An intelligent control method combining normal temperature and pressure solid-state hydrogen storage with hydrogen energy UPS

Abstract

The present application discloses an intelligent control method for the combination of solid-state hydrogen storage at room temperature and pressure and a hydrogen energy UPS, which relates to the field of intelligent control. The method comprises: obtaining current environmental information and operating status information of a power supply system corresponding to the hydrogen energy UPS; and controlling the corresponding working states of a first solid-state hydrogen storage system, a second solid-state hydrogen storage system and the hydrogen energy UPS based on the current environmental information and the operating status information of the power supply system, wherein the first solid-state hydrogen storage system is a physical adsorption material solid-state hydrogen storage system, and the second solid-state hydrogen storage system is a chemical hydrogen storage material.

Description

Technical Field

[0001] The present specification relates to the field of intelligent control, and more specifically, the present application relates to an intelligent control method combining solid-state hydrogen storage at room temperature and pressure with a hydrogen energy UPS. Background Art

[0002] In traditional energy supply systems, uninterruptible power supplies (UPS) usually rely on batteries or other traditional energy forms to provide backup power for critical facilities and equipment when the power grid is out of power. However, these systems often have problems such as low energy efficiency, large environmental impact, long response time and high maintenance cost.

[0003] In order to solve these problems, solid-state hydrogen storage technology has attracted widespread attention as an efficient and environmentally friendly energy storage method. Solid-state hydrogen storage stores hydrogen through physical adsorption or chemical reaction, releases hydrogen when needed, and converts it into electricity through fuel cells. However, the application effect of solid-state hydrogen storage systems is significantly affected by environmental factors such as temperature and humidity, and the changes in these external environmental conditions and the operating status of the power supply system are crucial to optimizing the performance of solid-state hydrogen storage systems and hydrogen UPS. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] In the first aspect, the present application proposes an intelligent control method for combining solid-state hydrogen storage at room temperature and pressure with a hydrogen energy UPS, the method comprising:

[0006] Obtain current environmental information and the operating status information of the power supply system corresponding to the hydrogen UPS;

[0007] Based on the above current environmental information and the above power supply system operating status information, the corresponding working states of the first solid-state hydrogen storage system, the second solid-state hydrogen storage system and the hydrogen energy UPS are controlled, wherein the above first solid-state hydrogen storage system is a physical adsorption material solid-state hydrogen storage system, and the above second solid-state hydrogen storage system is a chemical hydrogen storage material.

[0008] In a feasible implementation manner, the above-mentioned control of the corresponding working states of the first solid-state hydrogen storage system, the second solid-state hydrogen storage system and the hydrogen energy UPS based on the above-mentioned current environment information and the above-mentioned power supply system operation status information includes:

[0009] Determine environmental impact factors based on the above current environmental information and intelligent identification model;

[0010] Determine a first working weight coefficient corresponding to the first solid-state hydrogen storage system and a second working weight coefficient corresponding to the second solid-state hydrogen storage system based on the environmental impact factor;

[0011] Determine the power supply system stability coefficient based on the power supply system operation status information and the power supply stability identification model;

[0012] Determine the operation cycle and operation power of the hydrogen energy UPS based on the above power supply system stability coefficient;

[0013] Determine a first output parameter of the first solid-state hydrogen storage system based on the operating power and the first working weight coefficient;

[0014] A second output parameter of the second solid-state hydrogen storage system is determined based on the operating power and the second working weight coefficient.

[0015] In a feasible implementation manner, the above current environmental information includes temperature information, humidity information, atmospheric pressure information, light intensity information and wind speed information;

[0016] The above-mentioned intelligent recognition model includes a first data input layer, a first feature extraction layer, an environmental impact factor recognition layer, a weight coefficient calculation layer and a first output layer. The above-mentioned intelligent recognition model is an integrated learning model, and the above-mentioned environmental impact factor recognition layer includes a random forest structure and a support vector machine structure.

[0017] In a feasible implementation manner, the feature extraction operation corresponding to the feature extraction layer specifically includes:

[0018] Performing data cleaning, data normalization and data enhancement on the current environment information to obtain pre-processed environment information, wherein the data cleaning includes IQR outlier processing, the data normalization includes Z-score standardization, and the data enhancement includes noise addition and data expansion;

[0019] Based on the above pre-processed environmental information, time change trend characteristics and environmental information interaction characteristics are constructed;

[0020] Performing principal component analysis and importance assessment operations on the above-mentioned time change trend characteristics and the above-mentioned environmental information interaction characteristics to obtain effective environmental information;

[0021] The effective environment information is subjected to feature combination to obtain combined feature information, wherein the combined feature information is the target feature information extracted by the feature extraction layer.

[0022] In a feasible implementation manner, the current environmental information includes temperature information, humidity information, atmospheric pressure information, light intensity information and wind speed information, and the power supply system operation status information includes power supply voltage information, power supply current information, battery status information, load demand information, power supply frequency information and power supply reliability information;

[0023] The power supply stability identification model comprises a second data input layer, a second feature extraction layer, a state identification layer, a stability coefficient calculation layer and a second output layer;

[0024] The second feature extraction layer includes a time domain feature extraction module, a frequency domain feature extraction module and a statistical feature analysis module, and the state recognition layer includes a stability classification module and an anomaly detection module;

[0025] The stability classification module includes a stability classification support vector machine and a Bayesian classifier, and the anomaly detection module includes a historical data comparison and analysis unit and a trend analysis unit;

[0026] The stability coefficient calculation layer includes a weighted scoring module, and the weighted scoring module includes a multi-feature weighted calculation unit and a comprehensive stability scoring unit.

[0027] In a feasible implementation, the weight coefficient corresponding to the above-mentioned multi-feature weighted calculation unit is first determined based on the expert method, and then automatically updated and determined based on the data-driven method. The weight coefficient corresponding to the above-mentioned comprehensive stability scoring unit is determined based on the Bayesian optimization method.

[0028] In a feasible implementation, it also includes:

[0029] Calculate the first working weight coefficient or the second working weight coefficient W according to the following formula i :

[0030]

[0031] Among them, W i is the working weight coefficient of the i-th solid-state hydrogen storage system; E i is the weight value corresponding to the i-th environmental impact factor; E j is the weight value corresponding to the jth environmental impact factor; β is the adjustment factor used to adjust the sensitivity of environmental impact; n is the total number of environmental impact factors.

[0032] In a feasible implementation manner, the above adjustment factor is obtained by performing a regression analysis operation based on historical data, and the above regression analysis operation includes analyzing the relationship between the above adjustment factor and the energy efficiency, response time and stability of the UPS.

[0033] In a feasible implementation manner, the above-mentioned regression analysis operation includes a linear regression analysis operation, a ridge regression analysis operation and a combination operation.

[0034] In a feasible implementation manner, the power supply system stability coefficient is positively correlated with the operation cycle of the hydrogen energy UPS, and the stability coefficient is negatively correlated with the operation power.

[0035] In summary, the intelligent control method of the combination of normal temperature and pressure solid-state hydrogen storage and hydrogen energy UPS in the embodiment of the present application includes: obtaining the current environmental information and the operating status information of the power supply system corresponding to the hydrogen energy UPS; based on the above current environmental information and the above power supply system operating status information, the first solid-state hydrogen storage system, the second solid-state hydrogen storage system and the corresponding working state of the hydrogen energy UPS are controlled, wherein the first solid-state hydrogen storage system is a physical adsorption material solid-state hydrogen storage system, and the second solid-state hydrogen storage system is a chemical hydrogen storage material. Compared with the traditional energy supply system, the method proposed in this application can adjust the energy output according to the real-time environment and power supply demand and improve the energy utilization efficiency by accurately controlling the solid-state hydrogen storage system based on physical adsorption and chemical hydrogen storage materials. The system can adjust the hydrogen supply strategy according to the environmental information, enhance the system's adaptability to environmental changes, and maintain stable operation, especially under extreme climatic conditions. By real-time monitoring of the environment and power supply conditions, it can quickly respond to changes in power supply and demand, and improve the reaction speed and reliability of the system. Solid-state hydrogen storage technology is more environmentally friendly than traditional batteries, reducing the emission of harmful substances and the impact on the environment.

[0036] The intelligent control method of combining normal temperature and pressure solid-state hydrogen storage with hydrogen energy UPS proposed in this application, and other advantages, objectives and features of this application will be partially reflected through the following description, and will also be partially understood by technical personnel in this field through research and practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0038] Figure 1 A schematic flow chart of an intelligent control method for combining solid-state hydrogen storage at room temperature and pressure with a hydrogen UPS provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0040] See also Figure 1 , which is a schematic flow diagram of an intelligent control method for combining normal temperature and pressure solid-state hydrogen storage with a hydrogen energy UPS provided in an embodiment of the present application, which may specifically include:

[0041] S110, obtaining current environmental information and operating status information of the power supply system corresponding to the hydrogen energy UPS;

[0042] S120. Based on the above current environmental information and the above power supply system operating status information, the corresponding working states of the first solid-state hydrogen storage system, the second solid-state hydrogen storage system and the hydrogen energy UPS are controlled, wherein the above first solid-state hydrogen storage system is a physical adsorption material solid-state hydrogen storage system, and the above second solid-state hydrogen storage system is a chemical hydrogen storage material.

[0043] For example, environmental information is collected first, including temperature, humidity, atmospheric pressure and other data, which are crucial for subsequent system control and optimization. At the same time, it is also necessary to obtain the operating status information of the power supply system on which the hydrogen UPS relies, including power supply voltage, current, battery status and load demand. This information helps to evaluate the current status of the power supply system and predict possible power supply demand.

[0044] Based on the collected environmental information and the operating status of the power supply system, the working status of the two solid-state hydrogen storage systems is intelligently controlled. The first solid-state hydrogen storage system uses physical adsorption materials, which are mainly suitable for scenarios where environmental conditions change little and require rapid response. The second solid-state hydrogen storage system uses chemical hydrogen storage materials, which are suitable for long-term storage and can maintain relatively stable performance under adverse environmental conditions. According to the environmental information and the status of the power supply system, the system intelligently adjusts the activity of the two hydrogen storage systems, optimizes the hydrogen storage capacity and hydrogen release rate, and adjusts the operating mode of the hydrogen UPS to meet the predicted power supply needs.

[0045] Compared with traditional energy supply systems, the method proposed in this application can adjust energy output according to real-time environment and power supply demand and improve energy efficiency by precisely controlling the solid-state hydrogen storage system based on physical adsorption and chemical hydrogen storage materials. The system can adjust the hydrogen supply strategy according to environmental information, enhance the system's adaptability to environmental changes, and maintain stable operation, especially under extreme climate conditions. By real-time monitoring of the environment and power supply conditions, it can quickly respond to changes in power supply and demand, and improve the reaction speed and reliability of the system. Solid-state hydrogen storage technology is more environmentally friendly than traditional batteries, reducing the emission of harmful substances and the impact on the environment.

[0046] In some examples, the controlling of the corresponding working states of the first solid-state hydrogen storage system, the second solid-state hydrogen storage system and the hydrogen energy UPS based on the current environment information and the power supply system operating status information includes:

[0047] Determine environmental impact factors based on the above current environmental information and intelligent identification model;

[0048] Determine a first working weight coefficient corresponding to the first solid-state hydrogen storage system and a second working weight coefficient corresponding to the second solid-state hydrogen storage system based on the environmental impact factor;

[0049] Determine the power supply system stability coefficient based on the power supply system operation status information and the power supply stability identification model;

[0050] Determine the operation cycle and operation power of the hydrogen energy UPS based on the above power supply system stability coefficient;

[0051] Determine a first output parameter of the first solid-state hydrogen storage system based on the operating power and the first working weight coefficient;

[0052] A second output parameter of the second solid-state hydrogen storage system is determined based on the operating power and the second working weight coefficient.

[0053] Exemplarily, the system first collects key environmental information, such as temperature, humidity, etc., as well as operating status information of the power supply system, such as voltage, current, battery status, etc. This information is the basis for subsequent decision-making and is crucial to the optimization of overall system performance.

[0054] Using the intelligent recognition model, the system analyzes the current environmental information to determine the environmental factors that have the most significant impact on the performance of the solid-state hydrogen storage system. These factors will be used for subsequent weight coefficient calculations and system adjustments.

[0055] Based on the identified environmental impact factors, the system calculates the working weight coefficients of the first solid-state hydrogen storage system (physical adsorption material system) and the second solid-state hydrogen storage system (chemical hydrogen storage material system). These weight coefficients reflect the importance and priority of each system in the current environment, as well as their contribution to overall energy efficiency and performance.

[0056] Using the power supply stability identification model, the system calculates the power supply system stability coefficient based on the power supply system operation status information. This coefficient is an indicator to measure the reliability and stability of the current power supply system, which is crucial for adjusting the operation strategy of the hydrogen UPS.

[0057] Based on the stability coefficient of the power supply system, the system intelligently adjusts the operating cycle and operating power of the hydrogen UPS. When the power supply stability is high, the operating frequency and power may be reduced to save energy; otherwise, the operating frequency and power will be increased to ensure uninterrupted power supply.

[0058] Finally, the system determines the specific output parameters for the first and second solid-state hydrogen storage systems based on the operating power and the corresponding working weight coefficient. These parameters, including hydrogen storage capacity, hydrogen release rate, etc., are dynamically adjusted according to system requirements and priorities to maximize efficiency and response speed.

[0059] This intelligent control solution achieves highly coordinated and optimized operation of the solid-state hydrogen storage system and hydrogen UPS by comprehensively considering environmental changes and power supply needs. This solution enhances the adaptability of the system, improves energy utilization efficiency, and ensures the stability of energy supply for key facilities, demonstrating a high level of intelligence and automation.

[0060] In some examples, the current environment information includes temperature information, humidity information, atmospheric pressure information, light intensity information, and wind speed information;

[0061] The above-mentioned intelligent recognition model includes a first data input layer, a first feature extraction layer, an environmental impact factor recognition layer, a weight coefficient calculation layer and a first output layer. The above-mentioned intelligent recognition model is an integrated learning model, and the above-mentioned environmental impact factor recognition layer includes a random forest structure and a support vector machine structure.

[0062] Exemplarily, the main task of the first data input layer is to receive and organize the current environmental information collected from different sensors, including temperature information, humidity information, atmospheric pressure information, light intensity information and wind speed information. These data are the basis for the operation of the model and need to be accurately input into the system for subsequent processing.

[0063] The first feature extraction layer processes the input environmental data and extracts features that have a significant impact on system performance through data preprocessing operations (such as cleaning, normalization, and possible data conversion). These features provide a basis for identifying which environmental factors are most critical.

[0064] The environmental impact factor identification layer uses the random forest structure and support vector machine structure in the integrated learning model. This layer analyzes the data features extracted from the first feature extraction layer to identify the environmental impact factors that have the greatest impact on the performance of the solid-state hydrogen storage system. Random forest helps identify key factors by evaluating the importance of each feature, while support vector machine is used to optimize the classification boundary and improve recognition accuracy.

[0065] The weight coefficient calculation layer is based on the key environmental impact factors determined by the environmental impact factor identification layer, and this layer calculates the corresponding working weight coefficients. These coefficients indicate the weight distribution of the impact of different environmental factors on the performance of the first solid-state hydrogen storage system and the second solid-state hydrogen storage system under the current environment.

[0066] The first output layer is the task of outputting the determined environmental influencing factors based on the analysis and calculation of the previous layers. These influencing factors will be used to adjust the operating strategies of the solid-state hydrogen storage system and hydrogen UPS to ensure that the system can work efficiently and stably under various environmental conditions. Through the above intelligent recognition model, the system can respond to environmental changes in real time and intelligently adjust the parameters of the solid-state hydrogen storage system and hydrogen UPS to optimize performance and efficiency. This approach provides a highly automated and intelligent solution to adapt to changing environmental conditions and power supply needs, ensuring efficient and stable operation of the energy system.

[0067] In some examples, the feature extraction operations corresponding to the feature extraction layer specifically include:

[0068] Performing data cleaning, data normalization and data enhancement on the current environment information to obtain pre-processed environment information, wherein the data cleaning includes IQR outlier processing, the data normalization includes Z-score standardization, and the data enhancement includes noise addition and data expansion;

[0069] Based on the above pre-processed environmental information, time change trend characteristics and environmental information interaction characteristics are constructed;

[0070] Performing principal component analysis and importance assessment operations on the above-mentioned time change trend characteristics and the above-mentioned environmental information interaction characteristics to obtain effective environmental information;

[0071] The effective environment information is subjected to feature combination to obtain combined feature information, wherein the combined feature information is the target feature information extracted by the feature extraction layer.

[0072] Exemplarily, the system first cleans the collected current environment information to ensure data quality and accuracy, including using the IQR (interquartile range) method to handle outliers. This method calculates the first quartile (Q1) and the third quartile (Q3) of the data and determines the range of outliers (usually values ​​outside Q1-1.5IQR and Q3+1.5IQR) to exclude extreme values ​​or outliers in the data.

[0073] The system then performs Z-score normalization on the data. This method is performed by subtracting the mean from each data point and dividing by the standard deviation, thereby converting all data to the same scale so that it has zero mean and unit variance. This step is necessary because it helps reduce the impact of dimension when the subsequent model processes the data and speeds up the calculation process.

[0074] Data augmentation processing includes noise addition and data expansion, which aims to increase the diversity and volume of data by artificial means and improve the generalization ability of the model. Noise addition simulates possible data variation by adding randomly generated noise to the data, while data expansion artificially expands the data set through methods such as data rotation and scaling.

[0075] Based on the preprocessed environmental information, the system constructs time-varying trend features and environmental information interaction features. The time-varying trend features reflect the changing patterns of environmental parameters over time, while the environmental information interaction features explore the mutual influence and relationship between different environmental parameters. These features are particularly critical for identifying which environmental factors have the greatest impact on system performance within a specific time.

[0076] The above features are subjected to principal component analysis (PCA) and importance assessment. Principal component analysis is a technique for reducing data dimensions. It extracts key information by retaining the direction with the largest variation in the data while removing redundant and irrelevant data. Importance assessment further analyzes the contribution rate of each principal component to determine the most critical features.

[0077] Finally, the system combines the effective environmental information into features to obtain combined feature information. These combined feature information are the target feature information extracted by the feature extraction layer, which will be directly used for the next step of environmental impact factor identification and weight coefficient calculation to ensure the accuracy and efficiency of the control strategy.

[0078] Through these exhaustive data processing and analysis steps, the feature extraction layer effectively supports the precise operation of the entire intelligent control system and improves the adaptability and performance of the solid-state hydrogen storage system and hydrogen UPS under various environmental conditions.

[0079] In some examples, the current environment information includes temperature information, humidity information, atmospheric pressure information, light intensity information, and wind speed information, and the power supply system operation status information includes power supply voltage information, power supply current information, battery status information, load demand information, power supply frequency information, and power supply reliability information;

[0080] The power supply stability identification model comprises a second data input layer, a second feature extraction layer, a state identification layer, a stability coefficient calculation layer and a second output layer;

[0081] The second feature extraction layer includes a time domain feature extraction module, a frequency domain feature extraction module and a statistical feature analysis module, and the state recognition layer includes a stability classification module and an anomaly detection module;

[0082] The stability classification module includes a stability classification support vector machine and a Bayesian classifier, and the anomaly detection module includes a historical data comparison and analysis unit and a trend analysis unit;

[0083] The stability coefficient calculation layer includes a weighted scoring module, and the weighted scoring module includes a multi-feature weighted calculation unit and a comprehensive stability scoring unit.

[0084] Exemplarily, the second data input layer is responsible for receiving information related to the operation status of the power supply system, including power supply voltage information, power supply current information, battery status information, load demand information, power supply frequency information, and power supply reliability information. These data provide the original input for the model and are the basis for subsequent processing and analysis.

[0085] The second feature extraction layer further processes the data collected by the second data input layer and includes the following three main modules:

[0086] Time domain feature extraction module: Analyze data from the time dimension and extract time domain features such as waveform, peak value, fluctuation, etc.

[0087] Frequency domain feature extraction module: Convert time domain signals into frequency domain signals through Fourier transform and other technologies to analyze the frequency response and harmonic characteristics of the power supply system.

[0088] Statistical feature analysis module: Calculates statistical parameters of data, such as mean, variance, skewness, etc., to evaluate the consistency and reliability of power supply system operation.

[0089] The state recognition layer uses the data features provided by the second feature extraction layer to conduct in-depth analysis of the power supply system status, including:

[0090] Stability classification module: The stability classification support vector machine and Bayesian classifier are used to classify the stability of the power supply system based on the extracted features to distinguish between stable, unstable or potentially unstable states.

[0091] Anomaly detection module: includes historical data comparison and analysis unit and trend analysis unit, which are used to monitor and identify any abnormal behavior or trend in the power supply system and identify potential problems by comparing current data with historical patterns.

[0092] The stability coefficient calculation layer calculates the stability coefficient of the power supply system based on the analysis results of the state recognition layer, mainly including:

[0093] Weighted scoring module: Combines the multi-feature weighted calculation unit and the comprehensive stability scoring unit to comprehensively score the power supply stability according to the importance and contribution of different features. This score reflects the overall stability of the power supply system.

[0094] The second output layer is based on the stability coefficient. This layer outputs the final evaluation results, which will be used to adjust the operating parameters of the hydrogen UPS, such as switching backup power supplies, adjusting load management strategies, etc., to deal with any stability issues detected.

[0095] Through this complex and sophisticated model structure, the system can monitor and evaluate the power supply stability of the hydrogen UPS in real time and respond to any potential power supply problems in a timely manner, thereby ensuring the efficient and reliable operation of the entire power supply system. This method not only improves the operating efficiency of the system, but also greatly enhances its adaptability to changes in the environment and operating status.

[0096] In some examples, the weight coefficient corresponding to the above-mentioned multi-feature weighted calculation unit is first determined based on the expert method to determine the initial weight, and is automatically updated and determined based on the data-driven method, and the weight coefficient corresponding to the above-mentioned comprehensive stability scoring unit is determined based on the Bayesian optimization method.

[0097] Exemplarily, the multi-feature weighted calculation unit calculates the weights of different power supply system features, which determine the influence of each feature in the final stability score. The process includes two main steps:

[0098] The initial weights are set based on the Expert Method, in which experts from the power system and data science fields assign a weight to each feature based on their experience and understanding of system behavior. These weights reflect the relative importance of each feature in assessing power supply stability.

[0099] In order to adapt the model to changes in the environment and changes in system behavior, the initial weights will be automatically updated through data-driven methods. This process usually involves machine learning techniques such as regression analysis, neural networks or other algorithms, which dynamically adjust the weights to optimize stability prediction by analyzing historical and real-time data.

[0100] The comprehensive stability scoring unit is responsible for calculating a comprehensive score reflecting the stability of the overall power supply system based on the weights obtained from the multi-feature weighted calculation unit and all relevant features. This calculation process utilizes Bayesian optimization, which is an efficient global optimization method mainly used to optimize expensive black box functions. In this solution, it is used to optimize the weight configuration to achieve the best stability score. By establishing a probabilistic model between weights and stability scores, Bayesian optimization continuously adjusts the weights to find the optimal solution through Bayesian reasoning and Gaussian process regression.

[0101] Through the above steps, the stability coefficient calculation layer can accurately evaluate the stability of the power supply system while being able to adapt to changes in system parameters and environmental conditions. The expert method provides a robust starting point based on in-depth knowledge, while data-driven automatic updates ensure that the model remains up-to-date over time, and Bayesian optimization further optimizes the scoring process to ensure the accuracy and reliability of the scoring. This method not only improves the accuracy of the evaluation, but also enhances the system's ability to adapt to environmental changes. It is an efficient, dynamic and adaptive solution.

[0102] In some examples, this also includes:

[0103] Calculate the first working weight coefficient or the second working weight coefficient W according to the following formula i :

[0104]

[0105] Among them, W i is the working weight coefficient of the i-th solid-state hydrogen storage system; E i is the weight value corresponding to the i-th environmental impact factor; E j is the weight value corresponding to the jth environmental impact factor; β is the adjustment factor used to adjust the sensitivity of environmental impact; n is the total number of environmental impact factors.

[0106] For example, the weight value E of the environmental impact factor is i and E j The weights are determined by analyzing the impact of each factor on the performance of the solid-state hydrogen storage system. These weight values ​​reflect the specific impact of various environmental factors (such as temperature, humidity, pressure, etc.) on hydrogen storage efficiency and safety.

[0107] The adjustment factor β is used to adjust the sensitivity of the model to environmental changes. A higher β value means that the system is more sensitive to environmental changes, which will make the weight coefficient more concentrated on a few major environmental factors; on the contrary, a lower β value makes the system's response to the environment more uniform and moderate.

[0108] The working weight coefficient of each solid-state hydrogen storage system is calculated using the above formula. The denominator is the sum of the weight values ​​of all environmental impact factors after β adjustment of the exponential function, which ensures that the sum of all working weight coefficients is 1, so as to reasonably allocate resources and priorities under different environmental conditions.

[0109] In this way, the working priority of each solid-state hydrogen storage system can be dynamically adjusted according to the current environmental information. This not only optimizes the hydrogen storage efficiency and system response, but also improves the adaptability and robustness of the overall system, enabling it to respond to environmental changes more effectively.

[0110] In some examples, the adjustment factor is obtained by performing a regression analysis operation based on historical data, and the regression analysis operation includes analyzing the relationship between the adjustment factor and the energy efficiency, response time and stability of the UPS.

[0111] Exemplarily, first, the system needs to collect historical operating data about the hydrogen UPS, including but not limited to performance indicators such as UPS energy efficiency, response time, stability, and the value of the adjustment factor β in the same period as these performance indicators.

[0112] Regression analysis is used to analyze the relationship between the adjustment factor β and the energy efficiency, response time and stability of the hydrogen UPS. This step is achieved by building one or more regression models, the purpose of which is to determine how the β value affects these key performance indicators of the UPS system.

[0113] The historical data set is divided into a training set and a test set. The training set is used to build a regression model, and the test set is used to verify the accuracy and predictive ability of the model.

[0114] Based on the results of the regression analysis, the value of β is adjusted to optimize the performance of the hydrogen UPS. If the analysis shows that the current β value fails to maximize energy efficiency or optimize response time and stability, better performance can be sought by adjusting β.

[0115] The optimal β value can be found using gradient descent, genetic algorithms, or other optimization algorithms, depending on the complexity of the model and the performance goals.

[0116] By determining and adjusting the adjustment factor β through regression analysis based on historical data, it is possible to ensure that the working state of the solid-state hydrogen storage system and hydrogen UPS under different environmental conditions is properly adjusted to achieve the best energy efficiency and performance stability. This method not only enhances the system's ability to adapt to environmental changes, but also optimizes resource allocation and energy management, thereby improving the economy and reliability of the overall system.

[0117] In some examples, the above-mentioned regression analysis operation includes a linear regression analysis operation, a ridge regression analysis operation, and a combined use operation.

[0118] Exemplarily, a linear regression model is used to explore the linear relationship between the adjustment factor β and the performance index of the hydrogen UPS. The model is usually formalized as Y=α+βX+∈, where Y is a performance index of the hydrogen UPS (such as energy efficiency), X is the adjustment factor β, α and β are regression coefficients, and ∈ is the error term. Collect historical data related to the performance of the hydrogen UPS and pair these data with historical values ​​of the adjustment factor β. The data may require preprocessing, such as cleaning and normalization, to be suitable for regression analysis. Fit the linear regression model using techniques such as least squares, and evaluate the accuracy and predictive ability of the model through methods such as cross-validation.

[0119] Ridge regression is an improvement on linear regression, which handles the multicollinearity problem of data by adding a regularization term (L2 penalty) to the loss function. The model form is Y = α + β X + ∈ + λ || β || 2 , where λ is a regularization parameter that controls the strength of the penalty. Choosing an appropriate λ value is key, and the optimal λ is usually determined by methods such as grid search or cross-validation. The ridge regression model is also trained using historical data, and the fitted model can provide a more robust relationship between β and performance indicators.

[0120] The purpose of combining linear regression and ridge regression analysis is to take advantage of the strengths of both: the explanatory power of linear regression when the linear relationship in the data is obvious and the robustness of ridge regression in dealing with potential collinearity issues. The results of the two models are combined through model integration or decision strategies such as weighted averaging or selecting the best performing model as the final model in order to more accurately predict and adjust the adjustment factor β.

[0121] Through the use of linear regression, ridge regression and their combination, the impact of the adjustment factor β\betaβ on the performance of hydrogen UPS can be more accurately understood and predicted, thereby achieving more optimized system control and management. This method not only improves the accuracy of the prediction, but also enhances the adaptability and stability of the model when facing complex data structures.

[0122] In some examples, the power supply system stability coefficient is positively correlated with the operating cycle of the hydrogen-powered UPS, and the stability coefficient is negatively correlated with the operating power.

[0123] Exemplarily, the stability coefficient of the power supply system is positively correlated with the operating cycle of the hydrogen UPS. This means that when the stability coefficient of the power supply system is high, it indicates that the power supply system is relatively stable, so the operating cycle of the hydrogen UPS can be extended. This is because when the power supply is stable, reducing the startup frequency of the UPS can reduce equipment wear and energy consumption. The system dynamically adjusts the operating cycle of the hydrogen UPS according to the stability coefficient of the power supply system calculated in real time. When the stability coefficient is high, the operating interval of the UPS is increased and unnecessary operation is reduced, thereby improving the overall energy efficiency and life of the system.

[0124] The stability coefficient of the power supply system is negatively correlated with the operating power of the hydrogen UPS. This means that when the stability of the power supply system is high, the hydrogen UPS can operate at a lower power, because the stability of the power supply system itself ensures the continuous supply of power and reduces the demand for high power output of the UPS. According to the changes in the stability coefficient of the power supply system, the system automatically adjusts the operating power of the hydrogen UPS. When the power supply system shows high stability, the power output of the UPS is reduced to save energy and reduce the burden on the equipment. Conversely, when the stability is low, the power output of the UPS is increased to ensure power supply at critical moments.

[0125] Through this dynamic adjustment mechanism, the hydrogen UPS can effectively adjust its operation strategy according to the real-time stability of the power supply system. This not only improves energy utilization efficiency and reduces operating costs, but also enhances the system's adaptability to grid fluctuations and ensures uninterrupted operation of key equipment and services. In addition, by reducing unnecessary high-power operation, it also helps to extend the service life of the hydrogen UPS and related equipment.

[0126] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0127] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, 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 instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0128] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0130] An embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of predicting the decomposition rate in alumina production in the corresponding embodiment.

[0131] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0132] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0133] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0136] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0137] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent control method combining solid-state hydrogen storage at normal temperature and pressure with hydrogen energy UPS, comprising: Obtain current environmental information and the operating status information of the power supply system corresponding to the hydrogen UPS; Based on the current environmental information and the power supply system operating status information, the corresponding working states of the first solid-state hydrogen storage system, the second solid-state hydrogen storage system and the hydrogen energy UPS are controlled, wherein the first solid-state hydrogen storage system is a physical adsorption material solid-state hydrogen storage system, and the second solid-state hydrogen storage system is a chemical hydrogen storage material; The controlling the corresponding working states of the first solid-state hydrogen storage system, the second solid-state hydrogen storage system and the hydrogen energy UPS based on the current environmental information and the power supply system operating status information includes: Determine environmental impact factors based on the current environmental information and the intelligent recognition model; Determine a first working weight coefficient corresponding to the first solid-state hydrogen storage system and a second working weight coefficient corresponding to the second solid-state hydrogen storage system based on the environmental impact factor; Determine a power supply system stability coefficient based on the power supply system operating status information and a power supply stability identification model; Determine the operation cycle and operation power of the hydrogen energy UPS based on the power supply system stability coefficient; Determine a first output parameter of a first solid-state hydrogen storage system based on the operating power and the first working weight coefficient; A second output parameter of the second solid-state hydrogen storage system is determined based on the operating power and the second working weight coefficient.

2. The intelligent control method for combining normal temperature and pressure solid-state hydrogen storage with hydrogen energy UPS according to claim 1 is characterized in that: The current environmental information includes temperature information, humidity information, atmospheric pressure information, light intensity information and wind speed information; The intelligent recognition model includes a first data input layer, a first feature extraction layer, an environmental impact factor recognition layer, a weight coefficient calculation layer and a first output layer. The intelligent recognition model is an integrated learning model, and the environmental impact factor recognition layer includes a random forest structure and a support vector machine structure.

3. The intelligent control method for combining normal temperature and pressure solid hydrogen storage with hydrogen energy UPS according to claim 2 is characterized in that: The feature extraction operations corresponding to the feature extraction layer specifically include: Performing data cleaning, data normalization and data enhancement on the current environment information to obtain pre-processed environment information, wherein the data cleaning includes IQR outlier processing, the data normalization includes Z-score standardization, and the data enhancement includes noise addition and data expansion; Constructing time change trend characteristics and environmental information interaction characteristics based on the preprocessed environmental information; Performing principal component analysis and importance evaluation on the time-varying trend characteristics and the environmental information interaction characteristics to obtain effective environmental information; Perform feature combination on the effective environment information to obtain combined feature information, wherein the combined feature information is the target feature information extracted by the feature extraction layer.

4. The intelligent control method for combining normal temperature and pressure solid hydrogen storage with hydrogen energy UPS according to claim 2 is characterized in that: The current environment information includes temperature information, humidity information, atmospheric pressure information, light intensity information and wind speed information, and the power supply system operation status information includes power supply voltage information, power supply current information, battery status information, load demand information, power supply frequency information and power supply reliability information; The power supply stability identification model includes a second data input layer, a second feature extraction layer, a state identification layer, a stability coefficient calculation layer and a second output layer; The second feature extraction layer includes a time domain feature extraction module, a frequency domain feature extraction module and a statistical feature analysis module, and the state recognition layer includes a stability classification module and an anomaly detection module; The stability classification module includes a stability classification support vector machine and a Bayesian classifier, and the anomaly detection module includes a historical data comparison and analysis unit and a trend analysis unit; The stability coefficient calculation layer includes a weighted scoring module, and the weighted scoring module includes a multi-feature weighted calculation unit and a comprehensive stability scoring unit.

5. The intelligent control method for combining normal temperature and pressure solid hydrogen storage with hydrogen energy UPS according to claim 4 is characterized in that: The weight coefficient corresponding to the multi-feature weighted calculation unit is first determined based on the expert method to determine the initial weight, and then automatically updated and determined based on the data-driven method. The weight coefficient corresponding to the comprehensive stability scoring unit is determined based on the Bayesian optimization method.

6. The intelligent control method for combining normal temperature and pressure solid hydrogen storage with hydrogen energy UPS according to claim 1, characterized in that: Also includes: Calculate the first working weight coefficient or the second working weight coefficient W according to the following formula i : Among them, W i is the working weight coefficient of the i-th solid-state hydrogen storage system; E i is the weight value corresponding to the i-th environmental impact factor; E j is the weight value corresponding to the jth environmental impact factor; β is the adjustment factor used to adjust the sensitivity of environmental impact; n is the total number of environmental impact factors.

7. The intelligent control method for combining normal temperature and pressure solid hydrogen storage with hydrogen energy UPS according to claim 6, characterized in that: The adjustment factor is obtained by performing a regression analysis operation based on historical data, and the regression analysis operation includes analyzing the relationship between the adjustment factor and the energy efficiency, response time and stability of the UPS.

8. The intelligent control method for combining normal temperature and pressure solid hydrogen storage with hydrogen energy UPS according to claim 7, characterized in that: The regression analysis operation includes a linear regression analysis operation, a ridge regression analysis operation and a combined use operation.

9. The intelligent control method for combining normal temperature and pressure solid hydrogen storage with hydrogen energy UPS according to claim 1, characterized in that: The power supply system stability coefficient is positively correlated with the operating cycle of the hydrogen energy UPS, and the stability coefficient is negatively correlated with the operating power.

Images