CN112257956A - Method, device and equipment for predicting power transmission line suffering from rainstorm disaster - Google Patents
Method, device and equipment for predicting power transmission line suffering from rainstorm disaster Download PDFInfo
- Publication number
- CN112257956A CN112257956A CN202011244454.5A CN202011244454A CN112257956A CN 112257956 A CN112257956 A CN 112257956A CN 202011244454 A CN202011244454 A CN 202011244454A CN 112257956 A CN112257956 A CN 112257956A
- Authority
- CN
- China
- Prior art keywords
- disaster
- power transmission
- data
- transmission line
- rainstorm
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 164
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000012549 training Methods 0.000 claims abstract description 128
- 238000000547 structure data Methods 0.000 claims abstract description 15
- 238000013058 risk prediction model Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 16
- 239000002689 soil Substances 0.000 claims description 10
- 238000001556 precipitation Methods 0.000 claims description 6
- 230000003203 everyday effect Effects 0.000 claims description 5
- 239000004575 stone Substances 0.000 claims description 5
- 230000008014 freezing Effects 0.000 claims description 4
- 238000007710 freezing Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 description 48
- 230000008569 process Effects 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 4
- 230000004913 activation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000005284 excitation Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000010485 coping Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000012546 transfer Methods 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N3/045—Combinations of 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a method, a device and equipment for predicting that a power transmission line is subjected to a rainstorm disaster. The method comprises the following steps: acquiring the disaster causing factor data of the power transmission line to be predicted, wherein the disaster causing factor data of the power transmission line comprises the following steps: the method comprises the steps of inputting storm disaster causing factor data of a power transmission line to be predicted into a storm disaster prediction model to obtain the predicted storm disaster condition of the power transmission line to be predicted according to meteorological characteristic element data, power transmission line structure data, geological characteristic element data and historical storm data, wherein the storm disaster risk prediction model is a restricted Boltzmann model obtained by training of the storm disaster causing factor data of multiple groups of power transmission lines. According to the method, the rainstorm disaster condition of the power transmission line to be predicted is comprehensively predicted from the external cause, the internal cause and the historical rainstorm data which affect the power transmission line to be predicted, so that the prediction accuracy is high.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, and a device for predicting that a power transmission line is subjected to a storm disaster.
Background
Rainstorm can cause tower collapse and disconnection of a power transmission line of a power grid and show long-term faults, transformer substation equipment is damaged, even disaster-affected plants and stations stop completely, the safe operation of the power grid is seriously threatened, and great economic loss and social influence are caused. Therefore, it is necessary to predict the situation where the power transmission line is subjected to a storm disaster.
At present, an intelligent algorithm-based disaster risk assessment method mainly depends on accumulation and experience of historical data, and a related algorithm model is combined to predict the probability of the power transmission line suffering from the rainstorm disaster through a preliminary machine learning method.
However, the existing intelligent algorithm only stays in the one-sided machine learning process, and the prediction accuracy is not high.
Disclosure of Invention
To solve the above technical problem or at least partially solve the above technical problem, the present disclosure provides a method, an apparatus, and a device for predicting that a power transmission line is subjected to a storm disaster.
In a first aspect, the present disclosure provides a method for predicting that a power transmission line is subjected to a rainstorm disaster, including:
acquiring the disaster causing factor data of the power transmission line to be predicted, wherein the disaster causing factor data of the power transmission line comprises the following steps: meteorological characteristic element data, power transmission line structure data, geological characteristic element data and historical rainstorm data;
and inputting the data of the disaster causing factors of the rainstorm disasters of the power transmission lines to be predicted into a rainstorm disaster prediction model to obtain the predicted rainstorm disaster conditions of the power transmission lines to be predicted, wherein the rainstorm disaster risk prediction model is a restricted Boltzmann model obtained by training the data of the disaster causing factors of the rainstorm disasters of a plurality of groups of power transmission lines.
Optionally, the meteorological feature element data includes one or more of the following: precipitation, wind speed, relative humidity and temperature;
the power transmission line structure data includes: basic characteristic data of each base tower of the power transmission line;
the geological feature element data comprises one or more of: the method comprises the following steps of topographic and geomorphic data, basic characteristic data of each base tower, soil compactness, stratum lithology data, broken stone content in soil, slope characteristic data and debris flow disaster-causing factor data.
Optionally, the topographic data includes: freezing zone topographic data or tuyere region topographic data;
the debris flow disaster-causing factor data comprises one or more of the following data: mud level, mud velocity, infrasound and ground sounds;
the basic characteristic data of each base tower of the power transmission line comprises one or more of the following data: and the independent foundation, the pile foundation and the digging foundation of each base tower of the power transmission line.
Optionally, the predicting of the rainstorm disaster condition of the power transmission line to be predicted includes: whether a rainstorm disaster exists every day in a preset time period.
Optionally, before the data of the disaster causing factor of the rainstorm disaster of the power transmission line is input into the rainstorm disaster prediction model to obtain the predicted rainstorm disaster condition of the power transmission line, the method further includes:
acquiring rainstorm disaster causing factor data of a plurality of power transmission lines to obtain a training sample set, wherein the training sample set comprises a plurality of training samples, and each training sample comprises the rainstorm disaster causing factor data of one power transmission line in the plurality of power transmission lines at the same moment;
training the storm disaster prediction model using the training sample set until the storm disaster prediction model converges.
Optionally, the convergence condition of the rainstorm disaster prediction model is as follows: and the proportion threshold is smaller than a preset threshold, wherein the proportion threshold is the proportion of the difference value between the reset values of the training samples and the training samples in the training samples, and the reset value of the training samples is obtained by performing forward calculation on the training samples and then performing reverse calculation on the output obtained by performing forward calculation on the training samples.
In a second aspect, the present disclosure provides an apparatus for predicting that a power transmission line is subjected to a storm disaster, including:
the acquiring module is used for acquiring the disaster causing factor data of the power transmission line to be predicted, wherein the disaster causing factor data of the power transmission line comprises the following steps: meteorological characteristic element data, power transmission line structure data, geological characteristic element data and historical rainstorm data;
and the obtaining module is used for inputting the disaster causing factor data of the power transmission line to be predicted into a disaster causing factor prediction model to obtain the predicted disaster causing condition of the power transmission line to be predicted, wherein the disaster causing factor prediction model is a restricted boltzmann model obtained by training the disaster causing factor data of a plurality of groups of power transmission lines.
Optionally, the meteorological feature element data includes one or more of the following: precipitation, wind speed, relative humidity and temperature;
the power transmission line structure data includes: basic characteristic data of each base tower of the power transmission line;
the geological feature element data comprises one or more of: the method comprises the following steps of topographic and geomorphic data, basic characteristic data of each base tower, soil compactness, stratum lithology data, broken stone content in soil, slope characteristic data and debris flow disaster-causing factor data.
Optionally, the topographic data includes: freezing zone topographic data or tuyere region topographic data;
the debris flow disaster-causing factor data comprises one or more of the following data: mud level, mud velocity, infrasound and ground sounds;
the basic characteristic data of each base tower of the power transmission line comprises one or more of the following data: and the independent foundation, the pile foundation and the digging foundation of each base tower of the power transmission line.
Optionally, the predicting of the rainstorm disaster condition of the power transmission line to be predicted includes: whether a rainstorm disaster exists every day in a preset time period.
Optionally, the apparatus further comprises:
the acquisition module is further used for acquiring the disaster causing factor data of the rainstorm disasters of the plurality of power transmission lines to obtain a training sample set, wherein the training sample set comprises a plurality of training samples, and each training sample comprises the disaster causing factor data of one power transmission line in the plurality of power transmission lines at the same moment;
and the training module is used for training the rainstorm disaster prediction model by using the training sample set until the rainstorm disaster prediction model converges.
Optionally, the convergence condition of the rainstorm disaster prediction model is as follows: and the proportion threshold is smaller than a preset threshold, wherein the proportion threshold is the proportion of the difference value between the reset values of the training samples and the training samples in the training samples, and the reset value of the training samples is obtained by performing forward calculation on the training samples and then performing reverse calculation on the output obtained by performing forward calculation on the training samples.
In a third aspect, the present disclosure provides an apparatus for predicting that a power transmission line is subjected to a storm disaster, including:
a memory for storing processor-executable instructions;
a processor for implementing the method according to the first aspect as described above when the computer program is executed.
In a fourth aspect, the present disclosure provides a computer-readable storage medium having stored thereon computer-executable instructions for implementing the method for predicting that a power transmission line is exposed to a storm disaster as described in the first aspect above when the computer-executable instructions are executed by a processor.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:
through obtaining the disaster causing factor data of the power transmission line to be predicted, the disaster causing factor data of the rainstorm disaster comprises the following steps: the method comprises the steps of obtaining weather characteristic element data, power transmission line structure data, geological characteristic element data and historical rainstorm data, comprehensively predicting the rainstorm disaster condition of the power transmission line to be predicted according to external factors, internal factors and historical rainstorm data influencing the power transmission line to be predicted, inputting the rainstorm disaster causing factor data of the power transmission line to be predicted into a rainstorm disaster prediction model to obtain the predicted rainstorm disaster condition of the power transmission line to be predicted, training a limited Boltzmann machine model by adopting the rainstorm disaster causing factor data, and fully learning the influence of the rainstorm disaster causing factor data on the prediction of the rainstorm disaster by the obtained rainstorm disaster prediction model, so that the prediction accuracy is high.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present disclosure, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a method for predicting that a power transmission line is subjected to a storm disaster according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of another method for predicting that a power transmission line is subjected to a storm disaster according to an embodiment of the present disclosure;
fig. 3 is a schematic flow chart of a method for training a rainstorm disaster prediction model according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an apparatus for predicting that a power transmission line is subjected to a storm disaster according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an apparatus for predicting that a power transmission line is subjected to a storm disaster according to an embodiment of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, aspects of the present disclosure will be further described below. It should be noted that the embodiments and features of the embodiments of the present disclosure may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein; it is to be understood that the embodiments disclosed in the specification are only a few embodiments of the present disclosure, and not all embodiments.
The natural disasters bring inevitable influence on the power transmission line of the power grid, wherein the influence range of the rainstorm disasters and the icing and pollution disasters is the widest, and the rainstorm disasters account for more than 80 percent of the three natural disasters according to statistics. Rainstorm can cause the power transmission line to fall down and break and show long-term faults, transformer substation equipment is damaged, even the plant station in a disaster is stopped completely, the safe operation of a power grid is seriously threatened, and great economic loss and social influence are caused. The problem of rainstorm disasters of the power transmission line is one of the biggest threats threatening the safety of the power transmission line at present. The prediction of the condition of the power transmission line suffering from the rainstorm disaster has important significance and engineering practical value, and therefore the condition of the power transmission line suffering from the rainstorm disaster needs to be predicted.
At present, a disaster risk assessment method based on an intelligent algorithm mainly depends on accumulation and experience of historical rainstorm condition data, and a related algorithm model is combined to predict the probability of the power transmission line suffering from the rainstorm disaster through a preliminary machine learning method. However, the intelligent algorithm only stays in a one-sided machine learning process, and the prediction accuracy is not high.
Aiming at the problems of the method, the method for predicting the rainstorm disaster of the power transmission line is provided, the data of multiple disaster-causing factors of the power transmission line to be predicted are obtained, the data of the multiple disaster-causing factors of the power transmission line to be predicted are input into the deep neural network model obtained through training, the condition that the power transmission line to be predicted suffers from the rainstorm disaster in the future is obtained, and the prediction accuracy is high.
The following describes the technical solutions of the present invention and how to solve the above technical problems with reference to specific embodiments.
Fig. 1 is a schematic flowchart of a method for predicting that a power transmission line is subjected to a storm disaster according to an embodiment of the present disclosure, as shown in fig. 1, the method of the present embodiment is executed by a computer or a server, and the method of the present embodiment is as follows:
s101, acquiring disaster-causing factor data of the power transmission line to be predicted in the rainstorm disaster.
Wherein, the data of disaster-causing factors of rainstorm disasters include but are not limited to: meteorological characteristic element data, power transmission line structure data, geological characteristic element data and historical rainstorm data.
Wherein, the meteorological characteristic element data includes but is not limited to one or more of the following: precipitation, wind speed, relative humidity and temperature. The power transmission line structure data includes but is not limited to: and basic characteristic data of each base tower of the power transmission line. The geological feature factor data includes, but is not limited to, one or more of the following: the method comprises the following steps of topographic and geomorphic data, basic characteristic data of each base tower, soil compactness, stratum lithology data, broken stone content in soil, slope characteristic data and debris flow disaster-causing factor data.
Optionally, the topographic data includes, but is not limited to: and topographic data of the frozen zone or topographic data of the tuyere region. Debris flow disaster factor data include, but are not limited to, one or more of the following: mud level, mud velocity, infrasound, and ground sound. The basic characteristic data of each base tower of the transmission line comprises but is not limited to one or more of the following: independent foundation, pile foundation and digging foundation of each base tower of the power transmission line.
External factors (external factors) influencing the excitation of the rainstorm disaster of the power transmission line to be predicted mainly comprise meteorological characteristic element data and geological characteristic element data, internal factors (internal factors) influencing the excitation of the rainstorm disaster of the power transmission line to be predicted mainly comprise basic characteristics of all base towers of the power transmission line, and meanwhile historical rainstorm data also influence prediction. The internal cause of the transmission line is stable relative to the external cause, so the occurrence of the rainstorm disaster accident of the transmission line is mainly determined by the external cause after the internal cause is determined.
In this embodiment, the disaster causing factor data of the power transmission line to be predicted is first acquired, and the disaster causing factor data of the power transmission line includes: meteorological characteristic element data, power transmission line structure data, geological characteristic element data and historical rainstorm data.
Optionally, the original data of the disaster causing factors of the rainstorm disaster related to the disaster causing factor data of the power transmission line to be predicted are obtained, and the original data of the disaster causing factors of the rainstorm disaster are normalized to obtain the disaster causing factor data of the rainstorm disaster. For example, the numerical unit of the acquired original temperature data of the power transmission line to be predicted is fahrenheit, and the numerical unit of the input temperature in the rainstorm disaster prediction model is celsius, the original temperature data is converted into the numerical value with the celsius as the unit, so that the temperature data of the power transmission line to be predicted is obtained.
S102, inputting the data of the disaster causing factors of the rainstorm disasters of the power transmission line to be predicted into a rainstorm disaster prediction model to obtain the predicted rainstorm disaster condition of the power transmission line to be predicted.
The rainstorm disaster risk prediction model is a limited Boltzmann machine model obtained by training of rainstorm disaster causing factor data of a plurality of power transmission lines.
The constrained boltzmann model is a thermodynamic-based energy model, which is a model with a display layer v ═ v { (v })1,v2,...,vMH and a hidden layer h ═ h1,h2,...,hNAnd the neural network model is internally connected without any connection, is symmetrically connected among layers and has no self feedback, and belongs to an unsupervised generation model. For a group ofA given state (v, h) may define its energy function E (v, h), the joint probability distribution of the display layer v and the hidden layer h being denoted P (v, h), when the energy function is defined as the following equation (1):
wherein v isiThe ith neuron, h, representing the display layeriThe j-th neuron, ω, representing a hidden layerijIs the connection weight of the ith neuron of the hidden layer and the jth neuron of the display layer, aiTo show the bias of the ith neuron of the layer, biThe bias of the ith neuron of the display layer is shown, M is the number of nodes of the display layer, and N is the number of nodes of the hidden layer.
In this embodiment, the rainstorm disaster risk prediction model is obtained by training a limited boltzmann machine model by a method combining unsupervised learning and supervised learning, that is, high-level characteristic influence factors are extracted through unsupervised learning of a limited boltzmann machine, and the limited boltzmann machine is propagated in reverse, so that supervised learning is performed, and a rainstorm disaster causing factor is fitted, so that the rainstorm disaster prediction model based on the limited boltzmann machine is obtained.
The method for predicting the rainstorm disaster condition of the power transmission line to be predicted comprises the following steps: whether a rainstorm disaster exists every day in a preset time period. Alternatively, "0" may be used to indicate that there is no storm disaster in the day, and "1" may be used to indicate that there is a storm disaster in the day. For example, the output of the model is 011100, and the predicted rainstorm disaster condition of the power transmission line to be predicted is that rainstorm disasters exist from the second day to the 4 th day of prediction.
In this embodiment, through obtaining the disaster causing factor data of the power transmission line to be predicted, the disaster causing factor data of the disaster causing factor of the storm includes: the method comprises the steps of obtaining weather characteristic element data, power transmission line structure data, geological characteristic element data and historical rainstorm data, comprehensively predicting the rainstorm disaster condition of the power transmission line to be predicted according to external factors, internal factors and historical rainstorm data influencing the power transmission line to be predicted, inputting the rainstorm disaster causing factor data of the power transmission line to be predicted into a rainstorm disaster prediction model to obtain the predicted rainstorm disaster condition of the power transmission line to be predicted, training a limited Boltzmann machine model by adopting the rainstorm disaster causing factor data, and fully learning the influence of the rainstorm disaster causing factor data on the prediction of the rainstorm disaster by the obtained rainstorm disaster prediction model, so that the prediction accuracy is high. Therefore, measures for preventing the rainstorm disasters can be implemented in advance, the influence of the rainstorm disasters suffered by the power transmission line to be predicted is reduced, and the capability of the power transmission line for coping with the rainstorm disasters and the safe and stable operation level are improved.
Fig. 2 is a schematic flowchart of another method for predicting that a power transmission line is subjected to a storm disaster according to an embodiment of the present disclosure, where fig. 2 is based on the embodiment shown in fig. 1, and further, as shown in fig. 2, before S102, further includes:
s1021, acquiring the disaster causing factor data of the rainstorm disasters of the multiple groups of power transmission lines to form a plurality of training samples, wherein each training sample comprises the disaster causing factor data of one power transmission line in the multiple power transmission lines at the same moment.
Training the storm disaster prediction model using a plurality of training samples until the storm disaster prediction model converges.
Optionally, the convergence condition of the rainstorm disaster prediction model is as follows: the proportion threshold is smaller than a preset threshold, wherein the proportion threshold is the proportion of the difference value of the reset values of the training samples and the training samples in the training samples, and the reset values of the training samples are obtained by performing forward calculation on the training samples and then performing reverse calculation on the output obtained by performing forward calculation on the training samples.
The preset threshold is preset, for example, the preset threshold may be 3%.
In the embodiment, a plurality of training samples are formed by acquiring the disaster causing factor data of the plurality of groups of power transmission lines, and the plurality of training samples are used for training the disaster predicting model until the disaster predicting model converges, so that the disaster predicting model for fully learning the disaster causing factor data of the disaster causing storm is obtained.
The process of training the model may specifically include the following processes:
fig. 3 is a schematic flowchart of a method for training a rainstorm disaster prediction model according to an embodiment of the present disclosure, and as shown in fig. 3, the method according to the embodiment includes:
and constructing a rainstorm disaster prediction model based on the restricted Boltzmann machine model, and training the rainstorm disaster prediction model by using the training samples to obtain a converged rainstorm disaster prediction model.
S301, acquiring the disaster causing factor data of the rainstorm disasters of the power transmission lines, wherein the disaster causing factor data of the rainstorm disasters of each power transmission line at the same moment form a training sample, and a plurality of training samples are obtained.
For example, 42 groups of power transmission line rainstorm disaster causing factor data in 7 years in history are used for training and verifying the model, wherein the first 38 groups of data are used as a training sample set, and the last 4 groups of data are used as a verification sample set, wherein the verification sample set is used for verifying the accuracy of the trained rainstorm disaster prediction model. Optionally, the training sample set may be represented as: a { (X)1,y1,z1),(X2,y2,z2),...,(X36,y36,z36) In which X isiIs the characteristic factor vector, y, of the ith power transmission line rainstorm disaster sampleiThe mark of occurrence of rainstorm disasters of the ith sample is { -1,1}, wherein-1 indicates that the power transmission line has no rainstorm accidents, 1 indicates that the power transmission line has rainstorm accidents, and z indicates that the power transmission line has rainstorm accidentsiThe duration of the accident (in days) of the ith transmission line storm disaster is {0,1,2, 3.
S302, establishing a rainstorm disaster prediction model based on the limited Boltzmann machine, and initializing parameters of the limited Boltzmann machine.
The display layer is provided with M neurons, and v ═ v can be used for the display layeriI ═ 1., M }, where vi is the variable value of the ith neuron in the display layer, N neurons are set in the hidden layer, and the hidden layer may be represented by h ═ { h ═ h ·j1., N } where h isjTo hide the value of the j-th neuron variable, the two layers may be weighted with respect to each other by ω ═ ω { (ω {)ij1, ·, M; 1.., N } denotes ωijIs the ith neuron of the hidden layer and the jth neuron of the display layerConnection weight of aiTo show the bias of the ith neuron of the layer, biTo show the bias of the ith neuron in the layer, M, N may be preset, for example, where M is 30 and N is 30.
The parameters that may be desired for model training are noted as θ ═ ai,bj,ωij}. And taking an initial value for theta, wherein the initial value is an arbitrary value.
And S303, respectively inputting the training samples into the rainstorm disaster prediction model to obtain training sample output, and judging whether the training result of the current rainstorm disaster prediction model meets an iteration condition.
And (4) using the convergence condition in the training set as an iteration condition, if the iteration condition is not met, continuing to execute the step (S304), and if the iteration condition is met, continuing to execute the step (S306).
S304, inputting the training samples into a rainstorm disaster prediction model respectively for training, and calculating the conditional probability of the display layer and the hidden layer respectively.
Aiming at each training sample, wherein disaster-causing factor data of each category in contained disaster-causing factor data of the rainstorm disasters is vi in a forecasting model of the rainstorm disasters, for example, precipitation is v1, wind speed is v2, relative humidity is v3 and the like, the condition probabilities of a display layer and a hidden layer are respectively calculated, namely the activation probability of jth neuron of the hidden layer h can be calculated through the display layer v, and then the activation probability of ith neuron of the display layer v is reversely calculated according to the hidden layer h. And updating theta, and performing iterative training until an iterative condition is met.
The hidden layer h obtained by forward calculation of the display layer v, the reset value of the display layer is calculated reversely for the hidden layer h,
optionally, the activation probability p (h) of the jth neuron of the hidden layer hj1| v) can be obtained by the following formula (2):
display the activation probability p (v) of the ith neuron of layer vi1| h) can be expressed by the following formula (3)) Obtaining:
where f (x) is an excitation function, optionally, f (x) may be f (x) 1/(1+ e)-x)，aiTo show the bias of the ith neuron of the layer, bjBias for the jth neuron of the hidden layer, ωijThe connection weight value of the ith neuron of the hidden layer and the jth neuron of the display layer is obtained.
And S305, updating parameters of the rainstorm disaster prediction model.
Wherein, the parameters of the rainstorm disaster prediction model comprise: and the display layer bias, the hidden layer bias and the weight between the display layer and the hidden layer enable the rainstorm disaster prediction model to meet the iteration condition.
The parameters of the updated rainstorm disaster prediction model are all parameters of the updated rainstorm disaster prediction model, and one or more parameters of the parameters can also be updated, and the disclosure is not limited to the parameters updated each time.
Optionally, the biasing of the display layer comprises: the bias of each neuron of the layer is shown. The hidden layer biasing includes: hiding the bias of each neuron of the layer. The weight between the display layer and the hidden layer comprises the weight between each neuron of the display layer and each neuron of the hidden layer.
And S306, obtaining an initialization parameter of the rainstorm disaster prediction model according to the maximum log likelihood function.
The initialization parameters of the rainstorm disaster prediction model comprise an initial value of the display layer bias, an initial value of the hidden layer bias and an initial value of the weight between the two layers.
Through the training iteration process, the initialization parameter of the rainstorm disaster prediction model, namely the display layer bias a is obtainediHidden layer bias bjAnd the weight ω of two layers to each otherij(ωijThe connection weight between the ith neuron of the hidden layer and the jth neuron of the display layer), the initialization parameter of the rainstorm disaster prediction model may be recorded as θ ═ ai,bj,ωij}。
Optionally, the initialization parameter θ of the rainstorm disaster prediction model may be obtained by the following formula (4):
wherein T is the number of training samples in the training sample set, vtFor the t-th training sample, L (θ) is a log-likelihood function on the training sample set, and optionally, the log-likelihood function can be obtained by the following formula (5):
wherein, E (v, h) can be obtained from formula (1), and T is the number of training samples in the training sample set.
And S307, obtaining the average precision of the training errors according to the output predicted value and the actual value of the training sample.
And obtaining the average precision of the training errors aiming at the actual value and the predicted value of the rainstorm disaster risk of the power transmission line in the training sample.
Optionally, training error average precision EavgCan be obtained by the following equation (6):
wherein, XiThe actual value of the rainstorm disaster of the power transmission line in the ith training sample is obtained; y isiAnd D, predicting the rainstorm disaster prediction value of the power transmission line in the ith training sample, wherein T is the number of the training samples in the training sample set.
E.g. average accuracy of training errors Eavg≤0.1。
And S308, judging whether the current rainstorm disaster prediction model meets an iteration condition.
And judging whether the iteration condition is met or not by using the convergence in the training set as the iteration condition again, if the iteration condition is not met, continuing to execute S309, and if the iteration condition is met, continuing to execute S311.
S309, establishing a reverse-propagation rainstorm disaster prediction model.
The rainstorm disaster forecasting model of the back propagation is to input data from the hidden layer and output data from the display layer. Assume the K high-level abstract feature elements extracted in S306 as the input parameter set { x1,x2,...,xKEstablishing a rainstorm disaster prediction model based on a back propagation algorithm, wherein x is1,x2,...,xKIs the input of the neuron at the hidden layer in the model, λiIs the threshold, ω, of the ith neuron of the display layer1i,ω2i,...,ωkiThe ith neuron and x of the display layer respectively1,x2,...,xKWeight of connection, yiF is the output of the ith neuron, where f is the transfer function, which determines that the ith neuron is subject to input x1,x2,...,xKThe combined action of (a) and (b) is output as a non-linear output when the threshold is reached, which can be expressed by the following equation (7):
wherein λ isiIs the threshold, ω, of the ith neuron of the display layerjiIs the connection weight value, x, of the jth neuron of the hidden layer and the ith neuron of the display layerjT is the input of the jth neuron of the hidden layer, and T is the number of training samples in the training sample set.
And S310, adjusting parameters in the rainstorm disaster prediction model according to a back propagation algorithm.
Here, the connection weight includes the weight of the input and hidden neuron and the weight of the hidden neuron and the output.
S311, calculating a prediction result of the counter-propagating rainstorm disaster prediction model according to an output formula of each neuron.
Therefore, training of the rainstorm disaster prediction model based on the deep learning model is completed, and the converged rainstorm disaster prediction model is obtained.
Alternatively, the prediction result of the forecasting model of the back-propagation storm disaster can be obtained by the following formula (8):
wherein, yiOutput of the ith neuron which is the display layer of the storm disaster prediction model, xjIs the input of the jth neuron of the hidden layer of the rainstorm disaster prediction model, T is the number of training samples in the training sample set, and lambdaiIs the threshold, ω, of the ith neuron of the display layerjiIs the connection weight of the jth neuron of the hidden layer and the ith neuron of the display layer, K is the number of neurons of the display layer, psijiCoefficients between the jth neuron of the display layer and the ith neuron of the hidden layer are obtained through model learning in a training process.
For example, the output of the storm disaster prediction model is { y }i,zi}(1≤i≤36)。
It is understood that the training method of the present embodiment may be executed independently, or may be executed together with the steps of the embodiments shown in fig. 1 or fig. 2. The steps of the training method, if performed together with the steps of the embodiment shown in fig. 1 or fig. 2, precede S102.
In the embodiment, the plurality of historical storm disaster causing factor data are used, forward unsupervised training is carried out on the storm disaster prediction model based on the limited Boltzmann model, and reverse supervised training is carried out on the actual storm disaster situation corresponding to the plurality of historical storm disaster causing factor data, so that the converged storm disaster prediction model is obtained, and the accuracy rate of the storm disaster prediction model for predicting the storm disaster situation is high.
Fig. 4 is a schematic structural diagram of an apparatus for predicting that a power transmission line is subjected to a storm disaster according to an embodiment of the present disclosure, and as shown in fig. 4, the apparatus according to the embodiment includes:
the obtaining module 401 is configured to obtain disaster causing factor data of the power transmission line to be predicted, where the disaster causing factor data of the power transmission line includes: meteorological characteristic element data, power transmission line structure data, geological characteristic element data and historical rainstorm data;
the obtaining module 402 is configured to input the disaster causing factor data of the power transmission line to be predicted into a storm disaster prediction model to obtain a predicted storm disaster situation of the power transmission line to be predicted, where the storm disaster risk prediction model is a limited boltzmann model obtained by training the disaster causing factor data of multiple power transmission lines.
Optionally, the meteorological feature element data includes one or more of the following: precipitation, wind speed, relative humidity and temperature;
the transmission line structure data includes: basic characteristic data of each base tower of the power transmission line;
the geological feature element data comprises one or more of: the method comprises the following steps of topographic and geomorphic data, basic characteristic data of each base tower, soil compactness, stratum lithology data, broken stone content in soil, slope characteristic data and debris flow disaster-causing factor data.
Optionally, the topographic data includes: freezing zone topographic data or tuyere region topographic data;
the debris flow disaster-causing factor data comprises one or more of the following data: mud level, mud velocity, infrasound and ground sounds;
the basic characteristic data of each base tower of the power transmission line comprises one or more of the following data: independent foundation, pile foundation and digging foundation of each base tower of the power transmission line.
Optionally, the predicting rainstorm disaster condition of the power transmission line to be predicted includes: whether a rainstorm disaster exists every day in a preset time period.
Optionally, the apparatus further comprises:
the obtaining module 401 is further configured to obtain disaster causing factor data of the rainstorm disasters of the multiple power transmission lines to obtain a training sample set, where the training sample set includes multiple training samples, and each training sample includes disaster causing factor data of one power transmission line of the multiple power transmission lines at the same time;
and the training module is used for training the rainstorm disaster prediction model by using the training sample set until the rainstorm disaster prediction model converges.
Optionally, the convergence condition of the rainstorm disaster prediction model is as follows: the proportion threshold is smaller than a preset threshold, wherein the proportion threshold is the proportion of the difference value of the reset values of the training samples and the training samples in the training samples, and the reset values of the training samples are obtained by performing forward calculation on the training samples and then performing reverse calculation on the output obtained by performing forward calculation on the training samples.
The apparatus of the foregoing embodiment may be configured to implement the technical solution of the foregoing method embodiment, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 5 is a schematic structural diagram of an apparatus for predicting that a power transmission line is subjected to a storm disaster according to an embodiment of the present disclosure, and as shown in fig. 5, the apparatus according to the embodiment includes:
a memory 501 for storing instructions executable by the processor 502;
a processor 502 for implementing the method as described in any of fig. 1-3 above when the computer program is executed.
The apparatus of the foregoing embodiment may be configured to implement the technical solution of the foregoing method embodiment, and the implementation principle and the technical effect are similar, which are not described herein again.
The present disclosure provides a computer-readable storage medium having stored thereon computer-executable instructions for implementing a method for predicting that a power transmission line is exposed to a storm disaster as shown in any one of fig. 1-3 above, when the computer-executable instructions are executed by a processor.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for predicting that a power transmission line is subjected to a rainstorm disaster is characterized by comprising the following steps:
acquiring the disaster causing factor data of the power transmission line to be predicted, wherein the disaster causing factor data of the power transmission line comprises the following steps: meteorological characteristic element data, power transmission line structure data, geological characteristic element data and historical rainstorm data;
and inputting the data of the disaster causing factors of the rainstorm disasters of the power transmission lines to be predicted into a rainstorm disaster prediction model to obtain the predicted rainstorm disaster conditions of the power transmission lines to be predicted, wherein the rainstorm disaster risk prediction model is a restricted Boltzmann model obtained by training the data of the disaster causing factors of the rainstorm disasters of a plurality of groups of power transmission lines.
2. The method of claim 1, wherein the meteorological feature data comprises one or more of: precipitation, wind speed, relative humidity and temperature;
the power transmission line structure data includes: basic characteristic data of each base tower of the power transmission line;
the geological feature element data comprises one or more of: the method comprises the following steps of topographic and geomorphic data, basic characteristic data of each base tower, soil compactness, stratum lithology data, broken stone content in soil, slope characteristic data and debris flow disaster-causing factor data.
3. The method of claim 2, wherein the topographical data comprises: freezing zone topographic data or tuyere region topographic data;
the debris flow disaster-causing factor data comprises one or more of the following data: mud level, mud velocity, infrasound and ground sounds;
the basic characteristic data of each base tower of the power transmission line comprises one or more of the following data: and the independent foundation, the pile foundation and the digging foundation of each base tower of the power transmission line.
4. The method of claim 1, wherein the predicting a rainstorm disaster condition of the power transmission line to be predicted comprises: whether a rainstorm disaster exists every day in a preset time period.
5. The method according to any one of claims 1 to 4, wherein before inputting the data of the disaster causing factors of the power transmission line into the disaster predicting model to obtain the predicted disaster condition of the power transmission line, the method further comprises:
acquiring rainstorm disaster causing factor data of a plurality of power transmission lines to obtain a training sample set, wherein the training sample set comprises a plurality of training samples, and each training sample comprises the rainstorm disaster causing factor data of one power transmission line in the plurality of power transmission lines at the same moment;
training the storm disaster prediction model using the training sample set until the storm disaster prediction model converges.
6. The method of claim 5, wherein the convergence condition of the storm disaster prediction model is: and the proportion threshold is smaller than a preset threshold, wherein the proportion threshold is the proportion of the difference value between the reset values of the training samples and the training samples in the training samples, and the reset value of the training samples is obtained by performing forward calculation on the training samples and then performing reverse calculation on the output obtained by performing forward calculation on the training samples.
7. An apparatus for predicting that a power transmission line is subjected to a storm disaster, comprising:
the acquiring module is used for acquiring the disaster causing factor data of the power transmission line to be predicted, wherein the disaster causing factor data of the power transmission line comprises the following steps: meteorological characteristic element data, power transmission line structure data, geological characteristic element data and historical rainstorm data;
and the obtaining module is used for inputting the disaster causing factor data of the power transmission line to be predicted into a disaster causing factor prediction model to obtain the predicted disaster causing condition of the power transmission line to be predicted, wherein the disaster causing factor prediction model is a restricted boltzmann model obtained by training the disaster causing factor data of a plurality of groups of power transmission lines.
8. The apparatus of claim 7, further comprising:
the acquisition module is further used for acquiring the disaster causing factor data of the rainstorm disasters of the plurality of power transmission lines to obtain a training sample set, wherein the training sample set comprises a plurality of training samples, and each training sample comprises the disaster causing factor data of one power transmission line in the plurality of power transmission lines at the same moment;
and the training module is used for training the rainstorm disaster prediction model by using the training sample set until the rainstorm disaster prediction model converges.
9. An apparatus for predicting that a power transmission line is subjected to a storm disaster, comprising:
a memory for storing processor-executable instructions;
a processor for implementing the method of any one of claims 1 to 6 when the computer program is executed.
10. A computer-readable storage medium having stored thereon computer-executable instructions for implementing a method of predicting the exposure of a power transmission line to a storm disaster according to any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011244454.5A CN112257956A (en) | 2020-11-10 | 2020-11-10 | Method, device and equipment for predicting power transmission line suffering from rainstorm disaster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011244454.5A CN112257956A (en) | 2020-11-10 | 2020-11-10 | Method, device and equipment for predicting power transmission line suffering from rainstorm disaster |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112257956A true CN112257956A (en) | 2021-01-22 |
Family
ID=74266758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011244454.5A Pending CN112257956A (en) | 2020-11-10 | 2020-11-10 | Method, device and equipment for predicting power transmission line suffering from rainstorm disaster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112257956A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113256019A (en) * | 2021-06-15 | 2021-08-13 | 浙江中海达空间信息技术有限公司 | Geological disaster hidden danger sensitivity prediction method based on unsupervised characterization learning |
| CN113284000A (en) * | 2021-04-08 | 2021-08-20 | 南方电网数字电网研究院有限公司 | User electricity data anomaly detection method and device and computer equipment |
| CN113344297A (en) * | 2021-06-30 | 2021-09-03 | 广东电网有限责任公司 | Debris flow disaster prediction method, system, terminal and storage medium |
| CN113570133A (en) * | 2021-07-26 | 2021-10-29 | 广西电网有限责任公司电力科学研究院 | Power transmission and distribution line risk prediction method and system for dealing with heavy rainfall |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004046707A (en) * | 2002-07-15 | 2004-02-12 | Ishikawajima Harima Heavy Ind Co Ltd | Database for rbm, rbm support device, and method for executing rbm |
| CN102867110A (en) * | 2012-08-22 | 2013-01-09 | 广东电网公司电力科学研究院 | Rainstorm disaster risk evaluation method for foundation slope of transmission line tower |
| CN107169645A (en) * | 2017-05-09 | 2017-09-15 | 云南电力调度控制中心 | A kind of transmission line malfunction probability online evaluation method of meter and Rainfall Disaster influence |
| CN108898247A (en) * | 2018-06-22 | 2018-11-27 | 国网湖南省电力有限公司 | A kind of power grid Rainfall Disaster Risk Forecast Method, system and storage medium |
| CN110175386A (en) * | 2019-05-21 | 2019-08-27 | 陕西科技大学 | Substation Electric Equipment temperature predicting method |
-
2020
- 2020-11-10 CN CN202011244454.5A patent/CN112257956A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004046707A (en) * | 2002-07-15 | 2004-02-12 | Ishikawajima Harima Heavy Ind Co Ltd | Database for rbm, rbm support device, and method for executing rbm |
| CN102867110A (en) * | 2012-08-22 | 2013-01-09 | 广东电网公司电力科学研究院 | Rainstorm disaster risk evaluation method for foundation slope of transmission line tower |
| CN107169645A (en) * | 2017-05-09 | 2017-09-15 | 云南电力调度控制中心 | A kind of transmission line malfunction probability online evaluation method of meter and Rainfall Disaster influence |
| CN108898247A (en) * | 2018-06-22 | 2018-11-27 | 国网湖南省电力有限公司 | A kind of power grid Rainfall Disaster Risk Forecast Method, system and storage medium |
| CN110175386A (en) * | 2019-05-21 | 2019-08-27 | 陕西科技大学 | Substation Electric Equipment temperature predicting method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113284000A (en) * | 2021-04-08 | 2021-08-20 | 南方电网数字电网研究院有限公司 | User electricity data anomaly detection method and device and computer equipment |
| CN113256019A (en) * | 2021-06-15 | 2021-08-13 | 浙江中海达空间信息技术有限公司 | Geological disaster hidden danger sensitivity prediction method based on unsupervised characterization learning |
| CN113344297A (en) * | 2021-06-30 | 2021-09-03 | 广东电网有限责任公司 | Debris flow disaster prediction method, system, terminal and storage medium |
| CN113570133A (en) * | 2021-07-26 | 2021-10-29 | 广西电网有限责任公司电力科学研究院 | Power transmission and distribution line risk prediction method and system for dealing with heavy rainfall |
| CN113570133B (en) * | 2021-07-26 | 2024-05-24 | 广西电网有限责任公司电力科学研究院 | Power transmission and distribution line risk prediction method and system for coping with heavy rainfall |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112257956A (en) | Method, device and equipment for predicting power transmission line suffering from rainstorm disaster | |
| US11442420B2 (en) | Power grid reactive voltage control method based on two-stage deep reinforcement learning | |
| Rezaie-Balf et al. | New formulation for forecasting streamflow: evolutionary polynomial regression vs. extreme learning machine | |
| JP5888640B2 (en) | Photovoltaic power generation prediction apparatus, solar power generation prediction method, and solar power generation prediction program | |
| Kayadelen | Soil liquefaction modeling by genetic expression programming and neuro-fuzzy | |
| US20230252266A1 (en) | Method for predicting and controlling awater level of a series water conveyance canal on a basis of a fuzzy neural network | |
| Lu et al. | Short-term wind power forecasting based on meteorological feature extraction and optimization strategy | |
| Guo et al. | An ensemble solar power output forecasting model through statistical learning of historical weather dataset | |
| CN104616060A (en) | Method for predicating contamination severity of insulator based on BP neural network and fuzzy logic | |
| CN105184416A (en) | Fluctuation wind speed prediction method based on particle swarm optimization back propagation neural network | |
| Tongle et al. | Tailings saturation line prediction based on genetic algorithm and BP neural network | |
| Qiu et al. | Seepage monitoring models study of earth-rock dams influenced by rainstorms | |
| Nourani et al. | A new hybrid algorithm for rainfall–runoff process modeling based on the wavelet transform and genetic fuzzy system | |
| Li et al. | A method of rainfall runoff forecasting based on deep convolution neural networks | |
| Wei et al. | Two-stage pumping control model for flood mitigation in inundated urban drainage basins | |
| Abedinia et al. | Execution of synthetic Bayesian model average for solar energy forecasting | |
| CN116205513A (en) | Ship lock engineering monitoring method and system based on ISSA (integrated service and architecture) optimized BP (back propagation) network | |
| CN117039894B (en) | Photovoltaic power short-term prediction method and system based on improved dung beetle optimization algorithm | |
| Rohaimi et al. | 3 Hours ahead of time flood water level prediction using NNARX structure: Case study pahang | |
| CN116245222A (en) | Power grid icing prediction method, device, equipment and storage medium | |
| Rizianiza et al. | Prediction of significant wave height in the java sea using artificial neural network | |
| Wu et al. | Short-Term Electric Load Forecasting Model based on PSO-BP | |
| Herath et al. | Forecasting Electricity Power Generation of Pawan Danavi Wind Farm, Sri Lanka, Using Gene Expression Programming | |
| Sinha et al. | Rainfall Runoff modeling of Punpun River Basin using ANN—A Case Study | |
| Rathnayake | Review of binary tournament constraint handling technique in NSGA II for optimal control of combined sewer systems |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210122 |