Intelligent control method and system for methanol cracking hydrogen production based on big data

Abstract

The invention discloses an intelligent control method for methanol cracking hydrogen production based on big data. The method comprises the following steps: acquiring hydrogen demand data, methanol raw material parameter data and catalyst parameter data; predicting target hydrogen data in a preset time period based on the hydrogen demand data; inputting the target hydrogen data, the methanol raw material concentration data and the catalyst parameter data into the hydrogen production optimization process model to obtain target control parameters output by the hydrogen production optimization process model; adjusting purification process parameters and hydrogen production process parameters based on the target control parameters; and acquiring real-time hydrogen data based on the adjusted hydrogen production equipment, performing comparative analysis on the real-time hydrogen data and target hydrogen data, judging whether a deviation threshold is exceeded or not, and if the deviation threshold is exceeded, adjusting the purification process parameters and the hydrogen production process parameters in real time. According to the invention, intelligent quantitative control in cracking hydrogen production is realized, and the problems of resource waste and high production cost are avoided as much as possible.

Description

Technical Field

[0001] The present invention relates to the field of methanol hydrogen production, and in particular to a big data-based intelligent control method and system for methanol cracking hydrogen production. Background Art

[0002] With the development of clean energy technologies, hydrogen, as a clean and efficient energy source, has garnered widespread attention worldwide. Among various hydrogen production technologies, methanol cracking has become a research hotspot due to its abundant raw materials and simple process. Methanol cracking primarily decomposes methanol into hydrogen and carbon monoxide through a catalytic reaction, with the production of small amounts of byproducts such as dimethyl ether. This technology not only efficiently produces hydrogen but also demonstrates great potential for industrial and mobile applications due to its low energy consumption and relatively simple operation process.

[0003] Currently, hydrogen production generally adopts a production-driven sales model. This involves companies purchasing a certain amount of methanol feedstock based on past production experience and rough market demand estimates, then producing hydrogen according to established production processes. Under this model, due to the relatively fixed production processes and equipment, it's difficult to quickly adjust product mix. Consequently, after obtaining methanol as a production feedstock, companies often ignore actual demand and purify the methanol, leading to over-purification and waste of resources. Furthermore, under this production-driven sales model, companies may continue to operate hydrogen production equipment even when market demand is insufficient, in order to maintain a certain production scale and output. This wastes energy and increases production costs. Summary of the Invention

[0004] The purpose of the present invention is to solve the problems in the prior art and to propose an intelligent control method and system for methanol cracking hydrogen production based on big data.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for intelligent control of methanol cracking and hydrogen production based on big data, comprising the following steps:

[0007] Obtain hydrogen demand data, methanol feedstock parameter data, and catalyst parameter data;

[0008] predicting target hydrogen data within a preset time period based on the hydrogen demand data;

[0009] Inputting the target hydrogen data, methanol feed concentration data, and catalyst parameter data into a hydrogen production optimization process model to obtain target control parameters output by the hydrogen production optimization process model; the hydrogen production optimization process model is trained using sample data and its corresponding control parameter label results;

[0010] Adjusting purification process parameters and hydrogen production process parameters based on the target control parameters;

[0011] Real-time hydrogen data is obtained based on the adjusted hydrogen production equipment, and the real-time hydrogen data is compared and analyzed with the target hydrogen data to determine whether it exceeds the deviation threshold. If it exceeds the deviation threshold, the purification process parameters and hydrogen production process parameters are adjusted in real time.

[0012] A big data-based intelligent control system for methanol cracking and hydrogen production, comprising:

[0013] An acquisition unit, used to acquire hydrogen demand data, methanol raw material parameter data, and catalyst parameter data;

[0014] a prediction unit, configured to predict target hydrogen data within a preset time period based on the hydrogen demand data;

[0015] a control parameter determination unit, configured to input the target hydrogen data, methanol feed concentration data, and catalyst parameter data into a hydrogen production optimization process model to obtain target control parameters output by the hydrogen production optimization process model; the hydrogen production optimization process model is trained using sample data and its corresponding control parameter label results;

[0016] an output unit, configured to adjust purification process parameters and hydrogen production process parameters based on the target control parameters;

[0017] The feedback adjustment unit is used to obtain real-time hydrogen data based on the adjusted hydrogen production equipment, and compare and analyze the real-time hydrogen data with the target hydrogen data to determine whether it exceeds the deviation threshold. If the deviation threshold is exceeded, the purification process parameters and the hydrogen production process parameters are adjusted in real time.

[0018] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, the steps of the above-mentioned intelligent control method for methanol cracking and hydrogen production based on big data are implemented.

[0019] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned intelligent control method for methanol cracking and hydrogen production based on big data are implemented.

[0020] Compared with the prior art, the present invention has the following advantages:

[0021] The present invention provides an intelligent control method for methanol cracking hydrogen production based on big data. The method accurately predicts target hydrogen data within a preset time period, and then determines control parameters of a purification process and a hydrogen production process based on the predicted target hydrogen data, methanol feed parameter data, and catalyst parameter data, thereby preliminarily realizing intelligent control of cracking hydrogen production under a sales-based production mode, thereby avoiding waste problems caused by over-purification of methanol feed and over-production of hydrogen. The method then detects the real-time produced hydrogen data and compares it with the target hydrogen data to determine whether there is a deviation. If a deviation occurs, the parameters of the purification process and the hydrogen production process are adjusted in a targeted manner, thereby further realizing intelligent quantitative control of cracking hydrogen production, thereby avoiding waste of resources and high production costs as much as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 This is a flow chart of an intelligent control method for hydrogen production by methanol cracking based on big data provided by an embodiment of the present invention;

[0024] Figure 2 This is a schematic structural diagram of an intelligent control system for methanol cracking and hydrogen production based on big data provided by an embodiment of the present invention;

[0025] Figure 3 An embodiment diagram of an electronic device provided by an embodiment of the present invention;

[0026] Figure 4 An embodiment diagram of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0028] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0029] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0030] See Figure 1 , Figure 1 This is a flow chart of an intelligent control method for producing hydrogen from methanol cracking based on big data provided by the present invention. In an embodiment of the present invention, the execution subject of an intelligent control method for producing hydrogen from methanol cracking based on big data is an intelligent control system. Therefore, an intelligent control method for producing hydrogen from methanol cracking based on big data includes:

[0031] Step 10: Obtain hydrogen demand data, methanol raw material parameter data, and catalyst parameter data.

[0032] Specifically, the intelligent control system in the embodiment of the present invention selects the backend server of the hydrogen production workshop, wherein the hydrogen demand data includes historical hydrogen production data, historical hydrogen sales data, current pre-order data and industrial policy data. When obtaining hydrogen demand data, the intelligent control system collects data from multiple data sources, including market sales orders, industry reports, historical sales records, etc. After obtaining the corresponding data, the data is stored in the storage device of the cloud platform or backend server to which the intelligent control system is communicated.

[0033] Furthermore, the methanol raw material parameter data includes conventional concentration and purity data, as well as information such as impurity composition. When obtaining the methanol raw material parameter data, the intelligent control system uses a high-precision chemical analysis instrument (near-infrared spectrometer) for detection, and also stores the detection results in the background server or cloud platform; the catalyst parameter data includes parameters such as the activity, selectivity, and life of the catalyst, and is measured through methods such as X-ray diffraction and scanning electron microscopy. The measurement results are also stored in the background server or cloud platform to facilitate subsequent calls by the intelligent control system.

[0034] It should be noted that when storing hydrogen demand data, methanol raw material parameter data, and catalyst parameter data, the intelligent control system first cleans the collected data carefully to remove duplicates, errors, and missing values, and ensures the accuracy and consistency of the data through logical verification, cross-validation, and other methods to avoid the problem of subsequent prediction deviations due to poor data quality. At the same time, the collection of multiple sub-data adopts a collection method. For example, assuming that the hydrogen demand data set is D H1 , contains n data points of different types but The methanol raw material parameter data set is D MeOH , containing m parameters but The catalyst parameter data set is D cat , contains k parameters but This enables the storage of hydrogen demand data, methanol raw material parameter data, and catalyst parameter data, achieving comprehensive data acquisition, which can more accurately reflect the actual situation and provide a more reliable basis for subsequent prediction and control.

[0035] Step 20: predict target hydrogen data within a preset time period based on the hydrogen demand data.

[0036] Specifically, when the intelligent control system obtains hydrogen demand data, it predicts the target hydrogen data required to be produced in the current generation cycle (i.e., within a preset time period) based on the analysis of historical hydrogen production data, historical hydrogen sales data, current pre-order data, and industrial policy data in the hydrogen demand data, thereby making the prediction results more consistent with the actual situation based on multiple data and factor results, and enhancing the flexibility of the system. The specific process is described in steps 201 to 205.

[0037] Furthermore, the intelligent control system can predict the target hydrogen data and, during the methanol cracking hydrogen production control process, first provide accurate data support for the regulation of equipment parameters in subsequent actual production based on the accurately predicted production targets, including the target hydrogen purity and the corresponding purity quantity.

[0038] In step 30, the target hydrogen data, methanol raw material concentration data and catalyst parameter data are input into the hydrogen production optimization process model to obtain the target control parameters output by the hydrogen production optimization process model; the hydrogen production optimization process model is trained by the sample data and its corresponding control parameter label results.

[0039] Specifically, after obtaining the target hydrogen data, methanol raw material concentration data and catalyst parameter data, the intelligent control system processes the obtained data according to the pre-trained hydrogen production optimization process model to balance economic benefits and environmental protection goals, and finally obtains the target control parameters for the equipment, including the control parameters of the equipment used in the hydrogen production process and the equipment used in the methanol raw material purification process, to achieve precise control of the entire equipment.

[0040] Furthermore, the hydrogen production optimization process model utilizes a deep learning model, such as a neural network, and is trained using a large number of samples to ultimately obtain a trained hydrogen production optimization process model. The specific training process is described in step 301. Using a deep learning model as the basis for training can automatically learn complex relationships in the data, improving the model's accuracy and generalization capabilities.

[0041] Step 40: Adjust the purification process parameters and hydrogen production process parameters based on the target control parameters.

[0042] Specifically, the intelligent control system adopts an automated control system. After receiving the target control parameters, it automatically adjusts the purification process parameters (such as temperature, pressure, flow, etc.) and the hydrogen production process parameters (such as reaction temperature, catalyst dosage, etc.) according to the target control parameters. During the control and adjustment process, the overall parameters and the hydrogen production process are monitored in real time to facilitate real-time adjustment of the parameters based on subsequent feedback, thereby improving the efficiency and accuracy of the adjustment and reducing the interference of human factors. The specific adjustment process is described in steps 401 to 405.

[0043] Step 50: Acquire real-time hydrogen data based on the adjusted hydrogen production equipment, compare and analyze the real-time hydrogen data with the target hydrogen data to determine whether it exceeds the deviation threshold. If it exceeds the deviation threshold, adjust the purification process parameters and hydrogen production process parameters in real time.

[0044] Specifically, the intelligent control system uses high-precision sensors and video monitoring to monitor the adjustment process of target control parameters and the production of hydrogen. For monitoring the hydrogen production process, the sensors monitor the hydrogen production and purity data of the hydrogen production equipment in real time. At the same time, the intelligent control system, based on the target hydrogen data obtained in step 20, also includes data such as hydrogen production and purity within the corresponding time. Therefore, the real-time hydrogen data produced can be compared and analyzed with the target hydrogen data, and a reasonable deviation threshold is set to determine whether the real-time hydrogen data exceeds the deviation threshold. If the deviation threshold is not exceeded, it indicates that the overall production process is stably producing according to the preset production plan. If the deviation threshold is exceeded, it indicates that the overall production plan has an unexpected problem. Therefore, the purification process parameters and hydrogen production process parameters can be adjusted in real time according to the feedback control algorithm (such as PID control) to ensure that the real-time production process is steadily producing according to the preset production calculation. This allows for timely detection of abnormal conditions in the process and ensures production stability. This also improves the anti-interference ability of the intelligent control system.

[0045] Furthermore, in the process of comparing and analyzing the real-time hydrogen data with the target hydrogen data, the specific analysis process is as described in steps 501 to 503 .

[0046] The present invention relates to the technical field of methanol hydrogen production, and proposes a method for intelligent control of methanol cracking hydrogen production based on big data. In the present invention, the proposed intelligent control method accurately predicts target hydrogen data within a preset time period, and then determines the control parameters of the purification process and the hydrogen production process based on the predicted target hydrogen data, methanol raw material parameter data, and catalyst parameter data, thereby preliminarily realizing intelligent control of cracking hydrogen production under a sales-based production mode, avoiding waste problems caused by excessive purification of methanol raw materials and excessive production of hydrogen; then, the real-time produced hydrogen data is detected and compared with the target hydrogen data to determine whether a deviation occurs. If a deviation occurs, the parameters of the purification process and the hydrogen production process are adjusted in a targeted manner, further realizing intelligent quantitative control of cracking hydrogen production, and avoiding waste of resources and high production costs as much as possible.

[0047] In one embodiment, steps 201 to 205 are described as follows:

[0048] Step 201 : Match historical hydrogen production data and historical hydrogen sales data based on time series to obtain a hydrogen sales and production data set.

[0049] Specifically, after determining historical hydrogen production and sales data, the intelligent control system first sorts them chronologically to ensure the consistency of data timestamps. For example, using the Dynamic Time Warping (DTW) algorithm, the two time series data are elastically matched on the time axis to find the optimal matching path to address possible time interval inconsistencies between production and sales data. Ultimately, the historical hydrogen production and sales data are obtained at the same timestamp.

[0050] Furthermore, the intelligent control system will combine the corresponding production data and sales data into a data pair based on each matching time point, and all data pairs constitute the hydrogen sales and production data set.

[0051] Furthermore, in one embodiment, if the historical hydrogen production data sequence is P li ={p1,p2,…,p q}, the historical hydrogen sales data series is S li ={s1,s2,…,s w}, after matching with the DTW algorithm, the hydrogen sales and production dataset is obtained where i x and j x The indexes of production data and sales data in their respective sequences are determined by the DTW algorithm. This allows the dynamic time warping algorithm to match data at different time intervals, avoiding data misassociation caused by time alignment issues. This ensures that the resulting hydrogen sales and production dataset more accurately reflects the relationship between production and sales.

[0052] Step 202 : Segment the hydrogen sales and production data set based on a preset production cycle interval to obtain multiple inventory backlog rates.

[0053] Specifically, the intelligent control system presets a production cycle interval as T0 (for example, T0 can be one week or one month). Starting from the start time of the acquired hydrogen sales and production data set, the data is segmented with T0 as the interval to obtain multiple time periods. For each time period data, the inventory backlog rate is calculated. The calculation formula for the inventory backlog rate is: Among them, P t represents the hydrogen production in time period t, S t represents the hydrogen sales volume in time period t, se represents a specific time period obtained by segmenting the hydrogen sales and production dataset, ∑ t∈se Indicates the sum of data at all time points within the time period.

[0054] Furthermore, in one embodiment, if the preset production cycle interval is one month, for the first month, the hydrogen production and sales data of each day in that month are substituted into the above formula to calculate the inventory backlog rate of that month. Similarly, the entire hydrogen sales and production data set is segmented according to the preset intervals to obtain multiple inventory backlog rates IR1, IR2, ..., IR z By calculating the inventory backlog rate by segment according to the production cycle interval, we can clearly see the changes in inventory in different time periods, which is helpful to analyze the cyclical laws and trends of inventory backlog.

[0055] Step 203 : Based on the changing patterns of multiple inventory backlog rates, the current inventory backlog rate is predicted, and the fault tolerance rate in the current production cycle is determined based on the current inventory backlog rate.

[0056] Specifically, after the intelligent control system obtains multiple inventory backlog rates within a period of time, it can use multiple analysis methods to determine the change patterns between the multiple inventory backlog rates, and then, based on the change patterns, it can predict the inventory backlog rate in the current time period. At this time, in order to avoid accidents or emergencies in the production process, the company generally sets corresponding spare quantities for the production plan required to improve the company's fault tolerance rate during production and sales. Therefore, it fully utilizes the time correlation and change patterns and spare quantities in the historical inventory backlog rate data, and can more accurately predict the capacity rate, provide important reference for production decisions, and help companies arrange production reasonably and deal with possible inventory fluctuations. However, it should be noted that the inventory backlog rate and spare quantity of hydrogen production and sales are often affected by seasonal factors. Therefore, it is necessary to comprehensively consider seasonal factors and determine the fault tolerance rate more accurately. The specific process is as described in steps 2031 to 2034.

[0057] Step 204: Determine a policy impact index based on the impact of industrial policy data on hydrogen demand.

[0058] Specifically, when determining the target hydrogen data, the intelligent control system should also consider the impact of industrial policies on actual demand. This is because the research and development and use of hydrogen are affected by economic factors, which are in turn affected by industrial policies. For example, if industrial policies encourage the development of hydrogen fuel cell vehicles, it will stimulate automakers to increase their investment in the research and development of hydrogen fuel cells and their use, thereby affecting the demand for hydrogen. Therefore, comprehensively considering the impact of industrial policies and determining the policy impact index can more accurately predict the target hydrogen data. The specific process of determining the policy impact index is described in steps 2041 to 2044.

[0059] Step 205 , the current pre-order data is integrated with the fault tolerance rate and policy impact index in the current production cycle to obtain target hydrogen data.

[0060] Specifically, after determining the fault tolerance rate and government impact index within the current production cycle, the intelligent control system uses a weighted average method to integrate the three factors that affect the target hydrogen based on the initial current estimated data. Specifically, it can be expressed as: target hydrogen data THD = ω1*OD + ω2*FR + ω3*PI, where OD represents the current estimated data, FR represents the fault tolerance rate within the current production cycle, PI represents the government impact index, ω1, ω2, and ω3 are the corresponding weights, and ω1+ω2+ω3=1.

[0061] Furthermore, in the process of determining ω1, ω2, and ω3, the intelligent control system uses the AHP method to construct a judgment matrix A, where A ij Indicates the importance of factor i relative to factor j, by calculating the maximum eigenvalue λ of the judgment matrix max And the corresponding eigenvector W0, normalize the eigenvector to get the weight vector Make the weights reflect the relative importance of each factor reasonably

[0062] The embodiment of the present invention comprehensively considers multiple factors such as historical production and sales data, current pre-order data, inventory status, and industrial policies to predict target hydrogen data, so that the prediction results more comprehensively and accurately reflect the actual market demand. In addition, through time series analysis and real-time data processing, it can timely capture the impact of market changes and policy adjustments on hydrogen demand, and realize dynamic prediction and adjustment.

[0063] In one embodiment, steps 2031 to 2034 are described as follows:

[0064] Step 2031: Determine a change trend based on the change patterns of multiple inventory backlog rates, and predict the current inventory backlog rate based on the change trend.

[0065] Specifically, after receiving multiple inventory backlog rates, the intelligent control system can use time series analysis methods to process multiple inventory backlog rate data. First, calculate the moving average, and set the inventory backlog rate sequence as I o ={y1,y2,…,y i}, the moving average period is u, then the moving average sequence MA={ma1,ma2,…,ma i-u+1},in h=1,2,…,i-u+1, then observe the direction of the moving average sequence to determine the initial trend.

[0066] Furthermore, the inventory backlog rate series is fitted through a linear regression model, and the linear regression equation is y to =a+bto+∈ t0 , where yto represents the inventory backlog rate at the t0th time point, a represents the intercept, b represents the slope, ∈ t0 Denotes the error term. And the least squares method is used to estimate the parameters a and b, that is, by minimizing Determine the values of a and b, and judge the upward or downward trend of the inventory backlog rate based on the positive or negative value of b. Make a forecast based on the determined trend. If the trend is linear growth, predict the current inventory backlog rate. If the trend is linearly declining, the same formula can be used for prediction. On the other hand, for complex trends, more advanced time series models such as ARIMA (autoregressive integrated moving average model) can be used. First, the data is differentiated to make it stable and the model parameter p is determined. q (autoregressive order), d q (difference order), q q (moving average order), and make predictions after training the model with historical data.

[0067] Step 2032: Obtain the reserve quantity of the current production cycle, and determine the current reserve rate based on the reserve quantity.

[0068] Specifically, the intelligent control system is connected to the enterprise inventory management system to obtain the hydrogen reserve volume S reserved for the current production cycle. q , the calculated output P in the current production cycle ji , then the current reserve

[0069] Step 2033: Based on seasonal factors, the current inventory backlog ratio and the current reserve ratio are respectively corrected to obtain the target inventory backlog ratio and the target reserve ratio.

[0070] Specifically, the intelligent control system collects inventory backlog rate and reserve rate data from multiple production cycles in the past, classifies them by season, and calculates the average inventory backlog rate for each season. and the mean reserve rate and the overall mean and For the current inventory backlog rate Seasonal correction factor Target inventory backlog ratio If it is summer now, the average summer inventory backlog rate is 0.2, the overall average is 0.15, and the predicted current inventory backlog rate is 0.18, then the seasonal correction coefficient Target inventory backlog ratio For the current reserve ratio SR, the seasonal correction factor Target reserve ratio SR tar =SR*C SR .

[0071] Step 2034: Compare and judge the target inventory backlog ratio with the target reserve ratio. If the target inventory backlog ratio is greater than or equal to the target reserve ratio, the current inventory backlog ratio is determined as the fault tolerance ratio within the current production cycle; if the target inventory backlog ratio is less than the target reserve ratio, the target reserve ratio is determined as the fault tolerance ratio within the current production cycle.

[0072] Specifically, the intelligent control system receives the target inventory backlog rate I tar and target reserve ratio SR tar After that, it is judged. tar ≥SR tar When , it means that the current inventory backlog situation is more serious than the standby situation. At this time, the fault tolerance rate FR in the current production cycle is FR=I tar . When I tar <SR tar When , it indicates that the backup situation is relatively sufficient, and the fault tolerance rate FR in the current production cycle is SR tar Ultimately, the fault tolerance rate is determined by comparison, which reasonably considers the relative relationship between inventory backlog and spare capacity, and can provide a more practical reference indicator for production decision-making.

[0073] The embodiment of the present invention comprehensively analyzes and determines the fault tolerance rate by comprehensively considering multiple aspects such as the inventory backlog rate change trend, spare quantity, and seasonal factors, making the result more reliable. In addition, it also grasps the inventory backlog rate change trend through time series analysis and combines it with seasonal correction to adapt to the production and operation characteristics of different periods, providing a dynamic and practical fault tolerance rate.

[0074] In one embodiment, steps 2041 to 2044 are described as follows:

[0075] Step 2041: semantically parse and classify the industrial policy data to obtain multiple sub-policies.

[0076] Specifically, the intelligent control system uses natural language processing technology and pre-trained language models (such as BERT) to encode industrial policy text data, converting the text into a computer-understandable vector form. Through lexical analysis, syntactic analysis, and semantic analysis, key information from the policy text is extracted, such as the policy subject, policy object, policy measures, and policy objectives. Based on this extracted key information, classification rules are developed to categorize policies. For example, according to the role of policies, they can be divided into hydrogen production policies, hydrogen storage policies, hydrogen transmission policies, and hydrogen use policies; according to the nature of the policies, they can be divided into incentive policies, regulatory policies, and restrictive policies.

[0077] Step 2042 : Compare each sub-policy with the policy quantification database to obtain a quantitative score corresponding to each sub-policy.

[0078] Specifically, the intelligent control system first constructs a policy quantification database, pre-stored with various common sub-policies and their corresponding quantitative score ranges and quantitative criteria. Quantification criteria can include the policy's funding scale, coverage, and enforcement strength. For example, for a hydrogen production subsidy sub-policy, if the subsidy reaches a certain amount, it will be assigned a higher quantitative score; if the subsidy covers a large number of enterprises, the quantitative score will also be increased accordingly. For each sub-policy, the database is searched for matching quantitative criteria based on its specific content. For example, a hydrogen production subsidy sub-policy stipulates a 500 yuan subsidy per ton of green hydrogen. The database is searched for a mapping between the green hydrogen subsidy amount and the quantitative score. Assume that a 500 yuan subsidy corresponds to a quantitative score of 8 points. For sub-policies that are difficult to directly match, an expert scoring method is used in conjunction with reference criteria in the database for quantification. Experts assign a quantitative score within the database's specified score range based on the actual impact of the sub-policy.

[0079] Furthermore, let the sub-policy set be The policy quantification database is DS, which stores the sub-policy type t t and quantitative score q f The corresponding relationship (t t ,q f ). For sub-policy s i , determine its type Find the corresponding quantitative score in the database DS If there is no direct match in the database, let the expert scoring function be f(s i ), experts follow the sub-policy s i The score range specified by the database Quantitative scores are given and

[0080] Step 2043 , adding the quantitative scores of the multiple sub-policies to obtain a quantitative value of the comprehensive impact of the current policy on hydrogen demand.

[0081] Specifically, the intelligent control system obtains a quantitative score for each sub-policy Perform summation to obtain the comprehensive impact quantification value

[0082] Step 2044: judge the comprehensive impact quantification value based on the preset benchmark value to obtain the policy impact index.

[0083] Specifically, the intelligent control system presets a reference value Q0. This reference value represents the quantitative value at which the policy has no significant impact on hydrogen demand. For example, if the quantitative score range is 0-10, the reference value Q0 can be set to 5. Policy Impact Index I zh The calculation method is: when Qz ≥Q0, When Q z < Q0, Make the policy impact index range from [0, 1], and the larger the value, the stronger the promotion effect of the policy on hydrogen demand.

[0084] In the embodiment of the present invention, a complete system is formed through policy text parsing, sub-policy classification, quantification, and finally index determination, comprehensively and systematically evaluating the impact degree of industrial policies on hydrogen demand. With the help of natural language processing technology and policy quantification databases, human subjective factors are reduced, making the evaluation process and results more objective and accurate.

[0085] In one embodiment, the description of step 301 is as follows:

[0086] Step 301, obtain sample data; the sample data includes target hydrogen data, methanol raw material concentration data, and catalyst parameter data; input the sample data into a pre-trained model to obtain the prediction result output by the pre-trained model; obtain the loss value based on the loss function of the pre-trained model according to the pre-trained result; adjust the optimization function in the pre-trained model based on the loss value; predict the prediction result of the sample data based on the adjusted pre-trained module until the loss value output by the loss function is greater than zero, less than or equal to the first preset value (such as 0.05), at least five consecutive loss values decrease in sequence, and the difference between adjacent loss values is less than or equal to the second preset value (such as 0.005).

[0087] Specifically, the intelligent control system collects sample data from multiple channels such as enterprise historical production records, experimental data, and market research. When training the pre-trained model, deep neural networks (DNNs), recurrent neural networks (RNNs), and their variant long short-term memory networks (LSTMs) can be selected. For example, when using LSTM as the training model, the target hydrogen data, methanol raw material concentration data, and catalyst parameter data are pre-processed and transformed into a tensor form suitable for LSTM input. The processed sample data is input into the LSTM model batch by batch. After the input layer in the model receives the data, multiple LSTM units learn the time series features and complex non-linear relationships in the data. Each LSTM unit contains an input gate, a forget gate, and an output gate, which can effectively handle information transmission and memory problems in long sequence data. After layer-by-layer calculations in the hidden layer, the output layer finally outputs the prediction result, which includes predictions of various parameters in the hydrogen production process, such as reaction temperature, pressure, hydrogen production, and purity.

[0088] The embodiment of the present invention uses a comprehensive judgment based on multiple conditions to more accurately determine the convergence state of model training, avoid stopping training too early or too late, and improve the training quality of the model. The first preset value is determined based on the accuracy requirements and experience of the actual hydrogen production process to ensure that the loss value is within an acceptable range. When at least five consecutive groups of loss values show a decreasing trend, it indicates that the model is effectively converging towards the optimization direction. The large difference between adjacent loss values refers to the absolute difference between two adjacent loss values. The second preset value is also set based on experience. When the large difference between adjacent loss values is less than or equal to this value, it indicates that the change in loss value is tending to be stable and the model training is close to convergence.

[0089] In one embodiment, steps 401 to 404 are described as follows:

[0090] Step 401: construct a correlation matrix of target control parameters, hydrogen production process parameters, and purification process parameters.

[0091] Specifically, the intelligent control system first determines the target control parameter set CIC={cic1,cic2,…,cic i}、Hydrogen production process parameter set H2={H21,H22,…,H2 j} and the purification process parameter set PC={PC1,PC2,…,PC l Then, through statistical analysis of historical production data, process principle knowledge, and experimental design, the correlation between various parameters is determined. For example, the synchronous changes of target control parameters (such as hydrogen purity and output) and hydrogen production process parameters (such as reaction temperature, pressure, catalyst dosage, etc.) and purification process parameters (such as adsorbent temperature and regeneration time) in a large amount of historical data are analyzed to construct the correlation matrix A. g , where the incidence matrix A g It is a matrix (i*(j+l)) with elements Indicates the target control parameter cic γ The degree of correlation with the process parameters (hydrogen production or purification process parameters) δ ranges from [-1, 1]. Positive values indicate positive correlation, negative values indicate negative correlation, and larger absolute values indicate stronger correlation.

[0092] Step 402 : Based on the association matrix, the data in the target control parameters are matched one-to-one with the data in the purification process parameters and the hydrogen production process parameters to obtain a parameter matching list.

[0093] Specifically, the intelligent control system traverses the correlation matrix A g , for each target control parameter cic γ , find out the process parameters with the largest absolute value of correlation, and preset the management threshold ε, such as ε=0.5, when |A gγδ When |>ε, confirm the target control parameter cicγ There is a strong correlation with the process parameter δ. Then the associated target control parameters and process parameters are combined into a corresponding relationship pair, and all corresponding relationship pairs constitute the parameter corresponding list L c If the target control parameter cic1 is highly correlated with the hydrogen production process parameter H22 and the purification process parameter PC3, then the list L c It contains corresponding relationships such as (cic1, H22) and (cic1, PC3).

[0094] Step 403 : evaluating the influence of each process parameter on the target control parameter based on the parameter correspondence list to obtain the sensitivity coefficient of each process parameter.

[0095] Specifically, the intelligent control system corresponds to the parameter list L c Each parameter pair (cic γ , xx δ )(xx δ Represents hydrogen production or purification process parameters), adopts local sensitivity analysis method. Fix other process parameters unchanged, and analyze the process parameter xx δ Make a small perturbation Δxx δ , observe the target control parameter cic γ The change in Δcic γ Then the sensitivity coefficient Indicates process parameter xx δ When the relative change is one unit, the target control parameter cic γ Then, through multiple experiments or numerical simulations based on historical data, the sensitivity coefficient of each process parameter to its associated target control parameter is calculated.

[0096] Step 404 : Based on the process principles of the purification process and the hydrogen production process, a qualitative analysis is performed on the relationship between the target control parameters and the process parameters to obtain auxiliary analysis results for each process parameter.

[0097] Specifically, the intelligent control system analyzes the direction and mechanism of each process parameter's impact on the target control parameter from the perspective of process principles such as chemical kinetics and thermodynamics. For example, in hydrogen production, according to the principles of chemical reaction kinetics, increasing the reaction temperature generally accelerates the reaction rate, thereby increasing hydrogen production, but may affect hydrogen purity. Therefore, for each process parameter, a qualitative analysis conclusion is provided, combining process principles and actual production experience, such as "Increasing the reaction temperature will increase hydrogen production but may reduce hydrogen purity." Ultimately, this conclusion constitutes the auxiliary analysis results for each process parameter.

[0098] Step 405 : Adjust the purification process parameters and the hydrogen production process parameters based on the auxiliary analysis results of each process parameter, the sensitivity coefficient of each process parameter, and the target control parameters.

[0099] Specifically, the intelligent control system has a specific target control parameter cic γ , according to its desired adjustment value Δcic γ ,tar, combined with the sensitivity coefficient SS of the process parameters associated with it γδ And auxiliary analysis results to determine the adjustment direction and amount of process parameters.

[0100] Furthermore, process parameters with larger sensitivity coefficients are adjusted first. At the same time, refer to the auxiliary analysis results to avoid adverse effects on other target control parameters due to adjustment of one process parameter. For example, when it is necessary to increase hydrogen production, for process parameters with larger sensitivity coefficients and which can increase hydrogen production by increasing this parameter according to process principle analysis (such as reaction temperature), their values can be appropriately increased; but attention should be paid to whether they will have a negative impact on other target control parameters such as hydrogen purity. And through iterative adjustment, gradually make the target control parameters close to the desired value. After each adjustment, re-evaluate the actual changes in the target control parameters, and further adjust the process parameters based on the feedback results.

[0101] The embodiment of the present invention makes parameter adjustment more scientific and comprehensive by comprehensively considering the correlation, influence and process principles among parameters. By combining the quantitative analysis of the sensitivity coefficient with the qualitative analysis of the process principles, the adjustment direction and adjustment amount of the process parameters can be accurately determined, thereby improving the adjustment accuracy of the target control parameters.

[0102] In one embodiment, steps 501 to 503 are described as follows:

[0103] Step 501: align the real-time hydrogen data with the target hydrogen data according to the time series to obtain a time series list.

[0104] Specifically, the intelligent control system first checks the timestamp formats of the real-time hydrogen data and the target hydrogen data to ensure consistency. If the timestamp formats differ, a format conversion is performed to unify the different precision timestamps into a second-level timestamp.

[0105] Furthermore, the intelligent control system can use linear interpolation or spline interpolation methods to perform time alignment processing on the data. If the real-time hydrogen data sequence is The corresponding timestamp sequence is The target hydrogen data sequence is The corresponding timestamp sequence is Based on the real-time data timestamp, for the target data, if at a certain real-time data time point tr δ If there is no corresponding target data time point, the target data value at that time point is calculated by interpolation. For example, the linear interpolation formula is: γ <tr δ <th γ+1 , then tr δ Target data interpolation at time (hq γ+1 -hq γ ). The aligned real-time hydrogen data and target hydrogen data are arranged into a time series list in chronological order.

[0106] Step 502 : Calculate the deviation index between the real-time hydrogen data and the target hydrogen data based on the time series list.

[0107] Specifically, the deviation index includes absolute deviation index and relative deviation index. The intelligent control system first calculates the absolute deviation index, such as the mean absolute deviation (MAD). Assuming the length of the time series list is N, then in Represents real-time hydrogen data, Indicates the target hydrogen data. For relative deviation indicators, such as mean relative deviation (MRD),

[0108] Step 503 : Compare and analyze the deviation indicator with a preset deviation threshold to determine whether it exceeds the deviation threshold.

[0109] Specifically, the preset deviation threshold of the intelligent control system is determined according to the accuracy requirements of the hydrogen production process, production goals, historical experience and other factors. For example, for the hydrogen purity indicator, the absolute deviation threshold Δ is set according to the product quality standard. abs and relative deviation threshold Δ rel The calculated deviation index is compared with the preset threshold. If the calculated mean absolute deviation MAD>Δ abs or mean relative deviation MRD>Δ rel , it is judged that the real-time hydrogen data exceeds the deviation threshold.

[0110] The embodiment of the present invention ensures that data are compared on the same time scale through time alignment, and comprehensively measures the deviation situation with multiple deviation indicators. Combined with reasonable threshold judgment, the accuracy of judging the deviation between real-time hydrogen data and target hydrogen data is improved. In addition, a complete process is formed from data processing to deviation calculation to threshold judgment. The various steps cooperate with each other, which enhances the reliability of the judgment results and provides a solid basis for whether to adjust the process parameters in the future.

[0111] Optional, see Figure 2 , Figure 2 This is a schematic diagram of the structure of the intelligent control of methanol cracking and hydrogen production based on big data provided by the present invention. The intelligent control of methanol cracking and hydrogen production based on big data includes:

[0112] An acquisition unit 210 is used to acquire hydrogen demand data, methanol feedstock parameter data, and catalyst parameter data;

[0113] The prediction unit 220 is configured to predict target hydrogen data within a preset time period based on the hydrogen demand data;

[0114] The control parameter determination unit 230 is used to input the target hydrogen data, methanol feed concentration data, and catalyst parameter data into the hydrogen production optimization process model to obtain the target control parameters output by the hydrogen production optimization process model; the hydrogen production optimization process model is trained using sample data and its corresponding control parameter label results;

[0115] An output unit 240 is used to adjust purification process parameters and hydrogen production process parameters based on target control parameters;

[0116] The feedback adjustment unit 250 is used to obtain real-time hydrogen data based on the adjusted hydrogen production equipment, and compare and analyze the real-time hydrogen data with the target hydrogen data to determine whether it exceeds the deviation threshold. If it exceeds the deviation threshold, the purification process parameters and hydrogen production process parameters are adjusted in real time.

[0117] The embodiment of the present invention accurately predicts the target hydrogen data within a preset time period, and then determines the control parameters of the purification process and the hydrogen production process based on the predicted target hydrogen data, methanol raw material parameter data and catalyst parameter data, thereby preliminarily realizing intelligent control of cracking hydrogen production under a sales-based production mode, thereby avoiding waste problems caused by excessive purification of methanol raw materials and excessive production of hydrogen; then the real-time produced hydrogen data is detected and compared with the target hydrogen data to determine whether there is a deviation. If a deviation occurs, the parameters of the purification process and the hydrogen production process are adjusted in a targeted manner, thereby further realizing intelligent quantitative control of cracking hydrogen production, thereby avoiding waste of resources and high production costs as much as possible.

[0118] See also Figure 3 , Figure 3 This is a diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0119] Obtain hydrogen demand data, methanol feedstock parameter data, and catalyst parameter data;

[0120] Predict target hydrogen data within a preset time period based on hydrogen demand data;

[0121] Input the target hydrogen data, methanol feed concentration data, and catalyst parameter data into the hydrogen production optimization process model to obtain the target control parameters output by the hydrogen production optimization process model; the hydrogen production optimization process model is trained using sample data and its corresponding control parameter label results;

[0122] Adjusting purification process parameters and hydrogen production process parameters based on target control parameters;

[0123] Real-time hydrogen data is obtained based on the adjusted hydrogen production equipment, and the real-time hydrogen data is compared and analyzed with the target hydrogen data to determine whether it exceeds the deviation threshold. If it exceeds the deviation threshold, the purification process parameters and hydrogen production process parameters are adjusted in real time.

[0124] See also Figure 4 , Figure 4 Detailed description of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 400 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, the following steps are implemented:

[0125] Obtain hydrogen demand data, methanol feedstock parameter data, and catalyst parameter data;

[0126] Predict target hydrogen data within a preset time period based on hydrogen demand data;

[0127] Input the target hydrogen data, methanol feed concentration data, and catalyst parameter data into the hydrogen production optimization process model to obtain the target control parameters output by the hydrogen production optimization process model; the hydrogen production optimization process model is trained using sample data and its corresponding control parameter label results;

[0128] Adjusting purification process parameters and hydrogen production process parameters based on target control parameters;

[0129] Real-time hydrogen data is obtained based on the adjusted hydrogen production equipment, and the real-time hydrogen data is compared and analyzed with the target hydrogen data to determine whether it exceeds the deviation threshold. If it exceeds the deviation threshold, the purification process parameters and hydrogen production process parameters are adjusted in real time.

[0130] On the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute a method for intelligent control of methanol cracking and hydrogen production based on big data provided by the above methods, which includes:

[0131] Obtain hydrogen demand data, methanol feedstock parameter data, and catalyst parameter data;

[0132] Predicting target hydrogen data within a preset time period based on hydrogen demand data;

[0133] Input the target hydrogen data, methanol feed concentration data, and catalyst parameter data into the hydrogen production optimization process model to obtain the target control parameters output by the hydrogen production optimization process model; the hydrogen production optimization process model is trained using sample data and its corresponding control parameter label results;

[0134] Adjusting purification process parameters and hydrogen production process parameters based on target control parameters;

[0135] Real-time hydrogen data is obtained based on the adjusted hydrogen production equipment, and the real-time hydrogen data is compared and analyzed with the target hydrogen data to determine whether it exceeds the deviation threshold. If it exceeds the deviation threshold, the purification process parameters and hydrogen production process parameters are adjusted in real time.

[0136] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0137] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or certain parts of the embodiment.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the 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 various embodiments of the present invention.

Claims

1. A method for intelligent control of methanol cracking and hydrogen production based on big data, characterized in that: The following steps are involved: Obtain hydrogen demand data, methanol feedstock parameter data, and catalyst parameter data; predicting target hydrogen data within a preset time period based on the hydrogen demand data; Inputting the target hydrogen data, methanol feed concentration data, and catalyst parameter data into a hydrogen production optimization process model to obtain target control parameters output by the hydrogen production optimization process model; the hydrogen production optimization process model is trained using sample data and its corresponding control parameter label results; Adjusting purification process parameters and hydrogen production process parameters based on the target control parameters; Real-time hydrogen data is obtained based on the adjusted hydrogen production equipment, and the real-time hydrogen data is compared and analyzed with the target hydrogen data to determine whether it exceeds the deviation threshold. If it exceeds the deviation threshold, the purification process parameters and hydrogen production process parameters are adjusted in real time.

2. The intelligent control method for hydrogen production by methanol cracking based on big data according to claim 1, characterized in that: The hydrogen demand data includes historical hydrogen production data, historical hydrogen sales data, current pre-purchase data, and industrial policy data. The target hydrogen data within a preset time period is predicted based on the hydrogen demand data, including: Matching the historical hydrogen production data and the historical hydrogen sales data based on a time series to obtain a hydrogen sales and production data set; Segmenting the hydrogen sales and production data set based on preset production cycle intervals to obtain multiple inventory backlog rates; Predicting a current inventory backlog rate based on the multiple patterns of changes in the inventory backlog rates, and determining a fault tolerance rate within a current production cycle based on the current inventory backlog rate; Determine a policy impact index based on the impact of the industrial policy data on hydrogen demand; The current pre-order data is integrated with the fault tolerance rate in the current production cycle and the policy impact index to obtain target hydrogen data.

3. The intelligent control method for hydrogen production from methanol cracking based on big data according to claim 2, characterized in that: The predicting of the current inventory backlog rate based on the changing patterns of the multiple inventory backlog rates, and determining the fault tolerance rate within the current production cycle based on the current inventory backlog rate, includes: Determining a change trend based on the change patterns of the multiple inventory backlog rates, and predicting a current inventory backlog rate based on the change trend; Obtaining a reserve amount in a current production cycle, and determining a current reserve rate based on the reserve amount; Correcting the current inventory backlog rate and the current reserve rate based on seasonal factors to obtain a target inventory backlog rate and a target reserve rate; The target inventory backlog rate is compared with the target reserve rate. If the target inventory backlog rate is greater than or equal to the target reserve rate, the previous inventory backlog rate is determined as the fault tolerance rate within the current production cycle; if the target inventory backlog rate is less than the target reserve rate, the target reserve rate is determined as the fault tolerance rate within the current production cycle.

4. The intelligent control method for hydrogen production from methanol cracking based on big data according to claim 2, characterized in that: Determining the policy impact index based on the impact of the industrial policy data on hydrogen demand includes: Performing semantic analysis and classification on the industrial policy data to obtain multiple sub-policies; Comparing each of the sub-policies with the policy quantification database to obtain a quantitative score corresponding to each sub-policy; Adding the quantitative scores of the multiple sub-policies to obtain a quantitative value of the comprehensive impact of the current policy on hydrogen demand; The comprehensive impact quantification value is judged based on a preset benchmark value to obtain the policy impact index.

5. The intelligent control method for methanol cracking and hydrogen production based on big data according to claim 1 is characterized in that: The training steps of the hydrogen production optimization process model include: Obtain sample data; the sample data includes target hydrogen data, methanol feed concentration data and catalyst parameter data; input the sample data into a pre-training model to obtain a prediction result output by the pre-training model; obtain a loss value based on the pre-training result based on a loss function of the pre-training model; adjust the optimization function in the pre-training model based on the loss value; predict the prediction result of the sample data based on the adjusted pre-training module until the loss value output by the loss function is greater than zero, less than or equal to a first preset value, at least five groups of consecutive loss values decrease in sequence, and the difference between adjacent loss values is less than or equal to a second preset value.

6. The intelligent control method for hydrogen production from methanol cracking based on big data according to claim 1, characterized in that: The adjusting of purification process parameters and hydrogen production process parameters based on the target control parameters includes: Constructing a correlation matrix among the target control parameters, the hydrogen production process parameters, and the purification process parameters; Based on the association matrix, the data in the target control parameters are matched one-to-one with the data in the purification process parameters and the hydrogen production process parameters to obtain a parameter correspondence list; Evaluate the influence of each process parameter on the target control parameter based on the parameter corresponding list to obtain a sensitivity coefficient of each process parameter; Based on the process principles of the purification process and the hydrogen production process, a qualitative analysis is performed on the relationship between the target control parameters and the process parameters to obtain auxiliary analysis results for each process parameter; The purification process parameters and the hydrogen production process parameters are adjusted based on the auxiliary analysis results of each process parameter, the sensitivity coefficient of each process parameter and the target control parameter.

7. The intelligent control method for methanol cracking and hydrogen production based on big data according to claim 1, characterized in that: The comparing and analyzing the real-time hydrogen data with the target hydrogen data to determine whether a deviation threshold is exceeded includes: Aligning the real-time hydrogen data with the target hydrogen data in time series to obtain a time series list; Calculating a deviation index between the real-time hydrogen data and the target hydrogen data based on the time series list; The deviation index is compared and analyzed with a preset deviation threshold to determine whether it exceeds the deviation threshold.

8. A big data-based intelligent control system for methanol cracking to produce hydrogen, applied to the big data-based intelligent control method for methanol cracking to produce hydrogen as claimed in any one of claims 1 to 7; the big data-based intelligent control system for methanol cracking to produce hydrogen comprises: An acquisition unit, used to acquire hydrogen demand data, methanol raw material parameter data, and catalyst parameter data; a prediction unit, configured to predict target hydrogen data within a preset time period based on the hydrogen demand data; a control parameter determination unit, configured to input the target hydrogen data, methanol feed concentration data, and catalyst parameter data into a hydrogen production optimization process model to obtain target control parameters output by the hydrogen production optimization process model; the hydrogen production optimization process model is trained using sample data and its corresponding control parameter label results; an output unit, configured to adjust purification process parameters and hydrogen production process parameters based on the target control parameters; The feedback adjustment unit is used to obtain real-time hydrogen data based on the adjusted hydrogen production equipment, and compare and analyze the real-time hydrogen data with the target hydrogen data to determine whether it exceeds the deviation threshold. If the deviation threshold is exceeded, the purification process parameters and the hydrogen production process parameters are adjusted in real time.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the intelligent control method for methanol cracking and hydrogen production based on big data as described in any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent control method for methanol cracking and hydrogen production based on big data as described in any one of claims 1 to 7 are implemented.

Images