Green hydrogen production, storage and transportation integrated real-time operation monitoring method and system

Abstract

The invention relates to the technical field of storage and transportation monitoring, in particular to a green hydrogen production, storage and transportation integrated real-time operation monitoring method and system, and the method comprises the following steps: S1, respectively setting intelligent sensor networks in a hydrogen production link, a hydrogen storage link and a hydrogen transportation link of green hydrogen production, storage and transportation, and collecting the operation state data of each link in real time; s2, performing multi-state cooperative monitoring based on the operation state data of each link, and performing linkage monitoring on a plurality of state variables in the hydrogen production, hydrogen storage and hydrogen transportation processes; s3, constructing a multivariable model, and describing a nonlinear coupling relationship among a plurality of state variables in the links of hydrogen production, hydrogen storage and hydrogen transportation; and S4, designing a multi-state cooperative control algorithm based on the nonlinear coupling relationship described in the multivariable model. According to the method, control failure caused by simple linear hypothesis is effectively avoided, and particularly, relatively high prediction precision can be kept for state variables of nonlinear coupling.

Description

Technical Field

[0001] The present invention relates to the field of storage and transportation monitoring technology, and in particular to a real-time operation monitoring method and system for integrated green hydrogen production, storage and transportation. Background Art

[0002] As a clean energy, green hydrogen has gradually become one of the important ways to achieve energy structure transformation. In the process of green hydrogen production, storage and transportation, the key links involved include hydrogen production, storage and transportation. The operating status of each link has an important impact on the efficiency, safety and stability of the entire system. Traditional green hydrogen production, storage and transportation monitoring and control systems mostly adopt a single-link monitoring method, and most of them rely on linear control models. This method shows great limitations when dealing with complex working conditions, nonlinear coupling relationships and multi-state variables.

[0003] First of all, in the hydrogen production process, the voltage, current and temperature of the electrolyzer directly affect the production efficiency and quality of hydrogen. The hydrogen storage process requires real-time monitoring of the pressure, temperature and hydrogen purity of the hydrogen storage tank to avoid overpressure or abnormal temperature during storage. In the hydrogen transportation process, the flow rate, pressure and other states of the pipeline also need to be precisely controlled. In particular, when the pressure or temperature of the hydrogen storage tank changes, the hydrogen transportation state will often fluctuate, thereby affecting the stability of the entire process.

[0004] However, existing monitoring systems generally lack an overall grasp of the nonlinear coupling relationship between hydrogen production, storage and transportation, and are unable to effectively handle the complex linkage between state variables under abnormal conditions or emergencies. In addition, errors are prone to accumulation during long-term operation of the system, and traditional control methods are often unable to adaptively correct these errors, resulting in inaccurate predictions or reduced control effects, affecting the efficiency and safety of the entire production, storage and transportation system. Summary of the invention

[0005] The present invention provides a real-time operation monitoring method and system for integrated green hydrogen production, storage and transportation.

[0006] A green hydrogen production, storage and transportation integrated real-time operation monitoring method comprises the following steps:

[0007] S1, intelligent sensor networks are set up in the hydrogen production, storage and transportation links of green hydrogen production, storage and transportation to collect real-time operating status data of each link, including the voltage and current of the hydrogen production electrolyzer, the pressure and temperature of the hydrogen storage tank, the flow rate, pressure and hydrogen purity of the transportation pipeline;

[0008] S2, based on the operating status data of each link, conducts multi-state collaborative monitoring, conducts linkage monitoring of multiple state variables in the process of hydrogen production, storage and transportation, and forms a dynamic state diagram of the entire process of production, storage and transportation through data aggregation;

[0009] S3, based on the operating status data of each link collected in multi-state collaborative monitoring, a multivariable model is constructed to describe the nonlinear coupling relationship between multiple state variables in hydrogen production, storage and transportation;

[0010] S4, designs a multi-state collaborative control algorithm. Based on the nonlinear coupling relationship described in the multivariable model, the multi-state collaborative control algorithm dynamically adjusts the operating conditions of each link according to the operating status data of different links. When the operating status data of a link fluctuates abnormally, it automatically analyzes the impact of the abnormal fluctuation on other links, and compensates for the abnormal data through historical data and model predictions.

[0011] Optionally, the S1 specifically includes:

[0012] S11, hydrogen production process:

[0013] Voltage sensors and current sensors are arranged at various positions of the electrolytic cell to monitor the current and voltage changes in the electrolytic cell in real time;

[0014] A temperature sensor is provided to monitor the temperature in the electrolytic cell;

[0015] S12, hydrogen storage stage:

[0016] A pressure sensor and a temperature sensor are installed in the hydrogen storage tank to monitor the pressure fluctuation and temperature change in the hydrogen storage tank respectively;

[0017] The hydrogen purity sensor is installed at the inlet and outlet of the hydrogen storage tank to detect changes in hydrogen purity;

[0018] S13, hydrogen transportation:

[0019] Flow rate sensors and pressure sensors are arranged at each node of the transportation pipeline to monitor the flow of hydrogen during transportation in real time, including the flow rate and pressure in the pipeline.

[0020] Optionally, in S2, the voltage, current, and temperature data in the hydrogen production link, the pressure, temperature, and hydrogen purity data in the hydrogen storage link, and the flow rate and pressure data in the hydrogen transportation link are summarized to the central control unit; the central control unit synchronizes the data of each link using a timestamp to ensure that the status data of different links are integrated in chronological order, thereby eliminating monitoring errors caused by time differences;

[0021] Multi-state collaborative monitoring is used to monitor multiple state variables in the process of hydrogen production, storage and transportation in real time and independently, and to track multiple state variables in parallel at the same time;

[0022] Independently monitor important operating parameters in each link, such as hydrogen production efficiency, pressure and temperature of hydrogen storage tanks, flow rate and pressure during transportation, to ensure coordinated monitoring of state variables in each link and comprehensive data coverage.

[0023] The state variables of each link are mapped in real time to the dynamic state diagram of the entire process. The state diagram is used to display the current status of the entire process of hydrogen production, storage and transportation, including the operating parameters and state change trends of each link.

[0024] Optionally, the multivariate model in S3 is constructed based on a neural network, specifically including:

[0025] Input layer: The input layer includes the state variables of each link of green hydrogen production, storage and transportation. The vector representation of the input layer is:

[0026]

[0027] It includes:

[0028] Input variables for hydrogen production:

[0029] Voltage: V 制氢 (t);

[0030] Current: I 制氢 (t);

[0031] Temperature: T 制氢 (t);

[0032] Input variables for hydrogen storage:

[0033] Pressure: P 储荎 (t);

[0034] Temperature: T 储氢 (t);

[0035] Hydrogen purity: Q 储氢 (t);

[0036] Input variables for hydrogen transportation:

[0037] Flow rate: F 运氢 (t);

[0038] Pressure:P 运氢 (t);

[0039] Hidden layer: The hidden layer uses multiple neurons to capture the complex nonlinear relationship between the state variables. The output of the hidden layer is expressed as:

[0040] h(t)=σ(W·x(t)+b), where W is the weight matrix from the input layer to the hidden layer, b is the bias, and σ(·) is the nonlinear activation function;

[0041] Output layer: The output layer is used to predict the key state variables of hydrogen production, storage and transportation. The output of the output layer is expressed as: Among them, W out is the weight matrix from the hidden layer to the output layer, b out is bias.

[0042] Optionally, the training of the multivariate model is based on back propagation and weight updating to optimize weights, specifically including:

[0043] Forward propagation: computing predicted values ​​through the neural network

[0044] Calculate loss: Calculate error based on loss function, which uses mean square error.

[0045] Back propagation: adjust weights and biases based on error gradients;

[0046] Cumulative error detection and correction: When the prediction error accumulates beyond the threshold, the error correction mechanism is triggered.

[0047] Optionally, in the actual green hydrogen production, storage and transportation process, the data collection and transmission of state variables may be affected by factors such as delays and noise, resulting in gradually accumulated errors in the prediction process. Although traditional neural networks can be adjusted through error back propagation, they cannot quickly respond to accumulated errors. In particular, when the data fluctuates abnormally, the model is prone to the problem of local error expansion. In order to solve the problem of gradually accumulated errors, a gradually accumulated error correction mechanism is proposed. It can actively correct the model output when it detects that the error is constantly accumulating, so that the system can adaptively avoid error expansion; therefore, the error correction mechanism is used to monitor the cumulative error between the predicted output of the multivariable model and the true value. The cumulative error is expressed as:

[0048] in, is the predicted value of the model at time t, y(t) is the actual state value, and the cumulative trend of the error is determined by continuously accumulating the error value;

[0049] When the cumulative error exceeds the set safety threshold, the error correction mechanism is automatically triggered, and the correction is expressed as: Among them, β is the error correction coefficient, which is used to adjust the correction amplitude, E 累积 (t) is the cumulative error value.

[0050] Optionally, the collaborative control algorithm in S4 is based on the dynamic coupling relationship between various state variables and calculates the optimal operating conditions according to the real-time state data of each link. For example, when the voltage of the hydrogen production link is too high, the algorithm adjusts the current of the hydrogen production equipment to reduce the pressure of the hydrogen storage tank to ensure that the hydrogen storage tank is within a safe working range; when an abnormal fluctuation occurs in a certain link, the collaborative control algorithm performs an impact analysis and automatically analyzes the potential impact of the fluctuation on other links. For example, pressure fluctuations in the hydrogen storage tank may cause abnormal flow rate in the hydrogen transportation pipeline. The algorithm will analyze the impact of the abnormal fluctuation on other state variables through historical data and model prediction;

[0051] The collaborative control algorithm automatically compensates for abnormal conditions based on historical operating data and multivariable model predictions.

[0052] Optionally, the abnormal fluctuation includes the hydrogen storage tank pressure P 储氢 (t) Abnormal fluctuation analysis, expressed as: ΔP 储氢 (t) = P 储氢 (t)-P 目标 , if ΔP 储氢 (t) is too large, indicating abnormal fluctuations, P 目标 It is the target pressure of the hydrogen storage tank, and analyzes the impact of pressure changes on hydrogen production and transportation; for example, analyzes the impact of abnormal hydrogen storage tank pressure on hydrogen transportation flow rate.

[0053] A green hydrogen production, storage and transportation integrated real-time operation monitoring system, used to implement the above-mentioned green hydrogen production, storage and transportation integrated real-time operation monitoring method, includes the following modules:

[0054] Hydrogen production status data monitoring module: collects the operating data of the hydrogen production electrolyzer in real time, including voltage, current and temperature, and transmits it to the central processing unit for analysis;

[0055] Hydrogen storage status data monitoring module: used to monitor the pressure, temperature and hydrogen purity of the hydrogen storage tank;

[0056] Hydrogen transportation status data monitoring module: used to collect flow rate and pressure data of hydrogen transportation pipeline;

[0057] Multivariate analysis module: Based on the status data of each link, a multivariate nonlinear model is constructed to conduct linkage analysis on multiple state variables in hydrogen production, storage and transportation to capture the nonlinear coupling relationship between the variables;

[0058] Dynamic control module: According to the analysis results of the multivariable model, the operating conditions of each link are dynamically adjusted. When abnormal fluctuations occur in a certain link, the impact of the abnormal fluctuations on other links is automatically analyzed and real-time compensation is performed.

[0059] Beneficial effects of the present invention:

[0060] The present invention captures the nonlinear coupling relationship between various state variables in the hydrogen production, storage and transportation links through a multivariable model, and realizes accurate modeling and linkage control of key parameters such as voltage, pressure, flow rate and temperature. Utilizing this model, the complex influence of the pressure and temperature of the hydrogen storage tank on the flow rate of the hydrogen transportation pipeline can be effectively predicted, thereby providing a reliable data basis for the linkage monitoring of the entire process. Compared with traditional linear control methods, the present invention has stronger adaptability and accuracy under complex working conditions, effectively avoids control failures caused by simple linear assumptions, and can maintain a high prediction accuracy, especially when facing nonlinearly coupled state variables.

[0061] The present invention, by designing a gradual accumulation error correction mechanism, can detect the error accumulation between the predicted value and the actual value of the state variable during the operation of the system in real time. When the error exceeds the safety threshold, the output is automatically adjusted, and the hydrogen production voltage and current are dynamically corrected to ensure the stability of the system in long-term operation. Compared with the traditional single adjustment, the gradual correction strategy is adopted to effectively avoid over-correction and drastic fluctuations in the predicted value. Especially under complex and sudden working conditions, the mechanism can respond quickly and compensate, improving the system's anti-interference ability and long-term stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 A schematic diagram of a monitoring method flow chart of an embodiment of the present invention;

[0064] Figure 2 Schematic diagram of a multivariate model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0066] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0067] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0068] like Figure 1-Figure 2 As shown, a real-time operation monitoring method for integrated green hydrogen production, storage and transportation comprises the following steps:

[0069] S1, intelligent sensor networks are set up in the hydrogen production, storage and transportation links of green hydrogen production, storage and transportation to collect real-time operating status data of each link, including the voltage and current of the hydrogen production electrolyzer, the pressure and temperature of the hydrogen storage tank, the flow rate, pressure and hydrogen purity of the transportation pipeline;

[0070] S2, based on the operating status data of each link, conducts multi-state collaborative monitoring, conducts linkage monitoring of multiple state variables in the process of hydrogen production, storage and transportation, and forms a dynamic state diagram of the entire process of production, storage and transportation through data aggregation;

[0071] S3, based on the operating status data of each link collected in multi-state collaborative monitoring, a multivariable model is constructed to describe the nonlinear coupling relationship between multiple state variables in hydrogen production, storage and transportation;

[0072] S4, designs a multi-state collaborative control algorithm. Based on the nonlinear coupling relationship described in the multivariable model, the multi-state collaborative control algorithm dynamically adjusts the operating conditions of each link according to the operating status data of different links. When the operating status data of a link fluctuates abnormally, it automatically analyzes the impact of the abnormal fluctuation on other links, and compensates for the abnormal data through historical data and model predictions.

[0073] S1 specifically includes:

[0074] S11, hydrogen production process:

[0075] Voltage sensors and current sensors are arranged at various positions of the electrolyzer to monitor the current and voltage changes in the electrolyzer in real time to ensure the stability of energy consumption during the hydrogen production process;

[0076] A temperature sensor is set up to monitor the temperature in the electrolytic cell to ensure that the electrolytic cell operates within the optimal temperature range and prevent efficiency loss or equipment damage caused by overheating;

[0077] S12, hydrogen storage stage:

[0078] Install pressure sensors and temperature sensors in the hydrogen storage tanks to monitor pressure fluctuations and temperature changes in the hydrogen storage tanks, respectively, to ensure the stability and safety of the hydrogen storage tanks and to prevent potential dangers caused by excessive pressure or excessive temperature;

[0079] The hydrogen purity sensor is installed at the inlet and outlet of the hydrogen storage tank to detect the purity change of hydrogen and ensure that the stored hydrogen meets the specified purity requirements to prevent energy waste or system damage caused by insufficient purity;

[0080] S13, hydrogen transportation:

[0081] Flow rate sensors and pressure sensors are arranged at each node of the transportation pipeline to monitor the flow of hydrogen during transportation in real time, including the flow rate and pressure in the pipeline, to prevent energy loss or safety accidents caused by unstable flow rate or abnormal pressure.

[0082] In S2, the voltage, current, and temperature data in the hydrogen production link, the pressure, temperature, and hydrogen purity data in the hydrogen storage link, and the flow rate and pressure data in the hydrogen transportation link are summarized in the central control unit; the central control unit uses timestamps to synchronize the data of each link to ensure that the status data of different links are integrated in chronological order, eliminating monitoring errors caused by time differences;

[0083] Multi-state collaborative monitoring is used to monitor multiple state variables in the process of hydrogen production, storage and transportation in real time and independently, and to track multiple state variables in parallel at the same time;

[0084] Independently monitor important operating parameters in each link, such as hydrogen production efficiency, pressure and temperature of hydrogen storage tanks, flow rate and pressure during transportation, to ensure coordinated monitoring of state variables in each link and comprehensive data coverage.

[0085] The state variables of each link are mapped in real time to the dynamic state diagram of the entire process. The state diagram is used to display the current status of the entire process of hydrogen production, storage and transportation, including the operating parameters and state change trends of each link.

[0086] The multivariate model in S3 is based on a neural network and includes:

[0087] Input layer: The input layer includes the state variables of each link of green hydrogen production, storage and transportation. The vector representation of the input layer is:

[0088]

[0089] It includes:

[0090] Input variables for hydrogen production:

[0091] Voltage: V 制氢 (t);

[0092] Current: I 制氢 (t);

[0093] Temperature: T 制氢 (t);

[0094] Input variables for hydrogen storage:

[0095] Pressure: P 储荎 (t);

[0096] Temperature: T 储氢 (t);

[0097] Hydrogen purity: Q 储氢 (t);

[0098] Input variables for hydrogen transportation:

[0099] Flow rate: F 运氢 (t);

[0100] Pressure:P 运氢 (t);

[0101] Hidden layer: The hidden layer uses multiple neurons to capture the complex nonlinear relationship between the state variables. The output of the hidden layer is expressed as:

[0102] h(t)=σ(W·x(t)+b), where W is the weight matrix from the input layer to the hidden layer, b is the bias, and σ(·) is the nonlinear activation function;

[0103] Output layer: The output layer is used to predict the key state variables of hydrogen production, storage and transportation. The output of the output layer is expressed as: Among them, W out is the weight matrix from the hidden layer to the output layer, b out is bias.

[0104] The training of multivariate models is based on back propagation and weight update to optimize weights, including:

[0105] Forward propagation: computing predicted values ​​through the neural network

[0106] Calculate loss: Calculate error based on loss function, which uses mean square error.

[0107] Back propagation: adjust weights and biases based on error gradients;

[0108] Cumulative error detection and correction: When the prediction error accumulates beyond the threshold, the error correction mechanism is triggered.

[0109] In the actual green hydrogen production, storage and transportation process, the data collection and transmission of state variables may be affected by factors such as delay and noise, resulting in gradually accumulated errors in the prediction process. Although traditional neural networks can be adjusted through error back propagation, they cannot quickly respond to accumulated errors. Especially when the data fluctuates abnormally, the model is prone to the problem of local error expansion. In order to solve the problem of gradually accumulated errors, a gradually accumulated error correction mechanism is proposed. It can actively correct the model output when it detects that the error is constantly accumulating, so that the system can adaptively avoid error expansion; therefore, the error correction mechanism is used to monitor the cumulative error between the predicted output of the multivariable model and the true value. The cumulative error is expressed as:

[0110] in, is the predicted value of the model at time t, y(t) is the actual state value, and the cumulative trend of the error is determined by continuously accumulating the error value;

[0111] When the cumulative error exceeds the set safety threshold, the error correction mechanism is automatically triggered, and the correction is expressed as: Among them, β is the error correction coefficient, which is used to adjust the correction amplitude, E 累积 (t) is the cumulative error value.

[0112] Back propagation and weight update are used in the model training phase to adjust the weights of the neural network so that the overall error of the model is gradually reduced. The gradual cumulative error correction mechanism is used in the model deployment and operation phase to adjust the output of the model in real time to prevent the cumulative error from affecting the stability of the system.

[0113] Adjust the value of β through experiments to obtain the best correction effect. The steps are as follows:

[0114] Initial setting: Set an initial value βinitial, you can start from a smaller value (such as 0.1).

[0115] Experimental operation: During the actual operation of the model, different working conditions are simulated to detect the impact of different values ​​of β on the prediction correction effect.

[0116] Adjustment and optimization: Based on the feedback from the system during the experiment, gradually adjust the value of β until the corrected prediction value can effectively reduce the error without causing over-correction.

[0117] The collaborative control algorithm in S4 is based on the dynamic coupling relationship between various state variables and calculates the optimal operating conditions according to the real-time state data of each link. For example, when the voltage of the hydrogen production link is too high, the algorithm adjusts the current of the hydrogen production equipment to reduce the pressure of the hydrogen storage tank to ensure that the hydrogen storage tank is within the safe working range; when an abnormal fluctuation occurs in a certain link, the collaborative control algorithm performs an impact analysis and automatically analyzes the potential impact of the fluctuation on other links. For example, pressure fluctuations in the hydrogen storage tank may cause abnormal flow rate in the hydrogen transportation pipeline. The algorithm will analyze the impact of the abnormal fluctuation on other state variables through historical data and model prediction;

[0118] The collaborative control algorithm automatically compensates for abnormal conditions based on historical operating data and multivariable model predictions.

[0119] If you want to adjust the pressure P of the hydrogen storage tank 储氢 (t), when the pressure is too high, the algorithm adjusts the hydrogen production voltage and flow rate through the following calculation formula:

[0120] Adjustment formula for hydrogen production: ΔV 制氢 (t) = α1·(P 储氢 (t)-P 目标 ), where ΔV 制氢 (t) represents the adjustment of hydrogen production voltage, P 储氢 (t) is the current hydrogen storage pressure, α1 is the coefficient used to adjust the voltage, representing the sensitivity of voltage changes to the hydrogen storage pressure, P 目标 is the target pressure of the hydrogen storage tank;

[0121] Adjustment formula for hydrogen transportation: ΔF 运氢 (t) = α2·(P 储氢 (t)-P 目标 ), where ΔF 运氢 (t) represents the adjustment amount of the hydrogen transport flow rate, α2 is the coefficient used to adjust the flow rate, and represents the sensitivity of the flow rate change to the hydrogen storage pressure.

[0122] Example: Hydrogen storage tank pressure P 储氢 (t) Abnormal fluctuation analysis, expressed as: ΔP 储氢 (t) = P 储氢 (t)-P 目标 , if ΔP 储氢 (t) is too large, indicating abnormal fluctuations, P 目标 It is the target pressure of the hydrogen storage tank, and analyzes the impact of pressure changes on hydrogen production and transportation; for example, the impact of abnormal hydrogen storage tank pressure on hydrogen transportation flow rate:

[0123] ΔF 运氢 (t) = f2(ΔP 储氢 (t),T储氢 (t)), f2 is the functional expression of the multivariable model, which describes the nonlinear coupling relationship between the hydrogen storage tank state (pressure, temperature) and the hydrogen transportation pipeline state (flow rate, pressure). Through historical data, the effect of abnormal changes in hydrogen storage tank pressure on the hydrogen transportation flow rate F is calculated. 运氢 (t) impact.

[0124] A green hydrogen production, storage and transportation integrated real-time operation monitoring system, used to implement the above-mentioned green hydrogen production, storage and transportation integrated real-time operation monitoring method, includes the following modules:

[0125] Hydrogen production status data monitoring module: collects the operating data of the hydrogen production electrolyzer in real time, including voltage, current and temperature, and transmits it to the central processing unit for analysis;

[0126] Hydrogen storage status data monitoring module: used to monitor the pressure, temperature and hydrogen purity of the hydrogen storage tank;

[0127] Hydrogen transportation status data monitoring module: used to collect flow rate and pressure data of hydrogen transportation pipeline;

[0128] Multivariate analysis module: Based on the status data of each link, a multivariate nonlinear model is constructed to conduct linkage analysis on multiple state variables in hydrogen production, storage and transportation to capture the nonlinear coupling relationship between the variables;

[0129] Dynamic control module: According to the analysis results of the multivariable model, the operating conditions of each link are dynamically adjusted. When abnormal fluctuations occur in a certain link, the impact of the abnormal fluctuations on other links is automatically analyzed and real-time compensation is performed.

[0130] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0131] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A real-time operation monitoring method for integrated green hydrogen production, storage and transportation, characterized in that: The following steps are involved: S1, intelligent sensor networks are set up in the hydrogen production, storage and transportation links of green hydrogen production, storage and transportation to collect real-time operating status data of each link, including the voltage and current of the hydrogen production electrolyzer, the pressure and temperature of the hydrogen storage tank, the flow rate, pressure and hydrogen purity of the transportation pipeline; S2, based on the operating status data of each link, conducts multi-state collaborative monitoring, conducts linkage monitoring of multiple state variables in the process of hydrogen production, storage and transportation, and forms a dynamic state diagram of the entire process of production, storage and transportation through data aggregation; S3, based on the operating status data of each link collected in multi-state collaborative monitoring, a multivariable model is constructed to describe the nonlinear coupling relationship between multiple state variables in hydrogen production, storage and transportation; S4, designs a multi-state collaborative control algorithm. Based on the nonlinear coupling relationship described in the multivariable model, the multi-state collaborative control algorithm dynamically adjusts the operating conditions of each link according to the operating status data of different links. When the operating status data of a link fluctuates abnormally, it automatically analyzes the impact of the abnormal fluctuation on other links, and compensates for the abnormal data through historical data and model predictions.

2. A real-time operation monitoring method for integrated green hydrogen production, storage and transportation according to claim 1, characterized in that: The S1 specifically includes: S11, hydrogen production process: Voltage sensors and current sensors are arranged at various positions of the electrolytic cell to monitor the current and voltage changes in the electrolytic cell in real time; A temperature sensor is provided to monitor the temperature in the electrolytic cell; S12, hydrogen storage stage: A pressure sensor and a temperature sensor are installed in the hydrogen storage tank to monitor the pressure fluctuation and temperature change in the hydrogen storage tank respectively; The hydrogen purity sensor is installed at the inlet and outlet of the hydrogen storage tank to detect changes in hydrogen purity; S13, hydrogen transportation: Flow rate sensors and pressure sensors are arranged at each node of the transportation pipeline to monitor the flow of hydrogen during transportation in real time, including the flow rate and pressure in the pipeline.

3. A real-time operation monitoring method for integrated green hydrogen production, storage and transportation according to claim 1, characterized in that: In S2, the voltage, current, and temperature data in the hydrogen production link, the pressure, temperature, and hydrogen purity data in the hydrogen storage link, and the flow rate and pressure data in the hydrogen transportation link are summarized to the central control unit; the central control unit synchronizes the data of each link using a timestamp to ensure that the status data of different links are integrated in chronological order; Multi-state collaborative monitoring is used to conduct real-time and independent monitoring of multiple state variables in the process of hydrogen production, storage and transportation, and to track multiple state variables in parallel at the same time.

4. A real-time operation monitoring method for integrated green hydrogen production, storage and transportation according to claim 1, characterized in that: The multivariate model in S3 is built based on a neural network and specifically includes: Input layer: The input layer includes the state variables of each link of green hydrogen production, storage and transportation. The vector representation of the input layer is: Hidden layer: The hidden layer uses multiple neurons to capture the complex nonlinear relationship between the state variables. The output of the hidden layer is expressed as: h(t)=σ(W·x(t)+b), where W is the weight matrix from the input layer to the hidden layer, b is the bias, and σ(·) is the nonlinear activation function; Output layer: The output layer is used to predict the key state variables of hydrogen production, storage and transportation. The output of the output layer is expressed as: Among them, W out is the weight matrix from the hidden layer to the output layer, b out is bias.

5. A real-time operation monitoring method for integrated green hydrogen production, storage and transportation according to claim 4, characterized in that: The training of the multivariate model is based on back propagation and weight update to optimize weights, specifically including: Forward propagation: computing predicted values ​​through the neural network Calculate loss: Calculate error based on loss function; Back propagation: adjust weights and biases based on error gradients; Cumulative error detection and correction: When the prediction error accumulates beyond the threshold, the error correction mechanism is triggered.

6. A real-time operation monitoring method for integrated green hydrogen production, storage and transportation according to claim 5, characterized in that: The error correction mechanism is used to monitor the cumulative error between the predicted output of the multivariable model and the true value. The cumulative error is expressed as: in, is the predicted value of the model at time t, y(t) is the actual state value, and the cumulative trend of the error is determined by continuously accumulating the error value; When the cumulative error exceeds the set safety threshold, the error correction mechanism is automatically triggered, and the correction is expressed as: Among them, β is the error correction coefficient, which is used to adjust the correction amplitude, E 累积 (t) is the cumulative error value.

7. A real-time operation monitoring method for integrated green hydrogen production, storage and transportation according to claim 4, characterized in that: The collaborative control algorithm in S4 is based on the dynamic coupling relationship between various state variables and calculates the optimal operating conditions according to the real-time state data of each link; When an abnormal fluctuation occurs in a certain link, the collaborative control algorithm performs impact analysis and automatically analyzes the potential impact of the fluctuation on other links; The collaborative control algorithm automatically compensates for abnormal conditions based on historical operating data and multivariable model predictions.

8. A green hydrogen production, storage and transportation integrated real-time operation monitoring method according to claim 7, characterized in that: The abnormal fluctuation includes the hydrogen storage tank pressure P 储氢 (t) Abnormal fluctuation analysis, expressed as: ΔP 储氢 (t) = P 储氢 (t)-P 目标 , if ΔP 储氢 (t) is too large, indicating abnormal fluctuations, P 目标 is the target pressure of the hydrogen storage tank.

9. A green hydrogen production, storage and transportation integrated real-time operation monitoring system, used to implement a green hydrogen production, storage and transportation integrated real-time operation monitoring method as claimed in any one of claims 1 to 8, characterized in that: Includes the following modules: Hydrogen production status data monitoring module: collects the operating data of the hydrogen production electrolyzer in real time, including voltage, current and temperature, and transmits it to the central processing unit for analysis; Hydrogen storage status data monitoring module: used to monitor the pressure, temperature and hydrogen purity of the hydrogen storage tank; Hydrogen transportation status data monitoring module: used to collect flow rate and pressure data of hydrogen transportation pipeline; Multivariate analysis module: Based on the status data of each link, a multivariate nonlinear model is constructed to conduct linkage analysis on multiple state variables in hydrogen production, storage and transportation to capture the nonlinear coupling relationship between the variables; Dynamic control module: According to the analysis results of the multivariable model, the operating conditions of each link are dynamically adjusted. When abnormal fluctuations occur in a certain link, the impact of the abnormal fluctuations on other links is automatically analyzed and real-time compensation is performed.

Images