Wind power plant multi-point energy collection method and system

Abstract

The invention relates to the technical field of wind power plant intelligent control and fault management, and discloses a wind power plant multi-point energy collection method and system, and the method comprises the steps: collecting the data of a wind power plant through a sensor, and carrying out the analysis and processing; based on the analyzed and processed wind power plant data, constructing a layout model to obtain an optimal layout scheme of the wind power plant energy collection device; and after the optimal layout scheme is determined, designing a multi-layer redundant energy collection network structure, and setting redundant nodes and standby channels for each energy collection point location. The energy collecting device operates at the optimal position, and the energy collecting efficiency is remarkably improved. Meanwhile, by designing a multi-layer redundant energy collection network structure, the stability and reliability of the system are enhanced, it is ensured that when key point locations fail, redundant nodes can quickly replace tasks of the key point locations, and energy loss is avoided. And when the fault occurs or the performance is reduced, the redundant node is immediately started and the standby channel is switched, so that the fault response speed is improved, and the downtime is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control and fault management of wind farms, and in particular to a multi-point energy collection method and system for wind farms. Background Art

[0002] As the global demand for renewable energy continues to increase, wind power generation has been widely used and developed as a clean and sustainable form of energy. In the design and operation of wind farms, how to maximize the use of wind resources, improve energy collection efficiency, and ensure the reliability and stability of the system has become a key direction of technology research and development. Traditional wind farm layouts usually rely on experience and simplified models. Although they can meet the needs of energy collection to a certain extent, with the expansion of wind farm scale and the emergence of complex terrain, the limitations of traditional methods are becoming increasingly apparent. In recent years, the application of intelligent technology and big data analysis in wind farm layout optimization has provided new ideas for solving these problems. However, the existing technology still has many shortcomings in terms of the accuracy of data collection, the construction method of layout model, and the reliability of redundant design.

[0003] In the optimization of wind farm layout, the existing technology usually relies on the simple superposition of historical wind speed data and terrain data, and lacks the ability to dynamically respond to real-time environmental changes. This static optimization method cannot fully cope with the real-time changes in wind speed and wind direction, resulting in the difficulty in achieving the best energy collection efficiency. In addition, in the redundant design of energy collection points, the existing technology often only considers the response to local failures, while ignoring the overall systemic safety guarantee of the wind farm. The lag and insufficiency of the redundant design may cause the system to be unable to perform effective energy collection switching in time when a key point fails, resulting in energy loss and economic loss. In contrast, our invention collects wind farm data in real time through sensors, analyzes and processes these data, constructs a wind farm layout model, and thus develops the optimal energy collection plan. On this basis, a multi-level redundant energy collection network structure is designed to ensure that when any key point fails, the redundant node can immediately take over its task, greatly improving the reliability of the system and the overall energy collection efficiency. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: unreasonable wind farm energy collection layout, insufficient real-time environmental change response capability, redundant design and delayed fault response speed.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-point energy collection method for a wind farm, comprising:

[0007] Use sensors to collect data from wind farms and conduct analysis and processing;

[0008] Based on the analyzed and processed wind farm data, a layout model is constructed to obtain the optimal layout plan for the wind farm energy collection device;

[0009] After determining the optimal layout plan, a multi-level redundant energy collection network structure is designed, and redundant nodes and backup channels are set for each energy collection point.

[0010] As a preferred solution of the multi-point energy collection method of a wind farm described in the present invention, the sensors include LiDAR, satellite remote sensing, ultrasonic anemometer, mechanical anemometer, weather station, ADCP, temperature sensor, humidity sensor and air pressure sensor;

[0011] The data of the wind farm include terrain data, wind speed data, wind direction data, wind frequency data, wind speed duration, air density data, weather and meteorological conditions data, temperature, humidity, air pressure and extreme weather event data;

[0012] The analysis and processing includes: preprocessing the collected wind farm data; then analyzing the spatial distribution of wind speed and direction and the periodicity of wind speed changes through feature extraction and time series analysis; and finally extracting key factors affecting wind resources using a multivariate analysis method.

[0013] As a preferred solution of the multi-point energy collection method of a wind farm described in the present invention, the optimal layout solution of the energy collection device of the wind farm includes constructing a layout model using a multi-objective optimization algorithm based on the three constraints of maximizing energy collection efficiency, minimizing equipment cost and facilitating maintenance, so as to obtain the optimal layout solution of the energy collection device of the wind farm;

[0014] The formula of the layout model is expressed as:

[0015]

[0016] Among them, L opt represents the optimal layout solution, x represents the layout decision variable vector, η represents the energy conversion efficiency coefficient, E i (x i ) represents the energy collection efficiency function, v(x i ,t) represents the layout point x i The wind speed at location A varies with time t. i Indicates the layout point x i The effective wind receiving area at i ) indicates the layout point x iThe wind direction angle at the location, c(x) represents the equipment cost function, α represents the adjustment coefficient of the cost function, C k represents the infrastructure cost of the kth key facility, d(x,s k ) represents the layout point x to the kth key facility s k distance, β represents the coefficient used to adjust the distance effect, M(x,t) represents the maintenance convenience function, γ represents the adjustment coefficient of the maintenance convenience function, R l (x, t) represents the maintenance risk function of the lth maintenance point x at time t, λ1 and λ2 represent the adjustment parameters, represents the Laplace operator, V represents the integration area, T represents the maintenance time period, and w j represents the weight of the jth device, C j (x) is the installation cost function of the jth device, δ represents the adjustment coefficient of the device installation cost function, k m represents the stiffness coefficient of the mth point, ω m represents the vibration frequency of the mth point, φ j (x) represents the jth mode function at position x.

[0017] As a preferred solution of the multi-point energy collection method of the wind farm described in the present invention, wherein: the design of a multi-level redundant energy collection network structure includes, according to the wind resource distribution and energy collection efficiency of each energy collection point determined in the optimal layout plan, using the hierarchical analysis method to design an evaluation function to identify which points are key points;

[0018] Construct a weight matrix A that comprehensively considers wind resource distribution and energy collection efficiency, where each element a ij The formula is expressed as:

[0019]

[0020] Based on the weight matrix, the evaluation function of the key points is constructed, and the formula is expressed as:

[0021]

[0022] Among them, A represents the weight matrix of wind resource distribution and energy collection efficiency, a ij represents the elements in the matrix, t1 represents the start time of the integration, t2 represents the end time of the integration, W i (t) represents the wind resource distribution function of the i-th point at time t, E i (t) represents the energy collection efficiency of the i-th point at time t, P i (t) represents the power output of the i-th point at time t, T ij represents the wind resource transmission time between the i-th and j-th points, Sk Represents the critical evaluation function of the k-th point; is the element in the kth row and ith column of the inverse matrix of matrix A; n represents the total number of points, and exp represents the exponential function;

[0023] S k The value threshold is from 0 to positive infinity. The larger the value, the more important the energy collection point is.

[0024] As a preferred solution of the multi-point energy collection method of the wind farm described in the present invention, wherein: the design of the multi-level redundant energy collection network structure also includes, for the key points, selecting the positions of the redundant nodes according to the characteristics of the terrain and wind speed, ensuring that they can cover the influence range of the key points, and when any key point fails, the redundant nodes can immediately take over its energy collection task;

[0025] The selecting of the position of the redundant node includes constructing a redundant node position function by combining the Voronoi diagram and the Delaunay triangulation, and the formula is expressed as:

[0026]

[0027] Among them, L r Represents the redundant node position, p j represents the location of redundant nodes, N represents the set of redundant nodes, A j Indicates the key point p k The scope of influence, ω t (x) represents the wind speed function at time t, h(x) represents the terrain influence function, represents the modulus of terrain gradient;

[0028] Design a redundant node coverage evaluation function to evaluate the coverage effect of redundant nodes on key points. The formula is expressed as:

[0029]

[0030] Among them, C r Represents redundant node p r The coverage evaluation value, V(p k ) represents the Voronoi region area of ​​the key point, ∥p k -p r ∥ indicates the distance between the key point and the redundant node;

[0031] C r The value range of is from 0 to positive infinity. The higher the value, the better the coverage of key points by redundant nodes.

[0032] A backup channel is designed for each energy collection point so that when a failure occurs at the point, energy can be transmitted to the control center or energy storage system through the backup channel.

[0033] As a preferred solution of the multi-point energy collection method of the wind farm described in the present invention, wherein: the design of a multi-level redundant energy collection network structure also includes combining redundant nodes and backup channels to form a multi-level redundant structure;

[0034] The multi-level redundancy structure should include primary redundancy and secondary redundancy;

[0035] Build a monitoring model to monitor the operating status of energy collection points in real time. When a fault or performance degradation is detected, immediately start the redundant node and switch to the backup channel.

[0036] The monitoring model formula is expressed as:

[0037] Where R(t) represents the accumulated fault detection value, y(τ) represents the actual output of the system at time τ, Represents the output predicted by the model, α represents the attenuation coefficient, C represents the weight matrix, and y(τ) represents the output vector.

[0038] As a preferred solution of the wind farm multi-point energy collection method described in the present invention, the design of a multi-level redundant energy collection network structure also includes, based on the results of the monitoring model, using a decision function to determine the timing of switching to the backup channel

[0039]

[0040] Among them, γ represents the fault switching threshold, T represents the time interval, and R(t) represents the accumulated fault detection value;

[0041] The value range of R(t) is from negative infinity to positive infinity. A positive value indicates a fault or performance degradation, while a negative value or close to zero indicates that the system is operating normally.

[0042] The value range of S(t) is from 0 to 1, where 1 indicates triggering a switch and 0 indicates maintaining the status quo.

[0043] A multi-point energy collection system for a wind farm, wherein:

[0044] The data collection and analysis module uses sensors to collect wind farm data and analyzes and processes the data;

[0045] The layout model building module builds the layout model of the wind farm based on the analyzed and processed data to obtain the optimal layout plan of the energy collection device;

[0046] The multi-level redundant network design module designs a multi-level redundant energy collection network structure after determining the optimal layout plan, and sets redundant nodes and backup channels for each energy collection point.

[0047] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0048] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0049] Beneficial effects of the present invention: The multi-point energy collection method for wind farms provided by the present invention collects and analyzes wind farm data in real time, constructs an optimal layout model, ensures that the energy collection device operates in the optimal position, and significantly improves the energy collection efficiency. At the same time, by designing a multi-level redundant energy collection network structure, the stability and reliability of the system are enhanced, ensuring that when key points fail, redundant nodes can quickly take over their tasks to avoid energy loss. In addition, the present invention adopts an intelligent control model to monitor the operating status of the system in real time, and immediately starts redundant nodes and switches to backup channels when a fault occurs or performance degrades, thereby improving the fault response speed and reducing downtime. The invention can also dynamically respond to the complex terrain and real-time environmental changes of the wind farm, optimize the layout and redundant design, and ensure the long-term stable operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0051] Figure 1 This is an overall flow chart of a multi-point energy collection method for a wind farm provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0053] Example 1, reference Figure 1, as an embodiment of the present invention, provides a multi-point energy collection method for a wind farm, comprising:

[0054] S1: Use sensors to collect wind farm data and analyze and process it.

[0055] Sensors include, LiDAR, satellite remote sensing, ultrasonic anemometer, mechanical anemometer, weather station, ADCP, temperature sensor, humidity sensor and air pressure sensor;

[0056] The data of the wind farm include terrain data, wind speed data, wind direction data, wind frequency data, wind speed duration, air density data, weather and meteorological conditions data, temperature, humidity, air pressure and extreme weather event data;

[0057] The analysis and processing includes: preprocessing the collected wind farm data; then analyzing the spatial distribution of wind speed and direction and the periodicity of wind speed changes through feature extraction and time series analysis; and finally extracting key factors affecting wind resources using a multivariate analysis method.

[0058] Furthermore, detailed data of the wind farm, including wind speed, wind direction, temperature, humidity, etc., are collected in real time through a variety of sensors. Through the collection of these data, the system can fully grasp the actual operating conditions of the wind farm. Using high-precision sensors to obtain real-time data can ensure that the collected information is accurate and reliable, providing a solid foundation for subsequent analysis and optimization. Preprocessing and feature extraction in the data analysis process can remove noise and outliers, ensure the purity of the data, and make the analysis results more accurate. This step lays the foundation for the energy collection optimization of the entire wind farm, ensuring that the construction of the layout model is based on a reliable data source, so that the subsequent layout and redundancy design are more scientific and reasonable.

[0059] S2: Based on the analyzed and processed wind farm data, a layout model is constructed to obtain the optimal layout plan for the wind farm energy collection device.

[0060] The optimal layout of wind farm energy collection devices includes three constraints: maximizing energy collection efficiency, minimizing equipment cost, and facilitating maintenance. A layout model is constructed using a multi-objective optimization algorithm to obtain the optimal layout of wind farm energy collection devices.

[0061] The formula of the layout model is expressed as:

[0062]

[0063] Among them, L opt represents the optimal layout solution, x represents the layout decision variable vector, η represents the energy conversion efficiency coefficient, E i (x i) represents the energy collection efficiency function, v(x i ,t) represents the layout point x i The wind speed at location A varies with time t. i Indicates the layout point x i The effective wind receiving area at i ) indicates the layout point x i The wind direction angle at the location, c(x) represents the equipment cost function, α represents the adjustment coefficient of the cost function, C k represents the infrastructure cost of the kth key facility, d(x,s k ) represents the layout point x to the kth key facility s k distance, β represents the coefficient used to adjust the distance effect, M(x,t) represents the maintenance convenience function, γ represents the adjustment coefficient of the maintenance convenience function, R l (x, t) represents the maintenance risk function of the lth maintenance point x at time t, λ1 and λ2 represent the adjustment parameters, represents the Laplace operator, V represents the integration area, T represents the maintenance time period, and w j represents the weight of the jth device, C j (x) is the installation cost function of the jth device, δ represents the adjustment coefficient of the device installation cost function, k m represents the stiffness coefficient of the mth point, ω m represents the vibration frequency of the mth point, φ j (x) represents the jth mode function at position x.

[0064] Furthermore, the processed wind farm data is used to construct the optimal layout model of the energy collection device through a multi-objective optimization algorithm. Through a refined layout model, it can be ensured that the energy collection device is placed in the optimal position to maximize the use of wind resources while reducing equipment and maintenance costs. The use of a multi-objective optimization algorithm enables the layout design to balance multiple complex constraints and achieve a global optimal solution. This step significantly improves the overall energy collection efficiency of the wind farm, optimizes resource allocation, reduces energy waste and operating costs, and is of great significance for the planning and construction of large-scale wind farms.

[0065] S3: After determining the optimal layout scheme, a multi-level redundant energy collection network structure is designed, and redundant nodes and backup channels are set for each energy collection point.

[0066] Designing a multi-level redundant energy collection network structure includes designing an evaluation function using the hierarchical analysis method according to the wind resource distribution and energy collection efficiency of each energy collection point determined in the optimal layout plan, and identifying which points are key points;

[0067] Construct a weight matrix A that comprehensively considers wind resource distribution and energy collection efficiency, where each element a ij The formula is expressed as:

[0068]

[0069] Based on the weight matrix, the evaluation function of the key points is constructed, and the formula is expressed as:

[0070]

[0071] Among them, A represents the weight matrix of wind resource distribution and energy collection efficiency, a ij represents the elements in the matrix, t1 represents the start time of the integration, t2 represents the end time of the integration, W i (t) represents the wind resource distribution function of the i-th point at time t, E i (t) represents the energy collection efficiency of the i-th point at time t, P i (t) represents the power output of the i-th point at time t, T ij represents the wind resource transmission time between the i-th and j-th points, S k Represents the critical evaluation function of the k-th point; is the element in the kth row and ith column of the inverse matrix of matrix A; n represents the total number of points, and exp represents the exponential function;

[0072] S k The value threshold is from 0 to positive infinity. The larger the value, the more important the energy collection point is.

[0073] For the key points, the positions of the redundant nodes are selected according to the characteristics of the terrain and wind speed to ensure that they can cover the influence range of the key points. When any key point fails, the redundant nodes can immediately take over its energy collection task;

[0074] The selecting of the position of the redundant node includes constructing a redundant node position function by combining the Voronoi diagram and the Delaunay triangulation, and the formula is expressed as:

[0075]

[0076] Among them, L r Represents the redundant node position, p j represents the location of redundant nodes, N represents the set of redundant nodes, A j Indicates the key point p k The scope of influence, ω t (x) represents the wind speed function at time t, h(x) represents the terrain influence function, represents the modulus of terrain gradient;

[0077] Design a redundant node coverage evaluation function to evaluate the coverage effect of redundant nodes on key points. The formula is expressed as:

[0078]

[0079] Among them, C r Represents redundant node p r The coverage evaluation value, V(p k ) represents the Voronoi region area of ​​the key point, ∥p k -p r ∥ indicates the distance between the key point and the redundant node;

[0080] C r The value range of is from 0 to positive infinity. The higher the value, the better the coverage of key points by redundant nodes.

[0081] A backup channel is designed for each energy collection point so that when a failure occurs at the point, energy can be transmitted to the control center or energy storage system through the backup channel.

[0082] Combine redundant nodes and backup channels to form a multi-level redundant structure;

[0083] The multi-level redundancy structure should include primary redundancy and secondary redundancy;

[0084] Build a monitoring model to monitor the operating status of energy collection points in real time. When a fault or performance degradation is detected, immediately start the redundant node and switch to the backup channel.

[0085] The monitoring model formula is expressed as:

[0086]

[0087] Where R(t) represents the accumulated fault detection value, y(τ) represents the actual output of the system at time τ, Represents the output predicted by the model, α represents the attenuation coefficient, C represents the weight matrix, and y(τ) represents the output vector.

[0088] Based on the results of the monitoring model, a decision function is used to determine the timing of switching to the backup channel.

[0089]

[0090] Among them, γ represents the fault switching threshold, T represents the time interval, and R(t) represents the accumulated fault detection value;

[0091] The value range of R(t) is from negative infinity to positive infinity. A positive value indicates a fault or performance degradation, while a negative value or close to zero indicates that the system is operating normally.

[0092] The value range of S(t) is from 0 to 1, where 1 indicates triggering a switch and 0 indicates maintaining the status quo.

[0093] By designing a multi-level redundant structure, the impact range of key points can be effectively covered. When any point fails, the redundant node can quickly take over its energy collection task to ensure the high reliability and stability of the system. At the same time, the design of the backup channel can ensure that the energy can be smoothly transmitted to the control center or energy storage system. It greatly improves the system's fault tolerance and response speed, reduces energy loss caused by failures, and ensures that the wind farm can operate stably and long-term in a complex natural environment. Through redundant design, the system can maintain efficient operation under extreme conditions, improving the overall safety and economic benefits of the wind farm.

[0094] On the other hand, this embodiment also provides a wind farm multi-point energy collection system, which includes:

[0095] The data collection and analysis module uses sensors to collect data from wind farms and analyzes and processes the data.

[0096] The layout model building module builds the layout model of the wind farm based on the analyzed and processed data to obtain the optimal layout plan of the energy collection device.

[0097] The multi-level redundant network design module designs a multi-level redundant energy collection network structure after determining the optimal layout plan, and sets redundant nodes and backup channels for each energy collection point.

[0098] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0099] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0100] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0101] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0102] In Example 2, a real wind farm was selected as the test object. The wind farm has complex terrain and uneven wind speed distribution. The test first collected data such as wind speed, wind direction, temperature, humidity, and real-time output power of the energy collection device for 6 months through high-precision sensors installed at various key locations in the wind farm. The frequency of data collection was once per minute to ensure that sufficient real-time information was obtained for accurate analysis.

[0103] After data collection was completed, all data were preprocessed, including denoising, abnormal data filtering, and data normalization. Then, based on the processed data, the K-means clustering algorithm and principal component analysis (PCA) technology were used to conduct an in-depth analysis of the wind speed distribution and terrain characteristics of the wind farm to identify the areas with the richest wind resources in the wind farm and determine the key layout points of the energy collection device. By combining multiple factors such as wind speed distribution, terrain height differences, and wind direction change patterns, a wind farm layout model was constructed to determine the optimal energy collection device layout plan.

[0104] After the layout model was determined, a multi-level redundant energy collection network structure was further designed. Redundant nodes and backup channels were set for each key point, and the positions of the redundant nodes were optimized by genetic algorithm (GA) to ensure that these nodes can effectively cover the influence range of the key points. When a key point fails or the energy collection efficiency drops significantly, the redundant node can be immediately started and take over its energy collection task. In order to verify the stability of the system, a variety of failure scenarios were simulated, such as failure of key points, sudden changes in wind speed, etc., and the response time and energy collection efficiency of the redundant network were tested. The entire experiment lasted for 4 months, during which the changes in various parameters were recorded in detail, and continuous monitoring and data analysis were carried out. The experimental results are shown in Table 1.

[0105] Table 1 Experimental data table

[0106]

[0107] By analyzing the above test data, it can be seen that the multi-point energy collection method designed by the present invention has shown significant innovation and advantages in many aspects. First, the experimental results show that under different environmental conditions, the energy collection efficiency of key points has been significantly improved. The relationship between the average wind speed and the output power shows that the energy collection device layout scheme based on layout model optimization can effectively capture wind resources and maximize energy conversion efficiency. Compared with the traditional static layout method, the output power after the optimized layout is generally increased by about 15%, which proves the effectiveness of the K-means clustering algorithm and principal component analysis technology used in the present invention in layout optimization.

[0108] Secondly, in terms of fault response time and redundant node startup rate, the table data shows that when a redundant node fails at a key point, it can respond and start quickly within 0.3 to 0.6 seconds. The redundant node position optimized by the genetic algorithm enables the system to show extremely high reliability and rapid response capabilities when dealing with sudden failures. The startup rate of redundant nodes and the switching rate of backup channels reached more than 95%, which means that even in extreme cases, the system can still maintain efficient operation, greatly reducing the energy loss caused by failures.

[0109] Finally, through the analysis of the efficiency of the backup channel, it was found that the redundant network can smoothly switch to the backup channel in 95% of cases, ensuring the continuity of the energy collection task. This shows that the present invention has significant innovation and technical advantages in dealing with complex terrain and changing environments. Compared with the prior art, the present invention not only improves the energy collection efficiency of the system, but also significantly enhances the fault tolerance and stability of the system through intelligent redundant design, providing a solid guarantee for the long-term stable operation of the wind farm. On the whole, the present invention successfully solves the technical problems of unreasonable layout of existing wind farms and delayed redundant response through precise data collection, analysis and processing, and intelligent optimization, showing strong practical value and application prospects.

[0110] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-point energy collection method for a wind farm, characterized in that: include: Use sensors to collect data from wind farms and conduct analysis and processing; Based on the analyzed and processed wind farm data, a layout model is constructed to obtain the optimal layout plan for the wind farm energy collection device; After determining the optimal layout plan, a multi-level redundant energy collection network structure is designed, and redundant nodes and backup channels are set for each energy collection point.

2. The multi-point energy collection method for a wind farm as claimed in claim 1, characterized in that: The sensors include LiDAR, satellite remote sensing, ultrasonic anemometer, mechanical anemometer, weather station, ADCP, temperature sensor, humidity sensor and air pressure sensor; The data of the wind farm include terrain data, wind speed data, wind direction data, wind frequency data, wind speed duration, air density data, weather and meteorological conditions data, temperature, humidity, air pressure and extreme weather event data; The analysis and processing includes: preprocessing the collected wind farm data; then analyzing the spatial distribution of wind speed and direction and the periodicity of wind speed changes through feature extraction and time series analysis; and finally extracting key factors affecting wind resources using a multivariate analysis method.

3. The multi-point energy collection method for a wind farm as claimed in claim 2, characterized in that: The optimal layout of wind farm energy collection devices includes three constraints: maximizing energy collection efficiency, minimizing equipment cost, and facilitating maintenance. A layout model is constructed using a multi-objective optimization algorithm to obtain the optimal layout of wind farm energy collection devices. The formula of the layout model is expressed as: Among them, L opt represents the optimal layout solution, x represents the layout decision variable vector, η represents the energy conversion efficiency coefficient, E i (x i ) represents the energy collection efficiency function, v(x i ,t) represents the layout point x i The wind speed at location A varies with time t. i Indicates the layout point x i The effective wind receiving area at i ) indicates the layout point x i The wind direction angle at the location, c(x) represents the equipment cost function, α represents the adjustment coefficient of the cost function, C k represents the infrastructure cost of the kth key facility, d(x,s k ) represents the layout point x to the kth key facility s k distance, β represents the coefficient used to adjust the distance effect, M(x,t) represents the maintenance convenience function, γ represents the adjustment coefficient of the maintenance convenience function, R l (x, t) represents the maintenance risk function of the lth maintenance point x at time t, λ1 and λ2 represent the adjustment parameters, represents the Laplace operator, V represents the integration area, T represents the maintenance time period, and w j represents the weight of the jth device, C j (x) is the installation cost function of the jth device, δ represents the adjustment coefficient of the device installation cost function, k m represents the stiffness coefficient of the mth point, ω m represents the vibration frequency of the mth point, φ j (x) represents the jth mode function at position x.

4. The method for collecting energy at multiple points in a wind farm according to claim 3, characterized in that: The design of the multi-level redundant energy collection network structure includes designing an evaluation function using a hierarchical analysis method according to the wind resource distribution and energy collection efficiency of each energy collection point determined in the optimal layout plan to identify which points are key points; Construct a weight matrix A that comprehensively considers wind resource distribution and energy collection efficiency, where each element a ij The formula is expressed as: Based on the weight matrix, the evaluation function of the key points is constructed, and the formula is expressed as: Among them, A represents the weight matrix of wind resource distribution and energy collection efficiency, a ij represents the elements in the matrix, t1 represents the start time of the integration, t2 represents the end time of the integration, W i (t) represents the wind resource distribution function of the i-th point at time t, E i (t) represents the energy collection efficiency of the i-th point at time t, P i (t) represents the power output of the i-th point at time t, T ij represents the wind resource transmission time between the i-th and j-th points, S k Represents the critical evaluation function of the k-th point; is the element in the kth row and ith column of the inverse matrix of matrix A; n represents the total number of points, and exp represents the exponential function; S k The value threshold is from 0 to positive infinity. The larger the value, the more important the energy collection point is.

5. The multi-point energy collection method for a wind farm as claimed in claim 4, characterized in that: The design of the multi-level redundant energy collection network structure also includes, for the key points, selecting the positions of the redundant nodes according to the characteristics of the terrain and wind speed, ensuring that they can cover the influence range of the key points, and when any key point fails, the redundant nodes can immediately take over its energy collection task; The selecting of the position of the redundant node includes constructing a redundant node position function by combining the Voronoi diagram and the Delaunay triangulation, and the formula is expressed as: Among them, L r Represents the redundant node position, p j represents the location of redundant nodes, N represents the set of redundant nodes, A j Indicates the key point p k The scope of influence, ω t (x) represents the wind speed function at time t, h(x) represents the terrain influence function, represents the modulus of terrain gradient; Design a redundant node coverage evaluation function to evaluate the coverage effect of redundant nodes on key points. The formula is expressed as: Among them, C r Represents redundant node p r The coverage evaluation value, V(p k ) represents the Voronoi region area of ​​the key point, ∥p k -p r ∥ indicates the distance between the key point and the redundant node; C r The value range of is from 0 to positive infinity. The higher the value, the better the coverage of key points by redundant nodes. A backup channel is designed for each energy collection point so that when a failure occurs at the point, energy can be transmitted to the control center or energy storage system through the backup channel.

6. The multi-point energy collection method of a wind farm as claimed in claim 5, characterized in that: The design of a multi-level redundant energy harvesting network structure also includes combining redundant nodes and backup channels to form a multi-level redundant structure; The multi-level redundancy structure should include primary redundancy and secondary redundancy; Build a monitoring model to monitor the operating status of energy collection points in real time. When a fault or performance degradation is detected, immediately start the redundant node and switch to the backup channel. The formula of the monitoring model is expressed as: Where R(t) represents the accumulated fault detection value, y(τ) represents the actual output of the system at time τ, Represents the output predicted by the model, α represents the attenuation coefficient, C represents the weight matrix, and y(τ) represents the output vector.

7. The multi-point energy collection method for a wind farm as claimed in claim 6, characterized in that: The design of the multi-level redundant energy harvesting network structure also includes, based on the results of the monitoring model, using a decision function to determine the timing of switching the backup channel. Among them, γ represents the fault switching threshold, T represents the time interval, and R(t) represents the accumulated fault detection value; The value range of R(t) is from negative infinity to positive infinity. A positive value indicates a fault or performance degradation, while a negative value or close to zero indicates that the system is operating normally. The value range of S(t) is from 0 to 1, where 1 indicates triggering a switch and 0 indicates maintaining the status quo.

8. A multi-point energy collection system for a wind farm, characterized by: The data collection and analysis module uses sensors to collect wind farm data and analyzes and processes the data; The layout model building module builds the layout model of the wind farm based on the analyzed and processed data to obtain the optimal layout plan of the energy collection device; The multi-level redundant network design module designs a multi-level redundant energy collection network structure after determining the optimal layout plan, and sets redundant nodes and backup channels for each energy collection point.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, steps of a method for multi-point energy collection in a wind farm are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for multi-point energy collection in a wind farm are implemented.

Images