Breeze power generation system and method and related components thereof

Abstract

The invention discloses a breeze power generation system and method and related assemblies thereof, and relates to the field of breeze power generation, and the breeze power generation method comprises the following steps: step 1, deploying and initializing all parts, and completing the installation of an air duct, an air guide piece, a Venturi tube and a spiral blade; 2, wind direction optimization treatment is conducted through a wind guide piece, natural breeze is introduced into the wind cylinder to be converted into vertically-downward airflow, the airflow interacts with spiral blades in the wind cylinder and then is converted into mechanical energy, and residual breeze enters the Venturi tube and then interacts with spiral blades in the Venturi tube and then is converted into mechanical energy; through comprehensive analysis of historical data and real-time data, a power generation strategy is automatically adjusted in combination with an intelligent algorithm, potential trend changes and abnormal conditions are rapidly identified, then an operation strategy is responded and adjusted in time, breeze energy can be more effectively captured and converted through design optimization of airflow guiding and conversion, the power generation capacity is maximized, and the power generation efficiency is improved. And challenges of different meteorological conditions can be handled.

Description

Technical Field

[0001] The present invention relates to the technical field of micro-wind power generation, and in particular to a micro-wind power generation system, method and related components thereof. Background Art

[0002] The wind power generation system reduces dependence on fossil fuels and promotes the diversification of energy composition by utilizing wind energy, a renewable resource. It can be flexibly deployed in cities, rural areas and remote areas to adapt to local wind conditions, realize distributed power generation and improve the coverage of power supply. The impeller structures of existing breeze generators are generally divided into two categories: three-blade type and tile-shaped type. The three-blade type has a smaller windward surface area, a larger interval between two adjacent blades, and low efficiency. When the breeze blows toward the windward surface of one of the blades, thereby driving the entire impeller to rotate, the other two blades become a reaction force to prevent the impeller from rotating. This is because the two blades, when rotating with the impeller, have the windward surface counter-impacting the breeze, which makes the rotation of the impeller difficult. The reverse force of the windward surface of the tile-shaped type is relatively small, but this problem still exists. In the above two types of impeller structures, the breeze blows toward the windward surface of the blade head-on, and the overall energy conversion efficiency is low, and energy capture under natural breeze conditions is not fully considered; Existing technologies perform poorly under changing meteorological conditions. They often lack real-time monitoring and analysis and automatic adjustment mechanisms, rely on fixed adjustment mechanisms or strategies, and find it difficult to respond intelligently to environmental changes, resulting in fluctuations in power generation capacity. They often only focus on abnormal values ​​that violate standard thresholds, while ignoring fluctuation trends within standard thresholds, which in turn affects the accurate assessment of system status and timely prediction of potential faults. They are unable to respond and repair faults in a timely manner, and are not systematic enough in data storage and analysis, making it difficult to trace historical data or conduct long-term performance analysis. Summary of the invention

[0003] (I) Technical problems to be solved: In view of the above-mentioned shortcomings of the prior art, the present invention provides a micro-wind power generation system, method and related components thereof, which can effectively solve the problems of the prior art.

[0004] (II) Technical solution: To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention discloses a breeze power generation method, comprising the following steps: Step 1: Deploy and initialize all components, and complete the installation of the wind tube, air guide, venturi tube and spiral blades; Step 2: The wind direction is optimized through the wind guide, and the natural breeze is introduced into the wind tube to be converted into a vertical downward airflow, which is converted into mechanical energy after interacting with the spiral blades inside the wind tube. The residual breeze enters the Venturi tube and is converted into mechanical energy after interacting with the spiral blades inside the Venturi tube. The mechanical energy generated by the two spiral blades is converted into electrical energy and stored; Step 3: Continuously collect the status and environmental data of each component, obtain the speed, vibration, inclination, position information and energy transmission status of each component, and obtain wind speed, temperature, humidity and rainfall; Step 4: Set up standard thresholds for data collection, analyze the energy flow status in real-time data, identify normal fluctuations and abnormal trends in the current cycle, and summarize the information into trend data; Step 5: Build a machine learning model, train it based on the collected historical trend data and analyze the current real-time data, predict the abnormal state in the preset future period, mark the future abnormal targets, and conduct retroactive analysis on the data that currently violates the threshold and mark the current abnormal targets; Step 6: Combine the prediction results and traceability data to output adjustment strategies for the marked future and current anomaly targets; Step 7: Receive the adjustment strategy and conduct simulation operation, evaluate the effectiveness of the simulation operation results, and once the strategy is verified, feed it back to the corresponding target for application; Step 8: The feedback data is used as a reference for automatic adjustment of the standard threshold. When the feedback data exceeds the preset threshold, the standard threshold is automatically adjusted.

[0005] Furthermore, the machine learning model in step 5 is constructed by a long short-term memory network algorithm, combining the characteristics of a multi-layer neural network and a time series to represent the environmental meteorological data and the power generation system status data, and the calculation formula is: ; In the formula, represents the predicted value at time t, The feature vector representing the wind speed, temperature, humidity and rainfall collected at time t, as well as the speed, vibration, inclination and position information of each component, represents the hidden state at time t−1, indicating the state information of the system before that time point, R represents the model parameters, including the weights and biases of all neurons, Represents the error term, which represents the error between the model prediction result and the actual observation value.

[0006] Furthermore, the calculation logic of the calculation formula is: a. Obtain characteristic data of current weather and system status , the hidden state at the previous time point Introducing current calculations and combining historical memory to improve current predictions; b. Input data and historical hidden states Generate the output of the model through the forward propagation process of the deep learning model; c. Finally, the model outputs a prediction result , represents the possible future value under the current environment and historical status; d. Evaluate the accuracy of the model and adjust the model parameters by comparing the predicted results with the actual observed results.

[0007] A breeze power generation system, comprising: The control module is used as the management host to edit and issue various functional modules and module control instructions; The conversion module is used to deploy the wind tube, two spiral blades, an air guide and a venturi tube. The air guide is installed at the air inlet of the wind tube. A spiral blade is rotatably connected to the inside of the wind tube. The venturi tube is installed at the air outlet of the wind tube. Another spiral blade is rotatably connected to the inside of the venturi tube. The natural breeze is converted into a vertical downward airflow through the air guide, so that the spiral blade in the wind tube rotates to generate an axial and parallel airflow. The remaining breeze enters the venturi tube to accelerate and rotate the spiral blade inside it. The energy storage module is used to receive the mechanical energy generated by the rotation of the two spiral blades in the conversion module and convert the mechanical energy into electrical energy for storage; A collection unit, used to collect environmental meteorological data in the current power generation cycle, hardware position and posture data in the conversion module, hardware position and posture data in the energy storage module, and power transmission and storage status data in the energy storage module according to a preset period; A setting unit, used for setting a standard threshold scheme for data collection and receiving instructions for adaptive adjustment of the scheme; The trend identification module is used to analyze the data collected by the collection unit, evaluate the energy flow status, identify and record the normal fluctuations within the standard threshold and the threshold violations, and summarize them into trend data; The anomaly prediction module is used to build a machine learning model, train based on historical trend data, analyze current real-time trend data, predict anomaly data within a preset period in the future, and trace the data that violates the threshold and analyze the cause of the target anomaly; The adjustment module is used to combine the prediction and traceability results to output the adjustment strategy for the specified target; The early warning module is used to issue alarms to targets that currently violate the threshold and targets that are predicted to be abnormal in the future, and provide feedback to the control module; The simulation module is used to simulate the adjustment strategy output by the adjustment module and conduct availability evaluation. After verification, the strategy is submitted to the specified target.

[0008] Furthermore, the control module is interactively connected to a storage module via a wireless network, and the storage module is used to store all collected and analyzed data, classify them according to preset rules, and upload them to a cloud database synchronously.

[0009] Furthermore, the acquisition unit is deployed with submodules at the lower level, including: a power acquisition module, a posture acquisition module and an environment acquisition module. The posture acquisition module and the environment acquisition module are interactively connected with the conversion module through a wireless network, and the power acquisition module is interactively connected with the energy storage module through a wireless network, wherein: The power collection module is used to collect and analyze the power conversion and storage data of the energy storage module to the conversion module; The posture acquisition module is used to monitor the speed and vibration data of each component of the conversion module and identify the tilt and position change status; The environmental collection module is used to collect wind, rainfall, temperature and humidity data within the current preset range.

[0010] Furthermore, the setting unit has submodules deployed at the lower level, including: a threshold module, an adaptation module and a configuration module, and the threshold module, the adaptation module and the configuration module are interactively connected through a wireless network, wherein: The threshold module is used to customize the standard threshold of the acquisition unit. When the collected data hits this range, it is considered a normal value, otherwise it is an abnormal value; The adaptation module is used to determine whether to adjust the current standard threshold based on the feedback data of the simulation module on the availability evaluation of the adjustment plan. If it is determined to be yes, the standard threshold in the current state is automatically adjusted according to the preset rules. Otherwise, the initial standard threshold of the threshold module is maintained; The configuration module is used to update the threshold data based on a preset period and submit it to the acquisition unit for execution.

[0011] Furthermore, the management and control module is interactively connected to the conversion module and the energy storage module through a wireless network, the acquisition unit is interactively connected to the setting unit and the trend identification module through a wireless network, the abnormal prediction module is interactively connected to the trend identification module, the adjustment module and the early warning module through a wireless network, the simulation module is interactively connected to the adjustment module through a wireless network, and the simulation module is connected to the conversion module and the setting unit through an electrical medium.

[0012] A breeze power generation assembly, comprising: speed and vibration sensors respectively installed on a wind tube, a spiral blade and a wind guide for collecting vibration and speed, and a plurality of meteorological sensors for collecting meteorological data within a preset range; Memory for storing computer programs; The processor is used to perform a micro-wind power generation method when executing the computer program.

[0013] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a micro-wind power generation method is implemented.

[0014] (III) Beneficial effects: Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects: 1. Through real-time collection and monitoring of meteorological conditions and continuous tracking of the status of each component of the power generation system, through comprehensive analysis of historical data and real-time data, combined with intelligent algorithms to automatically adjust the power generation strategy, potential trend changes and abnormal situations can be quickly identified, and then timely response and adjustment of operation strategies can be made, thereby improving power generation stability and reducing dependence on traditional fixed strategies. This enables the system to dynamically adapt to different environmental changes and ensure efficient power generation under changing climate conditions.

[0015] 2. Combined with threshold setting and adjustment, it not only pays attention to abnormal conditions outside the standard threshold, but also considers the fluctuation trend within the standard threshold. Through the predictive ability of the machine learning model, the system can detect slight trend changes in real time, thereby preventing potential failures early. By combining artificial intelligence and machine learning, the data collection, analysis and decision-making processes of the power generation system are automated to reduce human intervention. This improvement in the level of intelligence enables the system to make autonomous adjustments during operation, simulate autonomous adjustment strategies, confirm their availability, and use simulation feedback as the basis for adjusting the standard threshold, further improving operational efficiency and reliability.

[0016] 3. The use of wind guides, wind tubes, venturi tubes and optimized spiral blades can effectively capture breezes and convert them into mechanical energy. This design can increase the kinetic energy of the airflow under low wind speed conditions, achieve one-time wind collection and two-time power generation, thereby improving the overall energy conversion efficiency. Through the design optimization of airflow guidance and conversion, the system can more effectively capture and convert breeze energy, maximize the power generation capacity, and meet the challenges under different meteorological conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of a process of a breeze power generation method in the present invention; Figure 2 A schematic diagram of a micro-wind power generation system in the present invention; Figure 3 It is a three-dimensional structural diagram of the air duct in the present invention; Figure 4 It is a three-dimensional structural diagram of the spiral blade in the present invention; Figure 5 It is a three-dimensional structural diagram of the air guide member in the present invention; Figure 6 It is a front view cross-sectional structural diagram of the air cylinder, air guide, venturi tube and spiral blade in the present invention; Figure 7 It is a front view cross-sectional structural diagram of the Venturi tube and spiral blades in the present invention.

[0019] The numbers in the figure represent respectively, 1. Management and control module; 2. Conversion module; 3. Energy storage module; 4. Collection unit; 41. Power collection module; 42. Posture collection module; 43. Environment collection module; 5. Setting unit; 51. Threshold module; 52. Adaptation module; 53. Configuration module; 6. Trend identification module; 7. Abnormal prediction module; 8. Adjustment module; 9. Early warning module; 10. Simulation module; 11. Storage module. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0021] The present invention will be further described below in conjunction with the embodiments.

[0022] Embodiment 1: A breeze power generation method of this embodiment, such as Figure 1-Figure 7 As shown, the following steps are included: Step 1: Deploy and initialize all components, and complete the installation of the wind tube, air guide, venturi tube and spiral blades; Step 2: The wind direction is optimized through the wind guide, and the natural breeze is introduced into the wind tube to be converted into a vertical downward airflow, which is converted into mechanical energy after interacting with the spiral blades inside the wind tube. The residual breeze enters the Venturi tube and is converted into mechanical energy after interacting with the spiral blades inside the Venturi tube. The mechanical energy generated by the two spiral blades is converted into electrical energy and stored; Step 3: Continuously collect the status and environmental data of each component, obtain the speed, vibration, inclination, position information and energy transmission status of each component, and obtain wind speed, temperature, humidity and rainfall; Step 4: Set up standard thresholds for data collection, analyze the energy flow status in real-time data, identify normal fluctuations and abnormal trends in the current cycle, and summarize the information into trend data; Step 5: Build a machine learning model, train it based on the collected historical trend data and analyze the current real-time data, predict the abnormal state in the preset future period, mark the future abnormal targets, and conduct retroactive analysis on the data that currently violates the threshold and mark the current abnormal targets; The machine learning model is constructed through the long short-term memory network algorithm, combining the characteristics of multi-layer neural network and time series to represent environmental meteorological data and power generation system status data. The calculation formula is: ; In the formula, represents the predicted value at time t, The feature vector representing the wind speed, temperature, humidity and rainfall collected at time t, as well as the speed, vibration, inclination and position information of each component. The feature data is used to capture the key information of the current environment and status of the system; Represents the hidden state at time t-1, indicating the state information of the system before that time point. It is transmitted through the hidden layer of the long short-term memory network, and contains the memory or context information of the model at the previous time point, reflecting the previous state of the system. This mechanism allows the model to use historical data to influence the current prediction and capture the dynamic changes in time series data. R represents the model parameters, including the weights and biases of all neurons, which are used to adjust the information transmission of the model. The model parameters are obtained through training, so that the model can learn the complex relationship between features. The optimization of parameters is carried out by comparing the difference between the actual value and the predicted value through the loss function. represents the error term, which indicates the error between the model prediction result and the actual observation value, and is usually assumed to be normally distributed; function f is the core of the deep learning model, which indicates how the model responds to the input Processed to generate predictions ,This function includes multiple layers of neural networks, each layer performs nonlinear transformation to enhance the expressiveness of the model; The calculation logic of the calculation formula is: a. Obtain characteristic data of current weather and system status , the hidden state at the previous time point Introducing current calculations and combining historical memory to improve current predictions; b. Input data and historical hidden states Generate the output of the model through the forward propagation process of the deep learning model; c. Finally, the model outputs a prediction result , represents the possible future value under the current environment and historical status; d. Evaluate the accuracy of the model and adjust the model parameters by comparing the predicted results with the actual observed results; Step 6: Combine the prediction results and traceability data to output adjustment strategies for the marked future and current anomaly targets; Step 7: Receive the adjustment strategy and conduct simulation operation, evaluate the effectiveness of the simulation operation results, and once the strategy is verified, feed it back to the corresponding target for application; Step 8: The feedback data is used as a reference for automatic adjustment of the standard threshold. When the feedback data exceeds the preset threshold, the standard threshold is automatically adjusted.

[0023] As a preferred implementation of this embodiment, a breeze power generation assembly is provided, including: speed and vibration sensors respectively installed on the wind tube, the spiral blade and the wind guide for collecting vibration and speed, and a plurality of meteorological sensors for collecting meteorological data within a preset range; Memory for storing computer programs; A processor, configured to perform a method for generating electricity from a breeze when executing a computer program; This embodiment also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, a micro-wind power generation method is implemented.

[0024] Compared with existing technologies, multiple mechanisms such as real-time monitoring, data analysis, dynamic adjustment, fault warning and systematic data management have been used to effectively solve the problems of existing technologies such as poor performance under changing meteorological conditions, lack of intelligent response capabilities, slow fault response and unsystematic data management. The overall performance of micro-wind power generation has been significantly improved, laying a good foundation for future sustainable energy utilization.

[0025] Embodiment 2: In other aspects, this embodiment also provides a breeze power generation system, such as Figure 2-6 As shown, including: The control module 1 is used as a management main control terminal to edit and issue control instructions for each functional module and module; the control module 1 is interactively connected to the storage module 11 through a wireless network, and the storage module 11 is used to store all collected and analyzed data, classify them according to preset rules, and upload them to the cloud database synchronously; it allows remote wireless editing and issuing of control instructions, improves the automation level of the system, and all collected and analyzed data can be stored and classified for later analysis; The conversion module 2 is used to deploy the wind tube, two spiral blades, the venturi tube and the air guide, such as Figure 6As shown, the air guide is installed at the air inlet of the wind tube, the spiral blade is installed inside the wind tube, and the gap between the spiral blade and the inner wall of the wind tube is controlled to be one thousandth to five thousandths of the diameter of the wind tube. The natural breeze is converted into a vertical downward airflow through the air guide and delivered to the spiral blade to generate an axial and parallel airflow. The Venturi tube is installed at the air outlet of the wind tube, as shown in FIG. Figure 7 As shown, another spiral blade is connected to the inside of the Venturi tube, and the remaining breeze enters the Venturi tube to accelerate and rotate the spiral blade inside it; like Figure 3 As shown in FIG. 1 , the diameter of the middle part of the wind tube is smaller than the diameter of the two ends, so that a trumpet shape is formed at both ends of the wind tube, and the overall shape of the blade is consistent with the shape of the wind tube, such as Figure 4 As shown, the blade is a spiral structure, including a fixed shaft, and a plurality of spiral blades arranged on the fixed shaft and extending along the axial direction; the breeze flows in from the air inlet of the wind tube and flows out from the air outlet of the wind tube. In this process, the breeze flows along the axial direction of the wind tube and even the blades, that is, the wind flows in a streamlined manner on the surface of the blades. The above structure needs to be arranged horizontally to receive the breeze in nature; like Figure 5 and Figure 6 As shown, an air guide is further provided at the inlet wind position of the wind tube, and the air guide comprises a shell, and the shell has an inlet and an outlet, and a plurality of air guide blades are evenly distributed on the circumference of the inlet, and the plurality of air guide blades convert the breeze in the horizontal direction into the wind in the vertical downward direction, and a plurality of spiral plates are provided along the direction from the inlet to the outlet, and the plurality of spiral plates make the breeze with unstable flow direction introduced by the air guide blades more stable, and the flow speed and flow direction are more stable, and the breeze is blown axially and parallelly to the wind tube; The energy storage module 3 is used to receive the mechanical energy generated by the rotation of the two spiral blades in the conversion module 2, convert the mechanical energy into electrical energy for storage; convert the natural breeze twice into usable mechanical energy and electrical energy, thereby improving the power generation efficiency; The collection unit 4 is used to collect the environmental meteorological data in the current power generation cycle, the hardware position and posture data in the conversion module 2, the hardware position and posture data in the energy storage module 3, and the power transmission storage state data in the energy storage module 3 according to a preset period; The acquisition unit 4 is deployed with submodules, including: power acquisition module 41, attitude acquisition module 42 and environment acquisition module 43. The attitude acquisition module 42 and the environment acquisition module 43 are interactively connected with the conversion module 2 through a wireless network. The power acquisition module 41 is interactively connected with the energy storage module 3 through a wireless network to monitor the environmental meteorological data in real time to ensure the robustness of the power generation process. The power collection module 41 is used to collect and analyze the power conversion and storage data of the energy storage module 3 to the conversion module 2; The posture acquisition module 42 is used to monitor the speed and vibration data of each component of the conversion module 2 and identify the tilt and position change state; The environment collection module 43 is used to collect wind speed, rainfall, temperature and humidity data within the current preset range; Setting unit 5, used to set the standard threshold scheme for data collection and receive scheme adaptive adjustment instructions; capable of automatically managing and adjusting the standard threshold, adapting to environmental changes, and ensuring the normal operation of the system; The setting unit 5 has submodules deployed at the lower level, including: a threshold module 51, an adaptation module 52 and a configuration module 53. The threshold module 51, the adaptation module 52 and the configuration module 53 are interactively connected through a wireless network, wherein: The threshold module 51 is used to customize the standard threshold value collected by the collection unit 4. When the collected data hits this range, it is regarded as a normal value, otherwise, it is an abnormal value; The adaptation module 52 is used to determine whether to adjust the current standard threshold based on the feedback data of the simulation module 10 on the availability evaluation of the adjustment scheme. If it is determined to be yes, the standard threshold in the current state is automatically adjusted according to the preset rules. Otherwise, the initial standard threshold of the threshold module 51 is maintained; A configuration module 53, used to update the threshold data based on a preset period and submit it to the acquisition unit 4 for execution; The trend identification module 6 is used to analyze the data collected by the collection unit 4, evaluate the energy flow state, identify and record the normal fluctuations within the standard threshold and the threshold violation, and summarize them as trend data; analyze the collected data in real time, identify and record the normal and abnormal states in time, and provide data support for maintenance; Abnormal prediction module 7 is used to build a machine learning model, train based on historical trend data, analyze current real-time trend data, predict abnormal data within a preset period in the future, and trace the data that violates the threshold and analyze the cause of the target abnormality; perform trend analysis based on historical data, predict potential abnormal situations, and improve system intelligence; Adjustment module 8 is used to combine the prediction and traceability results to output the adjustment strategy of the specified target; it can perform trend analysis based on historical data, predict potential abnormal situations, and improve the intelligence of the system; Early warning module 9 is used to issue alarms to targets that currently violate thresholds and targets that are predicted to be abnormal in the future, and to provide feedback to control module 1, ensuring that users can be informed of system status in a timely manner and providing security; The simulation module 10 is used to simulate the adjustment strategy output by the operation adjustment module 8 and conduct availability evaluation. After verification, the strategy is submitted to the specified target to simulate and evaluate the effectiveness of the adjustment strategy and reduce implementation risks.

[0026] As an implementation method in this embodiment, Figure 2 As shown, the management and control module 1 is interactively connected with the conversion module 2 and the energy storage module 3 through a wireless network, the acquisition unit 4 is interactively connected with the setting unit 5 and the trend identification module 6 through a wireless network, the abnormal prediction module 7 is interactively connected with the trend identification module 6, the adjustment module 8 and the early warning module 9 through a wireless network, the simulation module 10 is interactively connected with the adjustment module 8 through a wireless network, and the simulation module 10 is connected with the conversion module 2 and the setting unit 5 through an electrical medium.

[0027] In the specific implementation of this embodiment, the control module 1 controls each functional module, senses breeze through the conversion module 2 to convert electric energy and stores it through the energy storage module 3, obtains current environmental data through the environment acquisition module 43, acquires operating attitude data of working parts of the conversion module 2 and the energy storage module 3 through the attitude acquisition module 42, acquires power conversion and electric energy storage data of the conversion module 2 and the energy storage module 3 through the power acquisition module 41, and sets standard thresholds of each acquisition module through the threshold module 51; The trend identification module 6 analyzes the data collected by the three acquisition modules, analyzes the fluctuation state of each collected data within the standard threshold value and the data that directly violates the threshold value under the current breeze power generation cycle, performs trend analysis based on the fluctuation state within the standard threshold value of the current cycle and the data that directly violates the threshold value, predicts the abnormal targets and their abnormal states in the future cycle through the abnormal prediction module 7, and performs responsibility target tracing analysis on the data that directly violates the threshold value, and alarms the data of the direct range threshold through the early warning module 9, outputs the adjustment plan for the operation setting of the associated target based on the prediction content and the tracing analysis content through the adjustment module 8, and simulates the adjustment plan through the simulation module 10. After the simulation operation, the corresponding target is submitted for execution, and the adaptation module 52 receives the simulation feedback data as the basis for setting the standard threshold value of the threshold module 51, and the configuration module 53 configures the final setting data; It can improve power generation efficiency and safety while reducing operation and maintenance costs, providing a more efficient and intelligent solution for the use of renewable energy. With intelligence, dynamic adaptability and data-driven as its core advantages, it improves the feasibility and economy of wind power generation.

[0028] In summary, the present invention can efficiently convert natural breeze into directional airflow through the combination of designed wind guides and spiral blades, thereby improving the efficiency of wind energy conversion. This modular design enables the system to achieve effective power generation under low wind speed conditions, collect environmental meteorological data and equipment operating status in real time, and then conduct in-depth analysis. The ability to integrate data enables the power generation system to adapt to different environments and improve overall performance through intelligent control. By setting standard threshold schemes and making dynamic adjustments based on real-time data feedback, the system can adapt to environmental changes in a timely manner, improving the stability and reliability of the power generation system under different climatic conditions. Using machine learning models, the system can not only analyze historical trend data, but also predict future abnormal situations, allowing the system to take preventive measures before abnormal situations occur, thereby reducing failure rates and maintenance costs. The built-in multi-level monitoring and alarm mechanism can monitor the working status of each component in real time and issue an alarm immediately when an abnormality occurs. Based on the prediction and abnormality detection results, the system can output the optimized adjustment strategy and simulate the operation to evaluate its feasibility. This feedback mechanism ensures the effectiveness of the optimization plan and the successful implementation of the adjustment measures in actual applications.

[0029] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A breeze power generation method, characterized in that: The following steps are involved: Step 1: Deploy and initialize all components, and complete the installation of the wind tube, air guide, venturi tube and spiral blades; Step 2: The wind direction is optimized through the wind guide, and the natural breeze is introduced into the wind tube to be converted into a vertical downward airflow, which is converted into mechanical energy after interacting with the spiral blades inside the wind tube. The residual breeze enters the Venturi tube and is converted into mechanical energy after interacting with the spiral blades inside the Venturi tube. The mechanical energy generated by the two spiral blades is converted into electrical energy and stored; Step 3: Continuously collect the status and environmental data of each component, obtain the speed, vibration, inclination, position information and energy transmission status of each component, and obtain wind speed, temperature, humidity and rainfall; Step 4: Set up standard thresholds for data collection, analyze the energy flow status in real-time data, identify normal fluctuations and abnormal trends in the current cycle, and summarize the information into trend data; Step 5: Build a machine learning model, train it based on the collected historical trend data and analyze the current real-time data, predict the abnormal state in the preset future period, mark the future abnormal targets, and conduct retroactive analysis on the data that currently violates the threshold and mark the current abnormal targets; Step 6: Combine the prediction results and traceability data to output adjustment strategies for the marked future and current anomaly targets; Step 7: Receive the adjustment strategy and conduct simulation operation, evaluate the effectiveness of the simulation operation results, and once the strategy is verified, feed it back to the corresponding target for application; Step 8: The feedback data is used as a reference for automatic adjustment of the standard threshold. When the feedback data exceeds the preset threshold, the standard threshold is automatically adjusted.

2. A breeze power generation method according to claim 1, characterized in that: The machine learning model in step 5 is constructed by using a long short-term memory network algorithm, combining the characteristics of a multi-layer neural network and a time series to represent environmental meteorological data and power generation system status data. The calculation formula is: ; In the formula, represents the predicted value at time t, The feature vector representing the wind speed, temperature, humidity and rainfall collected at time t, as well as the speed, vibration, inclination and position information of each component, represents the hidden state at time t−1, indicating the state information of the system before that time point, R represents the model parameters, including the weights and biases of all neurons, Represents the error term, which represents the error between the model prediction result and the actual observation value.

3. A breeze power generation method according to claim 2, characterized in that: The calculation logic of the calculation formula is: a. Obtain characteristic data of current weather and system status , the hidden state at the previous time point Introducing current calculations and combining historical memory to improve current predictions; b. Input data and historical hidden states Generate the output of the model through the forward propagation process of the deep learning model; c. Finally, the model outputs a prediction result , represents the possible future value under the current environment and historical status; d. Evaluate the accuracy of the model and adjust the model parameters by comparing the predicted results with the actual observed results.

4. A micro-wind power generation system, the system is an implementation system of a micro-wind power generation method according to any one of claims 1 to 3, characterized in that: include: The control module (1) is used as a management host to edit and issue various functional modules and module control instructions; The conversion module (2) is used to deploy a wind tube, two spiral blades, an air guide and a venturi tube, wherein the air guide is installed at the air inlet of the wind tube, a spiral blade is rotatably connected to the inside of the wind tube, the venturi tube is installed at the air outlet of the wind tube, another spiral blade is rotatably connected to the inside of the venturi tube, the natural breeze is converted into a vertical downward airflow through the air guide, the spiral blade in the wind tube rotates to generate an axial and parallel airflow, and the remaining breeze enters the venturi tube to accelerate and rotate the spiral blade inside the venturi tube; The energy storage module (3) is used to receive the mechanical energy generated by the rotation of the two spiral blades in the conversion module (2), and convert the mechanical energy into electrical energy for storage; A collection unit (4) is used to collect environmental meteorological data within a current power generation cycle, hardware position and posture data in the conversion module (2), hardware position and posture data in the energy storage module (3), and power transmission storage state data in the energy storage module (3) according to a preset cycle; A setting unit (5), used for setting a standard threshold scheme for data collection and receiving an instruction for adaptively adjusting the scheme; A trend identification module (6) is used to analyze the data collected by the collection unit (4), evaluate the energy flow state, identify and record normal fluctuations within the standard threshold and threshold violations, and summarize them into trend data; The abnormality prediction module (7) is used to build a machine learning model, perform training based on historical trend data, analyze current real-time trend data, predict abnormal data within a future preset period, and conduct target tracing of data that violates the threshold and analyze the cause of the target abnormality; An adjustment module (8), used to combine the prediction and traceability results and output an adjustment strategy for a specified target; An early warning module (9) is used to issue an alarm to a target that is currently in a state of violating a threshold value and a target that is predicted to be in an abnormal state in the future, and to provide feedback to the control module (1); The simulation module (10) is used to simulate the adjustment strategy output by the operation adjustment module (8) and conduct a usability evaluation. After verification, the strategy is submitted to the specified target.

5. A micro-wind power generation system according to claim 4, characterized in that: The control module (1) is interactively connected to a storage module (11) via a wireless network; the storage module (11) is used to store all collected and analyzed data, classify them according to preset rules, and synchronously upload them to a cloud database.

6. A micro-wind power generation system according to claim 4, characterized in that: The acquisition unit (4) has submodules deployed at the lower level, including: a power acquisition module (41), a posture acquisition module (42) and an environment acquisition module (43); the posture acquisition module (42) and the environment acquisition module (43) are interactively connected to the conversion module (2) via a wireless network; the power acquisition module (41) is interactively connected to the energy storage module (3) via a wireless network, wherein: A power collection module (41) for collecting and analyzing data on power conversion and storage of the conversion module (2) by the energy storage module (3); The posture acquisition module (42) is used to monitor the speed and vibration data of each component of the conversion module (2) and identify the tilt and position change state; The environment collection module (43) is used to collect wind speed, rainfall, temperature and humidity data within a current preset range.

7. A micro-wind power generation system according to claim 4, characterized in that: The setting unit (5) has submodules deployed at a lower level, including: a threshold module (51), an adaptation module (52) and a configuration module (53), wherein the threshold module (51), the adaptation module (52) and the configuration module (53) are interactively connected via a wireless network, wherein: A threshold module (51) is used to customize the standard threshold value collected by the collection unit (4). When the collected data hits the range, it is regarded as a normal value, otherwise, it is an abnormal value; The adaptation module (52) is used to determine whether to adjust the current standard threshold based on the feedback data of the simulation module (10) on the usability evaluation of the adjustment plan. If it is determined to be yes, the standard threshold in the current state is automatically adjusted according to a preset rule. Otherwise, the initial standard threshold of the threshold module (51) is maintained; The configuration module (53) is used to update the threshold data based on a preset period and submit it to the collection unit (4) for execution.

8. A micro-wind power generation system according to claim 4, characterized in that: The control module (1) is interactively connected to the conversion module (2) and the energy storage module (3) via a wireless network; the acquisition unit (4) is interactively connected to the setting unit (5) and the trend identification module (6) via a wireless network; the abnormal prediction module (7) is interactively connected to the trend identification module (6), the adjustment module (8) and the early warning module (9) via a wireless network; the simulation module (10) is interactively connected to the adjustment module (8) via a wireless network; and the simulation module (10) is connected to the conversion module (2) and the setting unit (5) via an electrical medium.

9. A micro-wind power generation assembly, characterized in that: include: Speed ​​and vibration sensors for collecting vibration and speed, and several meteorological sensors for collecting meteorological data within a preset range, respectively installed on the wind tube, the spiral blade and the wind guide; Memory for storing computer programs; A processor, configured to execute the steps of a microwind power generation method as claimed in any one of claims 1 to 3 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a microwind power generation method as claimed in any one of claims 1 to 3 are implemented.

Images