CN112116160A - Important power transmission channel disaster monitoring method based on optimized neural network improved cellular automaton - Google Patents
Important power transmission channel disaster monitoring method based on optimized neural network improved cellular automaton Download PDFInfo
- Publication number
- CN112116160A CN112116160A CN202011021322.6A CN202011021322A CN112116160A CN 112116160 A CN112116160 A CN 112116160A CN 202011021322 A CN202011021322 A CN 202011021322A CN 112116160 A CN112116160 A CN 112116160A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- disaster
- neural network
- cellular
- cell
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 92
- 230000001413 cellular effect Effects 0.000 title claims abstract description 72
- 230000005540 biological transmission Effects 0.000 title claims abstract description 60
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011156 evaluation Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000003062 neural network model Methods 0.000 claims abstract description 7
- 238000007689 inspection Methods 0.000 claims abstract description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 33
- 239000002689 soil Substances 0.000 claims description 24
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 239000013598 vector Substances 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 230000010307 cell transformation Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 5
- 238000007418 data mining Methods 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 1
- 230000007547 defect Effects 0.000 description 4
- 238000012502 risk assessment Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000032823 cell division Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000034994 death Effects 0.000 description 1
- 231100000517 death Toxicity 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012806 monitoring device Methods 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
- 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
-
- 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)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an important power transmission channel disaster monitoring method based on an optimized neural network improved cellular automaton, belonging to the field of important power transmission channel disaster monitoring and comprising the following steps: s1, data acquisition is carried out through monitoring resources, meteorological departments and power grid meteorological sites; s2, storing and preprocessing the data in the step S1; s3, determining the state of the cells based on an analytic hierarchy process; s4, obtaining an RBF neural network data center by adopting cosine similarity, optimizing the weight from a hidden layer to an output layer by adopting an IWD algorithm, improving the network accuracy, and training and learning by adopting an RBF neural network model; and S5, performing prediction evaluation on the current monitoring data according to the rule to obtain a cellular state, namely a disaster prediction evaluation grade, forming a current overall disaster state grade distribution map of the monitoring area, and performing targeted routing inspection on the lines passing through the disaster grade abnormity and serious areas by combining the trend and the topological structure of the important power transmission channel to eliminate disaster hidden dangers.
Description
Technical Field
The invention relates to the field of monitoring of important transmission channel disasters, in particular to a method for monitoring important transmission channel disasters based on an optimized neural network improved cellular automaton.
Background
With the rapid development of electric power construction and the continuous expansion of the scale of a power grid, the importance of an important power transmission channel mainly comprising 750kV in the power grid is embodied more and more intensively, and the important power transmission channel is an important energy artery in the modern society. Therefore, when a large-scale power grid accident occurs, not only can huge economic loss be caused, but also great political and social influences and even personal injuries and deaths can be caused. Although the harmfulness of the important transmission line defect is less than the harmfulness degree of the fault, the occurrence frequency is much higher than that of the line fault, moreover, the defect can be changed from quantitative to qualitative into serious, and the factors causing the grid fault of the important transmission channel not only include the factors caused by equipment faults, manual operation, but also can be caused by extreme natural disasters. Therefore, in order to ensure the normal operation of the important power transmission line under the condition of complex terrain, the monitoring work of the line body, the surrounding environment and meteorological parameters must be strengthened, so that the defects are prevented in advance.
At present, a power grid meteorological station, a power transmission monitoring device, a meteorological department station and other disaster monitoring and forecasting platforms are established for important power transmission channels of a power grid, but the number of lines is large, monitoring equipment and data types are diversified, the prior art and means lack effective integration and utilization of existing monitoring data, the risk state of the important channel lines cannot be timely and effectively mastered, and the supporting force for operation and maintenance work is limited. Meanwhile, due to the fact that certain barriers exist in communication of monitoring modes in different regions, monitoring blind areas exist on the basis of existing monitoring equipment, and phenomena of collapse, line breakage and tripping of transmission lines of important channels occur occasionally.
The cellular automata has good advantages in the aspects of simulating complex space-time phenomena, behaviors and processes, and therefore, the cellular automata is widely applied to the field of disaster monitoring. The neural network has important advantages in the aspect of mining the nonlinear relation between data, so that the neural network can be combined with a cellular automaton model to establish a full-working-condition and all-around disaster monitoring method for the power transmission line for important power transmission channels, and the centralized monitoring and risk assessment are performed on the important power transmission channels, particularly on environmental parameters and operating states of disaster-prone areas, so that the safety early warning and disaster prediction of important power transmission lines of a regional power grid are realized, and the multi-parameter data fusion and intelligent analysis of the power transmission line are realized.
Disclosure of Invention
1. Technical problem to be solved
Aiming at the problems in the prior art, the invention aims to provide an important power transmission channel disaster monitoring method based on an optimized neural network improved cellular automata, which aims at the defects of the existing important power transmission channel disaster monitoring and provides the important power transmission channel disaster monitoring method based on the optimized neural network improved cellular automata, data acquisition and preprocessing are carried out through a monitoring terminal, a power grid meteorological station and a meteorological station, then grid division with the same size is carried out on disaster monitoring areas, each grid is taken as an independent cell, and then the state of the cell is determined by carrying out an analytic hierarchy process on the single cell according to the existing power transmission line monitoring historical information; determining the basis of the RBF neural network by combining cosine similarity and a mean value clustering algorithm; an improved intelligent water drop algorithm (IWD) is used for optimizing weight between a hidden layer and an output layer of a neural network, a cell conversion rule is obtained through training, disaster grade evaluation and prediction are carried out on the existing important power transmission channel according to the cell conversion rule, and operation and maintenance personnel can adopt a targeted strategy for a bearing body in a fragile area by combining a power transmission channel topological structure and a disaster evaluation result, so that real-time disaster monitoring and early warning evaluation of the important channel are realized, and the safety of the important power transmission channel is guaranteed.
2. Technical scheme
In order to solve the problems, the invention adopts the following technical scheme:
an important power transmission channel disaster monitoring method based on an optimized neural network improved cellular automaton comprises the following steps:
s1, data acquisition is carried out through monitoring resources, meteorological departments and power grid meteorological sites;
s2, storing and preprocessing the data in the step S1;
s3, determining the state of the cells based on an analytic hierarchy process;
s4, obtaining an RBF neural network data center by adopting cosine similarity, optimizing the weight from a hidden layer to an output layer by adopting an IWD algorithm, improving the network accuracy, training and learning by adopting an RBF neural network model, and obtaining the next-time state conversion rule of the current cellular through the state of the neighbor cellular;
and S5, performing prediction evaluation on the current monitoring data according to the rule to obtain a cellular state, namely a disaster prediction evaluation grade, forming a current overall disaster state grade distribution map of the monitoring area, and performing targeted routing inspection on the lines passing through the disaster grade abnormity and serious areas by combining the trend and the topological structure of the important power transmission channel to eliminate disaster hidden dangers.
As a preferred embodiment of the present invention, in step S3, a geographic information system is combined to perform cell division on a monitoring area, and a single cell in the monitoring area is analyzed hierarchically according to historical data and expert experience with a size of 3km × 3km as one cell, so as to determine a cell state.
As a preferable aspect of the present invention, the step S3 includes the steps of:
s301, preprocessing and normalizing data;
s302, forming a hierarchical structure diagram;
s303, acquiring a judgment matrix according to expert experience;
s304, checking consistency;
and S305, calculating a score according to the weight matrix.
As a preferred scheme of the present invention, in step S301, the important power transmission channels are divided into grids based on the geographic information system, each grid is used as a cell, data acquisition is performed according to the online monitoring terminal, the grid meteorological site and the meteorological department site arranged in the range of the cell, and the data is normalized by using the following formula:
wherein xiAnd a and b are threshold values of the evaluation indexes of the monitoring amount for the actual monitoring amount of certain monitoring data, the larger the normalized data is, the more serious the deviation of the monitoring amount from the normal state is represented, and the threshold value of each index is set according to the reference rule and the guide rule of related experts.
As a preferred solution of the present invention, in step S302, a hierarchical analysis model is constructed, which includes a target layer M, a criterion layer C, and a solution layer P, wherein: the target layer M is a disaster risk score; considering factors influencing the disaster model of the area, dividing the criterion layer C into 3 parts of climate factors, terrain factors and tower factors; the solution layer P is a specific influencing factor to be considered.
As a preferred embodiment of the present invention, in step S305, the results are evaluated by a hierarchic analysis method according to a hierarchic analysis model, and the finally obtained disaster risk scores are classified into three grades, i.e., "normal", "abnormal", and "serious", respectively, according to historical experience.
As a preferable aspect of the present invention, in step S4, a cellular automaton model is constructed; the cellular automata model can be described by the following formula:
a ═ C, S, N, R formula (2)
In the formula, C is a cellular space, i.e., the whole cells in the disaster monitoring area; s is a cellular state set, and according to the result of the analytic hierarchy process, the cellular states are divided into three types, namely 'normal' is '0', 'abnormal' is '1', and 'severe' is '2', so that the cellular state set S is {0,1,2 }; r represents the trellis of cellular automata, Sk(r, t) represents the kth state of the unit cell at the site r at the time t; n represents the neighborhood of a cellular centered on r, and a Moore type cellular neighborhood model is adopted, namely 8 neighbors are contained around each cellular, and N is { N ═ N }1,N2,…,Nq}，NqRepresents the location of the qth neighbor of cell r relative to r; r is the transformation rule of the cell, i.e., S (R, t) → S (R, t +1) R ═ R1,R2,…Rm)，RmThe m-th conversion rule is only related to the states of 8 neighbor cells around the cell at the time t, and due to the complexity and uncertainty of disasters, a specific cell transfer function rule cannot be found, so that data mining is performed through historical data, and an optimized RBF neural network model is adopted to obtain the cell conversion rule.
As a preferable aspect of the present invention, the step S4 includes the steps of:
s401: randomly and uniformly selecting k data in the cell historical data as sample centers;
s402: calculating the cosine similarity between each sample and the kth center according to the formula
Where j represents an element in vectors i and k;
s403: calculating the average value rho of cosine similarity of all samples of the kth central point; is given by the formula
S404: judging whether cos (i, k) of the ith sample and the kth center is less than rhok；
S405: if the sample number S404 is positive, the ith sample belongs to the kth class, and the traversal is continued;
s406: if not, increasing the ith vector as the (k +1) th sample center, and continuing to traverse until the whole data set.
As a preferred scheme of the invention, the method also comprises the step of optimizing the weight from the hidden layer to the output layer of the RBF neural network by adopting an intelligent water drop algorithm, and comprises the following steps:
s407: obtaining a central vector and the number of hidden layers according to the S406 result, setting RBF network parameters, and generating l k-dimensional random number vectors as initial weights based on levy distribution;
s408: initializing IWD algorithm parameters;
s409: each water drop will flow to a path with a smaller amount of soil with a greater probability, and assuming that the water drop is at node a, the probability of flowing to the next node b is:
wherein f (soil (a, b)) is the amount of soil between nodes a and b; to solve the possible local convergence situation, a linear decreasing function, k, is introducediterFor the current number of iterations, TmaxIn the initial stage of iteration, searching globally with a high probability, and in the later stage of iteration, searching locally with a low probability; p _ is a roulette selection mode;
s4010: the water drop speed, the amount of soil in the water drop and the amount of soil in the path are updated.
Wherein, the water drop speed updating formula is as follows:
wherein vel is the node speed of the water drops;
the updated formula of the soil amount in the water drop is as follows:
the soil amount in the path is updated according to the formula:
wherein alpha isnSp, sq, sr, vp, vq, vr are all static parameters, and are set during initialization
S4011: continuously traversing all the nodes;
s4012: selecting a path according to all the water drops obtained currently to calculate network output, calculating an error E according to an error function, selecting a path with the minimum error to be reserved as the optimal path at this time, and updating the soil amount in the path according to whether the water drops of the optimal path pass through, wherein the updating formula is as follows:
wherein, lambda is a static parameter, mu is the optimal number of water drops
S4013: judging whether the iteration times are reached;
s4014: and outputting the optimal path, namely the weight of the neural network, completing network training to obtain a cell conversion rule, and performing risk evaluation prediction.
As a preferred embodiment of the present invention, in step S5, a cell transformation rule is obtained by using an optimized RBF neural network, and the next state of the r-th cell is predicted by using a trained RBF network model, so that the next state is expanded to the entire cell space, thereby obtaining a power transmission channel disaster risk level prediction distribution map.
3. Advantageous effects
Compared with the prior art, the invention has the advantages that:
(1) the method has the first innovation point that the monitoring area is subjected to grid division, disaster monitoring is carried out by point-to-surface expansion, an analytic hierarchy process is applied to combine meteorological factors, topographic factors and tower self factors of an important power transmission channel to carry out comprehensive evaluation and analysis on the current disaster monitoring area, an evaluation result is directly converted into a cellular state, no application case for directly determining the cellular state by applying hierarchical analysis in the aspect of power transmission channel disaster monitoring exists at present, and the method is simple, feasible and fully considers the important factors influencing the line state of the area.
(2) At present, in the aspect of monitoring important power transmission channel disasters, no case of combining a neural network with a cellular automaton exists. The invention is different from the combination method of the neural network and the cellular automata in other fields, and the invention determines the center of the RBF network by using cosine similarity and mean value clustering algorithm aiming at the calculation process of the RBF neural network, so that the difference between individuals can be better distinguished compared with Euclidean distance; in addition, Levy flight and linear descending weight are introduced into the IED algorithm, the probability of convergence to local optimum is effectively reduced, the optimized weight is found by optimizing the weight of the RBF neural network through the improved IWD algorithm, and the training efficiency of the network is improved.
(3) The cell state conversion rule is also a classification problem essentially, and because the classification capability of the RBF neural network is obviously superior to that of other networks and the training speed is high, the optimized RBF neural network is directly input and trained to deeply dig the conversion rule of the current cell, so that the obtained cell conversion rule is closer to a true value while the algorithm precision is improved, and the method is an improvement and expansion of a cell automaton model. Meanwhile, in the process of accumulating new data next time, the model can be continuously corrected, and the precision is improved.
Drawings
FIG. 1 is an overall flow chart of an important transmission channel disaster monitoring method based on an optimized neural network improved cellular automata according to the invention;
FIG. 2 is a flow chart of an analytic hierarchy process in an important transmission channel disaster monitoring method based on an optimized neural network improved cellular automata according to the present invention;
FIG. 3 is a hierarchical diagram of a hierarchy analysis method in an important transmission channel disaster monitoring method of an improved cellular automata based on an optimized neural network according to the present invention;
FIG. 4 is a flow chart of an RBF neural network in the disaster monitoring method of an important transmission channel based on an optimized neural network improved cellular automata of the present invention;
fig. 5 is a structure diagram of an RBF neural network in the important transmission channel disaster monitoring method based on an optimized neural network improved cellular automata of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by those skilled in the art without any inventive work are within the scope of the present invention.
Example (b):
referring to fig. 1 to 5, a method for monitoring disaster of important power transmission channel based on an optimized neural network improved cellular automata includes the following steps:
s1, data acquisition is carried out through monitoring resources, meteorological departments and power grid meteorological sites: collecting field data including monitoring terminals, meteorological department sites and power grid meteorological sites which are arranged on the power transmission line and the tower; the monitoring terminal comprises image monitoring, wire temperature monitoring, microclimate monitoring, icing monitoring, windage yaw monitoring, breeze vibration monitoring, tower inclination monitoring, wire galloping monitoring and field filth degree monitoring; meanwhile, the meteorological department data and the power grid meteorological site data are respectively collected in different data communication modes to acquire information including temperature, humidity, wind speed, wind direction, rainfall and the like and all-dimensional multi-dimensional information including geographic information;
s2, storing and preprocessing the data in the step S1: multidimensional monitoring information collected from different data sources is stored in a special Oracle database in the power system in a safe transmission mode and an encryption mode and is stored in a grading mode according to different types of data information to form data information of a single tower node and overall channel meteorological information, and a monitoring center system can call the data information at any time through a special interface; preprocessing data, including data cleaning, unstructured conversion, data normalization and the like;
s3, determining the state of the cells based on an analytic hierarchy process: based on an important power transmission channel GIS system, grid division is carried out, the division size is 3km x 3km, each grid is used as a cell, data collected in the step S4 are subjected to normalization processing, then an analytic hierarchy process model is constructed, a target layer M is a disaster risk score, a criterion layer C is divided into 3 parts including climate factors, terrain factors and tower factors, a scheme layer P is a specific factor to be considered, a hierarchical model is shown in figure 3, finally, a disaster evaluation grade of each cell is obtained, the grade is converted into a cell state, and therefore the cell state of the whole cell space at a certain moment is obtained; the specific flow is shown in fig. 2, and the specific steps are as follows:
s301, data preprocessing and normalization: the method comprises the following steps of dividing an important power transmission channel into grids on the basis of a geographic information system, taking each grid as a cell, collecting data according to an online monitoring terminal, a power grid meteorological site and a meteorological department site which are arranged in the range of the cell, carrying out normalization processing on the data, and carrying out normalization by adopting the following formula:
wherein xiFor a certain monitoring data actual monitoring quantity, a and b are threshold values of the monitoring quantity evaluation index, the larger the normalized data is, the more serious the monitoring quantity deviates from the normal state, and the threshold value of each index is set according to the relevant expert reference rule and guide rule;
s302, forming a hierarchical structure diagram: carrying out hierarchical structure division according to factors influencing disaster assessment of the important power transmission channel, and constructing a hierarchical analysis model, wherein the hierarchical analysis model comprises a target layer M, a criterion layer C and a scheme layer P, and the hierarchical analysis model comprises the following steps: the target layer M is a disaster risk score; considering factors influencing the disaster model of the area, dividing the criterion layer C into 3 parts of climate factors, terrain factors and tower factors; the scheme layer P is a specific influence factor to be considered;
s303, acquiring a judgment matrix according to expert experience: comparing the importance degrees of the data of the criterion layer C and the data of the scheme layer P pairwise to construct a judgment matrix according to expert experience;
s304, consistency check: determining matrix eigenvalues lambdamaxAccording to the formula
Carrying out consistency check to obtain a weight matrix;
s305, calculating a score according to the weight matrix: according to the hierarchical analysis model, the result is evaluated by using an analytic hierarchy process, finally the disaster risk score is obtained, the disaster risk score is divided into three grades according to historical experience, wherein the three grades are normal, abnormal and severe, the disaster evaluation score grade is obtained by multiplying the weight matrix and the current normalized monitoring data, the state of each cell in the cell space is obtained according to the following table, and the state of each cell is vectorized and used for output calculation of the RBF network.
S4, obtaining an RBF neural network data center by adopting cosine similarity, optimizing the weight from a hidden layer to an output layer by adopting an IWD algorithm, improving the network accuracy, training and learning by adopting an RBF neural network model, and obtaining the next-time state conversion rule of the current cellular through the state of the neighbor cellular: optimizing the RBF neural network, taking the cell state of the historical cell space as training data, training, acquiring a cell conversion rule, and constructing a cell automaton model; the cellular automata model can be described by the following formula:
a ═ C, S, N, R formula (2)
In the formula, C is a cellular space, i.e., the whole cells in the disaster monitoring area; s is a cellular state set, and according to the result of the analytic hierarchy process, the cellular states are divided into three types, namely 'normal' is '0', 'abnormal' is '1', and 'severe' is '2', so that the cellular state set S is {0,1,2 }; r represents the trellis of cellular automata, Sk(r, t) represents the kth state of the unit cell at the site r at the time t; n represents the neighborhood of a cellular centered on r, and a Moore type cellular neighborhood model is adopted, namely 8 neighbors are contained around each cellular, and N is { N ═ N }1,N2,…,Nq}，NqRepresents the location of the qth neighbor of cell r relative to r; r is the transformation rule of the cell, i.e., S (R, t) → S (R, t +1) R ═ R1,R2,…Rm)，RmThe mth transformation rule is only related to the states of 8 neighboring cells around the cell at the time t, and due to the complexity and uncertainty of a disaster, a specific cell transformation function rule cannot be found, so data mining is performed through historical data, and the optimized RBF neural network model is used for obtaining the cell transformation rule, wherein a specific flow chart is shown in FIG. 4, and the specific steps are as follows:
s401: randomly and uniformly selecting k data in the cell historical data as sample centers;
s402: calculating the cosine similarity between each sample and the kth center according to the formula
Where j represents an element in vectors i and k;
s403: calculating the average value rho of cosine similarity of all samples of the kth central point; is given by the formula
S404: judging whether cos (i, k) of the ith sample and the kth center is smallAt rhok；
S405: if the sample number S404 is positive, the ith sample belongs to the kth class, and the traversal is continued;
s406: if not, increasing the ith vector as the (k +1) th sample center, and continuing to traverse until the whole data set.
S407: obtaining a central vector and the number of hidden layers according to the S406 result, setting RBF network parameters, and generating l k-dimensional random number vectors as initial weights based on levy distribution;
s408: initializing IWD algorithm parameters;
s409: each water drop will flow to a path with a smaller amount of soil with a greater probability, and assuming that the water drop is at node a, the probability of flowing to the next node b is:
wherein f (soil (a, b)) is the amount of soil between nodes a and b; to solve the possible local convergence situation, a linear decreasing function, k, is introducediterFor the current number of iterations, TmaxIn the initial stage of iteration, searching globally with a high probability, and in the later stage of iteration, searching locally with a low probability; p _ is a roulette selection mode;
s4010: the water drop velocity, the amount of soil in the water drop and the amount of soil in the path are updated.
Wherein, the water drop speed updating formula is as follows:
wherein vel is the node speed of the water drops;
the updated formula of the soil amount in the water drop is as follows:
the soil amount in the path is updated according to the formula:
wherein alpha isnSp, sq, sr, vp, vq, vr are all static parameters, and are set during initialization
S4011: continuously traversing all the nodes;
s4012: selecting a path according to all the water drops obtained currently to calculate network output, calculating an error E according to an error function, selecting a path with the minimum error to be reserved as the optimal path at this time, and updating the soil amount in the path according to whether the water drops of the optimal path pass through, wherein the updating formula is as follows:
wherein, lambda is a static parameter, mu is the optimal number of water drops
S4013: judging whether the iteration times are reached;
s4014: outputting an optimal path, namely a neural network weight, completing network training to obtain a cell conversion rule, performing risk assessment prediction, and recording as 1 when an element in a predicted output vector is more than or equal to 0.5, or recording as 0;
s5, performing prediction evaluation on the current monitoring data according to the obtained cellular automata conversion rule to obtain a cellular state, namely a disaster prediction evaluation grade, and forming a grade distribution map of the current overall disaster state of the monitoring area: the cell transformation rule is obtained by adopting an optimized RBF neural network, the next state of the r-th cell is predicted by using the RBF network model trained in the step S4, the next state is expanded to the whole cell space, a power transmission channel disaster risk grade prediction distribution graph is obtained, the trend and the topological structure of an important power transmission channel are combined, the circuit passing through disaster grade abnormity and a serious area is subjected to targeted routing inspection, and disaster hidden danger is eliminated. For example, as shown in fig. 5, the input vector X is [1,1,2,0,0,0,1,2], the output vector O is [1,0,0], disaster risk assessment is performed according to a disaster grade assessment result obtained by combining the trained RBF neural network with the current monitoring data, a risk map is drawn for the whole cellular space, and if an important power transmission channel passes through a disaster abnormality or serious area, the area is subjected to targeted inspection.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the equivalent replacement or change according to the technical solution and the modified concept of the present invention should be covered by the scope of the present invention.
Claims (10)
1. An important power transmission channel disaster monitoring method based on an optimized neural network improved cellular automaton is characterized by comprising the following steps:
s1, data acquisition is carried out through monitoring resources, meteorological departments and power grid meteorological sites;
s2, storing and preprocessing the data in the step S1;
s3, determining the state of the cells based on an analytic hierarchy process;
s4, obtaining an RBF neural network data center by adopting cosine similarity, optimizing the weight from a hidden layer to an output layer by adopting an IWD algorithm, improving the network accuracy, training and learning by adopting an RBF neural network model, and obtaining the next-time state conversion rule of the current cellular through the state of the neighbor cellular;
and S5, performing prediction evaluation on the current monitoring data according to the rule to obtain a cellular state, namely a disaster prediction evaluation grade, forming a current overall disaster state grade distribution map of the monitoring area, and performing targeted routing inspection on the lines passing through the disaster grade abnormity and serious areas by combining the trend and the topological structure of the important power transmission channel to eliminate disaster hidden dangers.
2. The method as claimed in claim 1, wherein in step S3, the monitoring area is divided into cells by using a geographic information system, and the state of each cell is determined by analyzing each cell in the monitoring area hierarchically according to historical data and expert experience with the size of 3km x 3km as one cell.
3. The method for monitoring the disaster of the important power transmission channel based on the cellular automata with the optimized neural network as claimed in claim 2, wherein in step S3, the method comprises the following steps:
s301, preprocessing and normalizing data;
s302, forming a hierarchical structure diagram;
s303, acquiring a judgment matrix according to expert experience;
s304, checking consistency;
and S305, calculating a score according to the weight matrix.
4. The method for monitoring disasters of an important transmission channel based on an optimized neural network improved cellular automata, according to claim 3, in step S301, the important transmission channel is divided into grids based on a geographic information system, each grid is used as a cell, data collection is performed according to an online monitoring terminal, a grid meteorological site and a meteorological department site which are arranged in the range of the cell, data is normalized, and the following formula is adopted for normalization:
wherein xiAnd a and b are threshold values of the evaluation indexes of the monitoring amount for the actual monitoring amount of certain monitoring data, the larger the normalized data is, the more serious the deviation of the monitoring amount from the normal state is represented, and the threshold value of each index is set according to the reference rule and the guide rule of related experts.
5. The method for monitoring the disasters of the important transmission channels of the cellular automata based on the optimized neural network as claimed in claim 3, wherein in step S302, a hierarchical analysis model is constructed, comprising a target layer M, a criterion layer C and a scheme layer P, wherein: the target layer M is a disaster risk score; considering factors influencing the disaster model of the area, dividing the criterion layer C into 3 parts of climate factors, terrain factors and tower factors; the solution layer P is a specific influencing factor to be considered.
6. The method for monitoring the disaster of the important power transmission channel based on the cellular automata with the optimized neural network as claimed in claim 3, wherein in step S305, the result is evaluated by the analytic hierarchy process according to the analytic hierarchy model, and the finally obtained disaster risk score is divided into three grades according to the historical experience, wherein the three grades are "normal", "abnormal" and "serious".
7. The important transmission channel disaster monitoring method based on the optimized neural network improved cellular automata as claimed in claim 6, wherein in step S4, a cellular automata model is constructed; the cellular automata model can be described by the following formula:
a ═ C, S, N, R formula (2)
In the formula, C is a cellular space, i.e., the whole cells in the disaster monitoring area; s is a cellular state set, and according to the result of the analytic hierarchy process, the cellular states are divided into three types, namely 'normal' is '0', 'abnormal' is '1', and 'severe' is '2', so that the cellular state set S is {0,1,2 }; r represents the trellis of cellular automata, Sk(r, t) represents the kth state of the unit cell at the site r at the time t; n represents the neighborhood of a cellular centered on r, and a Moore type cellular neighborhood model is adopted, namely 8 neighbors are contained around each cellular, and N is { N ═ N }1,N2,…,Nq}，NqRepresents the location of the qth neighbor of cell r relative to r; r is the transformation rule of the cell, i.e., S (R, t) → S (R, t +1) R ═ R1,R2,…Rm)，RmThe mth transformation rule is only related to the states of 8 neighboring cells around the cell at the time t, and the specific cell transformation cannot be found due to the complexity and uncertainty of the disasterAnd (4) function rules, so that data mining is performed through historical data, and the optimized RBF neural network model is adopted to obtain the cellular transformation rules.
8. The method for monitoring disaster of important power transmission channel based on cellular automata improved by optimized neural network as claimed in claim 7, wherein in step S4, the method comprises the following steps:
s401: randomly and uniformly selecting k data in the cell historical data as sample centers;
s402: calculating the cosine similarity between each sample and the kth center according to the formula
Where j represents an element in vectors i and k;
s403: calculating the average value rho of cosine similarity of all samples of the kth central point; is given by the formula
S404: judging whether cos (i, k) of the ith sample and the kth center is less than rhok；
S405: if the sample number S404 is positive, the ith sample belongs to the kth class, and the traversal is continued;
s406: if not, increasing the ith vector as the (k +1) th sample center, and continuing to traverse until the whole data set.
9. The important transmission channel disaster monitoring method based on the optimized neural network improved cellular automata as claimed in claim 8, further comprising optimizing the weight from hidden layer to output layer of the RBF neural network by using an intelligent water drop algorithm, comprising the steps of:
s407: obtaining a central vector and the number of hidden layers according to the S406 result, setting RBF network parameters, and generating l k-dimensional random number vectors as initial weights based on levy distribution;
s408: initializing IWD algorithm parameters;
s409: each water drop will flow to a path with a smaller amount of soil with a greater probability, and assuming that the water drop is at node a, the probability of flowing to the next node b is:
wherein f (soil (a, b)) is the amount of soil between nodes a and b; to solve the possible local convergence situation, a linear decreasing function, k, is introducediterFor the current number of iterations, TmaxIn the initial stage of iteration, searching globally with a high probability, and in the later stage of iteration, searching locally with a low probability;
selecting a mode for roulette;
s4010: the water drop speed, the amount of soil in the water drop and the amount of soil in the path are updated.
Wherein, the water drop speed updating formula is as follows:
wherein vel is the node speed of the water drops;
the updated formula of the soil amount in the water drop is as follows:
the soil amount in the path is updated according to the formula:
wherein alpha isnSp, sq, sr, vp, vq, vr are all static parameters, and are set during initialization
S4011: continuously traversing all the nodes;
s4012: selecting a path according to all the water drops obtained currently to calculate network output, calculating an error E according to an error function, selecting a path with the minimum error to be reserved as the optimal path at this time, and updating the soil amount in the path according to whether the water drops of the optimal path pass through, wherein the updating formula is as follows:
wherein, lambda is a static parameter, mu is the optimal number of water drops
S4013: judging whether the iteration times are reached;
s4014: and outputting the optimal path, namely the weight of the neural network, completing network training to obtain a cell conversion rule, and performing risk evaluation prediction.
10. The method for monitoring disaster of important power transmission channel based on optimized neural network improved cellular automata as claimed in claim 9, wherein in step S4, obtaining cellular transformation rules by using optimized RBF neural network, in learning phase, selecting spatial historical data of cells as training data, training with the state of 8 cells around the time t of the r-th cell as input and the state of the r-th cell at the time t +1 as output; in step S5, the next state of the r-th cell is predicted by using the trained RBF network model, and the next state is expanded to the entire cell space, thereby obtaining a power transmission channel disaster risk level prediction distribution map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011021322.6A CN112116160B (en) | 2020-09-25 | 2020-09-25 | Important power transmission channel disaster monitoring method based on improved cellular automaton of optimized neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011021322.6A CN112116160B (en) | 2020-09-25 | 2020-09-25 | Important power transmission channel disaster monitoring method based on improved cellular automaton of optimized neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112116160A true CN112116160A (en) | 2020-12-22 |
| CN112116160B CN112116160B (en) | 2024-07-02 |
Family
ID=73796767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011021322.6A Active CN112116160B (en) | 2020-09-25 | 2020-09-25 | Important power transmission channel disaster monitoring method based on improved cellular automaton of optimized neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116160B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113077159A (en) * | 2021-04-13 | 2021-07-06 | 中能融合智慧科技有限公司 | Data processing method and data processing device |
| CN113379942A (en) * | 2021-06-10 | 2021-09-10 | 平安国际智慧城市科技股份有限公司 | Construction site facility inspection method and device, computer equipment and storage medium |
| CN113537528A (en) * | 2021-07-28 | 2021-10-22 | 贵州电网有限责任公司 | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
| CN114089091A (en) * | 2021-09-27 | 2022-02-25 | 杭州柯林电气股份有限公司 | Power transmission line on-line monitoring method and system based on non-contact sensor |
| CN114819344A (en) * | 2022-04-25 | 2022-07-29 | 南京信息工程大学 | Global space-time meteorological agricultural disaster prediction method based on key influence factors |
| CN114841084A (en) * | 2022-07-04 | 2022-08-02 | 西南交通大学 | Aerial image-based personnel evacuation simulation method, system and equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014101636A1 (en) * | 2012-12-31 | 2014-07-03 | 北京邮电大学 | Method for evaluating risk in electric power communications network |
| WO2014203039A1 (en) * | 2013-06-19 | 2014-12-24 | Aselsan Elektronik Sanayi Ve Ticaret Anonim Sirketi | System and method for implementing reservoir computing using cellular automata |
| CN104361393A (en) * | 2014-09-06 | 2015-02-18 | 华北电力大学 | Method for using improved neural network model based on particle swarm optimization for data prediction |
| CN105956934A (en) * | 2016-05-05 | 2016-09-21 | 国网湖南省电力公司防灾减灾中心 | Power grid forest fire and icing disaster safety evaluation method based on fuzzy comprehensive evaluation approach |
| CN106021666A (en) * | 2016-05-10 | 2016-10-12 | 四川大学 | Mountain fire disaster early-warning method for overhead power transmission line |
| CN108182484A (en) * | 2017-12-04 | 2018-06-19 | 国网吉林省电力有限公司长春供电公司 | Spatial Load Forecasting method based on gridding technology and BP neural network |
| WO2018125008A1 (en) * | 2016-12-27 | 2018-07-05 | Yeditepe Universitesi | A method for solving the problem of clustering using cellular automata based on heat transfer process |
| AU2018101946A4 (en) * | 2018-11-07 | 2019-01-17 | Wuhan University | Geographical multivariate flow data spatio-temporal autocorrelation analysis method based on cellular automaton |
| US20190130321A1 (en) * | 2017-10-30 | 2019-05-02 | The Aerospace Corporation | Artificial intelligence system that employs windowed cellular automata to create plausible alternatives |
| JP2019101404A (en) * | 2017-11-28 | 2019-06-24 | 学校法人梅花学園 | Method for converting data, data converter, program, and method for forming cellular automaton |
| CN111144611A (en) * | 2019-11-22 | 2020-05-12 | 国网辽宁省电力有限公司经济技术研究院 | Spatial load prediction method based on clustering and nonlinear autoregression |
| US20200241487A1 (en) * | 2019-01-24 | 2020-07-30 | Qingdao university of technology | Networked control system time-delay compensation method based on predictive control |
-
2020
- 2020-09-25 CN CN202011021322.6A patent/CN112116160B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014101636A1 (en) * | 2012-12-31 | 2014-07-03 | 北京邮电大学 | Method for evaluating risk in electric power communications network |
| WO2014203039A1 (en) * | 2013-06-19 | 2014-12-24 | Aselsan Elektronik Sanayi Ve Ticaret Anonim Sirketi | System and method for implementing reservoir computing using cellular automata |
| CN104361393A (en) * | 2014-09-06 | 2015-02-18 | 华北电力大学 | Method for using improved neural network model based on particle swarm optimization for data prediction |
| CN105956934A (en) * | 2016-05-05 | 2016-09-21 | 国网湖南省电力公司防灾减灾中心 | Power grid forest fire and icing disaster safety evaluation method based on fuzzy comprehensive evaluation approach |
| CN106021666A (en) * | 2016-05-10 | 2016-10-12 | 四川大学 | Mountain fire disaster early-warning method for overhead power transmission line |
| WO2018125008A1 (en) * | 2016-12-27 | 2018-07-05 | Yeditepe Universitesi | A method for solving the problem of clustering using cellular automata based on heat transfer process |
| US20190130321A1 (en) * | 2017-10-30 | 2019-05-02 | The Aerospace Corporation | Artificial intelligence system that employs windowed cellular automata to create plausible alternatives |
| JP2019101404A (en) * | 2017-11-28 | 2019-06-24 | 学校法人梅花学園 | Method for converting data, data converter, program, and method for forming cellular automaton |
| CN108182484A (en) * | 2017-12-04 | 2018-06-19 | 国网吉林省电力有限公司长春供电公司 | Spatial Load Forecasting method based on gridding technology and BP neural network |
| AU2018101946A4 (en) * | 2018-11-07 | 2019-01-17 | Wuhan University | Geographical multivariate flow data spatio-temporal autocorrelation analysis method based on cellular automaton |
| US20200241487A1 (en) * | 2019-01-24 | 2020-07-30 | Qingdao university of technology | Networked control system time-delay compensation method based on predictive control |
| CN111144611A (en) * | 2019-11-22 | 2020-05-12 | 国网辽宁省电力有限公司经济技术研究院 | Spatial load prediction method based on clustering and nonlinear autoregression |
Non-Patent Citations (5)
| Title |
|---|
| HU, XL (HU, XIAOLI) [1] ; LI, X (LI, XIN) [2] , [3] , [4] ; LU, L (LU, LING) [1]: "Modeling the Land Use Change in an Arid Oasis Constrained by Water Resources and Environmental Policy Change Using Cellular Automata Models", SUSTAINABILITY, 31 August 2018 (2018-08-31), pages 1 - 14 * |
| 吴小君;方秀琴;任立良;吴陶樱;苗月鲜;: "基于随机森林的山洪灾害风险评估――以江西省为例", 水土保持研究, no. 03, 24 April 2018 (2018-04-24), pages 146 - 153 * |
| 李玲;麦雄发;: "基于CA-ANN喀斯特石漠化时空格局的动态模拟和预测", 广西师范学院学报(自然科学版), no. 01, 25 March 2009 (2009-03-25), pages 89 - 94 * |
| 梁荣;杨波;马润泽;吴健;吴奎华;林振智;文福拴;: "利用多源信息和深度置信神经网络的配电系统空间负荷预测", 电力建设, no. 10, 1 October 2018 (2018-10-01), pages 21 - 28 * |
| 蒋东荣;陈冠霖;贾勇;向洪伟;王培懿;: "基于元胞自动机与多层前馈神经网络的电力信息物理融合系统安全评估模型", 重庆理工大学学报(自然科学), no. 03, 15 March 2018 (2018-03-15), pages 223 - 232 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113077159A (en) * | 2021-04-13 | 2021-07-06 | 中能融合智慧科技有限公司 | Data processing method and data processing device |
| CN113077159B (en) * | 2021-04-13 | 2023-12-15 | 中能融合智慧科技有限公司 | Data processing method and data processing device |
| CN113379942A (en) * | 2021-06-10 | 2021-09-10 | 平安国际智慧城市科技股份有限公司 | Construction site facility inspection method and device, computer equipment and storage medium |
| CN113379942B (en) * | 2021-06-10 | 2023-11-24 | 平安国际智慧城市科技股份有限公司 | Construction site facility inspection method and device, computer equipment and storage medium |
| CN113537528A (en) * | 2021-07-28 | 2021-10-22 | 贵州电网有限责任公司 | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
| CN113537528B (en) * | 2021-07-28 | 2022-05-03 | 贵州电网有限责任公司 | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
| CN114089091A (en) * | 2021-09-27 | 2022-02-25 | 杭州柯林电气股份有限公司 | Power transmission line on-line monitoring method and system based on non-contact sensor |
| CN114819344A (en) * | 2022-04-25 | 2022-07-29 | 南京信息工程大学 | Global space-time meteorological agricultural disaster prediction method based on key influence factors |
| CN114819344B (en) * | 2022-04-25 | 2024-10-18 | 南京信息工程大学 | Global space-time weather agricultural disaster prediction method based on key influence factors |
| CN114841084A (en) * | 2022-07-04 | 2022-08-02 | 西南交通大学 | Aerial image-based personnel evacuation simulation method, system and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112116160B (en) | 2024-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112116160B (en) | Important power transmission channel disaster monitoring method based on improved cellular automaton of optimized neural network | |
| US8606418B1 (en) | Wind prediction for wind farms through the use of weather radar | |
| CN107358347A (en) | Equipment cluster health state evaluation method based on industrial big data | |
| CN102411729B (en) | Wind power prediction method based on adaptive linear logic network | |
| CN111680875B (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| CN113988273A (en) | Ice disaster environment active power distribution network situation early warning and evaluation method based on deep learning | |
| CN109102101A (en) | Wind speed prediction method and system for wind power plant | |
| CN116167527B (en) | Pure data-driven power system static safety operation risk online assessment method | |
| CN115099335A (en) | Abnormal identification and feature screening method and system for multi-source heterogeneous data | |
| CN112508442A (en) | Transient stability evaluation method and system based on automation and interpretable machine learning | |
| CN104123678A (en) | Electricity relay protection status overhaul method based on status grade evaluation model | |
| CN113344408B (en) | Processing method for multi-scale situation awareness process of civil aviation traffic control operation | |
| CN106526710A (en) | Haze prediction method and device | |
| CN118157132B (en) | Data mining method and device for voltage monitoring system based on neural network | |
| CN115526382B (en) | Road network level traffic flow prediction model interpretability analysis method | |
| CN116432123A (en) | Electric energy meter fault early warning method based on CART decision tree algorithm | |
| CN116614177A (en) | Optical fiber state multidimensional parameter monitoring system | |
| CN112434887B (en) | Water supply network risk prediction method combining network kernel density estimation and SVM | |
| CN118153950A (en) | Hydraulic engineering risk prediction method and system based on data analysis | |
| CN111912393A (en) | Hydrological environment monitoring method based on water surface mobile robot | |
| CN112257329A (en) | Method for judging influence of typhoon on line | |
| CN116777230A (en) | Intelligent substation site selection area division method based on GIS space analysis technology | |
| CN111965442A (en) | Energy internet fault diagnosis method and device under digital twin environment | |
| CN116451608A (en) | Mixed wind power prediction method and device for complex terrain | |
| CN116663393A (en) | Random forest-based power distribution network continuous high-temperature fault risk level prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |