CN118014374B

CN118014374B - Wind turbine generator set installation feasibility evaluation method and system based on motion amplitude

Info

Publication number: CN118014374B
Application number: CN202410411993.5A
Authority: CN
Inventors: 李庙双; 刘端阳; 汪争争
Original assignee: Jiangsu Hailong Wind Power Technology Co ltd
Current assignee: Jiangsu Hailong Wind Power Technology Co ltd
Priority date: 2024-04-08
Filing date: 2024-04-08
Publication date: 2024-06-14
Anticipated expiration: 2044-04-08
Also published as: CN118014374A

Abstract

The invention discloses a method and a system for evaluating the installation feasibility of a wind turbine based on a motion amplitude, which relate to the technical field of wind turbine installation, and the method for evaluating the installation feasibility of the wind turbine based on the motion amplitude comprises the following steps: obtaining environmental characteristic data and performance characteristic data; establishing a dynamic planning model for wind turbine installation; obtaining preliminary layout data of wind turbine installation; judging whether the installation layout of the wind turbine generator meets a preset installation standard or not, and applying the wind turbine generator in the field; and predicting the running fault occurrence of the wind turbine at the next moment. According to the invention, the dynamic planning model is established and analyzed by utilizing an analysis algorithm, so that an optimization scheme is provided for the installation layout of the wind turbine generator, the optimal installation layout is found, and the layout schemes can effectively cope with environmental changes and performance fluctuation, so that potential risks caused by motion amplitude are reduced.

Description

Wind turbine generator set installation feasibility evaluation method and system based on motion amplitude

Technical Field

The invention relates to the technical field of wind turbine installation, in particular to a method and a system for evaluating the feasibility of wind turbine installation based on a motion amplitude.

Background

With the continuous increase of energy demand and the continuous enhancement of environmental awareness, mountain wind farms have become one of the main forms of current new energy power generation. As one form of wind power generation fields, compared with a plain wind power plant, a mountain wind power plant is more flexible in layout and more changeable in terrain, so that the installation safety of a wind power generator set is more complex and important. The installation safety is an important link of wind power plant construction, and the operation safety and the power generation efficiency of the whole wind power plant are directly affected. Site selection is generally completed by a wind farm design team and a constructor, and is also one of important links of the whole wind farm construction. When site selection is carried out, factors such as surrounding environment topography, climate conditions, wind direction and wind speed, land utilization and the like are required to be considered so as to ensure the running efficiency and safety of the wind power plant, and for the mountain wind power plant, as the topography is diversified, factors such as the gradient of a mountain, geological structure, altitude and the like are required to be fully considered when the installation position of the unit is selected so as to ensure the safety and reliability of the unit and avoid potential safety hazards such as geological disasters, landslide and the like.

In the prior art, an optimization scheme is inconvenient to provide for the installation layout of the wind turbine generator, so that the optimal installation layout cannot be found, the layout schemes cannot be ensured to effectively cope with environmental changes and performance fluctuation, potential risks caused by motion amplitude are improved, comparison and verification of layout data are inconvenient, the installation layout of the wind turbine generator cannot be ensured to meet preset installation standards, feasibility evaluation of the installation scheme is reduced, safety and efficiency of the installation scheme are reduced, meanwhile, prediction of faults of the wind turbine generator is inconvenient, prospective risk management strategies are inconvenient to provide for operation of the wind turbine generator, fault risks caused by the motion amplitude are inconvenient to identify in advance, and preventive measures are inconvenient to take or emergency response plans are inconvenient to formulate.

For the problems in the related art, no effective solution has been proposed at present.

Disclosure of Invention

Aiming at the defects of the prior art, the invention provides a method and a system for evaluating the installation feasibility of a wind turbine based on a motion amplitude, which solve the problems that the prior art is inconvenient to provide an optimization scheme for the installation layout of the wind turbine, so that the optimal installation layout cannot be found, the environment change and the performance fluctuation cannot be effectively caused by the layout schemes, the potential risk caused by the motion amplitude is improved, the comparison and verification of layout data are inconvenient, the installation layout of the wind turbine cannot be ensured to meet the preset installation standard, the feasibility evaluation of the installation scheme is reduced, the safety and the efficiency of the installation scheme are reduced, meanwhile, the prediction of faults of the wind turbine is inconvenient, the prospective risk management strategy is inconvenient to provide for the operation of the wind turbine, the fault risk caused by the motion amplitude is inconvenient to identify in advance, and further preventive measures or emergency response plans are inconvenient to take.

In order to achieve the above purpose, the invention is realized by the following technical scheme:

according to one aspect of the invention, a method for evaluating the installation feasibility of a wind turbine based on a motion amplitude is provided, and the method for evaluating the installation feasibility of the wind turbine based on the motion amplitude comprises the following steps:

S1, acquiring environmental data and performance data of a wind turbine in a wind turbine installation area, and preprocessing the environmental data and the performance data of the wind turbine to obtain environmental characteristic data and performance characteristic data;

S2, establishing a dynamic programming model of wind turbine generator installation based on the obtained environmental characteristic data and performance parameter characteristic data;

S3, analyzing the dynamic planning model by using an analysis algorithm to obtain preliminary layout data of wind turbine installation;

S4, based on an optimization algorithm, comparing the obtained preliminary layout data with known wind turbine generator set installation layout data, judging whether the wind turbine generator set installation layout accords with a preset installation standard or not, and applying the wind turbine generator set installation layout in the field;

s5, a fault prediction model is established, and the occurrence of the running fault of the wind turbine at the next moment is predicted.

Further, the obtaining environmental data and performance data of the wind turbine in the wind turbine installation area, and preprocessing the environmental data and the performance data of the wind turbine to obtain environmental feature data and performance feature data includes the following steps:

s11, deploying data acquisition nodes in a preset installation area of the wind turbine, and acquiring environment data in the area and real-time performance data of the wind turbine by using a communication protocol;

S12, acquiring original environment data and wind turbine generator system performance data from a data acquisition node, converting the data from a time domain to a frequency domain by using a wavelet transformation technology, and screening out wave field records of each frequency band containing environment interference;

s13, tracking environmental interference waves one by one in wave field records of each frequency band, and acquiring the interference wave direction at a calculation sample point;

S14, selecting a plurality of road windows with the calculation sample points as centers to perform median filtering, and recovering environmental interference signals at the calculation sample points;

S15, recovering interference signals in wave field records of each frequency band one by one, and converting the interference wave field back to a time domain through wavelet inverse conversion to obtain the whole wave field information of the interference wave;

s16, subtracting the interference wave field from the original environment data and the wind turbine generator system performance data to obtain a denoised effective signal wave field, and generating denoised environment characteristic data and wind turbine generator system performance characteristic data based on the denoised effective signal wave field.

Further, the analyzing the dynamic programming model by using the analysis algorithm to obtain preliminary layout data of the wind turbine installation comprises the following steps:

S31, importing original installation layout data of wind turbines, initializing, and calculating the shortest distance between any two wind turbines in the wind power plant by using Dijkstra algorithm;

S32, each optimization agent represents a layout of wind turbine installation, the first N numbers represent position numbers of the wind turbines, the last N numbers represent operation setting levels of the corresponding wind turbines, and the operation setting levels correspond to the first N numbers one by one;

s33, finding a globally optimal optimization agent according to a set optimization target, and adding an environmental influence factor to influence the update of the optimization agent together with each group of locally optimal optimization agents and group trends;

S34, converting the updated optimization agent through Kent mapping, and comparing the mapped optimization agent with the original optimization agent before updating according to an optimization target;

s35, eliminating the layout of the wind turbine generator set installation with poor performance based on the comparison of the optimization targets;

S36, replacing the layout of the wind turbine generator set with poor performance with a global suboptimal optimization agent according to an optimization target through elite reservation;

And S37, repeatedly executing the steps S33 to S36 until the iteration termination condition is met, and outputting the global optimal optimization agent as preliminary layout data for the installation of the wind turbine.

Further, the method for finding the globally optimal optimization agent according to the set optimization target, adding the environmental impact factor to influence the update of the optimization agent together with each group of locally optimal optimization agents and group trends comprises the following steps:

S331, defining a set optimization objective function, and taking the set optimization objective function as the adaptability of an evaluation optimization agent;

s332, initializing an optimized agent set, and randomly generating an initial position of each optimized agent;

S333, evaluating the fitness of each optimization agent according to the defined set optimization objective function;

S334, finding out the optimization agent with the highest fitness from all the optimization agents to be used as the current globally optimal optimization agent;

S335, adding a random environmental impact factor to each group of optimal optimization agents, and calculating the average position of the optimization agents in the group;

s336, calculating the position of the new optimizing agent by using an updating mode formula from the original optimizing agent, and updating the position of each optimizing agent;

s337, repeating steps S333 to S336 until the termination condition is satisfied.

Further, the converting the updated optimization agent through Kent mapping, and comparing the mapped optimization agent with the original optimization agent before updating according to the optimization target includes the following steps:

s341, training and iterating the optimized proxy set to obtain an updated optimized proxy set;

S342, carrying out data normalization processing on the updated optimized proxy set to enable the updated optimized proxy set to be in a complete chaotic state;

s343, randomly generating parameters of Kent mapping, and presetting a value range;

s344, mapping each updated optimization agent by using a Kent mapping formula and the generated parameters to generate a new optimization agent individual;

S345, comparing the fitness of each optimization agent with the Kent mapping result of each optimization agent, and reserving the optimization agent individual with the highest fitness as the Kent optimization agent;

S346, performing fitness comparison on the Kent optimization proxy and the original optimization proxy set, and selecting a proxy individual with the highest fitness to enter the next generation of optimization proxy set.

Further, the comparing the obtained preliminary layout data with the known wind turbine installation layout data based on the optimization algorithm to determine whether the wind turbine installation layout meets the preset installation standard, and applying the wind turbine installation layout in the field comprises the following steps:

S41, comparing preliminary layout data of wind turbine installation with known wind turbine installation layout data, and identifying key factors influencing the wind turbine installation layout;

S42, analyzing key factors influencing the installation layout of the wind turbine generator, and setting corresponding evaluation levels;

S43, training the identified key factors influencing the installation layout of the wind turbine by an optimization algorithm, calculating the risk score of each wind turbine installation layout, and judging whether each wind turbine installation layout has high risk or not;

S44, normalizing the obtained risk score, and calculating a corresponding fuzzy set;

s45, evaluating influences of key factors influencing the installation layout of the wind turbine on different risk levels by professionals to form a risk evaluation matrix of the installation layout of the wind turbine;

S46, calculating the fuzzy set and the risk evaluation matrix through a fuzzy logic method to obtain fuzzy comprehensive risk evaluation result vectors of each layout;

S47, judging whether the risk level of each wind turbine generator installation layout exceeds a preset safety threshold, if so, marking the wind turbine generator installation layout as high risk; if not, the motor set installation layout of the low or medium wind risk meeting the installation standard is considered, and the motor set installation layout of the low or medium wind risk meeting the installation standard is applied in the field.

Further, the analyzing key factors influencing the installation layout of the wind turbine generator and setting corresponding evaluation levels comprises the following steps:

S421, collecting various key factor data influencing the installation layout of the wind turbine, screening and classifying the collected various key factor data influencing the installation layout of the wind turbine, removing repeated factors, and summarizing the collected key factor data into a measurable key factor set;

s422, setting weights for each key factor according to experience of actual wind turbine installation and operation, and setting evaluation levels for each key factor;

s423, evaluating the performance of each key factor in the installation layout of the wind turbine according to the set evaluation level.

Further, the formula for calculating the fuzzy set and the risk evaluation matrix by the fuzzy logic method is as follows:

；

Wherein, Represented as a fuzzy operator;

a fuzzy comprehensive evaluation result vector expressed as the f-th evaluation result type;

a fuzzy set of membership degrees expressed as all individual key factors;

The membership degree of key factors in the key factor set of the installation layout of the wind turbine to be evaluated to the evaluation result in the comment set is represented;

e. f is represented as a non-zero natural number;

D is expressed as a fuzzy comprehensive evaluation result vector;

k represents the number of rows of the membership matrix;

n represents the number of columns of the membership matrix.

Further, the establishing a fault prediction model and predicting occurrence of the operation fault of the wind turbine at the next moment comprises the following steps:

S51, collecting operation data and fault history data of the wind turbine under different working conditions, and constructing a fault prediction model of the wind turbine based on the operation data and the fault history data;

S52, estimating a parameter value in a fault prediction model by comparing and fitting actual operation data of the wind turbine generator with fault history data;

S53, calculating the running performance of the wind turbine and the possibility of occurrence of faults of the wind turbine in a next period of time by using the established and parameterized fault prediction model.

According to another aspect of the present invention, there is also provided a system for evaluating the installation feasibility of a wind turbine based on a motion amplitude, the system for evaluating the installation feasibility of a wind turbine based on a motion amplitude comprising:

The data processing module is used for acquiring environmental data and performance data of the wind turbine in the wind turbine installation area, and preprocessing the environmental data and the performance data of the wind turbine to obtain environmental characteristic data and performance characteristic data;

The dynamic model building module is used for building a dynamic planning model of wind turbine generator installation based on the obtained environmental characteristic data and performance parameter characteristic data;

The data analysis module is used for analyzing the dynamic programming model by utilizing an analysis algorithm to obtain preliminary layout data of the wind turbine generator set installation;

The data optimization module is used for comparing the obtained preliminary layout data with the known wind turbine installation layout data based on an optimization algorithm to obtain the optimal wind turbine installation layout data, and applying the optimal wind turbine installation layout data in the field;

The fault prediction module is used for establishing a fault prediction model and predicting the running fault of the wind turbine generator at the next moment;

The data processing module is connected with the data analysis module through the dynamic model building module, and the data analysis module is connected with the fault prediction module through the data optimization module.

The beneficial effects of the invention are as follows:

1. According to the method, the environment data in the wind turbine installation area and the performance data of the wind turbine are collected and preprocessed, a real-time and accurate data basis is provided for feasibility evaluation based on the motion amplitude, and an optimization scheme is provided for wind turbine installation layout by establishing a dynamic programming model and analyzing the dynamic programming model by utilizing an analysis algorithm. The method is not only beneficial to finding the optimal installation layout, but also ensures that the layout schemes can effectively cope with environmental changes and performance fluctuation, thereby reducing potential risks caused by motion amplitude, comparing and verifying layout data through an optimization algorithm, ensuring that the installation layout of the wind turbine generator meets preset installation standards, enhancing the feasibility evaluation of the installation scheme, simultaneously establishing a fault prediction model and predicting operation faults, providing a prospective risk management strategy for the operation of the wind turbine generator, facilitating the early identification of fault risks possibly caused by the motion amplitude, further taking preventive measures or making an emergency response plan, and ensuring the continuous operation and stability of the wind turbine generator.

2. According to the method, the shortest distance between the wind turbines is calculated by using the Dijkstra algorithm, accurate basic data can be provided for optimizing the internal layout of the wind turbine, the distance between the wind turbines is facilitated to be optimized, the energy loss caused by wind flow interference is reduced, the wind turbines are ensured to run at the optimal position, the overall efficiency is improved, an optimization objective function is defined, and an optimization agent is continuously updated, so that the globally optimal layout can be found, meanwhile, the layout of the wind turbines is continuously optimized through elite reservation and fitness comparison, the time lapse and environmental change are ensured, and the layout of the wind turbine is always kept in an optimal state.

3. According to the method, key factors affecting the installation of the wind turbine are identified by comparing the preliminary layout data with the standard layout data, variables possibly affecting the performance of the wind turbine are accurately found, each factor can be reasonably considered in a final layout decision, and by classifying the key factors, assigning weights and grading risks and combining specific running conditions and environment data of the wind turbine, risk assessment is systematic and quantitative, more scientific and accurate decision support is provided for the installation of the wind turbine, and a risk assessment result calculated by a fuzzy logic method is utilized, so that comprehensive safety assessment can be provided for the installation layout of the wind turbine.

4. According to the invention, the fault prediction model of the wind turbine generator is constructed by collecting the operation data and the fault history data, so that potential faults can be identified at an early stage, interference and maintenance can be performed before the faults occur, the downtime of the wind turbine generator is reduced, the operation efficiency and the safety are improved, the prediction of the future faults by the fault prediction model is facilitated, the overall high-reliability operation of the wind farm is realized, the operation condition and the potential risk of each wind turbine generator can be better understood, and further, more intelligent decisions can be made in the planning and daily operation and maintenance of the whole wind farm.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for evaluating the feasibility of installing a wind turbine based on motion amplitude according to an embodiment of the invention.

FIG. 2 is a functional block diagram of a wind turbine installation feasibility assessment system based on motion amplitude according to an embodiment of the invention.

In the figure:

1. A data processing module; 2. a dynamic model building module; 3. a data analysis module; 4. a data optimization module; 5. and a fault prediction module.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.

In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more. Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

According to the embodiment of the invention, a method and a system for evaluating the installation feasibility of a wind turbine generator based on a motion amplitude are provided.

The invention is further described with reference to the accompanying drawings and the specific embodiments, as shown in fig. 1, the method for evaluating the installation feasibility of the wind turbine generator based on the motion amplitude according to the embodiment of the invention comprises the following steps:

specifically, the environmental data includes:

Wind speed and direction: wind speed and wind direction change are the most direct factors influencing the generating efficiency of the wind turbine generator.

Air temperature and humidity: the environmental temperature and the air humidity influence the material performance and the mechanical efficiency of the wind turbine. Precipitation and snow load: precipitation conditions such as rain, snow and the like can influence the structural safety and the operation efficiency of the wind turbine generator.

Topography and topography: the topography has important influence on wind field distribution, and different topography such as mountain region, plain, coastal can cause wind speed distribution difference.

Lightning frequency: the lightning protection measures of the wind turbine generator are particularly considered in the areas with frequent lightning activities.

Specifically, the performance data of the wind turbine generator set includes:

generating capacity: actual power generation amount data under different wind speeds, temperatures and other environmental conditions.

Rotational speed and torque: the rotating speed of the wind wheel and the torque of the generator reflect the power performance of the wind turbine generator.

Unit state information: including the operational status of the unit, fault status, maintenance information, etc.

Power curve: the relation curve between wind speed and power generation is important data for evaluating the performance of the wind turbine generator.

Temperature monitoring data: including gearbox temperature, generator temperature, impeller temperature, etc., which reflect the thermal state and heat dissipation efficiency of the wind turbine.

In particular, the dynamic planning model refers to a mathematical model for determining the optimal wind turbine layout and configuration, which can take into account variations and uncertainties in time series. Dynamic programming is a method of handling a multi-stage decision process, particularly suited to solving the sequential decision problem, where the outcome of each decision affects the next state and selection.

Specifically, the building of the dynamic programming model includes:

defining state and decision variables:

The state variables typically represent the current configuration of the wind turbine, environmental conditions (e.g., wind speed, terrain), and their corresponding performance metrics (e.g., power generation, turbine efficiency).

Decision variables refer to factors that can be controlled, such as the location, number, model, etc. of the wind turbines.

Establishing an objective function:

the objective function is the core of the dynamic planning model, defining the objective of optimization, such as maximizing the total power generation, minimizing the cost or risk, etc. This needs to be constructed based on the environmental feature data and the performance parameter feature data.

And (3) making a transfer equation:

The transition equation describes the rule of change from the current state to the next state, which includes how to calculate the performance metrics for the next state based on the current decision and environmental conditions. For example, changing the layout of wind turbines affects the efficiency and cost of power generation for the entire wind farm.

Processing constraint conditions:

in the problem of wind farm layout, there are various constraints including terrain constraints, minimum distance constraints between wind turbines, budget constraints, etc. These constraints require proper representation and processing in the model.

Solving the model:

a dynamic programming model, such as the bellman equation, linear programming algorithm, etc., is solved using an appropriate algorithm. In the solution process, the different decision paths will be evaluated step by step until an optimal or near optimal solution is found.

specifically, preliminary layout data of wind turbine installation includes:

position coordinates: the specific location of each wind turbine within a wind farm is typically expressed in geographic coordinates (longitude and latitude) or distance and direction from a reference point.

Model and specification of wind turbine generator system: the preliminary layout data can specify specific models and specifications of the wind turbine generator set planned to be installed, and the specific models and specifications comprise information such as impeller diameter, tower height and rated power.

Mounting interval: the transverse and longitudinal distances between the wind turbines are used for reducing wind shadow effect between fans and ensuring that each wind turbine can effectively utilize wind resources.

Direction and orientation: the orientation of the wind turbine (i.e. the direction in which the impeller faces) is also important data in the preliminary layout, and the reasonable orientation is helpful for improving the efficiency of capturing wind energy of the wind turbine.

And (3) terrain adaptability analysis: the preliminary layout data may also include analysis results of the terrain adaptability for each installation site, such as whether terrain modification is required, whether the installation site is in an area where geological disasters are likely to occur, and the like.

Accessing a preset path of a power grid: considering that the electric energy of the wind farm needs to be transmitted to the power grid, the preliminary layout data also considers the access path from each wind turbine to the nearest transmission line.

Environmental impact assessment: for preliminary layouts that may affect local ecology, wildlife habitat or human living areas, an environmental impact assessment is required, which is also one of the important bases for layout decisions.

Economic analysis: including preliminary estimated construction costs, expected operating costs, and expected economic returns, etc., which help to assess the economic viability of the project.

specifically, the known wind turbine installation layout data includes:

Layout data for historical installation cases: the method comprises detailed layout information of success cases and failure cases, such as specific positions, models, intervals, orientations and the like of the wind turbines.

Design and installation criteria: including layout requirements for wind turbine installation in industry standards, regional regulations, or international guidelines, such as minimum pitch standards, requirements for terrain, adaptability to wind direction and speed, etc.

Environmental and geographic data: the data including the topography, wind speed distribution, meteorological conditions, etc. of the historical installation site are used for carrying out environmental adaptability comparison with the preliminary layout data.

Wind turbine performance data: the performance data of the wind turbine generator used in the known layout, including a power curve, an optimal working range and the like, are used for evaluating whether the wind turbine generator selected in the preliminary layout is suitable or not.

Grid access data: the scheme of wind turbine generator system and power grid access in the known layout comprises a power transmission line layout, a transformer station position and the like, and the scheme is used for evaluating whether the power grid access scheme of the preliminary layout is feasible or not.

Economic and cost data: the method comprises the steps of constructing cost, operation and maintenance cost, economic return and the like of the known layout, and is used for comparing and analyzing with the economical efficiency of the preliminary layout.

Environmental impact assessment report: the evaluation result of the layout on the environmental impact is known for evaluating whether the environmental impact of the preliminary layout is within an acceptable range.

Preferably, the obtaining environmental data and performance data of the wind turbine in the wind turbine installation area, and preprocessing the environmental data and the performance data of the wind turbine, obtaining environmental feature data and performance feature data includes the following steps:

Specifically, a plurality of data acquisition nodes are deployed in a preset installation area of the wind turbine generator, and are used for collecting environmental data of the area and performance data of the wind turbine generator in real time. The nodes may communicate with a central data management system using various communication protocols (e.g., loRaWAN, NB-IoT, wi-Fi, etc.), transmitting the collected data in real-time.

In particular, raw environmental and performance data obtained from data acquisition nodes typically contains various environmental disturbances. The wavelet transformation technology can be used for converting the data from the time domain to the frequency domain, thereby being helpful for more clearly identifying and separating the environmental interference signals in different frequency bands.

Specifically, in the frequency domain, bands containing environmental interference are tracked one by one, and the directions of these interference waves at the sample points are calculated. The key is that the environmental interference wave is accurately identified and the direction information is acquired, so that a foundation is laid for the next interference elimination.

Specifically, a plurality of road windows with the calculated sample points as centers are selected for median filtering treatment. The median filtering is an effective nonlinear filtering technique that can effectively remove noise interference in the wave field record while preserving the edge information of the signal.

specifically, the interference signals in the wave field record of each frequency band are recovered, and then the interference wave fields are converted back to the time domain through wavelet inverse transformation, so that the time domain waveform of the interference wave field is reconstructed.

Preferably, the analyzing the dynamic programming model by using an analysis algorithm to obtain preliminary layout data of wind turbine installation includes the following steps:

specifically, the Dijkstra algorithm is an algorithm for finding the shortest path between two points in a graph, and the algorithm can process a directed graph and an undirected graph, and simultaneously supports edges with weights, wherein the weights of the edges represent distances or costs and the like. The core idea of the algorithm is to extend gradually from the start point to all reachable vertices in the graph to find the shortest path.

Specifically, the Dijkstra algorithm maintains two main sets, a set of vertices for which the shortest path has been determined and a set of vertices for which the shortest path has not been determined. Each step selects an undetermined vertex with the smallest distance from the starting point, adds the undetermined vertex to the determined set, and updates the distance from all other undetermined vertices to the starting point. This process continues until the shortest path for all vertices is determined or the shortest path for the target vertex is found. In the invention, dijkstra algorithm can be used for calculating the shortest distance between any two wind turbines in the wind power plant. The "distance" herein may be an actual geographical distance or a weighted distance taking into account terrain, construction costs or other factors.

S32, each optimizing agent (namely each suburban wolf) respectively represents a layout of wind turbine installation, the first N numbers represent position numbers of the wind turbines, and the last N numbers represent operation setting levels of the corresponding wind turbines and are in one-to-one correspondence with the first N numbers;

Specifically, the position number of the wind turbine refers to a unique identifier of a predetermined or possible wind turbine installation point in the wind farm. In the wind farm planning process, a plurality of potential installation points are determined in advance, and each point is assigned a number according to the geographic position, the topographic features and the like. These numbers are used in the optimization process to refer to the specific mounting locations possible for the wind turbines. For example, number 1 may refer to the first potential mounting point in the wind farm, number 2 the second, and so on.

Specifically, the operation setting level refers to a setting level of an operation parameter or configuration corresponding to a position of the wind turbine, and the operation setting level may include a plurality of different parameters, such as an inclination angle, a rotation speed of a blade, a power output setting, and the like of the wind turbine, which are key factors affecting performance and efficiency of the wind turbine. Each set level represents a specific set of operating parameters intended to optimize the performance of the wind turbine under given environmental conditions.

S33, finding a globally optimal optimization agent (suburban wolf) according to a set optimization target, and adding an environmental impact factor to influence the update of the optimization agent together with each group of locally optimal optimization agents and group trends;

Specifically, elite preservation is an elite preservation strategy, the elite preservation strategy is to replace the optimal solution with the worst solution, so that the algorithm is prevented from eliminating the excellent solution in the optimizing process, the purpose of preserving excellent solution genes is achieved, so that the elite selection strategy is adjusted to be used for naming the suboptimal wolves before the whole population grows as Beta wolves, the Beta wolves are used for replacing the wolves with the worst social adaptability in the grown wolves, and the searching efficiency is improved while the excellent solution genes in the seed group are preserved.

Specifically, the analysis algorithm is an improved suburb optimization algorithm, a deformed elite retention strategy is introduced in the optimizing process of the suburb optimization algorithm, an environmental impact factor is added in the growing process of the suburb, and the growing suburb is substituted into a Kent mapping traversal search space, so that the exploitation capability and search performance of the algorithm are enhanced. The growth of suburban wolves during optimizing by the traditional suburban wolf optimizing algorithm is a main way for obtaining a new solution. The suburban wolf population group is grown by the suburban wolf optimization algorithm, the growth of suburban wolves in the group is guided by the group alpha wolves and the group cultural trend cult in the growth process, the population diversity of COA suburban wolves and the information exchange in the population are greatly limited, the global traversal of the suburban wolves in the growth process is lower, and meanwhile, the survival rate of the COA suburban wolves is low, the population diversity is lower, the exploration capability of the algorithm is poorer, and the suburban wolves are easy to sink into local optimum.

Preferably, the method for finding the globally optimal optimization agent according to the set optimization target, adding the environmental impact factor to affect the update of the optimization agent together with each group of locally optimal optimization agents and group trends comprises the following steps:

In particular, the given optimization objective function is a predefined mathematical function that is used to evaluate and compare the performance or fitness of different solutions (i.e., optimization agents).

Specifically, the optimization objectives include:

maximizing the total power generation: and (3) searching an optimal layout to maximize the total power generation of the wind power plant by considering factors such as wind speed, topography and the like.

Minimizing the total cost: including installation costs, maintenance costs, and possibly operating costs of wind turbines, a layout scheme is sought to minimize overall costs.

Minimizing environmental impact: on the premise of ensuring economic benefit, the influence of the wind power plant on the local ecology and environment is reduced.

Optimizing the distance between wind turbines: the proper distance between wind turbines is ensured, so that the wind shadow effect is reduced, and the overall efficiency of the wind power plant is improved.

S332, initializing an optimized agent set (namely suburb wolf population), and randomly generating an initial position of each optimized agent (namely the suburb wolf position in an improved suburb wolf optimization algorithm);

Specifically, the environmental impact factor is a parameter for simulating the effect of randomness in the natural environment on the development of suburban wolf population. In nature, the growth and development of the population of organisms is not only determined by the characteristics of the organisms themselves, but also by environmental factors such as food supply, climate change, predator pressure, etc. The environmental impact factors are introduced into the algorithm to simulate the natural phenomenon, and the actual applicability and effect of the algorithm are increased.

specifically, the updated formula mode is a novel suburb growth mode constructed in the improved suburb wolf optimization algorithm.

Preferably, the converting the updated optimization agent through Kent mapping, and comparing the mapped optimization agent with the original optimization agent before updating according to the optimization target includes the following steps:

Specifically, the normalization processing unifies the dimensions of the data, so that comparability exists among different data, and the normalization processing is performed on the prediction result, so that the influence of the dimensions of the data is eliminated, and the subsequent weighting processing and summation calculation are facilitated.

specifically, the Kent mapping is a chaotic mapping, and is a symmetric chaotic mapping when the value is 0.5.

Preferably, the comparing the obtained preliminary layout data with the known wind turbine installation layout data based on the optimization algorithm, and judging whether the wind turbine installation layout meets the preset installation standard, and applying the wind turbine installation layout in the field includes the following steps:

Specifically, training the identified key factors affecting the installation layout of the wind turbine by an optimization algorithm, calculating the risk score of each wind turbine installation layout, and judging whether the high risk exists in each wind turbine installation layout or not, wherein the method comprises the following steps:

s431, dividing the risk of the collected wind turbine installation layout into a training set and a testing set;

s432, training an isolated forest model by randomly selecting segmentation points in the characteristic and characteristic value range related to the wind turbine generator installation layout risk by utilizing a training set;

S433, constructing a plurality of isolated trees to form an isolated forest model which is specially used for analyzing the risk of the installation layout of the wind turbine generator;

s434, calculating the average path length of each wind turbine installation layout data point in the test set from the root node to the leaf node by using the constructed isolated forest model;

s435, calculating a risk score for each patient based on the average path length;

and S436, judging whether each wind turbine installation layout belongs to high risk or not by using risk scores according to a preset threshold value.

Specifically, during the training process, the data points are divided into two subsets (one of which contains the data points smaller than or equal to the characteristic value and the other contains the data points larger than the characteristic value) according to the selected characteristic value, and a splitting operation is performed; this process is repeated recursively for each subset until a stop condition is met (e.g., subset size reaches a predetermined threshold, tree depth reaches a maximum).

S46, calculating the fuzzy set and the risk evaluation matrix (namely the fuzzy relation matrix) through a fuzzy logic method (namely a fuzzy operator) to obtain fuzzy comprehensive risk evaluation result vectors of each layout;

Specifically, the optimization algorithm is a fuzzy isolated Forest algorithm, and is a fuzzy improvement algorithm based on isolated forests (Isolation Forest). An isolated forest is a very effective anomaly detection method, and the core idea is to isolate data points by using a binary tree structure, wherein the positions of normal data and abnormal data in the tree have significant differences, and the abnormal data are usually isolated earlier. In the invention, the risk score of the obtained wind turbine generator installation layout is normalized, and a fuzzy set is constructed to process the uncertainty and the ambiguity in the risk level of the wind turbine generator installation layout. In wind turbine installation layout risk level analysis, the fuzzy set can be used for more accurately describing key factors affecting wind turbine installation layout risk levels.

Preferably, the analyzing the key factors affecting the installation layout of the wind turbine generator and setting the corresponding evaluation level comprises the following steps:

Preferably, the formula for calculating the fuzzy set and the risk evaluation matrix by the fuzzy logic method is as follows:

；

Wherein, Represented as a fuzzy operator;

a fuzzy set of membership degrees expressed as all individual key factors;

e. f is represented as a non-zero natural number;

D is expressed as a fuzzy comprehensive evaluation result vector;

k represents the number of rows of the membership matrix;

n represents the number of columns of the membership matrix.

Preferably, the establishing a fault prediction model and predicting occurrence of the operation fault of the wind turbine at the next moment includes the following steps:

specifically, the operation data includes:

wind speed and direction: wind speed and wind direction directly influence the generated energy and the running state of the wind turbine generator.

Generating capacity: the comparison of the actual power generation amount with the expected power generation amount can help to evaluate the operating efficiency of the wind turbine.

Rotational speed and power output: the rotation speed and the power output of the wind turbine generator are key indexes of the performance of the wind turbine generator.

Temperature data: including the temperature of the critical components of the gearbox, generator, pitch system, etc.

Vibration data: the vibration level of each component of the wind turbine generator can be used for detecting abnormal conditions.

Electrical parameters: such as current, voltage, frequency, etc., reflect the electrical performance of the motor unit.

Operating state: including status information such as start-up, shut-down, failure mode, etc.

The fault history data includes:

fault type and description: classification and detailed description of specific faults.

Time and duration of failure: the specific time at which the fault occurs and the length of time it lasts.

Fault handling measures: specific measures and solutions to the faults.

And (3) maintenance record: including date of service, maintenance personnel, maintenance costs, and performance assessment after maintenance.

Part replacement record: the type of component replaced, the reason for replacement, and the time of replacement are recorded.

Comparing the operation data before and after the fault: the data before and after the fault occurs is compared to identify potential signs of the fault.

specifically, the parameter values are key mathematical variables that the model uses to predict the fault, including:

probability of failure: reflecting the probability of failure occurrence under specific conditions.

Influence factor weight: the degree of influence of different operating conditions and environmental factors (such as wind speed, temperature, vibration, etc.) on the probability of occurrence of faults.

Time threshold: a particular component or system may be more prone to failure at a point in time after a certain length of operation has been reached.

Sensitivity parameters: parameters describing the sensitivity of the wind turbine to certain variables (e.g., temperature changes, load fluctuations, etc.).

Health index decay rate: the rate at which the health of the wind turbine decays over time may be related to maintenance, frequency of use, environmental conditions, etc.

According to another embodiment of the present invention, as shown in fig. 2, there is further provided a system for evaluating the installation feasibility of a wind turbine based on a motion amplitude, the system for evaluating the installation feasibility of a wind turbine based on a motion amplitude comprising:

The data processing module 1 is used for acquiring environmental data and performance data of the wind turbine in the wind turbine installation area, and preprocessing the environmental data and the performance data of the wind turbine to obtain environmental characteristic data and performance characteristic data;

the dynamic model building module 2 is used for building a dynamic planning model of wind turbine generator installation based on the obtained environmental characteristic data and performance parameter characteristic data;

the data analysis module 3 is used for analyzing the dynamic planning model by utilizing an analysis algorithm to obtain preliminary layout data of the wind turbine installation;

The data optimization module 4 is used for comparing the obtained preliminary layout data with the known wind turbine installation layout data based on an optimization algorithm to obtain the optimal wind turbine installation layout data, and applying the optimal wind turbine installation layout data in the field;

The fault prediction module 5 is used for establishing a fault prediction model and predicting the running fault of the wind turbine generator at the next moment;

The data processing module 1 is connected with the data analysis module 3 through the dynamic model building module 2, and the data analysis module 3 is connected with the fault prediction module 5 through the data optimization module 4.

The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims

1. The method for evaluating the installation feasibility of the wind turbine generator based on the motion amplitude is characterized by comprising the following steps of:

s5, a fault prediction model is established, and the occurrence of the running fault of the wind turbine at the next moment is predicted;

The method for judging whether the wind turbine installation layout accords with a preset installation standard or not based on the optimization algorithm compares the obtained preliminary layout data with the known wind turbine installation layout data, and the method for judging whether the wind turbine installation layout accords with the preset installation standard or not and applying the wind turbine installation standard in the field comprises the following steps:

S47, judging whether the risk level of each wind turbine generator installation layout exceeds a preset safety threshold, if so, marking the wind turbine generator installation layout as high risk; if the motor group installation layout is not exceeded, the motor group installation layout of the low or medium wind risk meeting the installation standard is considered, and the motor group installation layout of the low or medium wind risk meeting the installation standard is applied in the field;

The analyzing of key factors influencing the installation layout of the wind turbine generator and the setting of corresponding evaluation levels comprise the following steps:

S423, evaluating the performance of each key factor in the installation layout of the wind turbine according to the set evaluation level;

The formula for calculating the fuzzy set and the risk evaluation matrix by the fuzzy logic method is as follows:

；

Wherein, Represented as a fuzzy operator;

a fuzzy set of membership degrees expressed as all individual key factors;

e. f is represented as a non-zero natural number;

D is expressed as a fuzzy comprehensive evaluation result vector;

k represents the number of rows of the membership matrix;

n represents the number of columns of the membership matrix.

2. The method for evaluating the installation feasibility of the wind turbine generator based on the motion amplitude according to claim 1, wherein the steps of obtaining the environmental data and the performance data of the wind turbine generator in the installation area of the wind turbine generator, and preprocessing the environmental data and the performance data of the wind turbine generator to obtain the environmental characteristic data and the performance characteristic data comprise the following steps:

3. The method for evaluating the installation feasibility of the wind turbine generator based on the motion amplitude according to claim 1, wherein the analyzing the dynamic programming model by using the analysis algorithm to obtain the preliminary layout data of the installation of the wind turbine generator comprises the following steps:

4. A method for evaluating the installation feasibility of a wind turbine generator set based on motion amplitude according to claim 3, wherein the steps of finding a globally optimal optimization agent according to a set optimization target, adding an environmental impact factor to affect the update of the optimization agent together with each group of locally optimal optimization agents and group trends comprise the following steps:

5. The method for evaluating the installation feasibility of the wind turbine generator system based on the motion amplitude according to claim 4, wherein the steps of converting the updated optimization agent through Kent mapping, and comparing the mapped optimization agent with the original optimization agent before updating according to the optimization target comprise the following steps:

6. The method for evaluating the installation feasibility of the wind turbine generator based on the motion amplitude according to claim 1, wherein the steps of establishing a fault prediction model and predicting the occurrence of the operation fault of the wind turbine generator at the next moment comprise the following steps:

7. A system for evaluating the installation feasibility of a wind turbine based on a motion amplitude, for implementing the method for evaluating the installation feasibility of a wind turbine based on a motion amplitude according to any one of claims 1 to 6, characterized in that the system for evaluating the installation feasibility of a wind turbine based on a motion amplitude comprises: