Synthesis gas hydrogen carbon ratio regulation system adaptive to green hydrogen fluctuation

Abstract

The application relates to a synthetic gas hydrogen-carbon ratio regulation system suitable for green hydrogen fluctuation, which comprises the following: a data acquisition module for acquiring training data and real-time operation data; a green hydrogen fluctuation prediction module receiving the training data of the data acquisition module, constructing a prediction model based on the training data, and being used for real-time prediction of the supply amount of green hydrogen in a future period of time to obtain a green hydrogen prediction value; a coal chemical production module for producing and purifying carbon-hydrogen synthetic gas; and a collaborative control module in communication connection with the green hydrogen fluctuation prediction module and the coal chemical production module, used for adjusting the carbon-hydrogen ratio of the synthetic gas according to the green hydrogen prediction value and in combination with the coal chemical production module, so as to ensure that the green hydrogen fluctuation is matched with the coal chemical production. The application realizes an intelligent regulation scheme of the hydrogen-carbon ratio of the synthetic gas suitable for the green hydrogen fluctuation through the green hydrogen fluctuation prediction module, and in combination with the technical scheme of the coal chemical production assistance, so as to predict the supply-demand change in advance.

Description

Technical Field

[0001] This application relates to the field of coal chemical production technology, and in particular to a synthesis gas hydrogen-carbon ratio control system that adapts to fluctuations in green hydrogen. Background Technology

[0002] Coal gasification is the leading technology in modern coal chemical industry. The syngas (CO + H2) produced can be used to produce a variety of chemical products, but the required H / C ratio varies depending on the product being produced. For example, methanol synthesis typically requires an H / C ratio of around 2.0, while methanation usually requires an H / C ratio of 3.0 or higher. Traditionally, the H / C ratio is adjusted mainly through water-gas shift conversion, a process that generates a large amount of CO2, which does not meet the "dual carbon" target. If the purified syngas is coupled with green hydrogen to directly adjust the H / C ratio, partially replacing the syngas shift conversion stage, it would not only reduce CO2 production and significantly lower the shift reaction load and carbon emissions, but also greatly improve the carbon atom utilization rate of the syngas. However, due to the unstable nature of green electricity, green hydrogen exhibits large fluctuations, requiring higher standards for the adaptability and dynamic adjustment capabilities of the coupling system.

[0003] Currently, technical solutions have been proposed to address the issue of unstable green hydrogen supply, including hydrogen storage tanks, gray hydrogen replenishment, load regulation of coal chemical systems, and reverse water gas reaction regulation. However, none of these solutions can completely solve the supply imbalance caused by fluctuations in renewable energy (wind and solar) output. They can only initially improve the hydrogen supply stability in the green hydrogen coupled syngas preparation process. They are difficult to adapt to the load characteristics of coal chemical plants, cope with long-term fluctuations to match the long-term operation requirements of the equipment, and cannot simultaneously take into account the low-carbon advantages of green hydrogen and the rigid requirements of coal chemical production. Summary of the Invention

[0004] This application provides a synthesis gas hydrogen-carbon ratio control system and storage medium adapted to green hydrogen fluctuations. It provides a technical solution for coal chemical production support by predicting supply and demand changes in advance through a green hydrogen volatility prediction module, thereby realizing an intelligent control scheme for the synthesis gas hydrogen-carbon ratio adapted to green hydrogen fluctuations.

[0005] This application provides a syngas hydrogen-to-carbon ratio regulation system adapted to green hydrogen fluctuations, comprising the following steps: a data acquisition module for acquiring training data and real-time operating data; wherein the training data includes historical renewable energy meteorological data and historical load demand data of coal chemical production units, and the real-time operating data includes real-time operating data of the green electricity and green hydrogen system; a green hydrogen fluctuation prediction module for receiving the training data from the data acquisition module, constructing a prediction model based on the training data, and predicting the supply of green hydrogen in real time over a future period to obtain a green hydrogen prediction value; a coal chemical production module for producing and purifying hydrocarbon syngas; and a collaborative control module, communicatively connected to both the green hydrogen fluctuation prediction module and the coal chemical production module, for adjusting the carbon-to-hydrogen ratio of the syngas according to the green hydrogen prediction value and in conjunction with the coal chemical production module, to ensure that green hydrogen fluctuations match coal chemical production.

[0006] Optionally, the green hydrogen volatility prediction module constructs a prediction model, including: based on the training data, using time series analysis to extract the periodic characteristics of green electricity output in the time dimension, obtaining the intraday output peaks and valleys caused by changes in day and night sunlight and wind speed, and the seasonal trend of output caused by seasonal climate differences; based on the training data, using a nonlinear fitting algorithm to process the abrupt changes in green hydrogen supply caused by extreme weather, quantifying the nonlinear relationship between meteorological conditions and green hydrogen production, in order to construct a prediction model.

[0007] Optionally, the green hydrogen volatility prediction module further includes: inputting the real-time operating data into the prediction model and comparing the predicted value at the current moment output by the prediction model with the actual value; if the prediction deviation is less than a set threshold, dynamically adjusting the parameters of the prediction model using a Kalman filter algorithm to make the prediction curve closer to the actual operating state; if the prediction deviation exceeds the set threshold, updating the state variables or parameters of the prediction model using a recursive least squares method based on the fixed hydrogen-to-carbon ratio setting in the gasifier to reduce subsequent prediction deviations.

[0008] Optionally, the coal chemical production module includes: a coal gasification unit for reacting coal with a gasifying agent at high temperature to generate crude syngas mainly composed of carbon monoxide and hydrogen; a syngas purification unit connected to the coal gasification unit for removing impurities from the crude syngas; and a conversion unit connected to the syngas purification unit for producing hydrogen through a water-gas conversion reaction, and adjusting the hydrogen-to-carbon ratio of the syngas by combining green hydrogen provided by the collaborative control module.

[0009] Optionally, the collaborative control module includes: a green hydrogen control unit for performing a two-way regulation function of excess storage and shortage release of green hydrogen; and a fluctuation control unit for adjusting the coal chemical production load according to the fluctuation of the predicted green hydrogen value.

[0010] Optionally, the green hydrogen control unit includes: a green electricity and green hydrogen supply subunit for converting renewable energy into green hydrogen; and a hydrogen storage buffer subunit connected to the green electricity and green hydrogen supply subunit for storing the green hydrogen.

[0011] Optionally, the conversion unit is provided with a green hydrogen injection interface; wherein, the green hydrogen from the green electricity and green hydrogen supply subunit or the hydrogen storage buffer subunit can be mixed with the purified syngas from the syngas purification unit through the green hydrogen injection interface to adjust the hydrogen-to-carbon ratio of the mixed syngas and partially or completely replace the function of the conversion unit.

[0012] Optionally, the fluctuation control unit includes: a conventional fluctuation regulation subunit, used to smooth fluctuations by controlling the hydrogen storage buffer subunit to perform micro-charging or micro-discharging when small fluctuations occur according to the green hydrogen prediction value, and to make slight adjustments to the coal chemical production load; an oversupply scenario regulation subunit, used to moderately increase the coal chemical production load and start the hydrogen storage buffer subunit to store hydrogen when green hydrogen production capacity is predicted to be oversupplied according to the green hydrogen prediction value; and a shortage scenario regulation subunit, used to schedule the hydrogen storage buffer subunit to release hydrogen and simultaneously adjust the coal chemical production load when green hydrogen production capacity is predicted to be short.

[0013] Optionally, the hydrogen storage buffer subunit includes: a high-pressure gaseous hydrogen storage tank, the inlet of which is equipped with a purification device to ensure hydrogen quality, and the capacity of the high-pressure gaseous hydrogen storage tank is configured to match the maximum green hydrogen shortage calculated by the green hydrogen volatility prediction module.

[0014] This application has at least the following advantages: This application primarily involves training a green hydrogen volatility prediction module based on training data collected by the data acquisition module. This module predicts the supply of green hydrogen in real time over a future period. The collaborative control module then adjusts the green hydrogen supply based on the predicted values ​​from the green hydrogen volatility prediction module and, in conjunction with the coal chemical production module, regulates the carbon-to-hydrogen ratio of the syngas to ensure that green hydrogen volatility matches coal chemical production. By predicting supply and demand changes in advance through the green hydrogen volatility prediction module, this application provides a basis for green hydrogen coupling in traditional coal chemical processes. Besides generating necessary gray hydrogen within the syngas, it reduces reliance on gray hydrogen supplementation, lowers carbon emissions from coal chemical processes, and provides stable and reliable technical support for the low-carbon transformation of traditional coal chemical industries. Attached Figure Description

[0015] Figure 1 This is a diagram illustrating the application environment of a synthesis gas hydrogen-to-carbon ratio control system adapted to green hydrogen fluctuations in one embodiment. Figure 2 This is a structural block diagram showing a synthesis gas hydrogen-to-carbon ratio control system adapted to green hydrogen fluctuations in one embodiment. Figure 3 This is a schematic diagram of a syngas hydrogen-to-carbon ratio control system based on green hydrogen fluctuations in one embodiment. Figure 4 This is a schematic structural diagram of a computer device in one embodiment. Detailed Implementation

[0016] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the scope of the present application.

[0017] For ease of understanding, the system to which this application applies will first be described. This application provides a synthesis gas hydrogen-to-carbon ratio control system adapted to fluctuations in green hydrogen, which can be applied to, for example... Figure 1 The system architecture shown includes a user-space file server 103 and a terminal device 101. The terminal device 101 communicates with the user-space file server 103 via a network. The user-space file server 103 can be a file server based on the NFSv3 / v4 protocol, running in a Linux environment. NFS (Network File System) is a network abstraction on top of a file system, allowing remote clients running on the terminal device 101 to access the file system over the network in a manner similar to a local file system. The terminal device 101 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, etc. The user-space file server 103 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0018] Figure 2 A structural block diagram of a synthesis gas hydrogen-to-carbon ratio control system adapted to green hydrogen fluctuations provided in this application embodiment, the system may include: The data acquisition module is used to collect training data and real-time operational data. The training data includes historical meteorological data for renewable energy and historical load demand data for coal chemical production units, while the real-time operational data includes real-time operational data for green electricity and green hydrogen systems. The green hydrogen volatility prediction module receives training data from the data acquisition module, builds a prediction model based on the training data, and uses it to predict the supply of green hydrogen in real time over a period of time, thus obtaining the green hydrogen prediction value. The coal chemical production module is used to produce and purify syngas. The collaborative control module is connected to both the green hydrogen fluctuation prediction module and the coal chemical production module. It is used to adjust the carbon-hydrogen ratio of the syngas based on the green hydrogen prediction value and in conjunction with the coal chemical production module to ensure that the green hydrogen fluctuation matches the coal chemical production.

[0019] In this embodiment, a green hydrogen volatility prediction module is constructed by training data collected by the data acquisition module. Based on this module, the supply of green hydrogen over a future period is predicted in real time. The collaborative control module then adjusts the green hydrogen supply according to the predicted values ​​from the green hydrogen volatility prediction module and, in conjunction with the coal chemical production module, regulates the carbon-hydrogen ratio of the syngas to ensure that green hydrogen volatility matches coal chemical production. By predicting supply and demand changes in advance through the green hydrogen volatility prediction module, a basis is provided for the green hydrogen coupling in traditional coal chemical processes. Besides generating necessary gray hydrogen within the syngas, this reduces reliance on gray hydrogen supplementation, safeguards the low-carbon advantages of green hydrogen, reduces carbon emissions from coal chemical processes, and provides stable and reliable technical support for the low-carbon transformation of traditional coal chemical industries.

[0020] The following is a detailed explanation of each module: Please refer to Figure 3 As shown, the data acquisition module is used to collect training data and real-time running data.

[0021] In one feasible approach, training data includes historical meteorological data for renewable energy and historical load demand data for coal chemical production units. The historical meteorological data for renewable energy includes time series data on wind speed, solar irradiance, and weather conditions from the past few years, used to predict the power generation potential of wind and solar energy, i.e., the source supply capacity of green hydrogen. The historical load demand data for coal chemical production units includes the load adjustment range of gasifiers and the unit's response rate. Real-time operational data includes real-time operational data from the green electricity and green hydrogen system, such as the energy consumption and hydrogen production flow rate of the water electrolysis hydrogen production unit, used to verify and calibrate the prediction model in real time, reflecting the current true state of the system. Thus, the collected training data and real-time operational data from the green electricity and green hydrogen system provide the data foundation for subsequently constructing a green hydrogen volatility prediction module.

[0022] Please continue to refer to Figure 3 As shown, the green hydrogen volatility prediction module is used to receive training data from the data acquisition module and build a prediction model based on the training data to predict the supply of green hydrogen in real time over a period of time, thereby obtaining the green hydrogen prediction value.

[0023] In one feasible approach, a multi-algorithm fusion model is constructed by combining time series analysis with nonlinear fitting algorithms. Specifically, based on training data, time series analysis is used to extract the periodic characteristics of green electricity output over time, obtaining the intraday peaks and valleys caused by changes in day and night sunlight and wind speed, as well as the seasonal trend of output caused by seasonal climate differences. A nonlinear fitting algorithm is then used to handle the abrupt changes in green hydrogen supply caused by extreme weather, quantifying the nonlinear relationship between meteorological conditions and green hydrogen production to construct the predictive model. It should be noted that time series analysis is used to capture the intraday peaks and valleys of green electricity output, enabling early identification of periodic fluctuations in green hydrogen supply. This provides a time window and quantitative basis for the coordinated control module to schedule hydrogen storage buffer subunits in advance and adjust the coal chemical production load, achieving predictive regulation to smooth supply and demand fluctuations. Nonlinear fitting algorithms are used to handle the abrupt changes in green hydrogen supply caused by extreme weather, i.e., rapid and short-term variations in supply. They can handle the nonlinear relationship between meteorological data (such as sudden changes in wind speed or a sharp drop in sunlight due to rapid cloud cover) and green hydrogen production. Their core function is to quantify the complex, non-linear, and non-simple proportional relationship between meteorological conditions such as wind speed, sunlight, and green hydrogen production. When wind speed increases to a certain threshold, the growth rate of green electricity output changes, thus affecting green hydrogen production. This allows the prediction model to accurately reflect the nonlinear patterns in actual production, rather than using a simple linear relationship for rough estimation. The nonlinear fitting algorithm here is a neural network, where the input layer includes wind speed and sunlight intensity. The output layer contains the predicted green hydrogen production, and the activation function is linear. This structure can effectively quantify the nonlinear relationship between meteorological conditions and green hydrogen production. Assuming that green hydrogen production y is related to meteorological variables x1 (wind speed) and x2 (sunlight intensity), the formula can be expressed as: y = β0 + β1x1 + β2x2 + β3x1 2 +β4x2 2 +β5x1x2+ Where β is a coefficient. This is the error term.

[0024] In one example, the time series analysis method uses LSTM to process nonlinear, long-term dependent time series data, such as intraday peaks and troughs and seasonal trends. It can automatically learn features without manual stabilization. By employing time series analysis to extract the periodic features of green electricity output over time, and utilizing a powerful nonlinear machine learning model, it automatically mines the complex chain relationship of "time-weather-output-green hydrogen production" from these features. First, the time information of the acquired high-frequency historical data with a long time span, at least 1-2 years, and preferably more than 3 years, is transformed into features that the model can understand. Then, periodic features are extracted over time, such as the correlation between diurnal changes in sunlight and wind speed and the fluctuations in green electricity output, and the correlation between seasonal climate differences and the seasonal trends in green electricity output. For example, according to time series analysis, on sunny summer days, photovoltaic output typically reaches its peak between 12:00-14:00 (e.g., reaching 85% of installed capacity), while nighttime output is essentially zero. Seasonal fluctuations also exist; at the same location, summer sunshine duration and intensity are higher than winter, and the average daily power generation in summer may be 1.5-2 times that in winter.

[0025] In one example, when real-time meteorological data indicates the possibility of extreme weather events (such as thunderstorms or sandstorms), a nonlinear fitting algorithm can predict a sharp decline in green hydrogen supply in a short period of time. For example, it first calculates the rate of change of green hydrogen production time series within a short time window, such as 15 minutes, i.e., Δproduction / Δt. Then, it calculates the standard deviation within the rolling window. Abnormally high standard deviations identify periods of drastic fluctuations. A high threshold is set, such as the 95th percentile of the historical rate of change. Exceeding this threshold is considered a "mutation point." The threshold exceedance feature is set not only by the absolute values ​​of wind speed and irradiance, but more importantly by the degree and duration of exceeding the key threshold, such as the duration for which wind speed exceeds the cutoff wind speed and the duration for which irradiance is below the start-up threshold (such as 100W / m²). In addition, the rate of change of meteorological data itself can also serve as an indicator feature, such as the rate of decrease in irradiance and the rate of increase in wind speed. These meteorological features, in combination with threshold exceedance features, also indicate extreme weather. For example, high wind speed × wind direction change rate may indicate turbulence, leading to frequent start-stop of wind turbines; low irradiance × high humidity × high cloud cover is more likely to indicate continuous rain rather than brief cloud cover. When real-time collected meteorological data indicates the possibility of extreme weather events (such as thunderstorms and sandstorms), nonlinear fitting algorithms employ model fusion or dedicated sub-model architectures, such as tree-based nonlinear fitting XGBoost and LightGBM, to handle the nonlinear relationships and interaction effects between features, accurately quantifying the magnitude and probability of sudden changes in green hydrogen production under different feature combinations.

[0026] Please continue to refer to Figure 3As shown, the green hydrogen volatility prediction module also includes: inputting real-time operating data into the prediction model and comparing the predicted value at the current moment output by the prediction model with the actual value; if the prediction deviation is less than a set threshold, the parameters of the prediction model are dynamically adjusted through the Kalman filter algorithm to make the prediction curve closer to the actual operating state; if the prediction deviation exceeds the set threshold, the state variables or parameters of the prediction model are updated using the recursive least squares method based on the fixed hydrogen-to-carbon ratio setting in the gasifier to reduce subsequent prediction deviations.

[0027] In one feasible approach, when discrepancies exist between the model's predicted values ​​and the real-time operating data of the green electricity and green hydrogen system, the parameters are dynamically corrected through an iterative process of "predicted green hydrogen supply + updated green hydrogen data" using Kalman filtering, ensuring the predicted curve closely matches the actual operating state. Specifically, Kalman filtering, during stable system operation, smoothly tracks the internal parameters of the prediction model, optimally weighting and correcting minor deviations at each moment, dynamically adjusting parameters in real time to ensure smooth and stable parameter updates and avoid fluctuations caused by measurement noise. This ensures the predicted curve smoothly and robustly reflects the actual operating state. By comparing real-time collected data such as green hydrogen production and electrolyzer power with the predicted values ​​at the current moment, if the deviation exceeds a set threshold of 5%, the state variables or parameters of the prediction model are updated using the least squares method based on real-time data. The least squares method updates the prediction model based on calculations of the fixed H / C ratio in the gasifier to reduce subsequent prediction deviations. The core parameters adjusted include the model's weight coefficients (i.e., the weight of meteorological factors on green hydrogen production), the error correction coefficients (used to match the deviation between predicted values ​​and actual operating data), and the model's nonlinear characteristic parameters. By combining dynamic and static corrections, the green hydrogen volatility prediction module possesses both robustness in daily operation and agility in responding to extreme events, thus improving its prediction accuracy. This allows the system to output green hydrogen supply prediction curves over a predetermined period, such as 6 to 72 hours, in a rolling manner. These curves not only predict future green hydrogen production but also clearly identify periods of hydrogen surplus, shortage, and the magnitude of fluctuations, providing a basis for proactive regulation.

[0028] Please refer to Figure 3 As shown, the collaborative control module includes: a fluctuation control unit, used to adjust the coal chemical production load according to the fluctuation of the green hydrogen predicted value of the green hydrogen fluctuation prediction module; and a green hydrogen control unit, used to perform the bidirectional regulation function of excess storage and shortage release of green hydrogen.

[0029] In one feasible implementation, the green hydrogen control unit includes a green electricity and green hydrogen supply subunit, a hydrogen storage buffer subunit, and a conversion unit. The green electricity and green hydrogen supply subunit is used to convert renewable energy into green hydrogen, such as through water electrolysis. The hydrogen storage buffer subunit is connected to the green electricity and green hydrogen supply subunit and is used to store green hydrogen. The hydrogen storage buffer subunit can be a high-pressure gaseous hydrogen storage tank with a purification device at its inlet to ensure hydrogen quality. The capacity of the high-pressure gaseous hydrogen storage tank is configured to match the maximum green hydrogen shortage calculated by the green hydrogen volatility prediction module. For example, if the green hydrogen production drops sharply during normal gasification operation, falling below the syngas produced under high gasification load, the hydrogen storage buffer subunit is scheduled to release hydrogen based on the required hydrogen volume according to the H / C ratio, simultaneously adjusting the coal chemical production load or optimizing the raw material ratio.

[0030] In one feasible implementation, the fluctuation control unit includes a conventional fluctuation regulation subunit, an excess scenario regulation subunit, and a shortage scenario regulation subunit. The conventional fluctuation regulation subunit is used to smooth out minor fluctuations in the green hydrogen forecast by controlling the hydrogen storage buffer subunit to perform micro-charging or micro-discharging, and to make minor adjustments to the coal chemical production load. The excess scenario regulation subunit is used to moderately increase the coal chemical production load and activate the hydrogen storage buffer subunit to store hydrogen when the green hydrogen forecast predicts an excess capacity. The shortage scenario regulation subunit is used to schedule the hydrogen storage buffer subunit to release hydrogen and simultaneously adjust the coal chemical production load when the green hydrogen forecast predicts a shortage capacity. The main method for making minor adjustments to the coal chemical production load is to prioritize the use of the hydrogen storage buffer subunit's "micro-charging and micro-discharging" to absorb fluctuations. If the forecast shows an afternoon green hydrogen surplus of 100 Nm³ / h, the conventional fluctuation regulation subunit will set the micro-charging flow rate to 50-100 Nm³ / h, while simultaneously slightly increasing the production load to consume the excess hydrogen energy. Conversely, during nighttime shortages, the micro-release flow rate is controlled at 50%-100% of the shortage amount. Production load adjustments are only made when fluctuations persist for an extended period, exceeding the short-term adjustment capacity of the high-pressure gaseous hydrogen storage tank. The demand data collection for coal chemical production load here can include real-time loads of downstream synthesis units, such as methanol and ammonia synthesis, to clarify the system's hydrogen demand target.

[0031] Please refer to Figure 3 As shown, the coal chemical production module includes: a coal gasification unit, used to react coal and gasifying agent at high temperature to generate crude syngas mainly composed of carbon monoxide and hydrogen; a syngas purification unit, connected to the coal gasification unit, used to remove impurities from the crude syngas; and a conversion unit, connected to the syngas purification unit, used to produce hydrogen through a water-gas conversion reaction, and combined with green hydrogen provided by the collaborative control module to adjust the hydrogen-carbon ratio of the syngas.

[0032] In one feasible implementation, the coal gasification unit is the core reactor, reacting coal with a gasifying agent at high temperatures (900°C-1600°C) to produce crude syngas, primarily composed of CO and H2, thus providing carbon atoms and some hydrogen atoms for production. The syngas purification unit removes impurities from the crude syngas, such as sulfides, dust, and chlorides, purifying the syngas to meet the requirements of downstream processes. The shift unit adjusts the H / C ratio of the syngas through the water-gas shift reaction, CO + H2O → CO2 + H2.

[0033] More importantly, the conversion unit is equipped with a green hydrogen injection interface. Green hydrogen from the green electricity and green hydrogen supply subunit or the hydrogen storage buffer subunit can be mixed with purified syngas from the syngas purification unit through the green hydrogen injection interface to adjust the hydrogen-to-carbon ratio of the mixed syngas and partially or completely replace the function of the conversion unit. For example, the green hydrogen fluctuation prediction module predicts and outputs the green hydrogen supply curve for the next 24 hours, showing that 14:00-16:00 today is a surplus period, with a predicted surplus of up to 500 Nm³ / h; and 04:00-08:00 tomorrow is a shortage period, with a predicted shortage of up to 300 Nm³ / h. Based on this, the collaborative control module will formulate a control strategy in advance. From 14:00 to 16:00 today, it will instruct the storage of excess green hydrogen, up to 500 Nm³ / h, into the hydrogen storage buffer subunit. From 04:00 to 08:00 tomorrow, it will instruct the release of hydrogen from the hydrogen storage buffer subunit, up to 300 Nm³ / h, through the green hydrogen injection interface set in the conversion unit, to the coal chemical production module to mix with the purified syngas from the syngas purification unit. This will adjust the hydrogen-to-carbon ratio of the mixed syngas to compensate for supply shortages and ensure that green hydrogen fluctuations match coal chemical production. For example, based on the target H / C ratio, such as 2.0 for methanol, and the initial composition of the syngas, the following stoichiometric formula can be used to calculate: Formula: ΔH = R target × C - H initial ΔH represents the amount of green hydrogen required, and R... target The target H / C ratio, where C is the CO flow rate and H is the CO flow rate. initialFor the initial H2 flow rate, the collaborative control module acquires data in real time (such as the CO / H2 flow rate of the purified syngas) and calculates ΔH. It compares the predicted green hydrogen value: when sufficient, it is directly injected; when insufficient, the hydrogen storage buffer subunit is scheduled to supplement. The green hydrogen injection interface of the conversion unit is used for mixing and adjustment to reduce CO2 emissions from the water-gas conversion. Furthermore, to adapt to the fluctuations in green hydrogen supply, the chemical synthesis unit of the coal chemical production module within the system adjusts the coal chemical production load according to the collaborative control module. The gasifier load adjustment range is 40%-110%, with a unit response rate ≥4%Pe / min. When there is an oversupply of green hydrogen, the hydrogen storage increases the load, i.e., the gasifier load is adjusted to 110%; when there is a shortage of green hydrogen, hydrogen is released to reduce the load, i.e., the gasifier load is adjusted to 40%, to adapt to the control requirements of green hydrogen fluctuations.

[0034] The implementation principle of this embodiment is as follows: This application mainly uses a data acquisition module to collect training data and real-time operational data. Based on historical renewable energy meteorological data and historical load demand data of coal chemical production units from the training data, a multi-algorithm fusion method combining time series analysis and nonlinear fitting is used to iteratively train the model to obtain a green hydrogen volatility prediction module. The prediction results of the green hydrogen volatility prediction module are then corrected in real time based on real-time operational data using a dual-mode adaptive update mechanism. This ensures that the green hydrogen volatility prediction module possesses both robustness in daily operation and agility in responding to extreme events, thereby improving the prediction accuracy of the green hydrogen volatility prediction module. Finally, a collaborative control module is used to perform a two-way adjustment function of "excess hydrogen storage and shortage hydrogen release" according to the prediction results under the conditions of normal green hydrogen fluctuation, shortage, and surplus. This is combined with the mixing of syngas produced by coal chemical production module and coal gasification to adjust the H / C ratio of syngas, achieving partial or complete replacement of high carbon emissions and ensuring that green hydrogen volatility matches coal chemical production. By predicting supply and demand changes in advance through the green hydrogen volatility prediction module, the core pain point of "unpredictable volatility and untimely response" in the traditional coal chemical green hydrogen coupling is solved. In addition to generating the necessary gray hydrogen in the syngas, the dependence on gray hydrogen supplementation is reduced, ensuring the low-carbon advantages of green hydrogen, reducing carbon emissions of coal chemical industry, and providing stable and reliable technical support for the low-carbon transformation of traditional coal chemical industry.

[0035] like Figure 4 The diagram shown is a block diagram of a computer device according to an embodiment of this application. The term "computer device" is intended to represent various forms of digital computers or mobile devices. The digital computer may include a desktop computer, a portable computer, a workbench, a personal digital assistant, a server, a mainframe computer, and other suitable computers. The mobile device may include a tablet computer, a smartphone, a wearable device, etc.

[0036] like Figure 4As shown, device 600 includes a computing unit 601, a ROM 602, a RAM 603, a bus 604, and an I / O interface 605. The computing unit 601, ROM 602, and RAM 603 are interconnected via the bus 604. The I / O interface 605 is also connected to the bus 604.

[0037] The computing unit 601 can execute various processes in the method embodiments of this application according to computer instructions stored in the read-only memory (ROM) 602 or computer instructions loaded from the storage unit 608 into the random access memory (RAM) 603. The computing unit 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. The computing unit 601 can include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. In some embodiments, the methods provided in the embodiments of this application can be implemented as computer software programs, which are tangibly contained in a computer-readable storage medium, such as the storage unit 608.

[0038] RAM 603 can also store various programs and data required for the operation of device 600. Part or all of the computer program can be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609.

[0039] The input unit 606, output unit 607, storage unit 608, and communication unit 609 in device 600 can be connected to I / O interface 605. The input unit 606 can be, for example, a keyboard, mouse, touchscreen, or microphone; the output unit 607 can be, for example, a display, speaker, or indicator light. Device 600 can exchange information and data with other devices through the communication unit 609.

[0040] It should be noted that the device may also include other components necessary for normal operation. It may also include only the components necessary for implementing the solution of this application, without necessarily including all the components shown in the figures.

[0041] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), payload programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof.

[0042] The computer instructions used to implement the methods of this application may be written in any combination of one or more programming languages. These computer instructions may be provided to the computing unit 601 such that when executed by the computing unit 601, such as a processor, the computer instructions cause the execution of the steps involved in the embodiments of the methods of this application.

[0043] The computer-readable storage medium provided in this application can be a tangible medium that can contain or store computer instructions for performing the steps involved in the method embodiments of this application. The computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, and other forms of storage media. The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A synthesis gas hydrogen-to-carbon ratio control system adapted to fluctuations in green hydrogen, characterized in that, include: The system includes a data acquisition module for collecting training data and real-time operational data. The training data includes historical meteorological data for renewable energy and historical load demand data for coal chemical production units. The real-time operational data includes real-time operational data for the green electricity and green hydrogen system. A green hydrogen volatility prediction module receives the training data from the data acquisition module and constructs a prediction model based on the training data to predict the supply of green hydrogen over a future period, obtaining a predicted green hydrogen value. A coal chemical production module produces and purifies syngas. A collaborative control module is communicatively connected to both the green hydrogen volatility prediction module and the coal chemical production module, and adjusts the carbon-to-hydrogen ratio of the syngas according to the predicted green hydrogen value and in conjunction with the coal chemical production module's settings to ensure that green hydrogen volatility matches coal chemical production.

2. The system according to claim 1, characterized in that, The green hydrogen volatility prediction module constructs a prediction model, including: Based on the training data, time series analysis is used to extract the periodic characteristics of green electricity output in the time dimension, obtaining the intraday output peaks and valleys caused by changes in day and night sunlight and wind speed, as well as the seasonal trend of output caused by seasonal climate differences. Based on the training data, a nonlinear fitting algorithm is used to process the abrupt changes in green hydrogen supply caused by extreme weather, quantifying the nonlinear relationship between meteorological conditions and green hydrogen production, in order to construct a prediction model.

3. The system according to claim 2, characterized in that, The green hydrogen volatility prediction module also includes: The real-time operating data is input into the prediction model, and the predicted value output by the prediction model at the current moment is compared with the actual value. If the prediction deviation is less than a set threshold, the parameters of the prediction model are dynamically adjusted using the Kalman filter algorithm to make the prediction curve closer to the actual operating state. If the prediction deviation exceeds the set threshold, the state variables or parameters of the prediction model are updated using the recursive least squares method based on the fixed hydrogen-to-carbon ratio in the gasifier to reduce subsequent prediction deviations.

4. The system according to claim 3, characterized in that, The coal chemical production module includes: The coal gasification unit reacts coal with a gasifying agent at high temperature to produce crude syngas, which is mainly composed of carbon monoxide and hydrogen. The syngas purification unit is connected to the coal gasification unit and is used to remove impurities from the crude syngas. The conversion unit is connected to the syngas purification unit and is used to produce hydrogen through a water-gas conversion reaction, and to adjust the hydrogen-to-carbon ratio of the syngas by combining the green hydrogen provided by the collaborative control module.

5. The system according to claim 4, characterized in that, The collaborative control module includes: The green hydrogen control unit is used to perform a two-way regulation function of excess storage and shortage release of green hydrogen; the fluctuation control unit is used to adjust the coal chemical production load according to the fluctuation of the predicted green hydrogen value.

6. The system according to claim 5, characterized in that, The green hydrogen control unit includes: A green electricity and green hydrogen supply subunit is used to convert renewable energy into green hydrogen; a hydrogen storage buffer subunit is connected to the green electricity and green hydrogen supply subunit and is used to store the green hydrogen.

7. The system according to claim 6, characterized in that: The conversion unit is equipped with a green hydrogen injection interface; wherein... The green hydrogen from the green electricity and green hydrogen supply subunit or the hydrogen storage buffer subunit can be mixed with the purified syngas from the syngas purification unit through the green hydrogen injection interface to adjust the hydrogen-to-carbon ratio of the mixed syngas and partially or completely replace the function of the conversion unit.

8. The system according to claim 5, characterized in that, The fluctuation control unit includes: The conventional fluctuation control subunit is used to smooth out fluctuations by controlling the hydrogen storage buffer subunit to perform micro-charging or micro-discharging when there are small fluctuations based on the predicted green hydrogen value, and to make small adjustments to the coal chemical production load. The surplus scenario control subunit is used to moderately increase the coal chemical production load and start the hydrogen storage buffer subunit to store hydrogen when the predicted green hydrogen value indicates a surplus of green hydrogen production capacity. The shortage scenario control subunit is used to schedule the hydrogen storage buffer subunit to release hydrogen and simultaneously adjust the coal chemical production load when the predicted green hydrogen value indicates a shortage of green hydrogen production capacity.

9. The system according to claim 6, characterized in that, The hydrogen storage buffer subunit includes: The high-pressure gaseous hydrogen storage tank is equipped with a purification device at its inlet to ensure hydrogen quality. The capacity of the high-pressure gaseous hydrogen storage tank is configured to match the maximum green hydrogen shortage calculated by the green hydrogen volatility prediction module.

Images