Fan-hydrogen energy storage power generation system specially designed for polar region environment

Abstract

The invention relates to the technical field of power generation, and discloses a fan-hydrogen energy storage power generation system specially designed for a polar region environment, which comprises an intelligent control module, a fan module, an electrolysis module, a hydrogen fuel cell module and a temperature control system module, the fan module is configured to collect wind energy for wind power generation; the electrolysis module is configured to decompose alkaline water into hydrogen and oxygen through an exchange membrane based on wind power generation; the hydrogen fuel cell module is configured to utilize hydrogen and oxygen to supply power based on wind power generation; the temperature control system module is configured to monitor the environment temperature; and the intelligent control module is configured to control the fan module, the electrolysis module, the hydrogen fuel cell module and the temperature control system module. Through a wind energy-electric energy-hydrogen energy-electric energy circulation framework, redundant electric energy is converted into hydrogen energy which can be stored for a long time, and then the hydrogen energy is released as required through the fuel cell, so that time and space translation of energy is realized, and unstable wind energy is converted into stable electric energy which can be scheduled as required.

Description

Technical Field

[0001] The present invention relates to the technical field of power generation, and more particularly, to a wind turbine - hydrogen energy storage power generation system designed specifically for polar environments. Background Art

[0002] With the continuous deepening of human exploration of the Earth, remote and extreme regions such as the polar regions and the deep sea have gradually become key areas for scientific research and strategic development. Polar regions such as Antarctica, due to their unique geographical environment and climatic conditions, contain important scientific data and resources, such as glacier evolution, climate change, and ecosystem research. However, the energy supply in these regions has always been a core problem restricting scientific research expeditions and long-term stays.

[0003] In polar environments, traditional energy mainly relies on diesel generators or disposable batteries. These methods have significant drawbacks. Diesel needs to be transported over long distances to the polar regions, which is costly and restricted by weather conditions. At the same time, burning diesel produces carbon emissions, which goes against the environmental protection goals of polar scientific research. Traditional power generation equipment has a sharp drop in efficiency at extremely low temperatures and may even fail to start, and low temperatures will accelerate equipment aging and shorten the service life. Disposable batteries have limited capacity and cannot meet the long-term scientific research needs, while conventional storage batteries have a significant decline in energy storage performance in low-temperature environments. The particularity of the polar environment places almost demanding requirements on the energy system. Existing technologies are difficult to meet the long-term scientific research needs due to problems such as low efficiency, poor adaptability, and difficult maintenance.

[0004] Therefore, it is necessary to design a wind turbine - hydrogen energy storage power generation system specifically for polar environments to solve the problems existing in current technologies. Summary of the Invention

[0005] In view of this, the present invention proposes a wind turbine - hydrogen energy storage power generation system designed specifically for polar environments, aiming to solve the problem of difficult energy acquisition in current polar environments.

[0006] The present invention proposes a wind turbine - hydrogen energy storage power generation system designed specifically for polar environments, comprising:

[0007] An intelligent control module, a wind turbine module, an electrolysis module, a hydrogen fuel cell module, and a temperature control system module;

[0008] The temperature control system module includes a temperature controller and a distributed temperature sensing optical cable, and the distributed temperature sensing optical cable is electrically connected to the temperature controller;

[0009] The wind turbine module is electrically connected to the electrolysis module and the hydrogen fuel cell module;

[0010] The intelligent control module is electrically connected to the wind turbine module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module;

[0011] The wind turbine module is configured to collect wind energy for wind power generation;

[0012] The electrolysis module is configured to decompose alkaline water into hydrogen and oxygen through an exchange membrane based on wind power generation;

[0013] The hydrogen fuel cell module is configured to perform an electrochemical reaction using hydrogen and oxygen for power supply based on wind power generation;

[0014] The temperature control system module is configured to monitor the ambient temperature and send the ambient temperature to the intelligent control module;

[0015] The intelligent control module is configured to control the wind turbine module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module. The intelligent control module is further configured to perform an environmental score on the ambient temperature. When the environmental score is abnormal, an abnormal warning is given and the ambient temperature is adjusted through the temperature controller.

[0016] Furthermore, the wind turbine - hydrogen energy storage power generation system designed specifically for polar environments further includes:

[0017] A remote monitoring module, which is electrically connected to the intelligent control module. The remote monitoring module is configured to monitor the operating states of the intelligent control module, the wind turbine module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module, and send the operating state monitoring information to the Internet and the cloud data platform.

[0018] Furthermore, the wind turbine - hydrogen energy storage power generation system designed specifically for polar environments further includes:

[0019] A structure module, including a bracket and a container. The bracket is fixedly connected to the container. The container is configured to load the intelligent control module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module. The container is arranged on the bracket.

[0020] Furthermore, the wind turbine module is a Q - type vertical axis wind turbine.

[0021] Furthermore, the electrolysis module is a solid polymer electrolyte electrolyzer.

[0022] Furthermore, the hydrogen fuel cell module is a proton exchange membrane fuel cell.

[0023] Furthermore, when performing an environmental score on the ambient temperature, it includes:

[0024] Obtain the ambient temperature and perform pre - processing to obtain a pre - processed ambient temperature;

[0025] Divide the optimal electrolysis operating temperature range, the minimum tolerable electrolysis temperature, and the maximum tolerable electrolysis temperature according to the performance of the electrolysis module. Divide the optimal power generation operating temperature range, the minimum tolerable power generation temperature, and the maximum tolerable power generation temperature according to the performance of the power generation module, and generate an electrolysis environment temperature set and a power generation environment temperature set in combination with the pre-treatment ambient temperature;

[0026] Obtain the standard deviation of the electrolysis temperature within 24 hours based on the electrolysis environment temperature set, and obtain the absolute value of the hourly change in the electrolysis temperature. Obtain the standard deviation of the power generation temperature within 24 hours based on the power generation environment temperature set, and obtain the absolute value of the hourly change in the power generation temperature;

[0027] Determine their weight ratios based on the range where the current power generation temperature is located and the range where the current electrolysis temperature is located, and calculate the power generation environment score and the electrolysis environment score;

[0028] Construct anomaly type labels for the power generation environment score and the electrolysis environment score.

[0029] Furthermore, when constructing anomaly type labels for the environment score, it includes:

[0030] When the electrolysis environment temperature is lower than the optimal electrolysis operating temperature range, control the temperature controller to increase the temperature of the electrolysis module and reduce the hydrogen production current of the electrolysis module;

[0031] When the electrolysis environment temperature is higher than the optimal electrolysis operating temperature range, control the temperature controller to cool down and limit the input voltage of the electrolysis module;

[0032] When the power generation environment temperature is lower than the optimal power generation operating temperature range, control the temperature controller to preheat the power generation module;

[0033] When the power generation environment temperature is higher than the optimal power generation operating temperature range, control the temperature controller to cool down and reduce the load current;

[0034] When the electrolysis environment temperature is lower than the optimal electrolysis operating temperature range and when the power generation environment temperature is lower than the optimal power generation operating temperature range, give priority to preheating the power generation module;

[0035] When the electrolysis environment temperature is higher than the optimal electrolysis operating temperature range and the power generation environment temperature is normal, limit the power of the electrolysis module and call on the hydrogen storage to maintain the operation of the power generation module.

[0036] Furthermore, when the environment score is abnormal and an anomaly warning is given and the environment temperature is adjusted through the temperature controller, it includes;

[0037] Obtain the anomaly type label and adjust the anomaly area based on the anomaly type label;

[0038] Train a neural network model based on historical temperature data;

[0039] Inputting the current ambient temperature data of the abnormal area into the trained neural network model, and predicting the ambient temperature change trend of the abnormal area and the environmental score based on the neural network model;

[0040] When the predicted environmental score and the environmental temperature change trend are lower than or higher than the electrolysis environmental temperature set or the power generation environmental temperature set, an abnormal warning is triggered and a warning message is sent through the remote monitoring module;

[0041] When the environmental score returns to normal, the abnormal warning is lifted and the abnormal event and the handling process are recorded and sent to the Internet and cloud data platform through the remote monitoring module.

[0042] Furthermore, when training the neural network model based on historical temperature data, it includes:

[0043] Sampling the historical temperature data according to a preset ratio to obtain a training set and a validation set;

[0044] Obtaining a pre-selected neural network model, and iteratively training the neural network model according to the training set, and determining a loss value of the iteratively trained neural network model through the validation set;

[0045] If the loss value of the current validation set tends to be stable and the loss value of the neural network model after iterative training continues to decrease, the iterative training is stopped to obtain the pre-trained neural network model.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows: The key problem of wind energy capture is solved by the Q-shaped fan. The Q-shaped fan reduces wind resistance through its streamlined structure. The electrolysis module uses a solid polymer electrolyte (SPE) electrolyzer to achieve efficient electrolysis in a low-temperature environment (-30°C to 0°C). The SPE electrolyzer does not require liquid electrolyte, avoiding the risk of freezing. At the same time, through the optimization of the membrane electrode assembly (MEA), the electrolysis voltage is reduced, and the energy consumption is reduced compared with the traditional technology. The hydrogen energy storage and re-power generation links achieve a technical closed-loop through the adaptation of proton exchange membrane fuel cells (PEMFC). The advantages of PEMFC in polar environments lie in its low-temperature startup ability and high energy density characteristics. Traditional fuel cells are difficult to start at low temperatures due to dehydration of the proton exchange membrane or reduced catalyst activity. However, through the modular packaging of the fuel cell stack and internal humidity control technology, this system uses waste heat circulation to maintain the humidity of the membrane electrode during the startup phase, making up for the defects such as the intermittency of solar energy and the startup delay of diesel generators in polar environments, and forming a stable power output network. Through the control module, a variety of processing mechanisms are integrated to achieve precise regulation of the energy flow. The control module can analyze the power generation of the fan, the hydrogen production rate of the electrolyzer, the output power of the fuel cell, and the load demand in real time, and dynamically adjust the operating status of each unit. In addition, through sensors, the system monitors the temperature changes of key parts such as the fan blades, the membrane electrode of the electrolyzer, and the fuel cell stack in real time, and dynamically adjusts the power of the temperature control unit to ensure that the equipment is always in the optimal working temperature range, reducing the risk of shutdown caused by environmental fluctuations. By utilizing the low-temperature environment, the ohmic loss and thermal management energy consumption in the electrolysis process are reduced. The mechanical challenges brought by strong polar winds are transformed into the power source for the efficient operation of the fan. Through the "wind energy - electrical energy - hydrogen energy - electrical energy" circular architecture, redundant electrical energy is converted into hydrogen energy that can be stored for a long time, and then released on demand through the fuel cell, achieving the time and space translation of energy. It not only solves the problem of spatio-temporal mismatch between polar energy supply and demand, but also converts unstable wind energy into stable electrical energy that can be scheduled on demand through the medium of hydrogen energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0048] Figure 1 is a structural block diagram of a fan - hydrogen energy storage power generation system designed specifically for polar environments provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0050] In some embodiments of the present application, referring to Figure 1 as shown, a wind turbine - hydrogen energy storage power generation system designed specifically for polar environments includes:

[0051] An intelligent control module, a wind turbine module, an electrolysis module, a hydrogen fuel cell module, and a temperature control system module.

[0052] The temperature control system module includes a temperature controller and a distributed temperature sensing optical cable, and the distributed temperature sensing optical cable is electrically connected to the temperature controller.

[0053] The wind turbine module is electrically connected to the electrolysis module and the hydrogen fuel cell module.

[0054] The intelligent control module is electrically connected to the wind turbine module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module.

[0055] The wind turbine module is configured to collect wind energy for wind power generation.

[0056] The electrolysis module is configured to decompose alkaline water into hydrogen and oxygen through an exchange membrane based on wind power generation.

[0057] The hydrogen fuel cell module is configured to perform an electrochemical reaction using hydrogen and oxygen for power supply based on wind power generation.

[0058] The temperature control system module is configured to monitor the ambient temperature and send the ambient temperature to the intelligent control module.

[0059] The intelligent control module is configured to control the wind turbine module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module. The intelligent control module is also configured to perform an environmental score on the ambient temperature. When the environmental score is abnormal, an abnormal warning is given and the ambient temperature is dynamically adjusted through the temperature controller.

[0060] Specifically, there are an intelligent control module, a fan module, an electrolysis module, a hydrogen fuel cell module, and a temperature control system module. The fan module efficiently converts wind energy into electrical energy through a wind power generation unit. The electrolysis module electrolyzes water into hydrogen and oxygen, and the hydrogen fuel cell module can convert the stored hydrogen into electrical energy to supply the load. As the core of the system, the intelligent control module not only regulates the operation of the fan module, the electrolysis module, and the hydrogen fuel cell module, but also monitors the ambient temperature in real time through the temperature control system module and intelligently controls the heaters and coolers in the temperature controller according to the ambient temperature to achieve efficient heat recovery and operation of the equipment at an appropriate temperature. The temperature control system module is equipped with various temperature sensors, including thermocouples, resistance temperature detectors (RTDs), and thermistors, etc., to ensure the accuracy of temperature monitoring. In addition, the intelligent control module can automatically adjust the system parameters according to the monitoring results, optimize the operation efficiency, and alarm and remotely maintain abnormal situations. It can maintain a high power generation efficiency in the polar environment and effectively collect and utilize solar energy. Using electrolysis technology, water is decomposed into hydrogen and oxygen at low energy consumption. Through the cooperation of the temperature control system module and the intelligent control module, the equipment can be kept operating within an appropriate temperature range to prevent icing and ensure the normal operation of the equipment. The hydrogen fuel cell module can convert the stored hydrogen into electrical energy to provide renewable energy. Through the intelligent control module, the automation and intelligent management of the system can be realized, the operation status of the system can be monitored in real time, and it is applicable to energy supply in special environments such as the polar region.

[0061] In some embodiments of the present application, it further includes:

[0062] A remote monitoring module, which is electrically connected to the intelligent control module and is configured to monitor the operation status of the intelligent control module, the fan module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module, and send the operation status monitoring information to the Internet and the cloud data platform.

[0063] Specifically, the remote monitoring module monitors the operation status and abnormal situations of each module. When an abnormal situation occurs, the remote monitoring module can help the staff quickly locate the abnormal range by uploading the specific data of the abnormal situation. The collaborative work of the intelligent control module and the remote monitoring module realizes the automation and intelligent management of the system. It can monitor the operation status of the system in real time, give an immediate alarm for abnormal situations and perform remote maintenance, thereby improving the reliability and safety of the system. The remote monitoring module realizes the real-time monitoring and management of the system performance through remote technology, realizes the convenient operation of unattended, and the remote monitoring module can monitor the operation status of the system in real time through the Internet, remotely access the system database, and obtain operation data and alarm information.

[0064] It can be understood that the collaborative work of the remote monitoring module and the intelligent control module realizes the automated and intelligent management of the system by real-time monitoring the operating states of the fan module, electrolysis module, hydrogen fuel cell module, and temperature control system module. It can timely detect and upload the specific data of abnormal situations, helping the staff quickly locate the problem scope, thereby improving the reliability and safety of the system. Through the connection of the remote monitoring module to the cloud data platform via the Internet, the real-time monitoring and management of the system performance are achieved, supporting remote access to the system database to obtain operation data and alarm information, which not only realizes the convenient operation without personnel on-site but also reduces the cost and risk of manual inspection. In addition, the instant alarm function of the remote monitoring module ensures that abnormal situations can be quickly responded to and processed, improving the maintenance efficiency and the continuity of system operation. The core function of the remote monitoring module lies in real-time monitoring of the operating states of each subsystem. The fan module, electrolysis module, hydrogen fuel cell module, and temperature control system module are key components in the system, and their operating states directly affect the performance and stability of the entire system. Through the remote monitoring module, the operation data of these modules can be collected in real-time and uploaded to the cloud data platform, enabling the management personnel to understand the operating conditions of the system at any time. This real-time monitoring function can not only help detect potential problems in a timely manner. For example, when the rotation speed of the fan module is abnormal or the current fluctuation of the electrolysis module exceeds the normal range, the remote monitoring module will immediately send an alarm signal and upload the relevant data to the cloud for technical personnel to analyze and process. This instant response mechanism shortens the fault handling time and improves the operation efficiency of the system.

[0065] In some embodiments of the present application, it further includes:

[0066] A structure module, including a bracket and a container, the bracket is fixedly connected to the container, the container is configured to load the intelligent control module, electrolysis module, hydrogen fuel cell module, and temperature control system module, and the container is arranged on the bracket.

[0067] Specifically, the structure module adopts a strengthened design, including a bracket made of high-strength material and a housing made of heat-insulating material, enabling the system to withstand harsh weather conditions such as strong winds and heavy snow in the polar region, and at the same time preventing the equipment from icing in low temperatures, ensuring the stable operation of the system.

[0068] It can be understood that the structural module fully considers the stability and adaptability of the system. Through the fixed connection between the bracket and the container, a safe and reliable loading space is provided for the intelligent control module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module. The bracket is made of high-strength materials, which can not only withstand harsh weather conditions such as strong winds and heavy snow in the polar environment but also ensure the stability of the equipment in extreme environments. The outer shell of the container is made of thermal insulation materials to prevent the equipment from freezing in low-temperature environments, ensuring the normal operation of the system, so that this embodiment can operate under various extreme conditions. In polar or high-altitude regions, strong winds and heavy snow are common natural phenomena, and these extreme weather conditions pose a huge challenge to the stable operation of the equipment. By using a bracket made of high-strength materials, the structural module can resist the impact of strong winds and heavy snow, preventing the equipment from being displaced or damaged due to the influence of the external environment. The thermal insulation outer shell of the container provides an important guarantee for the normal operation of the system in low-temperature environments. In polar or cold regions, the low-temperature environment may cause the equipment to freeze or the operating efficiency to decrease, thereby affecting the overall performance of the system. By using an outer shell made of thermal insulation materials, the structural module can isolate the external low temperature to a certain extent, maintain the temperature stability inside the equipment, and prevent the equipment from freezing or being damaged due to low temperature.

[0069] In some embodiments of the present application, the fan module is a Q-shaped vertical axis wind turbine.

[0070] It can be understood that in the polar environment, the wind direction is changeable and unstable. Traditional horizontal axis wind turbines (HAWTs) need to continuously adjust the blade direction to capture wind energy, while the Q-shaped vertical axis wind turbine is insensitive to the wind direction and can capture wind energy from any direction. This characteristic enables it to maintain efficient operation under the changeable wind directions in the polar region, improving the wind energy utilization rate.

[0071] In some embodiments of the present application, the electrolysis module is a solid polymer electrolyte electrolyzer.

[0072] It is understandable that the solid polymer electrolyte electrolyzer uses a solid polymer as the electrolyte, which has a high ionic conductivity and electrochemical activity, and can maintain relatively efficient electrolysis performance in a low-temperature environment. In the polar environment, traditional liquid electrolyte electrolyzers will freeze or have a reduced efficiency due to the low temperature, while the solid polymer electrolyte electrolyzer can operate under low-temperature conditions, ensuring the efficient progress of the electrolysis process. This not only improves the production efficiency of hydrogen but also provides an important guarantee for the energy conversion efficiency of the system. In the polar environment, the temperature can be as low as dozens of degrees below zero Celsius. Traditional electrolyzers cannot work properly due to the low temperature, while the solid electrolyte of the solid polymer electrolyte electrolyzer will not freeze and can maintain stable electrolysis performance under low-temperature conditions. This low-temperature adaptability makes the solid polymer electrolyte electrolyzer an ideal choice in the polar environment. Moreover, the solid polymer electrolyte electrolyzer has a compact structure and occupies a small area, making it suitable for deployment in the polar environment with limited space. At polar research stations or remote areas, the solid polymer electrolyte electrolyzer is integrated with other modules (such as fan modules, hydrogen fuel cell modules, etc.) to form an efficient integrated energy system. Its structure is simple and the maintenance requirements are few, reducing the maintenance cost and difficulty in the polar environment.

[0073] In some embodiments of the present application, the hydrogen fuel cell module is a proton exchange membrane fuel cell.

[0074] It is understandable that the proton exchange membrane fuel cell (PEMFC), as the core component of the hydrogen fuel cell module, has a high energy conversion efficiency and can directly convert the chemical energy of hydrogen into electrical energy, reducing energy loss. In the polar environment, the energy supply is usually limited, and the high-efficiency energy conversion of PEMFC can maximize the utilization of hydrogen resources, providing a stable power supply for the system. This not only improves the overall performance of the system but also reduces energy consumption, providing important support for energy management in the polar environment. The proton exchange membrane fuel cell has excellent low-temperature start-up performance and can start quickly and operate stably in the polar low-temperature environment. In the polar environment, the temperature can be as low as dozens of degrees below zero Celsius. Traditional fuel cells cannot start properly due to the low temperature, while PEMFC uses proton exchange membrane technology and can start quickly and maintain operation under low-temperature conditions. This low-temperature start-up performance makes PEMFC an ideal choice in the polar environment.

[0075] In some embodiments of the present application, when performing an environmental score on the ambient temperature, it includes:

[0076] Obtain the ambient temperature and perform preprocessing to obtain the preprocessed ambient temperature.

[0077] Divide the optimal operating temperature range of electrolysis, the minimum tolerable temperature of electrolysis, and the maximum tolerable temperature of electrolysis according to the performance of the electrolysis module. Divide the optimal operating temperature range of power generation, the minimum tolerable temperature of power generation, and the maximum tolerable temperature of power generation according to the performance of the power generation module. Combine the preprocessed ambient temperature to generate an electrolysis ambient temperature set and a power generation ambient temperature set.

[0078] Obtain the temperature standard deviation within 24 hours based on the electrolysis ambient temperature set, and obtain the absolute value of the hourly temperature change. Obtain the temperature standard deviation within 24 hours based on the power generation ambient temperature set, and obtain the absolute value of the hourly temperature change.

[0079] Determine the weight ratio based on the current range of power generation temperature and the current range of electrolysis temperature, and calculate the power generation environment score and the electrolysis environment score.

[0080] Construct anomaly type labels for the power generation environment score and the electrolysis environment score.

[0081] It can be understood that the temperature data of the power generation module and the electrolysis module are obtained in real time through temperature sensors, and the sliding window mean filtering is used to remove instantaneous noise. Since the sliding window mean filtering is a mature existing technology, it will not be elaborated here. After the preprocessing is completed, a smooth temperature sequence can be ensured. At the same time, the optimal operating temperature range, the minimum tolerable temperature, and the maximum tolerable temperature are determined according to the suitable operating temperature performance of the electrolysis module and the power generation module. For example, the suitable temperature of the electrolysis module is -30°C - 10°C, which is used to enable the intelligent control module to control the temperature around the power generation module and the electrolysis module, so that the electrolysis module and the power generation module can work normally without being affected by temperature stability. Furthermore, calculate the temperature standard deviation within 24 hours and obtain the absolute value of the hourly temperature change. When the change in temperature standard deviation is less than or equal to 5°C, it is a stable state. When the change in temperature standard deviation is greater than 5°C and less than or equal to 10°C, it is a fluctuating state. When the change in temperature standard deviation is greater than 10°C, it is a violently fluctuating state. When the absolute value of the hourly temperature change is greater than or equal to 10°C, it is a sudden change state, which needs to be monitored key. Determine the weight for the ambient temperature score. Among them, the compliance with the temperature safety threshold accounts for 0.4, the suitable temperature interval accounts for 0.3, the control of the temperature change rate accounts for 0.2, and the temperature stability accounts for 0.1. Specifically, the compliance with the temperature safety threshold is deducted 2 points for every hour below the threshold, with a full score of 40 points. The suitable temperature interval gets 3 points for every 10% of the running time, with a full score of 30 points. The control of the temperature change rate is deducted 1 point for each sudden change, with a full score of 20 points. The temperature stability is scored proportionally according to the temperature standard deviation, with a full score of 10 points. The temperature standard deviation is calculated as follows: where, T i is the i-th temperature sampling value, μ is the average temperature within 24 hours, N is the number of sampling points (24 hours × 60 minutes = 1440 points). Divide the stability level according to the temperature standard deviation. The specific scoring formula is: wherein is the score. For example, if σ is 3°C, the score is 8.5 points, and both the power generation module and the electrolysis module are obtained through the above content.

[0082] In some embodiments of the present application, when constructing abnormal type tags for environmental scoring, it includes:

[0083] When the electrolysis environment temperature is lower than the electrolysis optimal operating temperature range, control the temperature controller to increase the temperature of the electrolysis module and reduce the hydrogen production current of the electrolysis module;

[0084] When the electrolysis environment temperature is higher than the electrolysis optimal operating temperature range, control the temperature controller to cool down and limit the input voltage of the electrolysis module;

[0085] When the power generation environment temperature is lower than the power generation optimal operating temperature range, control the temperature controller to preheat the power generation module;

[0086] When the power generation environment temperature is higher than the power generation optimal operating temperature range, control the temperature controller to cool down and reduce the load current;

[0087] When the electrolysis environment temperature is lower than the electrolysis optimal operating temperature range and when the power generation environment temperature is lower than the power generation optimal operating temperature range, give priority to preheating the power generation module;

[0088] When the electrolysis environment temperature is higher than the electrolysis optimal operating temperature range and the power generation environment temperature is normal, limit the power of the electrolysis module and call on the hydrogen storage to maintain the operation of the power generation module.

[0089] It can be understood that by constructing abnormal type tags, when an abnormal situation occurs, the intelligent control module can directly determine the abnormal area through the tags, improving the response ability, and at the same time adjusting the abnormal area according to the tags to make it return to normal.

[0090] In some embodiments of the present application, when the environmental score is abnormal and an abnormal warning is given and the environmental temperature is dynamically adjusted through the temperature controller, it includes.

[0091] Obtain the abnormal type tag and adjust the abnormal area based on the abnormal type tag.

[0092] Train a neural network model based on historical temperature data.

[0093] Input the environmental temperature data of the current abnormal area into the trained neural network model, and predict the environmental temperature change trend and environmental score of the abnormal area based on the neural network model.

[0094] When the predicted environmental score and the trend of environmental temperature change are lower or higher than the electrolysis environmental temperature set or the power generation environmental temperature set, an abnormal warning is triggered and a warning message is sent through the remote monitoring module.

[0095] When the environmental score returns to normal, the abnormal warning is lifted, the abnormal event and the handling process are recorded, and sent to the Internet and the cloud data platform through the remote monitoring module.

[0096] It can be understood that the abnormal area can be directly determined through the abnormal type label. The abnormal area is the module with abnormal temperature. For example, when the temperature of the power generation module is higher than the optimal working temperature range, it can be directly determined that the power generation module is abnormal, that is, the power generation module is the abnormal area. At the same time, the current temperature of the abnormal area is input into the pre-trained neural network model, and the temperature change trend during processing and the changing environmental score during the processing process are predicted through the neural network model. When the predicted situation is still abnormal, an abnormal warning message is sent. By predicting the future environmental score and the change trend of temperature, when the predicted future environmental score and the change trend of temperature do not return to normal, an abnormal warning message is sent, and the power of the temperature control unit is adjusted to make it return to normal. When it returns to normal after being processed by the intelligent control module, the abnormal warning is lifted and the whole process is recorded and sent to the Internet and the cloud data platform for the staff to view.

[0097] In some embodiments of the present application, when training the neural network model based on historical temperature data, it includes:

[0098] Sampling the historical temperature data according to a preset ratio to obtain a training set and a validation set.

[0099] Obtain a pre-selected neural network model, perform iterative training on the neural network model according to the training set, and determine its loss value through the validation set for the iteratively trained neural network model.

[0100] If the loss value of the current validation set tends to be stable and the loss value of the iteratively trained neural network model continues to decrease, then stop the iterative training to obtain the pre-trained neural network model.

[0101] It can be understood that first, historical temperature data is collected, and corresponding high-temperature labels or low-temperature labels are set for the historical temperature data according to the corresponding temperature. According to the optimal temperature range for the operation of the electrolysis module and the power generation module, when the temperature is higher than the upper limit of this range, it is set as a high-temperature label, when it is lower than the lower limit of the range, it is set as a low-temperature label, and when it is within the range, it can be regarded as a normal state and temporarily not participate in the training of high and low temperature judgment.

[0102] The data is divided into a training set and a validation set according to a certain ratio. The training set is used for the parameter learning of the model, enabling the model to learn the mapping relationship between temperature data and high / low temperature labels from the data. The validation set is used to adjust the hyperparameters of the model (such as learning rate, number of neurons in the hidden layer, etc.) during the training process to prevent the model from overfitting. The collected historical temperature data (including the temperature of the heat exchange pipeline, the temperature difference between the cold end and the hot end, and the oil delivery speed of the oil pump) is input into the neural network model. The model, based on the current weight and bias parameters, calculates through weighted summation between neurons and activation functions, and finally passes from the input layer through the hidden layer to the output layer to obtain the prediction result of the high / low temperature state. For example, if a multi-layer perceptron (MLP) is used, the input layer receives the temperature data, the hidden layer performs a non-linear transformation on the features, and the output layer outputs a value representing the probability of high temperature or low temperature.

[0103] According to the prediction result and the pre-set high / low temperature labels, a selected loss function is used to calculate the loss value. For a binary classification problem (high temperature or low temperature), the cross-entropy loss function formula is:

[0104] where M is the number of samples, y i is the true label of the i-th sample (1 for high temperature and 0 for low temperature), is the predicted probability of the model for the i-th sample. The loss value reflects the degree of difference between the model's prediction result and the true label. The larger the loss value, the less accurate the model's prediction. The dataset is divided into a training set and a validation set. During the training process, in addition to observing the loss value of the training set, it is also necessary to regularly evaluate the performance of the model on the validation set. Calculate metrics such as the loss value and accuracy on the validation set. If the loss value on the validation set also decreases with the increase in the number of training rounds and starts to stabilize or slightly increase after a certain round of training, while the loss value of the training set continues to decrease, it may mean that the model has overfitted. At this time, training needs to be stopped, and the model with the smallest loss value on the validation set is selected as the final model because this model has better generalization ability on unseen data and the loss function is relatively the smallest.

[0105] At the beginning of training, the model begins to learn effective features related to the target task from the training set. Since the data of the training set and the validation set have certain similarities, these features learned by the model can not only make its predictions on the training set more accurate (as shown by the decrease in the loss value of the training set), but also be transferred to the validation set, so that the loss value on the validation set also decreases. For example, in the task of judging high and low temperature states based on temperature data, the model may have learned the initial association between temperature and high and low temperature labels. This association is applicable to both the training set and the validation set, so the loss values ​​of both sets are reduced. As the training progresses, the model continuously adjusts its own parameters to better fit the data. At this stage, the generalization ability of the model gradually improves, and it can make more accurate predictions for different data samples. Therefore, the loss value of the validation set continues to decrease, which indicates that the model gradually grasps the general laws of the data during the learning process, rather than just remembering the individual features of the training set. After a certain number of rounds of training, the model may have over-learned on the training set. It begins to remember some noise and the characteristics of specific samples in the training set, rather than the general pattern of the data. Although these specific features can make the model's predictions on the training set more and more accurate, resulting in a continuous decrease in the loss value of the training set, these over-learned features are not applicable to new data in the validation set. Instead, they interfere with the model's judgment, causing the validation set loss value to no longer decrease or even begin to increase. For example, the model may over-focus on the temperature fluctuation characteristics of certain special cases in the training set, which do not exist in the validation set, resulting in poor prediction results on the validation set. If the complexity of the model (such as the number of layers and neurons in the neural network) is too high, the model has sufficient ability to fit all the details in the training set relative to the size and complexity of the data set. As training progresses, the model will continue to explore subtle features in the training set, resulting in overfitting of the training set. However, due to different data, the validation set cannot benefit from these overly complex fits, and the loss value will tend to stabilize or increase. In contrast, the training set loss value will continue to decrease as the model continues to adapt to its data.

[0106] In the above embodiments, the key problem of wind energy capture is solved by the Q-shaped wind turbine. The Q-shaped wind turbine reduces wind resistance through its streamlined structure. The electrolysis module uses a solid polymer electrolyte (SPE) electrolyzer to achieve efficient electrolysis in a low-temperature environment (-30°C to 0°C). The SPE electrolyzer does not require liquid electrolyte, avoiding the risk of freezing. At the same time, through the optimization of the membrane electrode assembly (MEA), the electrolysis voltage is reduced, and the energy consumption is reduced compared with traditional technologies. The hydrogen energy storage and re-power generation links achieve a technical closed-loop through the adaptation of proton exchange membrane fuel cells (PEMFC). The advantages of PEMFC in polar environments lie in its low-temperature startup ability and high energy density characteristics. Traditional fuel cells are difficult to start at low temperatures due to dehydration of the proton exchange membrane or reduced catalyst activity. However, through the modular packaging of the fuel cell stack and internal humidity control technology, this system maintains the humidity of the membrane electrode using waste heat circulation during the startup phase, compensating for the defects such as the intermittency of solar energy and the startup delay of diesel generators in polar environments, and forming a stable power output network. Through the control module, a variety of processing mechanisms are integrated to achieve precise regulation of the energy flow. The control module can analyze the power generation of the wind turbine, the hydrogen production rate of the electrolyzer, the output power of the fuel cell, and the load demand in real time, and dynamically adjust the operating states of each unit. In addition, through sensors, the system monitors the temperature changes of key parts such as the wind turbine blades, the membrane electrode of the electrolyzer, and the fuel cell stack in real time, and dynamically adjusts the power of the temperature control unit to ensure that the equipment is always in the optimal working temperature range, reducing the risk of shutdown caused by environmental fluctuations. By taking advantage of the low-temperature environment to reduce the ohmic loss and thermal management energy consumption during electrolysis, the mechanical challenges brought by strong polar winds are transformed into the power source for the efficient operation of the wind turbine. Through the "wind energy - electrical energy - hydrogen energy - electrical energy" circular architecture, redundant electrical energy is converted into hydrogen energy that can be stored for a long time, and then released on demand through the fuel cell, achieving the time and space translation of energy. It not only solves the spatio-temporal mismatch problem of polar energy supply and demand, but also, through the medium role of hydrogen energy, converts unstable wind energy into stable electrical energy that can be scheduled on demand.

[0107] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0108] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, as well as the combination of flows and / or blocks in the flowchart and / or block diagram. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a machine for implementing in the process Figure 1 one process or multiple processes and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0109] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements in the process Figure 1 one process or multiple processes and / or blocks Figure 1 the functions specified in one block or multiple blocks.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the specific implementation manners of the present invention can still be modified or equivalently replaced, and any modification or equivalent replacement without departing from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A wind turbine - hydrogen energy storage power generation system designed specifically for polar environments, characterized in that, Including: An intelligent control module, a fan module, an electrolysis module, a hydrogen fuel cell module, and a temperature control system module; The temperature control system module includes a temperature controller and a distributed temperature sensing optical cable, and the distributed temperature sensing optical cable is electrically connected to the temperature controller; The fan module is electrically connected to the electrolysis module and the hydrogen fuel cell module; The intelligent control module is electrically connected to the fan module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module; The fan module is configured to collect wind energy for wind power generation; The electrolysis module is configured to decompose alkaline water into hydrogen and oxygen through an exchange membrane based on wind power generation; The hydrogen fuel cell module is configured to perform an electrochemical reaction using hydrogen and oxygen based on wind power generation for power supply; The temperature control system module is configured to monitor the ambient temperature and send the ambient temperature to the intelligent control module; The intelligent control module is configured to control the fan module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module. The intelligent control module is also configured to perform an environmental score on the ambient temperature. When the environmental score is abnormal, an abnormal warning is given and the ambient temperature is adjusted through the temperature controller.

2. The wind turbine - hydrogen energy storage power generation system designed specifically for polar environments according to claim 1, wherein Further including: A remote monitoring module, the remote monitoring module is electrically connected to the intelligent control module, and the remote monitoring module is configured to monitor the operating states of the intelligent control module, the fan module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module, and send the operating state monitoring information to the Internet and the cloud data platform.

3. The wind turbine - hydrogen energy storage power generation system designed specifically for polar environments according to claim 2, characterized in that, Further including: A structure module, including a bracket and a container. The bracket is fixedly connected to the container. The container is configured to load the intelligent control module, the electrolysis module, the hydrogen fuel cell module, and the temperature control system module. The container is provided on the bracket.

4. The wind turbine - hydrogen energy storage power generation system designed specifically for polar environments according to claim 3, wherein, The fan module is a Q-shaped vertical axis wind turbine.

5. The wind turbine - hydrogen energy storage power generation system designed specifically for polar environments according to claim 4, characterized in that, The electrolysis module is a solid polymer electrolyte electrolytic cell.

6. The wind turbine - hydrogen energy storage power generation system designed specifically for polar environments according to claim 5, characterized in that, The hydrogen fuel cell module is a proton exchange membrane fuel cell.

7. The wind turbine - hydrogen energy storage power generation system designed specifically for polar environments according to claim 6, wherein, When performing an environmental score on the ambient temperature, it includes: Obtaining the ambient temperature and performing preprocessing to obtain a preprocessed ambient temperature; Dividing the optimal operating temperature range for electrolysis, the minimum tolerable temperature for electrolysis, and the maximum tolerable temperature for electrolysis according to the performance of the electrolysis module, dividing the optimal operating temperature range for power generation, the minimum tolerable temperature for power generation, and the maximum tolerable temperature for power generation according to the performance of the power generation module, and generating an electrolysis ambient temperature set and a power generation ambient temperature set in combination with the preprocessed ambient temperature; Obtaining the standard deviation of the electrolysis temperature within 24 hours based on the electrolysis ambient temperature set, and obtaining the absolute value of the change in the electrolysis temperature per hour. Obtaining the standard deviation of the power generation temperature within 24 hours based on the power generation ambient temperature set, and obtaining the absolute value of the change in the power generation temperature per hour; Determining the weight ratio based on the range where the current power generation temperature is located and the range where the current electrolysis temperature is located, and calculating the power generation environmental score and the electrolysis environmental score; Constructing abnormal type labels for the power generation environmental score and the electrolysis environmental score.

8. The wind turbine - hydrogen energy storage power generation system designed specifically for polar environments according to claim 7, characterized in that, When constructing abnormal type labels for the environmental score, it includes: When the electrolysis environment temperature is lower than the optimal operating temperature range of electrolysis, controlling the temperature controller to increase the temperature of the electrolysis module and reduce the hydrogen production current of the electrolysis module; When the electrolysis environment temperature is higher than the optimal operating temperature range of the electrolysis, the temperature controller is controlled to cool down and the input voltage of the electrolysis module is limited; When the power generation environment temperature is lower than the power generation optimal operating temperature range, controlling the temperature controller to preheat the power generation module; When the power generation environment temperature is higher than the power generation optimal operating temperature range, controlling the temperature controller to cool down and reduce the load current; When the electrolysis environment temperature is lower than the electrolysis optimal operating temperature range, and when the power generation environment temperature is lower than the power generation optimal operating temperature range, the power generation module is preheated first; When the electrolysis environment temperature is higher than the optimal electrolysis operating temperature range and the power generation environment temperature is normal, the power of the electrolysis module is limited, and hydrogen storage is called to maintain the operation of the power generation module.

9. The wind turbine - hydrogen energy storage power generation system designed specifically for polar environments according to claim 8, characterized in that, When the environmental score is abnormal, an abnormal warning is issued and the environmental temperature is adjusted by the temperature controller, including: Acquire the abnormal type label, and adjust the abnormal area based on the abnormal type label; Train a neural network model based on historical temperature data; Inputting the current ambient temperature data of the abnormal area into the trained neural network model, and predicting the ambient temperature change trend of the abnormal area and the environmental score based on the neural network model; When the predicted environmental score and the environmental temperature change trend are lower than or higher than the electrolysis environmental temperature set or the power generation environmental temperature set, an abnormal warning is triggered and a warning message is sent through the remote monitoring module; When the environmental score returns to normal, the abnormal warning is lifted and the abnormal event and the handling process are recorded and sent to the Internet and cloud data platform through the remote monitoring module.

10. The wind turbine - hydrogen energy storage power generation system designed specifically for polar environments according to claim 9, characterized in that, When training a neural network model based on historical temperature data, it includes: Sampling the historical temperature data according to a preset ratio to obtain a training set and a validation set; Obtaining a pre-selected neural network model, and iteratively training the neural network model according to the training set, and determining a loss value of the iteratively trained neural network model through the validation set; If the loss value of the current validation set is stable and the loss value of the neural network model after iterative training continues to decrease, the iterative training is stopped to obtain the pre-trained neural network model.

Images