusion prediction result.
The invention discloses a preferable scheme of a method for predicting defective materials of a power grid through multi-model fusion, wherein the method comprises the following steps: the regression model solves the optimization objective by, as follows,
wherein ,nsamplesSample number, w is the weight coefficient of the vector in each dimension of the sample, X is the sample data, y is the amount of material defects, α, β are regular coefficients, | | w | | magnetism1、||w||2Respectively a first-order norm and a second-order norm of the coefficient;
wherein ,
predicted values of defect materials (unit is piece, value is positive real number), x: input deviceThe characteristic data of the power grid material (commissioning date, manufacturer, defect occurrence date, weather of weather such as temperature and humidity and whether snow is heavy or not when the defect occurs, etc.), theta: a weight parameter vector; the GBDT model and the XgBoost prediction are as follows,
wherein, K: the model has K classification regression trees: a classification regression tree space of the model; the negative feedback neural network model predicts that,
wherein ,w1: parameters of the first layer, σ: activation function, w2: a weight parameter of the second layer.
The invention discloses a preferable scheme of a method for predicting defective materials of a power grid through multi-model fusion, wherein the method comprises the following steps: training the plurality of constructed models, including dividing the meteorological data and the historical defect data by using a time principle to respectively form a training set, a verification set and a test set; performing precision training on the regression model, the negative feedback neural network model, the GBDT model and the XgBoost model in sequence by using the training set to perform N-round iteration until the output prediction result meets the prediction decision requirement, and stopping training; and verifying the precision of the trained models by using the verification set, and testing the generalization performance of the trained models by combining the test set.
The invention discloses a preferable scheme of a method for predicting defective materials of a power grid through multi-model fusion, wherein the method comprises the following steps: dividing the sample data set comprises dividing collected meteorological data and historical defect data from 2015 to 2017, and defining the meteorological data and the historical defect data as the training set; dividing the collected 2018-year meteorological data and the collected historical defect data, and defining the meteorological data and the collected historical defect data as the verification set; dividing the collected 2019 weather data and the collected historical defect data, and defining the weather data and the collected historical defect data as the test set.
The invention discloses a preferable scheme of a method for predicting defective materials of a power grid through multi-model fusion, wherein the method comprises the following steps: acquiring the meteorological data comprises acquiring historical meteorological information and weather forecast information; the historical meteorological information comprises temperature, visibility, cloud cover, precipitation, air pressure, wind speed, wind direction and relative humidity; the weather forecast information comprises heavy rain, light rain, thunder, heavy snow, light snow, hail and haze.
The invention discloses a preferable scheme of a method for predicting defective materials of a power grid through multi-model fusion, wherein the method comprises the following steps: acquiring the historical defect data comprises acquiring basic information of the power defect materials and field application information of the power defect materials; the basic information of the power defect materials comprises the region to which the defect materials belong, the load during operation, a manufacturer, a production date and a production date; the power defect material field application information comprises real-time monitoring information of equipment running states related to the defect materials.
The invention discloses a preferable scheme of a method for predicting defective materials of a power grid through multi-model fusion, wherein the method comprises the following steps: forming the prediction model further comprises averaging and rounding the prediction results of the plurality of models, as fused below,
wherein ,fm: model requiring fusion, round: getting the whole; and outputting a final fusion prediction result.
The invention discloses a preferable scheme of a method for predicting defective materials of a power grid through multi-model fusion, wherein the method comprises the following steps: the prediction result also comprises the quantity of defective materials of the power grid in each region and each category.
The invention discloses a preferable scheme of a system for predicting defective materials of a power grid through multi-model fusion, which comprises the following steps: the system comprises an acquisition module, a data acquisition module and a data acquisition module, wherein the acquisition module is used for acquiring the meteorological data and the historical defect data and constructing the sample data set; the data processing center module is used for receiving, calculating, storing and outputting data information to be processed and comprises an operation unit, a database and an input and output management unit, wherein the operation unit is connected with the acquisition module and used for receiving the data information acquired by the acquisition module to perform operation processing and calculating the prediction result and the fusion prediction result of each model, the database is connected with each module and used for storing all the received data information and providing allocation supply service for the data processing center module, and the input and output management unit is used for receiving the information of each module and outputting the operation result of the operation unit.
The invention discloses a preferable scheme of a system for predicting defective materials of a power grid through multi-model fusion, which comprises the following steps: the system comprises a prediction module, an input/output management unit, a data acquisition module and a database, wherein the prediction module is connected with the input/output management unit and used for analyzing the operation result of the original unit, judging by reading the information of the acquisition module and the information of the database and outputting the prediction result; and the fusion module is connected with the prediction module and used for merging and processing the prediction result output by the prediction module, feeding the prediction result back to the operation unit for fusion operation and finally outputting the fusion prediction result.
The invention has the beneficial effects that: according to the method, the quantity of the material faults of different time, different places and different types is predicted by utilizing big data and a machine learning modeling technology aiming at the materials with the emergency defects, so that the advanced storage of the types, scales and places of the materials for emergency repair is guided, the forward-looking planning capacity of the material management of a power grid company is improved, the operation reliability of a power grid is enhanced, and the cost of the material operation of the power grid enterprise is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flowchart of a method for predicting defective materials of a power grid through multi-model fusion according to a first embodiment of the present invention;
fig. 2 is a schematic diagram illustrating comparison of test result output curves of a method for predicting defective materials of a power grid through multi-model fusion according to a first embodiment of the present invention;
fig. 3 is a schematic block diagram illustrating a distribution of a multi-model fusion power grid defect material prediction system according to a second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1 and 2, a first embodiment of the present invention provides a method for predicting defective materials of a power grid through multi-model fusion, including:
s1: and sequentially constructing a regression model, a negative feedback neural network model, a gradient lifting tree GBDT model and an XgBoost model based on fault probability strategies of different regions, time and equipment. Wherein, it is required to be noted that:
the regression model solves the optimization objective by, as follows,
wherein ,nsamplesSample number, w is the weight coefficient of the vector in each dimension of the sample, X is the sample data, y is the amount of material defects, α, β are regular coefficients, | | w | | magnetism1、||w||2Respectively a first-order norm and a second-order norm of the coefficient;
wherein ,
predicted values of defect materials (unit is piece, value is positive real number), x: the characteristic data (commissioning date, manufacturer, defect occurrence date, weather of weather such as temperature and humidity and whether snow is heavy or not when the defect occurs, and the like) of the input power grid materials are as follows: a weight parameter vector;
the GBDT model and XgBoost predictions are as follows,
wherein, K: the model has K classification regression trees: a classification regression tree space of the model;
the negative feedback neural network model predicts that,
wherein ,w1: parameters of the first layer, σ: activation function, w2: a weight parameter of the second layer.
Specifically, the method comprises the following steps:
optimizing the first-order norm and the second-order norm, reducing parameters and selecting characteristics;
predicting the time series defect materials by a negative feedback neural network model;
predicting the time sequence by the gradient lifting tree GBDT model;
and predicting the time series of the defective materials by the XgBoost model.
S2: and uniformly inputting the acquired defect material data and the corresponding meteorological data into a regression model, a negative feedback neural network model, a gradient lifting tree GBDT model and an XgBoost model for training. The steps to be explained are as follows:
respectively acquiring meteorological data and historical defect data, and preprocessing the meteorological data and the historical defect data to form a sample data set;
acquiring meteorological data, including acquiring historical meteorological information and weather forecast information;
historical meteorological information includes, temperature, visibility, cloud cover, precipitation, air pressure, wind speed, wind direction and relative humidity;
the weather forecast information includes heavy rain, light rain, thunder, heavy snow, light snow, hail and haze.
Further, the acquiring of the historical defect data includes:
acquiring basic information and field application information of the power defect materials;
the basic information of the power defect materials comprises the region to which the defect materials belong, the load during operation, a manufacturer, a production date and a production date;
the power defect material field application information comprises real-time monitoring information of equipment running states related to defect materials.
Specifically, the training comprises:
dividing meteorological data and historical defect data by using a time principle to respectively form a training set, a verification set and a test set;
performing precision training on the regression model, the negative feedback neural network model, the gradient lifting tree GBDT model and the XgBoost model in sequence by utilizing a training set;
setting preset parameters, and finding the optimal parameters of each model by using a grid optimization strategy;
performing N rounds of iteration, and stopping training until the output prediction result meets the prediction decision requirement (the ratio of the real value to the predicted value error is smaller than a preset value);
and verifying the precision of the trained models by using the verification set, and testing the generalization performance of the trained models by combining the test set.
Further, dividing the sample data set includes:
dividing collected meteorological data and historical defect data from 2015 to 2017, and defining the meteorological data and the historical defect data as a training set;
dividing collected 2018-year meteorological data and historical defect data, and defining the meteorological data and the historical defect data as verification sets;
and dividing the collected 2019 meteorological data and historical defect data, and defining the meteorological data and the historical defect data as a test set.
S3: and respectively outputting the prediction results corresponding to the models. It should be noted that, the defect materials are predicted by using the trained models and the predicted material defect data is output, so as to obtain the number of the materials which may have defects and need to be replaced.
S4: and forming a prediction model by fusing the trained multiple models by utilizing a multi-model fusion strategy, and solving the average value of the prediction results to obtain the final fusion prediction result. It should be further noted that, the forming of the prediction model further includes:
the average value of the prediction results of a plurality of models is obtained and integrated, and the average value is fused as follows,
wherein ,fm: model requiring fusion, round: getting the whole;
and outputting a final fusion prediction result, namely the number of the defective materials of the power grid in each region and each category.
Preferably, the embodiment also needs to be described in the above, the existing SVM material demand prediction method mainly converts the power industry material demand prediction problem into a text classification problem, extracts text data of material demand history, performs feature extraction under a power field knowledge base, trains a power industry text content analysis model by using an SVM for feature vectors to obtain material text data, preprocesses semi-structured data to extract identification information to determine material demand text features, and predicts the industry material demand by using an SVM combined with the trained analysis model, although the method uses relevant text information of a project, the text information only contains descriptions of partial materials, so that a prediction result is incomplete, and a great error influence is generated for other unexplained material predictions; the method collects meteorological data and historical defect data of nearly five years to construct a sample data set, constructs data of different types of mutual balance error prediction of four models, combines the four models by utilizing a fusion processing strategy to form a prediction model so as to obtain a final average value, performs multi-aspect prediction under the condition of providing data samples for comprehensively predicting material requirements, and eliminates error influence existing in the traditional method.
In order to better verify and explain the technical effects adopted in the method, the method selects the traditional SVM material demand prediction method to perform a comparative test with the method of the invention so as to verify the real effect of the method of the invention; in order to verify that the prediction range of the method has higher prediction precision and more comprehensive prediction range compared with the traditional method, the traditional method and the method of the invention are adopted to respectively test and compare different material data in a certain area.
And (3) testing environment: (1) the traditional SVM prediction method reads data source extraction attribute features and utilizes a prediction model to output feature prediction for visual analysis;
(2) the two methods adopt Python to write a program and MATLB to run a simulation output data curve;
(3) the method of the invention predicts the defective materials in the area by using a plurality of models, and obtains the final prediction result by combining the output result of the fusion model to obtain the average value, as shown in the following table:
table 1: the invention relates to a prediction error data table.
| County area | Material | True value (piece) | Predicted value (part) | Error ratio |
| Cleaning and pressing device | Overhead conductor | 70 | 73 | 2％ |
| Cleaning and pressing device | Concrete electric wire pole | 68 | 62 | 5％ |
| Cloud rock | Body | 1 | 1 | 0％ |
| Nanming tea | Composite insulator | 3 | 3 | 0％ |
Referring to table 1, the predicted result of the method of the present invention can be accurate to 100% at best, and can not exceed 5% at worst, referring to fig. 2, the solid line is the curve output by the method of the present invention, and the dotted line is the curve output by the conventional method, and according to the schematic diagram of fig. 2, it can be visually seen that the method of the present invention has extremely high accuracy in the detection of various types of data and the comprehensiveness compared with the conventional method, the dotted line has a straight line decrease in the prediction accuracy when predicting a large amount of data, and has a large amplitude, which illustrates the error of the conventional method, and thus, referring to table 1 and fig. 2, the method of the present invention can be illustrated to have high accuracy while the comprehensiveness prediction.
Example 2
Referring to fig. 3, a second embodiment of the present invention is different from the first embodiment in that a system for predicting defective materials of a power grid by multi-model fusion is provided, which includes:
and the acquisition module 100 is used for acquiring meteorological data and historical defect data and constructing a sample data set.
The data processing center module 200 is configured to receive, calculate, store, and output data information to be processed, and includes an arithmetic unit 201, a database 202, and an input/output management unit 203, where the arithmetic unit 201 is connected to the acquisition module 100, and is configured to receive the data information acquired by the acquisition module 100 to perform arithmetic processing, and calculate a prediction result and a fusion prediction result of each model, the database 202 is connected to each module, and is configured to store all received data information, and provide a deployment and supply service for the data processing center module 200, and the input/output management unit 203 is configured to receive information of each module and output an arithmetic result of the arithmetic unit 201.
The prediction module 300 is connected to the input/output management unit 203, and is configured to analyze an operation result of the primitive unit 201, perform judgment by reading information of the acquisition module 100 and information of the database 202, and output a prediction result.
The fusion module 400 is connected to the prediction module 300, and configured to merge the prediction results output by the prediction module 300, feed the prediction results back to the operation unit 201 for fusion operation, and finally output a fusion prediction result.
It should be noted that the data processing center module 200 is mainly divided into three layers, including a control layer, an operation layer and a storage layer, the control layer is a command control center of the data processing center module 200, and is composed of an instruction register IR, an instruction decoder ID and an operation controller OC, the control layer can sequentially fetch each instruction from a memory according to a program pre-programmed by a user, place the instruction in the instruction register IR, analyze and determine the instruction by the instruction decoder, notify the operation controller OC to operate, and send a micro-operation control signal to a corresponding component according to a determined time sequence; the operation layer is the core of the data processing center module 200, can execute arithmetic operation (such as addition, subtraction, multiplication, division and addition operation thereof) and logical operation (such as shift, logical test or two-value comparison), is connected to the control layer, and performs operation by receiving a control signal of the control layer; the storage layer is a database of the data processing center module 200, and can store data (data to be processed and data already processed).
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. A method for predicting power grid defect materials through multi-model fusion is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
sequentially constructing a regression model, a negative feedback neural network model, a gradient lifting tree GBDT model and an XgBoost model based on fault probability strategies of different regions, time and equipment;
uniformly inputting the collected defect material data and the corresponding meteorological data into the regression model, the negative feedback neural network model, the gradient lifting tree GBDT model and the XgBoost model for training;
respectively outputting the prediction results corresponding to the models;
and forming a prediction model by fusing the trained models by using a multi-model fusion strategy, and solving the average value of the prediction results to obtain the final fusion prediction result.
2. The method for predicting defective materials of the power grid through multi-model fusion according to claim 1, wherein: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the regression model solves the optimization objective by, as follows,
wherein ,nsamplesSample number, w is the weight coefficient of the vector in each dimension of the sample, X is the sample data, y is the amount of material defects, α, β are regular coefficients, | | w | | magnetism1、||w||2Respectively a first-order norm and a second-order norm of the coefficient;
wherein ,
predicted values of defect materials (unit is piece, value is positive real number), x: the characteristic data (commissioning date, manufacturer, defect occurrence date, weather of weather such as temperature and humidity and whether snow is heavy or not when the defect occurs, and the like) of the input power grid materials are as follows: a weight parameter vector;
the GBDT model and the XgBoost prediction are as follows,
wherein, K: the model has K classification regression trees: a classification regression tree space of the model;
the negative feedback neural network model predicts that,
wherein ,w1: parameters of the first layer, σ: activation function, w2: a weight parameter of the second layer.
3. The method for predicting the defective materials of the power grid through multi-model fusion according to claim 1 or 2, wherein: training the constructed plurality of models, including,
dividing the meteorological data and the historical defect data by using a time principle to respectively form a training set, a verification set and a test set;
performing precision training on the regression model, the negative feedback neural network model, the gradient lifting tree GBDT model and the XgBoost model in sequence by using the training set;
performing N rounds of iteration until the output prediction result meets the prediction decision requirement, and stopping training;
and verifying the precision of the trained models by using the verification set, and testing the generalization performance of the trained models by combining the test set.
4. The method for predicting defective materials of the power grid through multi-model fusion according to claim 3, wherein: dividing the set of sample data comprises dividing the set of sample data,
dividing the collected meteorological data and the collected historical defect data from 2015 to 2017, and defining the meteorological data and the collected historical defect data as the training set;
dividing the collected 2018-year meteorological data and the collected historical defect data, and defining the meteorological data and the collected historical defect data as the verification set;
dividing the collected 2019 weather data and the collected historical defect data, and defining the weather data and the collected historical defect data as the test set.
5. The method for predicting defective materials of the power grid through multi-model fusion according to claim 4, wherein: acquiring the meteorological data comprises acquiring historical meteorological information and weather forecast information;
the historical meteorological information comprises temperature, visibility, cloud cover, precipitation, air pressure, wind speed, wind direction and relative humidity;
the weather forecast information comprises heavy rain, light rain, thunder, heavy snow, light snow, hail and haze.
6. The method for predicting the defective materials of the power grid through multi-model fusion according to claim 4 or 5, wherein: acquiring the historical defect data comprises acquiring basic information of the power defect materials and field application information of the power defect materials;
the basic information of the power defect materials comprises the region to which the defect materials belong, the load during operation, a manufacturer, a production date and a production date;
the power defect material field application information comprises real-time monitoring information of equipment running states related to the defect materials.
7. The method for predicting defective materials of the power grid through multi-model fusion according to claim 6, wherein: forming the predictive model further includes forming the predictive model,
the average value of the prediction results of a plurality of models is obtained and integrated, and the average value is fused as follows,
wherein ,fm: model requiring fusion, round: getting the whole;
and outputting a final fusion prediction result.
8. The method for predicting defective materials of the power grid through multi-model fusion according to claim 7, wherein: the prediction result also comprises the quantity of defective materials of the power grid in each region and each category.
9. The utility model provides a system for many models fuse prediction electric wire netting defect goods and materials which characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
an acquisition module (100) for acquiring the meteorological data and the historical defect data and constructing the sample data set;
the data processing center module (200) is used for receiving, calculating, storing and outputting data information to be processed, and comprises an operation unit (201), a database (202) and an input and output management unit (203), wherein the operation unit (201) is connected with the acquisition module (100) and used for receiving the data information acquired by the acquisition module (100) to perform operation processing and calculating the prediction result and the fusion prediction result of each model, the database (202) is connected with each module and used for storing all the received data information and providing allocation supply service for the data processing center module (200), and the input and output management unit (203) is used for receiving the information of each module and outputting the operation result of the operation unit (201).
10. The system for predicting defective materials of a power grid through multi-model fusion according to claim 9, wherein: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the prediction module (300) is connected to the input and output management unit (203) and is used for analyzing the operation result of the original unit (201), judging by reading the information of the acquisition module (100) and the information of the database (202) and outputting the prediction result;
the fusion module (400) is connected with the prediction module (300) and is used for merging and processing the prediction results output by the prediction module (300), feeding the prediction results back to the operation unit (201) for fusion operation, and finally outputting the fusion prediction results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010490388.3A CN111639815B (en) | 2020-06-02 | 2020-06-02 | Method and system for predicting power grid defect materials through multi-model fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010490388.3A CN111639815B (en) | 2020-06-02 | 2020-06-02 | Method and system for predicting power grid defect materials through multi-model fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111639815A true CN111639815A (en) | 2020-09-08 |
| CN111639815B CN111639815B (en) | 2023-09-05 |
Family
ID=72330403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010490388.3A Active CN111639815B (en) | 2020-06-02 | 2020-06-02 | Method and system for predicting power grid defect materials through multi-model fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111639815B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258039A (en) * | 2020-10-23 | 2021-01-22 | 贵州电网有限责任公司 | Intelligent scheduling method for defective materials of power system based on reinforcement learning |
| CN112365077A (en) * | 2020-11-20 | 2021-02-12 | 贵州电网有限责任公司 | Construction method of intelligent storage scheduling system for power grid defective materials |
| CN112613642A (en) * | 2020-12-07 | 2021-04-06 | 国网北京市电力公司 | Emergency material demand prediction method and device, storage medium and electronic equipment |
| CN112801417A (en) * | 2021-03-16 | 2021-05-14 | 贵州电网有限责任公司 | Optimized model parallel defect material prediction method |
| CN112801418A (en) * | 2021-03-16 | 2021-05-14 | 贵州电网有限责任公司 | Power grid defect material prediction method |
| CN112836883A (en) * | 2021-02-08 | 2021-05-25 | 贵州电网有限责任公司 | Self-adaptive two-stage power grid defect material prediction method |
| CN112836880A (en) * | 2021-02-08 | 2021-05-25 | 贵州电网有限责任公司 | RMSE-based model fusion method for power grid defect material demand accuracy |
| CN113269351A (en) * | 2021-04-28 | 2021-08-17 | 贵州电网有限责任公司 | Feature selection method for power grid equipment fault probability prediction |
| CN113516280A (en) * | 2021-04-28 | 2021-10-19 | 贵州电网有限责任公司 | Optimization method for power grid equipment fault probability prediction based on big data |
| CN114579712A (en) * | 2022-05-05 | 2022-06-03 | 中科雨辰科技有限公司 | Text attribute extraction and matching method based on dynamic model |
| CN114765575A (en) * | 2021-01-04 | 2022-07-19 | 中国移动通信有限公司研究院 | Network fault cause prediction method and device and electronic equipment |
| CN116502771A (en) * | 2023-06-21 | 2023-07-28 | 国网浙江省电力有限公司宁波供电公司 | Power distribution method and system based on electric power material prediction |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014041566A (en) * | 2012-08-23 | 2014-03-06 | Nippon Telegr & Teleph Corp <Ntt> | Device, method, and program for linear regression model estimation |
| CN108399575A (en) * | 2018-01-24 | 2018-08-14 | 大连理工大学 | A kind of five-factor model personality prediction technique based on social media text |
| CN110378932A (en) * | 2019-07-10 | 2019-10-25 | 上海交通大学 | A kind of correlation filtering Vision Tracking based on the correction of space canonical |
| CN110443413A (en) * | 2019-07-23 | 2019-11-12 | 华南理工大学 | The construction method of Power Material demand forecast system and Power Material demand model |
| CN110929836A (en) * | 2018-09-20 | 2020-03-27 | 北京市商汤科技开发有限公司 | Neural network training and image processing method and device, electronic device and medium |
-
2020
- 2020-06-02 CN CN202010490388.3A patent/CN111639815B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014041566A (en) * | 2012-08-23 | 2014-03-06 | Nippon Telegr & Teleph Corp <Ntt> | Device, method, and program for linear regression model estimation |
| CN108399575A (en) * | 2018-01-24 | 2018-08-14 | 大连理工大学 | A kind of five-factor model personality prediction technique based on social media text |
| CN110929836A (en) * | 2018-09-20 | 2020-03-27 | 北京市商汤科技开发有限公司 | Neural network training and image processing method and device, electronic device and medium |
| CN110378932A (en) * | 2019-07-10 | 2019-10-25 | 上海交通大学 | A kind of correlation filtering Vision Tracking based on the correction of space canonical |
| CN110443413A (en) * | 2019-07-23 | 2019-11-12 | 华南理工大学 | The construction method of Power Material demand forecast system and Power Material demand model |
Non-Patent Citations (2)
| Title |
|---|
| SEDAT GOLGIYAZ等: "Artificial neural network regression model to predict flue gas temperature and emissions with the spectral norm of flame image", 《FUEL》 * |
| 闫卓男 等: "城市灾害应急物流配送干扰管理系统模型研究", 《工程管理学报》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258039A (en) * | 2020-10-23 | 2021-01-22 | 贵州电网有限责任公司 | Intelligent scheduling method for defective materials of power system based on reinforcement learning |
| CN112365077B (en) * | 2020-11-20 | 2022-06-21 | 贵州电网有限责任公司 | Construction method of intelligent storage scheduling system for power grid defective materials |
| CN112365077A (en) * | 2020-11-20 | 2021-02-12 | 贵州电网有限责任公司 | Construction method of intelligent storage scheduling system for power grid defective materials |
| CN112613642A (en) * | 2020-12-07 | 2021-04-06 | 国网北京市电力公司 | Emergency material demand prediction method and device, storage medium and electronic equipment |
| CN112613642B (en) * | 2020-12-07 | 2024-03-15 | 国网北京市电力公司 | Emergency material demand prediction method and device, storage medium and electronic equipment |
| CN114765575B (en) * | 2021-01-04 | 2024-06-11 | 中国移动通信有限公司研究院 | Network fault cause prediction method and device and electronic equipment |
| CN114765575A (en) * | 2021-01-04 | 2022-07-19 | 中国移动通信有限公司研究院 | Network fault cause prediction method and device and electronic equipment |
| CN112836883A (en) * | 2021-02-08 | 2021-05-25 | 贵州电网有限责任公司 | Self-adaptive two-stage power grid defect material prediction method |
| CN112836880A (en) * | 2021-02-08 | 2021-05-25 | 贵州电网有限责任公司 | RMSE-based model fusion method for power grid defect material demand accuracy |
| CN112801418A (en) * | 2021-03-16 | 2021-05-14 | 贵州电网有限责任公司 | Power grid defect material prediction method |
| CN112801418B (en) * | 2021-03-16 | 2023-10-10 | 贵州电网有限责任公司 | Method for predicting defective materials of power grid |
| CN112801417A (en) * | 2021-03-16 | 2021-05-14 | 贵州电网有限责任公司 | Optimized model parallel defect material prediction method |
| CN113516280A (en) * | 2021-04-28 | 2021-10-19 | 贵州电网有限责任公司 | Optimization method for power grid equipment fault probability prediction based on big data |
| CN113269351A (en) * | 2021-04-28 | 2021-08-17 | 贵州电网有限责任公司 | Feature selection method for power grid equipment fault probability prediction |
| CN114579712A (en) * | 2022-05-05 | 2022-06-03 | 中科雨辰科技有限公司 | Text attribute extraction and matching method based on dynamic model |
| CN114579712B (en) * | 2022-05-05 | 2022-07-15 | 中科雨辰科技有限公司 | Text attribute extraction and matching method based on dynamic model |
| CN116502771A (en) * | 2023-06-21 | 2023-07-28 | 国网浙江省电力有限公司宁波供电公司 | Power distribution method and system based on electric power material prediction |
| CN116502771B (en) * | 2023-06-21 | 2023-12-01 | 国网浙江省电力有限公司宁波供电公司 | Power distribution method and system based on electric power material prediction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111639815B (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639815B (en) | Method and system for predicting power grid defect materials through multi-model fusion | |
| KR102159692B1 (en) | solar photovoltatic power generation forecasting apparatus and method based on big data analysis | |
| CN111695731B (en) | Load prediction method, system and equipment based on multi-source data and hybrid neural network | |
| CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
| CN112182720B (en) | Building energy consumption model evaluation method based on building energy management application scene | |
| CN112285807B (en) | Meteorological information prediction method and device | |
| CN106251001A (en) | A kind of based on the photovoltaic power Forecasting Methodology improving fuzzy clustering algorithm | |
| CN111292020B (en) | Power grid real-time operation risk assessment method and system based on random forest | |
| CN104318332A (en) | Power load predicting method and device | |
| CN109325607A (en) | A kind of short-term wind power forecast method and system | |
| CN114493052B (en) | Multi-model fusion self-adaptive new energy power prediction method and system | |
| CN112367400B (en) | Intelligent inspection method and system for power internet of things with edge cloud coordination | |
| CN114548509A (en) | Multi-type load joint prediction method and system for multi-energy system | |
| Dong | Combining unsupervised and supervised learning for asset class failure prediction in power systems | |
| CN116186548A (en) | Power load prediction model training method and power load prediction method | |
| CN112949207A (en) | Short-term load prediction method based on improved least square support vector machine | |
| CN108830407A (en) | Sensor distribution optimization method under the conditions of multi-state in monitoring structural health conditions | |
| CN115829145A (en) | Photovoltaic power generation capacity prediction system and method | |
| CN114912716A (en) | Short-term power load prediction method and system based on bidirectional long-term and short-term memory network | |
| CN111651603A (en) | Power industry single-level text classification method and system based on LAV parameter fine adjustment | |
| CN110490220A (en) | A kind of bus load discrimination method and system | |
| CN114862363A (en) | Evaluation analysis method based on substation project cost data analysis | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN117575564A (en) | Extensible infrastructure network component maintenance and transformation decision evaluation method and system | |
| CN107590537A (en) | For constructing the granulation Forecasting Methodology in probabilistic forecasting section |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yu Hong Inventor after: Tang Chengxuan Inventor after: Jiang Qunqun Inventor after: Chen Yuyi Inventor after: Zhang Xiu Inventor after: Cheng Wenmei Inventor after: Dai Zhou Inventor after: Xu Yidie Inventor before: Yu Hong Inventor before: Tang Chengxuan Inventor before: Jiang Qunqun Inventor before: Chen Yuyi Inventor before: Zhang Xiu Inventor before: Cheng Wenmei Inventor before: Dai Zhou Inventor before: Xu Yidie |
|
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yu Hong Inventor after: Tang Chengxuan Inventor after: Jiang Qunqun Inventor after: Chen Jueyi Inventor after: Zhang Xiu Inventor after: Cheng Wenmei Inventor after: Dai Zhou Inventor after: Xu Yidie Inventor before: Yu Hong Inventor before: Tang Chengxuan Inventor before: Jiang Qunqun Inventor before: Chen Yuyi Inventor before: Zhang Xiu Inventor before: Cheng Wenmei Inventor before: Dai Zhou Inventor before: Xu Yidie |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |