CN117010691A - Transmission tower safety evaluation method and device, computer equipment and storage medium - Google Patents
Transmission tower safety evaluation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117010691A CN117010691A CN202311001573.1A CN202311001573A CN117010691A CN 117010691 A CN117010691 A CN 117010691A CN 202311001573 A CN202311001573 A CN 202311001573A CN 117010691 A CN117010691 A CN 117010691A
- Authority
- CN
- China
- Prior art keywords
- tower
- stress
- iron tower
- stress value
- information
- 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 55
- 238000011156 evaluation Methods 0.000 title claims abstract description 33
- 238000003860 storage Methods 0.000 title claims abstract description 14
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims abstract description 224
- 229910052742 iron Inorganic materials 0.000 claims abstract description 112
- 238000006073 displacement reaction Methods 0.000 claims abstract description 66
- 238000000034 method Methods 0.000 claims abstract description 61
- 238000012549 training Methods 0.000 claims abstract description 33
- 241000283153 Cetacea Species 0.000 claims description 94
- 238000004422 calculation algorithm Methods 0.000 claims description 79
- 238000005457 optimization Methods 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 25
- 238000004088 simulation Methods 0.000 claims description 22
- 230000000739 chaotic effect Effects 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 15
- 238000005259 measurement Methods 0.000 abstract description 6
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 238000013528 artificial neural network Methods 0.000 description 32
- 230000008569 process Effects 0.000 description 12
- 230000006870 function Effects 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 8
- 210000002569 neuron Anatomy 0.000 description 7
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008602 contraction Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 102100037651 AP-2 complex subunit sigma Human genes 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 101000806914 Homo sapiens AP-2 complex subunit sigma Proteins 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
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
- G06Q10/06—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/0418—Architecture, e.g. interconnection topology using chaos or fractal principles
-
- 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
- G06Q10/04—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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
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)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a transmission tower safety evaluation method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: obtaining displacement information of each tower leg of an iron tower, wind speed information and wind direction angle information of wind load borne by the iron tower; inputting the displacement information, the wind speed information and the wind direction angle information into a stress prediction model after training is completed, so as to obtain a predicted stress value aiming at the iron tower; and determining the safety state of the iron tower based on the comparison result between the predicted stress value and the reference stress value. According to the method, on the basis of considering the influence of the displacement of the support of the tower leg on the safety of the iron tower, the influence of environmental factors such as wind speed, wind direction angle and the like on the safety of the iron tower is considered, so that the accuracy of an evaluation result can be improved; and the stress value is predicted by the stress prediction model, so that the method is not influenced by subjective experience of a person, and compared with other evaluation methods, the method reduces the interference of human subjective factors and reduces the workload and cost of traditional manual measurement.
Description
Technical Field
The application relates to the technical field of power grids, in particular to a power transmission tower safety evaluation method, a device, computer equipment, a storage medium and a computer program product.
Background
The existing method for evaluating the safety of the power transmission tower mainly comprises analysis methods such as principal component analysis and hierarchical analysis, a great deal of practical experience is needed to assign the influence factors, subjectivity is high, and the development trend of the safety of the power transmission tower cannot be predicted.
Disclosure of Invention
Based on this, it is necessary to provide a method, an apparatus, a computer device, a computer readable storage medium and a computer program product for evaluating the safety of a pylon according to the above technical problem of poor effect of evaluating the safety of a pylon.
In a first aspect, the application provides a transmission tower safety assessment method. The method comprises the following steps:
obtaining displacement information of each tower leg of an iron tower, wind speed information and wind direction angle information of wind load borne by the iron tower;
inputting the displacement information, the wind speed information and the wind direction angle information into a stress prediction model after training is completed, so as to obtain a predicted stress value aiming at the iron tower;
And determining the safety state of the iron tower based on the comparison result between the predicted stress value and the reference stress value.
In one embodiment, the stress prediction model is determined by:
determining initial model parameters of a stress prediction model through an improved whale optimization algorithm, and obtaining the stress prediction model to be trained based on the initial model parameters;
acquiring a sample data set; the sample data set comprises displacement information of each tower leg of the iron tower, wind speed information of the borne wind load, wind direction angle information and actual stress values of the iron tower;
and training the stress prediction model to be trained by taking the displacement information, the wind speed information and the wind direction angle information as input variables and taking the actual stress value of the iron tower as supervision information to obtain a stress prediction model after training.
In one embodiment, the determining, by using the improved whale optimization algorithm, initial model parameters of the stress prediction model, and obtaining the stress prediction model to be trained based on the initial model parameters includes:
iteratively determining a global optimal position and a minimum fitness value of a whale individual through an improved whale optimization algorithm;
Determining an initial weight and an initial threshold of the stress prediction model based on the global optimal position and the minimum fitness value;
and taking the initial weight and the initial threshold value as initial model parameters to obtain a stress prediction model to be trained.
In one embodiment, the acquiring a sample dataset includes:
constructing a tower line system numerical model of the iron tower;
carrying out simulation on the tower line system numerical model through a plurality of influence parameter combinations to obtain simulation stress values of the iron tower under different influence parameter combinations; each influence parameter combination comprises displacement information of each tower leg of the iron tower, wind speed information and wind direction angle information of wind load borne by the iron tower;
and obtaining the sample data set based on each influence parameter combination and the simulation stress values under different influence parameter combinations.
In one embodiment, the method further comprises:
and optimizing the whale algorithm by adopting an improved chaotic mapping model, an improved self-adaptive inertia weight and a Lewy flight strategy to obtain an improved whale optimization algorithm.
In one embodiment, the determining the safety state of the iron tower based on the comparison between the predicted stress value and the reference stress value includes:
Generating a plurality of stress value intervals based on the reference stress value, and setting a safety state corresponding to each stress value interval;
determining a target stress value interval corresponding to the predicted stress value in the stress value intervals;
and determining the safety state corresponding to the target stress value interval as the safety state of the iron tower.
In a second aspect, the application further provides a transmission tower safety evaluation device. The device comprises:
the device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring displacement information of each tower leg of an iron tower, wind speed information of wind load borne by the iron tower and wind direction angle information;
the prediction module is used for inputting the displacement information, the wind speed information and the wind direction angle information into a stress prediction model after training is completed, so as to obtain a predicted stress value aiming at the iron tower;
and the determining module is used for determining the safety state of the iron tower based on the comparison result between the predicted stress value and the reference stress value.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
Obtaining displacement information of each tower leg of an iron tower, wind speed information and wind direction angle information of wind load borne by the iron tower;
inputting the displacement information, the wind speed information and the wind direction angle information into a stress prediction model after training is completed, so as to obtain a predicted stress value aiming at the iron tower;
and determining the safety state of the iron tower based on the comparison result between the predicted stress value and the reference stress value.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
obtaining displacement information of each tower leg of an iron tower, wind speed information and wind direction angle information of wind load borne by the iron tower;
inputting the displacement information, the wind speed information and the wind direction angle information into a stress prediction model after training is completed, so as to obtain a predicted stress value aiming at the iron tower;
and determining the safety state of the iron tower based on the comparison result between the predicted stress value and the reference stress value.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
Obtaining displacement information of each tower leg of an iron tower, wind speed information and wind direction angle information of wind load borne by the iron tower;
inputting the displacement information, the wind speed information and the wind direction angle information into a stress prediction model after training is completed, so as to obtain a predicted stress value aiming at the iron tower;
and determining the safety state of the iron tower based on the comparison result between the predicted stress value and the reference stress value.
According to the power transmission tower safety evaluation method, the power transmission tower safety evaluation device, the computer equipment, the storage medium and the computer program product, displacement information of each tower leg of the power transmission tower, wind speed information and wind direction angle information of the wind load are taken as input variables, a predicted stress value of the power transmission tower is determined through a stress prediction model, and the safety state of the power transmission tower is determined based on a comparison result between the predicted stress value and a reference stress value. According to the method, on the basis of considering the influence of the displacement of the support of the tower leg on the safety of the iron tower, the influence of environmental factors such as wind speed, wind direction angle and the like on the safety of the iron tower is considered, and the accuracy of an evaluation result is improved; in addition, the method predicts the stress value through the stress prediction model, is not influenced by subjective experiences of people, reduces the interference of human subjective factors compared with other evaluation methods, and reduces the workload and cost of traditional manual measurement.
Drawings
FIG. 1 is a diagram of an application environment for a method for evaluating the safety of a pylon in one embodiment;
FIG. 2 is a flow chart of a method for evaluating the safety of a pylon in one embodiment;
FIG. 3 is a flow chart illustrating a stress prediction model determination step in one embodiment;
FIG. 4 is a schematic flow chart of a method for evaluating the safety of a pylon in another embodiment;
FIG. 5 is a block diagram of a pylon safety evaluation apparatus in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Currently, a main approximate scheme for an evaluation method of the safety of a transmission line tower mainly comprises the following steps: (1) According to the monitoring method based on the fiber bragg grating strain sensor, the fiber bragg grating sensor is installed at the tower leg of the 110kV power transmission tower, the running state of the iron tower is judged by recording the actual value of stress, but the scheme can only monitor the rod state of a certain point of the iron tower, and the whole state of the iron tower cannot be evaluated. (2) The safety evaluation of the in-service iron tower is carried out by comparing the abrasion degree of the tower material at the dangerous position of the in-service iron tower with that of the normal iron tower, but the method needs to measure the average thickness of the tower material at the dangerous position by means of a coating thickness gauge on the artificial upper tower, and has troublesome practical operation and low efficiency. (3) The safety evaluation of the power transmission tower in the landslide area is carried out by taking the number of tower legs moving and the tower leg moving direction as evaluation indexes based on an analytic hierarchy process and an index weight determining method based on index correlation, but the method requires manual calculation and is complex in process, and the evaluation method based on the analytic hierarchy process is high in subjectivity and cannot accurately judge the safety of the power transmission tower.
The analysis shows that the existing method for evaluating the safety of the transmission tower mainly comprises analysis methods such as principal component analysis and hierarchical analysis, and a great deal of practical experience is required to assign the influence factors, so that subjectivity is high, and the development trend of the safety of the tower cannot be predicted; the measurement index data related to the rest methods need manual field measurement, so that the efficiency is low, the periodicity is long, the abnormal stress of the iron tower cannot be quickly found, and the real-time evaluation of the safety state of the power transmission iron tower in the landslide area cannot be realized; secondly, monitoring the iron tower through a sensor with a single function, wherein the sensor can only reflect the stress condition of a local rod piece of the iron tower, and the safety analysis of the whole iron tower in a complex working condition of the transmission tower in a landslide area can not be realized; in addition, the prior art is mostly focused on analyzing the rule of influence of tower leg support displacement caused by side slope deformation on the internal force of a tower rod piece, and the safety of a power transmission line under the combined action of wind load and side slope deformation is rarely considered.
Aiming at the problems, the application provides a power transmission tower line system stress prediction method considering the comprehensive influence of side slope deformation and wind load, and the core content of the method is BP neural network algorithm based on Improved Whale Optimization Algorithm (IWOA) optimization, and the maximum stress of the tower line system is used as a power transmission tower safety evaluation index to predict the stress of the tower line system influenced by the side slope deformation and strong wind weather. The application optimizes the landslide area tower line system stress prediction model of the BP neural network based on an improved whale algorithm, and can pointedly solve the problems of strong subjectivity, low evaluation accuracy and low efficiency of the existing transmission tower line system safety evaluation system.
Specifically, the method takes displacement of a tower leg support, wind speed and wind direction angle caused by side slope deformation as input of a tower line system stress prediction model and takes maximum stress of a tower line system as output. On one hand, the influence of side slope deformation and wind load is comprehensively considered, and the displacement of the tower leg support can be obtained in real time by installing a displacement sensor on the tower leg without manual field measurement; on the other hand, the method for predicting the stress of the power transmission tower line system in the landslide area based on the IWOA-BP neural network can reduce the subjective experience influence of people, realize the stress prediction of the power transmission tower line system in the landslide area in a short time, and give out the future development trend of the safety of the iron tower, thereby increasing the reaction time of the operation and inspection personnel of the power transmission line and reducing the iron tower accidents.
The method for evaluating the safety of the power transmission tower, provided by the embodiment of the application, can be applied to an application environment shown in fig. 1. Wherein the sensor 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The sensor 102 may include a displacement sensor, a wind speed sensor, and a wind direction sensor. The server 104 may be implemented as a stand-alone server or a server cluster including a plurality of servers.
In an application scenario of the present application, displacement information of each leg of the power pylon may be monitored by a displacement sensor in the sensor 102, wind speed information by a wind speed sensor, and wind direction angle information by a wind direction sensor. The server 104 can acquire displacement information, wind speed information and wind direction angle information of each tower leg of the power transmission tower from various sensors, and then call a stress prediction model after training to process the displacement information, the wind speed information and the wind direction angle information of each tower leg so as to obtain a predicted stress value of the power transmission tower; and determining the safety state of the iron tower based on a comparison result between the predicted stress value and the reference stress value.
In one embodiment, as shown in fig. 2, a method for evaluating the safety of a power pylon is provided, and the method is applied to the server 104 in fig. 1 for illustration, and includes the following steps:
and step S210, obtaining displacement information, wind speed information and wind direction angle information of each tower leg of the iron tower.
Wherein the displacement information comprises displacement information of the tower legs in three directions X, Y, Z.The tower legs of the power transmission tower are generally four, and the displacement information comprises 12 displacements d of the four tower legs in the X, Y, Z three directions AX ，d AY ，d AZ ，d BX ，d BY ，d BZ ，d CX ，d CY ，d CZ ，d DX ，d DY ，d DZ . Wherein A, B, C, D respectively represents four tower legs of the iron tower, d AX Representing the displacement variable of the tower leg A in the X direction, d AY Representing the displacement variation of the tower leg a in the Y direction, other parameters and so on.
Specifically, displacement information of each tower leg can be acquired through a displacement sensor arranged on each tower leg of the iron tower, wind speed information of wind load borne by the iron tower is acquired through a wind speed sensor arranged on the iron tower, and wind direction angle information of wind load borne by the iron tower is acquired through a wind direction sensor arranged on the iron tower. The server 104 may obtain displacement information, wind speed information, and wind direction angle information for each leg of the iron tower from the displacement sensor, the wind speed sensor, and the wind direction sensor.
And step S220, inputting the displacement information, the wind speed information and the wind direction angle information into a stress prediction model after training is completed, and obtaining a predicted stress value for the iron tower.
The stress prediction model may be a neural network model, specifically may be a BP neural network (Back Propagation neural network), where the BP neural network has a relatively strong approximation and learning capabilities, may process high-dimensional data and has fault tolerance, and may perform parallel computation, so as to improve efficiency of iron tower assessment.
The predicted stress value may be a maximum stress value of the power pylon.
Specifically, the topology of the BP neural network may be determined in advance from the input data and the output data. More specifically, the topology of the BP neural network is determined according to the number of input data and the number of output data. The topology structure of BP neural network is formed from three portions of input layer, hidden layer and output layer, and the input data in the application includes displacement of four tower legs in three directions, i.e. 12 displacementThe data, the wind speed and the wind direction angle of wind load are 14 input data in total, and the output data are the maximum stress value of the power transmission tower, namely 1 output data. Therefore, the input node M=14 of the input layer of the BP neural network structure corresponds to the displacement of four tower legs of the tower in the x, y and z directions and the wind speed and the angle of the wind load borne by the tower line system; the output node N=1 of the output layer, namely the maximum stress value of the transmission tower line system; number of hidden layers And b is an adjustment constant between 1 and 10. Namely, the topology structure of the BP neural network constructed by the application is 14-9-1.
After the topological structure of the BP neural network is determined, the BP neural network can be trained through a sample data set, and the trained BP neural network is obtained and used as a stress prediction model.
Further, displacement information of each tower leg of the iron tower is obtained through actual monitoring, wind speed information and wind direction angle information of the wind load can be called to be processed by a stress prediction model after training, and the maximum stress value of the iron tower is obtained and used as a predicted stress value.
And step S230, determining the safety state of the iron tower based on the comparison result between the predicted stress value and the reference stress value.
The safety state of the iron tower can comprise a serious unsafe state, an unsafe state, a warning state and a safe state.
In a specific implementation, a plurality of stress value intervals can be set according to the reference stress value, each stress value interval is provided with a corresponding safety state, and corresponding grades of each state can be recorded as grade I, grade II, grade III and grade IV. Further determining a target stress value interval corresponding to the predicted stress value in the stress value intervals, and determining a safety state corresponding to the target stress value interval as a safety state of the power transmission tower.
In the power transmission tower safety evaluation method, displacement information of each tower leg of the power transmission tower, wind speed information of the load of the wind and wind direction angle information are taken as input variables, a predicted stress value of the power transmission tower is determined through a stress prediction model, and the safety state of the power transmission tower is determined based on a comparison result between the predicted stress value and a reference stress value. According to the method, on the basis of considering the influence of the displacement of the support of the tower leg on the safety of the iron tower, the influence of environmental factors such as wind speed, wind direction angle and the like on the safety of the iron tower is considered, and the accuracy of an evaluation result is improved; in addition, the method predicts the stress value through the stress prediction model, is not influenced by subjective experiences of people, reduces the interference of human subjective factors compared with other evaluation methods, and reduces the workload and cost of traditional manual measurement.
In an exemplary embodiment, as shown in fig. 3, the stress prediction model in the above step S220 is determined by:
step S221, determining initial model parameters of the stress prediction model through an improved whale optimization algorithm, and obtaining the stress prediction model to be trained based on the initial model parameters.
Specifically, iteratively determining a global optimal position and a minimum fitness value of a whale individual through an improved whale optimization algorithm; determining an initial weight and an initial threshold of the stress prediction model based on the global optimal position and the minimum fitness value; and taking the initial weight and the initial threshold value as initial model parameters to obtain the stress prediction model to be trained.
Step S222, acquiring a sample data set; the sample data set comprises displacement information of each tower leg of the iron tower, wind speed information of the loaded wind, wind direction angle information and actual stress value of the iron tower.
Specifically, a numerical simulation experiment can be performed, an integral finite element model of interaction among a tower line, a foundation and a foundation is established by utilizing finite element calculation software, dynamic response of a power transmission tower line system under the actions of different side slope deformations and wind loads of different wind directions is calculated, simulation data are used as sample data sets of a stress prediction model, the sample data sets are divided into a test set and a training set, the stress prediction model is trained through the training set, and the stress prediction model is tested through the test set.
And step S223, training the stress prediction model to be trained by taking displacement information, wind speed information and wind direction angle information as input variables and taking an actual stress value of the iron tower as supervision information to obtain the stress prediction model after training.
Specifically, a BP algorithm may be used to train the stress prediction model to be trained. Specifically, after determining a stress prediction model to be trained, inputting a training sample into the stress prediction model to be trained to obtain a predicted stress value, and calculating an error between the predicted stress value and an actual stress value. And then updating model parameters of the stress prediction model by using a back propagation algorithm according to the error, and continuously iterating the training until the maximum iteration number is reached or the error converges to a threshold value, ending the training, and obtaining the stress prediction model after the training is completed.
In this embodiment, the whale algorithm is an optimization algorithm for solving a globally optimal solution, and the BP algorithm is an algorithm for training a neural network. By combining the whale algorithm and the BP algorithm, the initial model parameters of the neural network can be found through the optimization algorithm, and then the BP algorithm is used for training, so that the training effect and the convergence rate of the neural network can be improved.
In an exemplary embodiment, the step S221 determines initial model parameters of the stress prediction model through a modified whale optimization algorithm, and obtains the stress prediction model to be trained based on the initial model parameters, including:
step S221a, iteratively determining global optimal position and minimum fitness value of whale individual through improved whale algorithm.
Step S221b, determining an initial weight and an initial threshold of the stress prediction model based on the global optimal position and the minimum fitness value.
In step S221c, the initial weight and the initial threshold are used as initial model parameters to obtain the stress prediction model to be trained.
The improved whale optimization algorithm (Improved Whale Optimization Algorithm, IWOA) can be obtained by optimizing the whale algorithm by adopting an improved chaotic mapping model, an improved self-adaptive inertia weight and a Laevice flight strategy.
The whale algorithm is an optimization algorithm based on group intelligence and has the capacity of global searching. It finds the optimal solution in the search space by simulating the migration behavior of whales.
The initial weight refers to a connection weight between network layers of the BP neural network, and comprises a connection weight between an input layer and an implicit layer, and a connection weight between the implicit layer and an output layer.
Wherein the initial threshold includes a threshold of an implied layer and a threshold of an output layer of the BP neural network.
Specifically, the implementation steps of this embodiment include:
(1) The improved whale optimization algorithm is initialized, the whale population number n, the maximum iteration number tmax and the search dimension d are set, and the predicted mean square error of the BP neural network is used as the fitness function of the whale optimization algorithm.
(2) Initializing whale population by adopting an improved chaotic mapping model, and optimizing the position updating mode of whale individuals by using an improved self-adaptive inertia weight in a shrink wrapping and spiral updating stage. When the random probability variable p is less than 0.5, if the coefficient vector |A| is less than or equal to 1, updating the individual position; if the coefficient vector |A| >1, the individual position is selectively updated. When the random probability variable p is more than or equal to 0.5, the individual position is updated. And continuously updating the whale population position through iteration, calculating the fitness value of each whale individual, and selecting the optimal solution.
(3) In each iteration process, searching is carried out in a small range of the optimal solution by utilizing the Lewy flight strategy, and the global optimal solution is determined according to the fitness values before and after searching.
(4) And (3) assigning the global optimal solution obtained by solving the improved whale optimization algorithm to an initial weight and an initial threshold value of the BP neural network, and taking the initial weight and the initial threshold value as initial model parameters to obtain a stress prediction model to be trained.
(5) Updating the weight and the threshold according to an error back propagation mechanism of the BP neural network, and when the error reaches the maximum iteration number t max And ending training.
In the embodiment, the BP neural network weight and the threshold are optimized by adopting an improved whale optimization algorithm, so that compared with the traditional gradient descent method, the whale algorithm can better avoid sinking into a local optimal solution, and the parameter optimizing effect is improved; moreover, the whale algorithm adopts a strategy of searching a plurality of whale individuals in parallel, and can explore a plurality of candidate solutions at the same time, so that the searching speed is increased; the basic idea and operation of the whale algorithm are simpler, and the whale algorithm is easy to understand and realize; the whale algorithm has low dependence on the initial solution and good robustness.
In an exemplary embodiment, step S222, acquiring a sample dataset includes: constructing a tower line system numerical model of the iron tower; carrying out simulation on the tower line system numerical model through a plurality of influence parameter combinations to obtain simulation stress values of the iron tower under different influence parameter combinations; each influence parameter combination comprises displacement information of each tower leg of the iron tower, wind speed information of wind load borne by the iron tower and wind direction angle information; and obtaining a sample data set based on each influence parameter combination and the simulation stress values under different influence parameter combinations.
Specifically, through carrying out a numerical simulation experiment, an integral finite element model (namely a numerical model of a tower line system) of interaction among a tower line, a foundation and a foundation is established by utilizing finite element calculation software, dynamic responses of the power transmission tower line system under the actions of different side slope deformations and wind loads of different wind directions and angles are calculated, and simulation data are used as a sample data set.
Specifically, after a numerical model of the tower line system is built, the maximum stress value of the power transmission tower line system under different working conditions (namely different influence parameter combinations) can be obtained by changing the position and the magnitude of downhill downward thrust applied to a foundation and changing the wind speed and the wind direction angle (included angles with the downline direction are 30 degrees, 45 degrees, 60 degrees and 90 degrees respectively) of wind load applied to a simulation point, and 12 displacements of four tower legs of the iron tower in the X, Y, Z direction are extracted. And respectively forming a sample data set by the displacement amounts and wind speeds and wind direction angles of the four tower leg supports of the iron tower in the three directions of X, Y, Z.
Further, in order to ensure the comparability and consistency of the data, after the sample data set is obtained, the sample data set may be normalized, and the processed data is used as the sample data set of the stress prediction model.
In the embodiment, the interaction among the tower line, the foundation and the foundation is fully considered, a complete tower line system numerical model is established, the displacement of the four tower leg supports of the iron tower in the x direction, the y direction and the z direction respectively and the influence of wind speed and wind direction angles on the maximum stress of the tower line system are evaluated, on the basis of considering the influence of the displacement of the tower leg supports on the iron tower, the environmental factors such as wind speed, wind direction angles and the like are considered, and the accuracy of an evaluation result can be improved.
In an exemplary embodiment, the method further includes: and optimizing the whale algorithm by adopting an improved chaotic mapping model, an improved self-adaptive inertia weight and a Lewy flight strategy to obtain an improved whale optimization algorithm.
The chaotic mapping model is a Circle chaotic mapping model.
Specifically, in order to facilitate understanding of the present embodiment, a brief description of the whale algorithm will be given below. The whale algorithm generally comprises three main phases: an exploration phase, a shrink wrap phase and a spiral update phase.
The spatial location of whale populations of number n and search dimension d can be represented by matrix X:
position X of each whale in matrix X i Representing each solution in the solution space. During the initial exploration phase, whale individuals search through randomly generated locations to explore the solution space. The position of each whale individual at this stage can be calculated by the following expression:
Wherein: x is X i (t+1) is the position of whale at which the t+1st search for prey was performed; x is X i (t) is the position of whale after the t-th prey search; x is X rand (t) is the location of any whale in the population; d (D) 1 To explore the distance between whale and prey in the stage; t is the current iteration number; A. c is a coefficient vector, and the expression is:
wherein: r is (r) 1 ，r 2 A random vector with a value between 0 and 1; a is an iteration variable, the value of the iteration variable is linearly decreased from 2 to 0, and the expression of a is as follows:
wherein: t is t max Is the set maximum iteration number.
In the process of continuously searching for a prey, the coefficient vector A becomes smaller along with the gradual decrease of the iteration variable a. When the A is less than or equal to 1, the algorithm enters a shrink wrapping stage. During the contraction-surrounding phase, whale individuals perform a contraction search around a better solution to find a more optimal solution. The new position of each whale individual can be calculated by the following expression:
wherein: x is X p (t) is the prey location, i.e., globally optimal solution, D 2 To shrink the distance from the prey to the whale during the wrapping phase.
In the spiral updating stage, the whale individual performs position updating in a spiral movement mode so as to further improve the searching effect. The new position of each whale individual can be calculated by the following expression:
Wherein: d' is the distance between whale and prey in the spiral updating stage; b is a shape constant, 1 is taken here; l is a random value of [ -1,1 ].
Contraction wrapping and spiral updating are often performed simultaneously during the hunting of whales, and in order to simulate such simultaneous behavior, we have introduced a random probability variable p to select the hunting behavior of whales. During hunting, whales will perform different operations based on the value of p. When the random probability variable p is less than 0.5, if the coefficient vector |A| is less than or equal to 1, updating the individual position; if the coefficient vector |A| >1, the individual position is selectively updated. When the random probability variable p is more than or equal to 0.5, the individual position is updated. By introducing a random probability variable p, the behavior selection of whales during hunting can be better simulated. Where p is a random value of [0,1], the mathematical model of this stage is:
because the positions of whale individuals in the d-dimensional space are randomly generated, the phenomenon of aggregation of the positions of the whale initialization population, namely the problem of low coverage of solving space, is caused, and the phenomenon of aggregation of whale individuals in the d-dimensional space, namely the problem of low coverage of solving space, is possibly caused during population initialization. To solve this problem, an improved Circle chaotic mapping model is introduced in the whale optimization algorithm for initializing populations. Through the improved model, the diversity of population positions can be improved, so that the whale initialization population positions have stronger ergodic performance, and the global optimizing capability of an algorithm is improved. The improved Circle chaotic mapping model expression is as follows:
Wherein: x is X i+1 Position i+1 whale; x is X i Is the position of the ith whale.
Inertial weights are an important parameter of the WOA algorithm, and appropriate inertial weights can help balance the global search and local optimization capabilities of the algorithm. The improved self-adaptive inertial weight is utilized to optimize the position updating mode of whales in the shrink wrapping and spiral updating stages, so that the global searching and local optimizing capabilities of the algorithm can be balanced.
An important parameter in the WOA algorithm is the inertial weight, which plays a key role in balancing the global searching and local optimizing capabilities of the algorithm. In order to optimize the position updating mode of whales in the contraction surrounding and spiral updating stages, the improved self-adaptive inertial weight is introduced in the application to better balance the global searching and local optimizing capabilities of the algorithm, so that the algorithm can search the optimal solution in the global range, and meanwhile, fine adjustment and optimization can be carried out in the local range, thereby improving the performance and convergence rate of the WOA algorithm. The improved position updating mode is as follows:
X i (t+1)＝ωX p (t)-AD 2 (9)
X i (t+1)＝ωX p (t)+D′e bl cos(2πl) (10)
wherein: f (i) is the fitness value of individual whale i; u is the fitness value of the optimal whale individual generated in the first iteration.
The Levy flight strategy is a random walk strategy based on Levy distribution, and can carry out larger jump in the searching process, thereby being beneficial to jumping out of a local optimal solution and exploring a global optimal solution. By utilizing the Levy flight strategy, the global searching capability of the WOA algorithm can be enhanced through additional small-range searching after each iteration, so that the situation that the local optimal solution is trapped is avoided, and the performance and the convergence speed of the algorithm are improved. The mathematical model is as follows:
wherein: alpha is a step size scale factor, and 0.01 is taken; one is an inner product operation symbol; levy (beta) is the Levy flight step,
wherein: beta is a constant of 0 to 2, 1.5 being taken here; u and v are random numbers conforming to normal distribution; u to N (0, sigma 2), v to N (0, 1);
wherein: Γ (x) is a Gamma function.
In this embodiment, the Circle chaotic mapping model, the adaptive inertial weight and the Levy flight strategy are adopted to optimize the whale algorithm, and the Circle chaotic mapping model can generate a large number of random number sequences in the searching process, and the random numbers are used as variation factors, so that the diversity of the searching space is increased. Thus, the whole solution space can be better traversed, and the optimizing capability is improved. The introduction of adaptive inertial weights can balance the strategies explored and exploited. By adjusting the magnitude of the inertial weights and adaptively updating, the algorithm may focus more on exploration in early searches and on utilizing the better solutions found in later searches. The method is favorable for considering global and local optimization in the searching process, and improves the searching efficiency and effect. The Levy flight strategy is a long-distance jump strategy, and can help the algorithm jump out of the local optimal solution and continue to explore in the solution space. The jump characteristic helps the whale algorithm to avoid being trapped in local optimum in the searching process, and improves global searching capability. By introducing the optimization method, the whale algorithm has better robustness and convergence when solving various optimization problems. It can converge to the globally optimal solution faster and has less dependence on the initial solution, reducing the sensitivity of the algorithm to the initial solution.
Further, in the step S223, the stress prediction model to be trained is trained by using the displacement information, the wind speed information and the wind direction angle information as input variables and the actual stress value of the iron tower as supervision information, so as to obtain a trained stress prediction model, which can be understood as: the initial weight and the threshold value determined based on the improved whale optimization algorithm are continuously and iteratively updated by taking displacement information, wind speed information and wind direction angle information as input variables and taking the actual stress value of the iron tower as supervision information, so that the training speed and the training precision of the network are improved.
The BP neural network topological structure consists of an input layer, an implicit layer and an output layer. Wherein, the weight and threshold updating formula is as follows:
let the output value of the kth neuron be y k The j-th neuron has an output value y j The weight w from the jth neuron to the kth neuron kj The iterative update formula is:
Δw kj ＝ηδ k y j (15)
wherein eta is learning rate and delta k The calculation method is as follows:
δ k ＝(d k -y k )f'(net k ) (16)
wherein d k Net for the actual output value k For the input value of the kth neuron (i.e., the result of the weighted sum plus the bias term), f' (net k ) To activate the derivative of the function, a sigmoid function is typically used in the BP network as the activation function, the derivative of which is:
f'(net k )＝y k (1-y k ) (17)
Threshold value θ of jth neuron j The iterative update formula is:
Δθ j ＝-ηδ j (18)
wherein delta j The calculation method is as follows:
δ j ＝f'(net j )∑ k (δ k w kj ) (19)
wherein f' (net j ) To activate the derivative of the function, a sigmoid function is typically used in the network as the activation function, Σk (δ k w kj ) Is the result of the error back-propagation of the jth neuron.
Optimization of whale algorithm (WOA) is performed by using a Circle chaotic mapping model, adaptive inertial weights and Levy flight strategy, so that an improved whale algorithm (IWOA) is obtained, and an adaptation function of the IWOA is given as follows:
substituting the data in the sample data set into an initial BP neural network (namely a stress prediction model to be trained), simultaneously using an fitness function as an initial condition of a fitness formula to calculate a fitness value fitness, importing the initial fitness value into an IWOA model, and solving a weight, a threshold and a minimum fitness value in the supporting BP neural network. Updating the fitness value of each whale individual in each iteration and the corresponding weight and threshold value according to formulas (2) - (14); when the algorithm reaches the maximum iteration number t max And when the running of the program is finished, outputting a global optimal position and a minimum fitness value to obtain optimal parameters of a weight and a threshold value, and constructing a BP prediction model through formulas (15) - (20) to obtain the improved IWOA-BP neural network.
In an exemplary embodiment, the step S230 determines the safety state of the iron tower based on the comparison between the predicted stress value and the reference stress value, including: generating a plurality of stress value intervals based on the reference stress value, and setting a safety state corresponding to each stress value interval; determining a target stress value interval corresponding to the predicted stress value in the stress value intervals; and determining the safety state corresponding to the target stress value interval as the safety state of the iron tower.
Specifically, examples of the plurality of stress value intervals generated based on the reference stress value and the safety state corresponding to each stress value interval are as follows:
interval 1: the stress value exceeds a reference stress value of 1.2 times, corresponding to a first order-severely unsafe condition.
Interval 2: the stress value is larger than or equal to the reference stress value and smaller than or equal to 1.2 times of the reference stress value, and corresponds to a secondary-unsafe state.
Interval 3: the stress value is larger than or equal to 0.8 times of the reference stress value and smaller than the reference stress value, and corresponds to the three-level warning state.
Interval 4: the stress value is less than 0.8 times the reference stress value, corresponding to a four-level-safe state.
After the predicted stress value is determined, comparing the predicted stress value with the reference stress value, and if the predicted stress value is 0.9 times of the reference stress value, determining that the safety state of the iron tower is a warning state according to the corresponding section 3.
In this embodiment, a plurality of stress value intervals are generated by using the reference stress value, and the safety state corresponding to each stress value interval is set, so that the multi-level division of the stress values is realized, and the evaluation granularity of the determined safety state can be improved.
The application provides a power transmission tower line system stress prediction method considering comprehensive influence of side slope deformation and wind load, which comprises the following specific contents: firstly, a numerical simulation experiment is carried out, an integral finite element model of interaction among a tower line, a foundation and a foundation is established by utilizing finite element calculation software, dynamic response of a power transmission tower line system under the actions of different side slope deformations and wind loads of different wind directions and angles is calculated, and simulation data are used as a test set and a training set of a prediction model. And then optimizing a whale algorithm by using an improved Circle chaotic mapping sequence, a self-adaptive inertia weight and a Levy flight strategy, and then carrying out parameter optimization on the weight and the threshold value of the BP neural network by using the optimized whale algorithm to obtain an optimal power transmission tower state prediction model. When the state analysis of the power transmission tower in the landslide area is carried out, the displacement of the tower leg support, the wind speed and the wind direction angle are taken as the model input, and the maximum stress of the tower line system is taken as the output. And finally, taking the predicted maximum stress value of the power transmission tower as an index for evaluating the safety of the power transmission tower in the landslide area, dividing the power transmission tower state into a serious unsafe state, an unsafe state, a warning state and a safe state, and marking the states as a first level, a second level, a third level and a fourth level.
In one embodiment, to facilitate understanding of embodiments of the application by those skilled in the art, a specific example will be described below in conjunction with the accompanying drawings. Referring to fig. 4, a complete flow diagram of a method for evaluating the safety of a power pylon is shown, comprising the steps of:
and step S410, carrying out a numerical simulation experiment, and establishing an overall finite element model of interaction among the tower line, the foundation and the foundation by utilizing finite element calculation software to serve as a tower line system numerical model of the iron tower.
And step S420, carrying out simulation on the tower line system numerical model through a plurality of influence parameter combinations, and obtaining a sample data set based on the obtained simulation stress value and each influence parameter combination.
Step S430, determining a basic topology structure of the BP neural network according to the input data and the output data, and constructing the BP neural network according to the determined basic topology structure.
Step S440, optimizing the initial weight and the initial threshold of the BP neural network through the improved whale optimization algorithm. The method specifically comprises the following steps:
step S440a, optimizing the whale algorithm through the improved Circle chaotic mapping sequence, the adaptive inertia weight and the Levy flight strategy to obtain an improved whale optimization algorithm.
Step S440b, iteratively determining global optimal position and minimum fitness value of whale individual through improved whale optimization algorithm.
In step S440c, the global optimal position and the minimum fitness value are assigned to the initial weight and the initial threshold of the BP neural network.
And S450, carrying out iterative updating on the initial weight and the initial threshold value through a sample data set to obtain a trained IWOA-BP neural network model serving as a stress prediction model.
And step S460, predicting the maximum stress of the tower line system in the landslide area by using the trained IWOA-BP neural network model.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a power transmission tower safety evaluation device for realizing the power transmission tower safety evaluation method. The implementation scheme of the solution provided by the device is similar to the implementation scheme recorded in the method, so the specific limitation in the embodiment of the safety assessment device for the power pylon provided below can be referred to as the limitation of the safety assessment method for the power pylon hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 5, there is provided a transmission tower safety assessment device, including: an acquisition module 510, a predictive model 520, and a determination module 530, wherein:
the obtaining module 510 is configured to obtain displacement information of each tower leg of the iron tower, wind speed information of wind load borne by the iron tower, and wind direction angle information;
the prediction module 520 is configured to input displacement information, wind speed information and wind direction angle information into a stress prediction model after training is completed, so as to obtain a predicted stress value for the iron tower;
the determining module 530 is configured to determine a safety state of the iron tower based on a comparison result between the predicted stress value and the reference stress value.
In one embodiment, the apparatus further includes a model determining module configured to determine, by using an improved whale optimization algorithm, initial model parameters of a stress prediction model, and obtain the stress prediction model to be trained based on the initial model parameters; acquiring a sample data set; the sample data set comprises displacement information of each tower leg of the iron tower, wind speed information of the borne wind load, wind direction angle information and actual stress value of the iron tower; and training the stress prediction model to be trained by taking displacement information, wind speed information and wind direction angle information as input variables and taking an actual stress value of the iron tower as supervision information to obtain a stress prediction model after training.
In one embodiment, the model determination module is further configured to iteratively determine a global optimal position and a minimum fitness value for the individual whales by using an improved whale optimization algorithm; determining an initial weight and an initial threshold of the stress prediction model based on the global optimal position and the minimum fitness value; and taking the initial weight and the initial threshold value as initial model parameters to obtain the stress prediction model to be trained.
In one embodiment, the obtaining module 510 is further configured to construct a tower line system numerical model of the iron tower; carrying out simulation on the tower line system numerical model through a plurality of influence parameter combinations to obtain simulation stress values of the iron tower under different influence parameter combinations; each influence parameter combination comprises displacement information of each tower leg of the iron tower, wind speed information of wind load borne by the iron tower and wind direction angle information; and obtaining a sample data set based on each influence parameter combination and the simulation stress values under different influence parameter combinations.
In one embodiment, the apparatus further includes an algorithm optimization module configured to optimize the whale algorithm using the improved chaotic mapping model, the improved adaptive inertial weight, and the lewy flight strategy to obtain an improved whale optimization algorithm.
In one embodiment, the determining module 530 is configured to generate a plurality of stress value intervals based on the reference stress value, and set a security state corresponding to each stress value interval; determining a target stress value interval corresponding to the predicted stress value in the stress value intervals; and determining the safety state corresponding to the target stress value interval as the safety state of the iron tower.
All or part of the modules in the power transmission tower safety evaluation device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing data in the security evaluation process of the transmission tower. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is used for realizing a transmission tower safety assessment method.
It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. A method for evaluating the safety of a power transmission tower, comprising the steps of:
obtaining displacement information of each tower leg of an iron tower, wind speed information and wind direction angle information of wind load borne by the iron tower;
inputting the displacement information, the wind speed information and the wind direction angle information into a stress prediction model after training is completed, so as to obtain a predicted stress value aiming at the iron tower;
And determining the safety state of the iron tower based on the comparison result between the predicted stress value and the reference stress value.
2. The method of claim 1, wherein the stress prediction model is determined by:
determining initial model parameters of a stress prediction model through an improved whale optimization algorithm, and obtaining the stress prediction model to be trained based on the initial model parameters;
acquiring a sample data set; the sample data set comprises displacement information of each tower leg of the iron tower, wind speed information of the borne wind load, wind direction angle information and actual stress values of the iron tower;
and training the stress prediction model to be trained by taking the displacement information, the wind speed information and the wind direction angle information as input variables and taking the actual stress value of the iron tower as supervision information to obtain a stress prediction model after training.
3. The method according to claim 2, wherein said determining initial model parameters of the stress prediction model by means of a modified whale optimization algorithm, deriving the stress prediction model to be trained based on said initial model parameters, comprises:
iteratively determining a global optimal position and a minimum fitness value of a whale individual through an improved whale optimization algorithm;
Determining an initial weight and an initial threshold of the stress prediction model based on the global optimal position and the minimum fitness value;
and taking the initial weight and the initial threshold value as initial model parameters to obtain a stress prediction model to be trained.
4. The method of claim 2, wherein the acquiring a sample dataset comprises:
constructing a tower line system numerical model of the iron tower;
carrying out simulation on the tower line system numerical model through a plurality of influence parameter combinations to obtain simulation stress values of the iron tower under different influence parameter combinations; each influence parameter combination comprises displacement information of each tower leg of the iron tower, wind speed information and wind direction angle information of wind load borne by the iron tower;
and obtaining the sample data set based on each influence parameter combination and the simulation stress values under different influence parameter combinations.
5. The method according to any one of claims 2-4, further comprising:
and optimizing the whale algorithm by adopting an improved chaotic mapping model, an improved self-adaptive inertia weight and a Lewy flight strategy to obtain an improved whale optimization algorithm.
6. The method of claim 1, wherein determining the safe state of the pylon based on the comparison between the predicted stress value and a baseline stress value comprises:
generating a plurality of stress value intervals based on the reference stress value, and setting a safety state corresponding to each stress value interval;
determining a target stress value interval corresponding to the predicted stress value in the stress value intervals;
and determining the safety state corresponding to the target stress value interval as the safety state of the iron tower.
7. A pylon safety evaluation apparatus, the apparatus comprising:
the device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring displacement information of each tower leg of an iron tower, wind speed information of wind load borne by the iron tower and wind direction angle information;
the prediction module is used for inputting the displacement information, the wind speed information and the wind direction angle information into a stress prediction model after training is completed, so as to obtain a predicted stress value aiming at the iron tower;
and the determining module is used for determining the safety state of the iron tower based on the comparison result between the predicted stress value and the reference stress value.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, carries out the steps of the pylon safety evaluation method of any one of claims 1 to 6.
9. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the pylon safety evaluation method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program when executed by a processor implements the steps of the pylon safety evaluation method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311001573.1A CN117010691A (en) | 2023-08-09 | 2023-08-09 | Transmission tower safety evaluation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311001573.1A CN117010691A (en) | 2023-08-09 | 2023-08-09 | Transmission tower safety evaluation method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117010691A true CN117010691A (en) | 2023-11-07 |
Family
ID=88563263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311001573.1A Pending CN117010691A (en) | 2023-08-09 | 2023-08-09 | Transmission tower safety evaluation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117010691A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117807888A (en) * | 2024-01-11 | 2024-04-02 | 国网湖北省电力有限公司经济技术研究院 | Method, system and equipment for calculating tower icing load by considering corrosion influence |
-
2023
- 2023-08-09 CN CN202311001573.1A patent/CN117010691A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117807888A (en) * | 2024-01-11 | 2024-04-02 | 国网湖北省电力有限公司经济技术研究院 | Method, system and equipment for calculating tower icing load by considering corrosion influence |
| CN117807888B (en) * | 2024-01-11 | 2024-05-24 | 国网湖北省电力有限公司经济技术研究院 | Method, system and equipment for calculating tower icing load by considering corrosion influence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023284142A1 (en) | Signal processing method for neuron in spiking neural network and method for training said network | |
| CN111784061B (en) | Training method, device and equipment for power grid engineering cost prediction model | |
| CN117010691A (en) | Transmission tower safety evaluation method and device, computer equipment and storage medium | |
| CN114861890B (en) | Method and device for constructing neural network, computing equipment and storage medium | |
| CN114492191A (en) | Heat station equipment residual life evaluation method based on DBN-SVR | |
| CN114548591B (en) | Sequential data prediction method and system based on mixed deep learning model and Stacking | |
| CN108665052A (en) | The method and apparatus of drosophila algorithm optimization generalized regression nerve networks | |
| CN111598329A (en) | Time sequence data prediction method based on automatic parameter adjustment recurrent neural network | |
| CN115618732A (en) | Nuclear reactor digital twin key parameter autonomous optimization data inversion method | |
| CN116454863A (en) | Optimal weight determining method of wind power combination prediction model based on improved hawk optimization algorithm | |
| CN113486926B (en) | Automatic change pier equipment anomaly detection system | |
| CN117824756B (en) | Building structure monitoring method, equipment and storage medium | |
| CN112926251B (en) | Landslide displacement high-precision prediction method based on machine learning | |
| CN111582634B (en) | Multi-factor safety grading method and system for underground large-space construction | |
| CN117520954A (en) | Abnormal data reconstruction method and system based on isolated forest countermeasure network | |
| Shen et al. | Lasso regression based on halton sequence initialized capuchin search algorithm | |
| CN115936773A (en) | Internet financial black product identification method and system | |
| CN115081856A (en) | Enterprise knowledge management performance evaluation device and method | |
| KR102184395B1 (en) | Apparatus for classifying massive amounts of data using decision trees and deep neural networks, method therefor, and computer recordable medium storing program to perform the method | |
| CN113673015B (en) | Intelligent system construction and parameter identification method for beam column end plate connection node optimization design | |
| Wang et al. | A new mixed precision quantization algorithm for neural networks based on reinforcement learning | |
| CN117910120B (en) | Buffeting response prediction method for wind-bridge system based on lightweight transducer | |
| CN114692310B (en) | Dueling DQN-based virtual-real fusion primary separation model parameter optimization method | |
| CN115034426B (en) | Rolling load prediction method based on phase space reconstruction and multi-model fusion Stacking integrated learning mode | |
| CN112670996B (en) | CNN-based GPU parallel power flow out-of-limit discrimination 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 |