A distributed methanol power generation method and device

Abstract

The present invention discloses a distributed methanol power generation method and device, relating to the technical field of fuel cell power generation. The method includes: predicting power demand through historical power data, grid load information and real-time environmental factors, generating a methanol supply plan, and dynamically controlling the methanol pumping of a target independent power generation unit; adjusting the operating parameters of a reforming reactor by using a two-way optimization feedback mechanism to obtain an optimal reforming plan and prepare hydrogen-rich gas for fuel cell power generation; dynamically adjusting the number of operating independent power generation units according to real-time power demand changes. The present invention solves the technical problems that the existing distributed methanol power generation method relies on single-parameter adjustment, is difficult to cope with the coupling effect of multiple factors, has low operating efficiency and poor adaptability, and achieves the technical effect of improving the operating efficiency and adaptability of the methanol power generation system by introducing a multi-index optimization algorithm and a two-way optimization feedback mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cell power generation, and particularly to a distributed methanol power generation method and device. Background Art

[0002] With the continuous growth of global energy demand and the increasingly strict environmental protection requirements, clean and efficient energy utilization technologies have become a research hotspot. As a clean fuel with high energy density and easy storage, methanol has shown broad application prospects in the field of distributed power generation due to its wide sources and low carbon emission characteristics.

[0003] However, existing distributed methanol power generation methods usually adopt a fixed scheduling mode, that is, fuel supply and power output are carried out according to fixed parameters and preset conditions. This method lacks dynamic response ability when facing power demand fluctuations or environmental changes, and is prone to problems such as fuel waste, insufficient power supply, or uneven load of power generation units. In addition, as the core component of methanol power generation, the performance of the reforming reactor is affected by multiple factors such as temperature, pressure, and catalyst activity. The traditional single-parameter adjustment method is difficult to achieve global optimization, resulting in reduced system efficiency. Summary of the Invention

[0004] This application provides a distributed methanol power generation method and device, which are used to solve the technical problems that the existing distributed methanol power generation method relies on single-parameter adjustment, is difficult to cope with the coupling effect of multiple factors, has low operating efficiency and poor adaptability.

[0005] In the first aspect of this application, a distributed methanol power generation method is provided. The method includes: performing stage power demand prediction based on the historical power usage data, grid load information, and real-time environmental factors of the target area to obtain a stage power demand prediction result; performing methanol supply analysis according to the stage power demand prediction result to generate a methanol supply plan; controlling the methanol pumping of corresponding numbers of target independent power generation units according to the methanol supply plan, where the methanol supply plan includes methanol pumping plans for multiple target independent power generation units, and the multiple target independent power generation units are multiple independent power generation units connected in parallel; for the methanol reforming process of the multiple target independent power generation units, using a two-way optimization feedback mechanism to perform adaptive dynamic adjustment on the reforming process of the reforming reactor to obtain an optimal reforming plan; preparing hydrogen-rich gas according to the optimal reforming plan, transporting the generated hydrogen-rich gas to the fuel cells of each independent power generation unit for power supply, and during the power generation process, monitoring the change of power demand in real time and adding or removing independent power generation units.

[0006] In a second aspect of the present application, a distributed methanol power generation device is provided. The device includes: a power demand prediction module configured to perform stage-based power demand prediction based on historical power usage data, grid load information, and real-time environmental factors of a target area to obtain a stage power demand prediction result; a methanol supply analysis module configured to perform methanol supply analysis based on the stage power demand prediction result to generate a methanol supply plan; a methanol pumping module configured to control methanol pumping of corresponding numbers of target independent power generation units according to the methanol supply plan, wherein the methanol supply plan includes methanol pumping plans of multiple target independent power generation units, and the multiple target independent power generation units are multiple parallel independent power generation units; a reforming process optimization module configured to adaptively and dynamically adjust the reforming process of the reforming reactor for the methanol reforming processes of the multiple target independent power generation units by using a two-way optimization feedback mechanism to obtain an optimal reforming plan; and a power supply module configured to prepare hydrogen-rich gas according to the optimal reforming plan, deliver the generated hydrogen-rich gas to the fuel cells of each independent power generation unit for power supply, and during the power generation process, monitor changes in power demand in real time to add or remove independent power generation units.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] A distributed methanol power generation method and device provided in the present application relate to the technical field of fuel cell power generation. A methanol supply plan is generated through power demand prediction, the methanol pumping of independent power generation units is dynamically controlled, the parameters of the reforming reactor are regulated by using a two-way optimization feedback, an optimal reforming plan is obtained and hydrogen-rich gas is prepared for fuel cell power generation, and changes in power demand are monitored in real time to flexibly adjust the number of operating power generation units, so as to achieve efficient and stable power supply. The technical problem that existing distributed methanol power generation methods rely on single-parameter adjustment, are difficult to cope with the coupling effect of multiple factors, have low operating efficiency and poor adaptability is solved. By introducing a multi-index optimization algorithm and a two-way optimization feedback mechanism, the operating efficiency and adaptability of the methanol power generation system are comprehensively improved, and the technical effect of meeting the dynamic power supply requirements in multiple scenarios is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0010] Figure 1Schematic flow diagram of a distributed methanol power generation method provided by an embodiment of the present application.

[0011] Figure 2 Schematic structural diagram of a distributed methanol power generation device provided by an embodiment of the present application.

[0012] Explanation of reference numerals: Power demand prediction module 11, methanol supply analysis module 12, methanol pumping module 13, reforming process optimization module 14, power supply module 15. Detailed implementation manners

[0013] The present application provides a distributed methanol power generation method and device, which are used to solve the technical problems that the existing distributed methanol power generation method relies on single parameter adjustment, is difficult to cope with the coupling effect of multiple factors, has low operating efficiency and poor adaptability.

[0014] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices.

[0016] Embodiment 1, as Figure 1 shown, the present application provides a distributed methanol power generation method, which is applied to a distributed methanol power generation device. The device includes a plurality of independent power generation units, and each independent power generation unit includes a methanol storage tank, a methanol pump, a reforming reactor and a fuel cell. The method includes:

[0017] P10: According to the historical power usage data, grid load information and real-time environmental factors of the target area, perform stage power demand prediction to obtain the stage power demand prediction result.

[0018] It should be understood that by deeply analyzing and predicting the electricity consumption characteristics of the target area, a scientific basis is provided for subsequent power generation strategies.

[0019] First, collect the historical electricity usage data of the target area, including the electricity consumption trends of users over a past period, the load characteristics during daily peak and trough hours, and seasonal fluctuations, etc. These data provide a basic basis for power demand modeling. Then, obtain the grid load information, that is, the current supply-demand situation and load change trend of the power grid, such as real-time grid frequency, voltage fluctuations, and reserve capacity. These information can reflect the operating pressure of the current power system. Subsequently, combine real-time environmental factors, including weather conditions (such as temperature, humidity, wind speed) and social activity characteristics (such as holidays, major events, etc.), and analyze the dynamic impact of external factors on power demand.

[0020] Through the fusion processing of the above data, through the integration of these multi-source data, use time series prediction models (such as ARIMA, LSTM) or machine learning algorithms (such as random forest, support vector machine) to predict the future power demand in time segments, generate the phased power demand prediction results, that is, the power demand in time segments. The phased power demand prediction results not only include the total power demand but also can be refined to the demand per day or per hour, providing a scientific basis for the dynamic allocation of subsequent methanol supply and power generation units. Through this step, it can be ensured that the power generation system can accurately match the actual power consumption demand of the region, avoid problems of resource waste and insufficient power supply, and achieve the efficient operation of the system.

[0021] P20: According to the phased power demand prediction results, conduct methanol supply analysis and generate a methanol supply plan.

[0022] Furthermore, step P20 of the embodiment of the present application further includes:

[0023] P21: Calculate the total power demand and the power demand in each time segment according to the phased power demand prediction results; P22: Calculate the maximum power generation capacity of each unit according to the power generation efficiency, methanol inventory, and transportation rate limit of the multiple independent power generation units; P23: Based on the total power demand and the power demand in each time segment, conduct matching of independent power generation units to generate a parallel power generation plan, and the parallel power generation plan includes the number of independent power generation units participating in power generation and the corresponding power generation quantity indicators; P24: According to the parallel power generation plan, calculate the methanol demand of each independent power generation unit and generate the methanol supply plan.

[0024] Optionally, according to the phased power demand prediction results, by comprehensively analyzing the performance of the power generation units and fuel supply conditions, formulate a scientific and reasonable methanol supply plan to provide guarantee for efficient power generation.

[0025] First, based on the phased power demand forecast results, determine the total power demand of the target area, that is, the total power consumption that needs to be met within a specific time period. At the same time, subdivide the total demand into power demands for each time period, that is, decompose the power demand according to different time periods of a day (such as peak, flat valley time periods), and clarify the power supply capacity required for each time period. This process can use time series decomposition methods to map the phased forecast results to specific time periods, ensuring the timeliness and accuracy of power distribution.

[0026] Next, evaluate the performance of the independent power generation units and calculate the maximum power generation capacity of each unit. The independent power generation unit is a basic power generation module composed of a methanol storage tank, a methanol pump, a reforming reactor, and a fuel cell, and its power generation efficiency is limited by the methanol conversion efficiency, fuel cell performance, and operating parameters. By comprehensively considering the methanol inventory, pumping capacity, and delivery rate limit of each unit, calculate the maximum power generation capacity of each unit to clarify its contribution potential in the parallel structure.

[0027] Subsequently, according to the total power demand and the power demands for each time period, match the independent power generation units. According to the maximum power generation capacity of each unit, allocate power tasks in order from high-efficiency units to low-efficiency units, giving priority to meeting the power generation potential of high-efficiency units to ensure the overall optimal energy consumption and generate a parallel power generation plan. The parallel power generation plan is a scheduling strategy that determines which power generation units need to be started, when to start, and the target power generation quantity index for each unit. This plan uses optimization algorithms (such as linear programming or heuristic algorithms) to achieve the optimal combination of the number of power generation units and power generation efficiency to ensure that both dynamic demands can be met and resource consumption can be minimized.

[0028] Finally, according to the parallel power generation plan and combined with the power generation quantity index of each unit, calculate the methanol demand required for each unit to complete the power generation task. Furthermore, based on the methanol demand and the delivery rate limit, generate a methanol supply plan, which includes the methanol delivery rate, pumping duration, and replenishment time sequence arrangement for each unit to ensure uninterrupted methanol supply during the task execution of each unit. Ultimately, the methanol supply plan provides fuel guarantee for the power generation execution of the entire system, and at the same time optimizes the resource utilization rate through intelligent distribution to avoid over-supply or fuel shortage situations.

[0029] Through the above steps, the methanol supply plan can accurately match the power demand and power generation capacity, not only optimizing the methanol utilization efficiency, but also ensuring the stability and flexibility of power supply, providing a solid foundation for the efficient operation of the distributed power generation system.

[0030] P30: According to the methanol supply plan, control the corresponding number of target independent power generation units to perform methanol pumping. Among them, the methanol supply plan includes the methanol pumping plans of multiple target independent power generation units, and the multiple target independent power generation units are multiple independent power generation units connected in parallel.

[0031] Specifically, according to the methanol supply plan, control the corresponding number of target independent power generation units to perform methanol pumping to ensure the accurate supply and efficient utilization of methanol fuel. This step realizes the dynamic allocation and stable operation of system resources by coordinating multiple target independent power generation units (configured in parallel).

[0032] First, according to the generated methanol supply plan, determine the number of target independent power generation units that need to operate and the specific fuel demand of each unit. The target independent power generation unit refers to the power generation module that needs to participate in the power generation task during the current period, and its operating state is dynamically adjusted according to the power demand and the methanol supply plan. Priority is given to selecting units with high power generation efficiency and sufficient methanol stock to participate in power generation to ensure the optimal overall energy consumption.

[0033] Next, according to the methanol pumping plan of each unit, control the methanol pump to perform the pumping operation. The methanol pumping plan includes information such as the fuel demand, pumping rate, and pumping duration of each power generation unit. The pumping rate is adjusted by a real-time flow control system to match the actual consumption rate of the unit, ensuring that the fuel supply is synchronized with the power generation load and avoiding fuel surplus or shortage. In addition, the pumping operation is limited by the maximum delivery rate of the methanol pump, and the pumping timing needs to be optimized through time-sharing scheduling.

[0034] During the pumping process, use a real-time monitoring system to dynamically monitor the fuel delivery status of each power generation unit, including fuel flow, remaining stock, and the operating status of the pumping equipment. If it is found that the pumping rate does not match the actual demand of the unit, the system immediately adjusts the pumping parameters through a feedback regulation mechanism to ensure the accuracy and continuity of the supply process.

[0035] Finally, all target independent power generation units operate in parallel to jointly complete the stage power generation task. In the parallel mode, each power generation unit operates independently but supplies power collaboratively, which can effectively share the load and improve the stability and flexibility of the system. At the same time, the standby unit is in a standby state to cope with sudden power demands or operating failures.

[0036] Through the above steps, this process realizes the efficient allocation and supply of methanol fuel, ensures the continuous and stable operation of the target power generation units during the power generation task, and provides support for subsequent real-time optimization and dynamic adjustment. The entire process relies on intelligent control and real-time monitoring technologies to ensure the optimal utilization of system resources and operating efficiency.

[0037] P40: For the methanol reforming process of the multiple target independent power generation units, an adaptive dynamic regulation is performed on the reforming process of the reforming reactor by using a two-way optimization feedback mechanism to obtain an optimal reforming scheme.

[0038] Further, step P40 of the embodiment of the present application further includes:

[0039] P41: Real-time monitor the key operation indexes of the reforming reactor of each target independent power generation unit, where the key operation indexes include positive indexes and negative indexes; P42: Based on the key operation indexes, construct a reforming decision matrix: ; where represents the value of the i-th power generation unit on the j-th index; P43: Perform weighted normalization processing on the reforming decision matrix, and assign weights to each key operation index , to obtain a standard decision matrix: V , * , ; where V is the standard decision matrix, is the value after standardization, is the key index weight; P44: Calculate and obtain the ideal solution and negative ideal solution of each key operation index, and based on the ideal solution and negative ideal solution, combine the standard decision matrix to optimize the reforming scheme to obtain an optimal reforming scheme.

[0040] It should be understood that through the two-way optimization feedback mechanism, an adaptive dynamic regulation is performed on the methanol reforming process of the independent power generation unit to achieve the optimal methanol conversion efficiency and stable fuel cell power generation performance.

[0041] First, the system real-time monitors the operation status of the reforming reactor of each target independent power generation unit through an intelligent sensor network, and extracts key operation indexes. The key operation indexes are the core parameters describing the performance of the reforming reactor, and are divided into positive indexes (such as hydrogen production and temperature stability, the larger the value, the better) and negative indexes (such as energy consumption and by-product emissions, the smaller the value, the better). By real-time monitoring the operation status of the equipment and collecting these indexes, data support is provided for subsequent optimization regulation. The data of the key operation indexes can be collected through sensors or an intelligent monitoring system and transmitted to the control center in real time to ensure the accuracy and timeliness of the system operation data.

[0042] Further, based on the key operation indexes monitored in real time, construct a reforming decision matrix, denoted as ; where represents the value of the i-th power generation unit on the j-th index. This matrix serves as the basis for subsequent optimization calculations and comprehensively describes the performance of each power generation unit on different key indexes.

[0043] To improve the comparability of data and the scientificity of weight assignment, the system performs weighted normalization on the reforming decision matrix. First, the original data is converted into standardized values , and the formula is: . After such processing, the data values of all indicators are scaled to a relative scale, eliminating the dimensional differences. Then, the importance assignment weights of the indicators can be determined through experience, the Analytic Hierarchy Process (AHP), or the entropy weight method , ensuring that the optimization process better meets the actual requirements. For example, the weight of the hydrogen production rate may be relatively high, while the weight of the temperature volatility is relatively low. Finally, the standard decision matrix V is obtained, where * . This matrix is used for subsequent optimization analysis and represents the weighted standardized performance of each power generation unit in terms of key operating indicators.

[0044] Next, the standard decision matrix is analyzed to calculate the ideal solution and the negative ideal solution respectively. Among them, the ideal solution refers to the best combination of values for key operating indicators (for example, the maximum hydrogen production rate and the minimum carbon accumulation rate). The negative ideal solution refers to the worst combination of values for key operating indicators. Based on these solutions, the distances between each power generation unit and the ideal solution and the negative ideal solution are calculated through optimization algorithms (such as TOPSIS or the weighted summation method), and the relative closeness is defined as a measurement index for ranking the advantages and disadvantages of the reforming schemes.

[0045] Finally, according to the ranking of the relative closeness of all units, the operation scheme of the unit with the highest relative closeness is selected as the optimal reforming scheme. For units with relatively low relative closeness, their operating parameters (such as temperature, pressure, etc.) are adjusted to make their performance gradually approach the optimal scheme. By precisely regulating the reforming reaction processes of multiple target independent power generation units, the overall efficiency and stability of the system operation are ensured.

[0046] Furthermore, step P44 of the embodiment of the present application further includes:

[0047] P44-1: Based on the standard decision matrix, calculate the distances between each power generation unit and the ideal solution and the negative ideal solution to obtain the relative distances; P44-2: According to the relative distances, calculate the relative closeness, and use this to rank the power generation states, and select the reforming scheme corresponding to the currently optimal power generation unit as the initial optimal scheme; P44-3: According to the two-way optimization feedback mechanism, correct and adjust the initial optimal scheme to obtain the optimal reforming scheme.

[0048] In a possible embodiment of the present application, to further optimize the efficiency and quality of the methanol reforming reaction, the operating state of the power generation unit is deeply analyzed using a standard decision matrix, and is gradually adjusted through a two-way optimization feedback mechanism to finally obtain an optimal reforming scheme.

[0049] First, according to each key index value of the power generation unit in the standard decision matrix, calculate its distance from the ideal solution and the negative ideal solution. The calculation formula can be:

[0050] ; ; d; where and respectively represent the Euclidean distances between the i-th power generation unit and the ideal solution and the negative ideal solution, and are the ideal value and the negative ideal value of the j-th index respectively. Through this calculation, the system can quantify the degree of closeness of each power generation unit to the optimal performance state and the worst state, that is, the relative distance.

[0051] Furthermore, based on the relative distance, calculate the relative closeness: ; where is the sample relative closeness, which is between 0 and 1. The closer the value is to 1, the closer the operating state of the unit is to the ideal solution and the better the performance.

[0052] Next, sort all power generation units according to the relative closeness, and screen out the power generation unit with the optimal current operating state. The reforming operation parameters corresponding to the optimal power generation unit (such as temperature, pressure, methanol flow rate) are extracted as the initial optimal scheme. After obtaining the initial optimal scheme, further correct and adjust it through a two-way optimization feedback mechanism to obtain the final optimal reforming scheme.

[0053] Furthermore, step P44-3 of the embodiment of the present application further includes:

[0054] P44-31: The two-way optimization feedback mechanism is embedded with a two-way tuning model, and the two-way tuning model includes a value evaluation network and an advantage evaluation network; P44-32: Use the initial optimal scheme as the state vector, input it into the two-way tuning model, the value evaluation network evaluates the value of the scheme to obtain the comprehensive value of the scheme, and the advantage evaluation network outputs the corresponding action advantage for each adjustment action; P44-33: Calculate the action value according to the comprehensive value of the scheme and the action advantage, and select the adjustment action with the maximum action value as the current optimization strategy to correct and adjust the initial optimal scheme to obtain the optimal reforming scheme.

[0055] Furthermore, step P44-33 of the embodiment of the present application further includes:

[0056] P44 - 331: Calculate the action value through the combination of a value evaluation network and an advantage evaluation network: ; where is the action value, is the adjustment action, is the comprehensive value of the solution, is the action 's action advantage.

[0057] Specifically, further adjust and optimize the initial optimal solution through a two - way optimization feedback mechanism, and finally obtain the globally optimal methanol reforming operation solution. This process relies on the synergistic effect of the two - way tuning model to comprehensively evaluate the solution value and the effect of adjustment actions.

[0058] Among them, the two - way optimization feedback mechanism is embedded with a two - way tuning model, and the two - way tuning model includes a value evaluation network and an advantage evaluation network. The value evaluation network is used to globally evaluate the comprehensive performance of the entire initial solution and judge the overall value of the current solution. The advantage evaluation network is used to evaluate the optimization potential and relative importance of each adjustment action (such as temperature, pressure, catalyst activity adjustment) in the solution, and guide the optimization direction of specific parameters. The design of this model ensures that it can not only globally evaluate the overall adaptability of the solution, but also locally optimize the feasibility of key parameters, providing accurate support for dynamic optimization.

[0059] First, represent the initial optimal solution as a state vector , and input it into the two - way tuning model. The state vector includes the key performance indicators of the initial solution (such as the current hydrogen production, energy consumption, temperature, pressure, etc.), and the current operating environment of the solution (such as external conditions such as load demand, power fluctuation, etc.).

[0060] Furthermore, the value evaluation network analyzes the input state vector and outputs the comprehensive value of the solution , which is used to quantify the global performance of the solution. The higher the comprehensive value, the better the adaptability and efficiency of the solution under the current operating conditions. And the advantage evaluation network outputs the action advantage of each action according to the state vector and possible adjustment actions (such as increasing temperature, decreasing pressure, etc.). The action advantage represents the potential of each adjustment action to improve the solution performance.

[0061] Finally, combining the outputs of the value evaluation network and the advantage evaluation network, calculate the action value of each adjustment action: ; where is the action value, indicating the potential of each adjustment action to improve the solution performance under the current state The total optimization potential of executing adjustment action a under the condition of , the larger the value, the more likely the action is to improve the performance of the solution. To adjust the action, It is the comprehensive value of the solution, reflecting the global adaptability of the current solution. For Action The action advantage reflects the potential for optimizing the solution after executing action a.

[0062] From all possible adjustment actions, select the one with the greatest action value Adjustment action , as the current optimization strategy, and implement the selected adjustment action , adjust the parameters of the initial optimal solution (such as increasing the reactor temperature, optimizing the catalyst distribution, adjusting the feed flow rate, etc.) to make the solution state closer to the ideal solution. The revised solution is verified by dynamic feedback to ensure that it is closer to the global optimal state in terms of multi-dimensional performance indicators.

[0063] Through the two-way optimization feedback mechanism embedded in the two-way tuning model, the system can not only globally evaluate the adaptability of the initial optimal solution, but also fine-tune the specific operating parameters. The optimal restructuring solution finally obtained is close to the ideal solution in terms of multi-dimensional performance indicators, and can dynamically adapt to changes in the external operating environment, providing a guarantee for the overall stable and efficient operation of the system.

[0064] P50: Prepare hydrogen-rich gas according to the optimal reforming scheme, transport the generated hydrogen-rich gas to the fuel cells of each independent power generation unit for power supply, and monitor the change of power demand in real time during the power generation process to add or remove independent power generation units.

[0065] Furthermore, step P50 of the embodiment of the present application also includes:

[0066] P51: According to the optimal reforming scheme of the optimal power generation unit, optimize the operating parameters of the remaining target independent power generation units; P52: When the relative proximity of all target independent power generation units is close to the optimal value, stop the scheme adjustment, and prepare hydrogen-rich gas according to the adjusted scheme.

[0067] It should be understood that based on the optimal reforming scheme, efficient preparation and transportation of hydrogen-rich gas is achieved, and during the power generation process, the operating status of independent power generation units is dynamically adjusted to achieve real-time optimization of power supply and maximize resource utilization.

[0068] First, based on the selected optimal power generation unit, according to its optimal reforming scheme, optimize the operating parameters of the remaining target independent power generation units. Exemplarily, by adjusting the temperature curve, make the reaction efficiency of each unit close to the optimal state; dynamically optimize the pressure level to match the methanol conversion rate and hydrogen production efficiency; for different load conditions, adjust the catalyst activation method to reduce reaction delay or by-product generation. Adjust the operating states of all power generation units to be close to the ideal solution to improve the overall system performance. This process uses an intelligent adjustment algorithm to transfer the operating experience of the optimal unit to other units to form an overall optimization.

[0069] Furthermore, calculate the relative proximity of all target independent power generation units in real time. By analyzing the distance between each unit and the optimal state, evaluate the optimization effect of each unit. When the proximity deviation meets the preset threshold (such as less than 5%), stop the scheme adjustment, indicating that the states of all units reach equilibrium and stability. According to the adjusted optimal reforming scheme, start the reforming reactor to prepare hydrogen-rich gas, ensuring that the output and purity of hydrogen generation meet the requirements of the fuel cell. Through the intelligent pipeline system, transport the hydrogen-rich gas to the fuel cells of each independent power generation unit, and utilize the chemical reaction between hydrogen and oxygen to achieve efficient power generation.

[0070] During the power generation process, monitor the fluctuations in power demand in real time. If the power demand increases, dynamically increase the operating independent power generation units; if the demand decreases, appropriately shut down some units to save resources. The adjustment mechanism relies on the power load prediction model and real-time monitoring data to ensure the flexibility of the system.

[0071] Under the guidance of the optimal reforming scheme, gradually optimize the operating parameters of all target power generation units to make the performance of each unit close to the optimal state. During the power generation process, by monitoring the power demand in real time, flexibly adjust the number and state of power generation units to ensure that the system is efficient and stable while meeting the dynamic power supply requirements. Finally, this step realizes the efficient preparation and utilization of hydrogen-rich gas, while improving the flexibility and resource utilization rate of the entire power generation system.

[0072] In summary, the embodiments of the present application have at least the following technical effects:

[0073] The present application predicts power demand through historical power data, grid load information, and real-time environmental factors, generates a methanol supply plan, and dynamically controls the methanol pumping of target independent power generation units. It uses a two-way optimization feedback mechanism to adjust the operating parameters of the reforming reactor to obtain the optimal reforming scheme, prepares hydrogen-rich gas for fuel cell power generation, and dynamically adjusts the number of operating independent power generation units according to the real-time power demand changes to ensure efficient, stable, and environmentally friendly power supply and improve resource utilization rate.

[0074] It has achieved the technical effect of comprehensively improving the operating efficiency and adaptability of the methanol power generation system and meeting the dynamic power supply requirements in multiple scenarios by introducing a multi-index optimization algorithm and a two-way optimization feedback mechanism.

[0075] Example 2. Based on the same inventive concept as the distributed methanol power generation method in the foregoing example, as Figure 2 shown, the present application provides a distributed methanol power generation device. The device in the embodiment of the present application and the method embodiment are based on the same inventive concept. Among them, the device includes:

[0076] A power demand prediction module 11, which is used to perform phased power demand prediction according to the historical power usage data, grid load information and real-time environmental factors of the target area, and obtain the phased power demand prediction result.

[0077] A methanol supply analysis module 12, which is used to perform methanol supply analysis according to the phased power demand prediction result and generate a methanol supply plan.

[0078] A methanol pumping module 13, which is used to control the methanol pumping of corresponding numbers of target independent power generation units according to the methanol supply plan. Among them, the methanol supply plan includes methanol pumping plans for multiple target independent power generation units, and the multiple target independent power generation units are multiple parallel independent power generation units.

[0079] A reforming process optimization module 14, which is used to adaptively and dynamically adjust the reforming process of the reforming reactor for the methanol reforming process of the multiple target independent power generation units by using a two-way optimization feedback mechanism to obtain an optimal reforming plan.

[0080] A power supply module 15, which is used to prepare hydrogen-rich gas according to the optimal reforming plan, transport the generated hydrogen-rich gas to the fuel cells of each independent power generation unit for power supply, and during the power generation process, monitor the change of power demand in real time and add or remove independent power generation units.

[0081] Further, the methanol supply analysis module 12 is further used to perform the following steps:

[0082] Calculate the total power demand and the power demand in each time period according to the phased power demand prediction result;

[0083] Calculate the maximum power generation capacity of each unit according to the power generation efficiency, methanol stock and transmission rate limit of the multiple independent power generation units; based on the total power demand and the power demand in each time period, perform matching of independent power generation units to generate a parallel power generation plan, where the parallel power generation plan includes the number of independent power generation units participating in power generation and the corresponding power generation volume indicators; according to the parallel power generation plan, calculate the methanol demand of each independent power generation unit to generate the methanol supply plan.

[0084] Further, the reforming process optimization module 14 is further configured to perform the following steps:

[0085] Real-time monitor the key operation indicators of the reforming reactor of each target independent power generation unit, where the key operation indicators include positive indicators and negative indicators; based on the key operation indicators, construct a reforming decision matrix: ; where represents the value of the i-th power generation unit on the j-th indicator; perform weighted normalization processing on the reforming decision matrix, and assign weights to each key operation indicator to obtain a standard decision matrix: V , * , ; where V is the standard decision matrix, is the value after standardization, is the weight of the key indicator; calculate and obtain the ideal solution and negative ideal solution of each key operation indicator, and based on the ideal solution and negative ideal solution, combine the standard decision matrix to optimize the reforming plan to obtain the optimal reforming plan.

[0086] Further, the reforming process optimization module 14 is further configured to perform the following steps:

[0087] Based on the standard decision matrix, calculate the distances between each power generation unit and the ideal solution and negative ideal solution to obtain relative distances; according to the relative distances, calculate the relative closeness, and perform power generation status ranking based on this, and select the reforming plan corresponding to the currently optimal power generation unit as the initial optimal plan; according to the two-way optimization feedback mechanism, correct and adjust the initial optimal plan to obtain the optimal reforming plan.

[0088] Further, the reforming process optimization module 14 is further configured to perform the following steps:

[0089] The two-way optimization feedback mechanism is embedded with a two-way tuning model, and the two-way tuning model includes a value evaluation network and an advantage evaluation network; taking the initial optimal solution as a state vector, inputting it into the two-way tuning model, evaluating the value of the solution by the value evaluation network to obtain the comprehensive value of the solution, and outputting the corresponding action advantage for each adjustment action by the advantage evaluation network; calculating the action value according to the comprehensive value of the solution and the action advantage, and selecting the adjustment action with the maximum action value as the current optimization strategy to correct and adjust the initial optimal solution to obtain the optimal reorganized solution.

[0090] Further, the reorganization process optimization module 14 is further configured to perform the following steps:

[0091] Calculate the action value through the combination of the value evaluation network and the advantage evaluation network: ; where is the action value, is the adjustment action, is the comprehensive value of the solution, is the action 's action advantage.

[0092] Further, the power supply module 15 is further configured to perform the following steps:

[0093] Optimize the operating parameters of the remaining target independent power generation units according to the optimal reorganized solution of the optimal power generation unit; when the relative proximity of all target independent power generation units approaches the optimal value, stop the solution adjustment and perform hydrogen-rich gas preparation according to the adjusted solution.

[0094] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0095] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0096] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A distributed methanol power generation method, characterized in that: The method is applied to a distributed methanol power generation device, the device comprising a plurality of independent power generation units, each of which comprises a methanol storage tank, a methanol pump, a reforming reactor and a fuel cell, and the method comprises: According to the historical power usage data, grid load information and real-time environmental factors of the target area, the power demand forecast is carried out to obtain the power demand forecast results; Conduct methanol supply analysis and generate a methanol supply plan based on the electricity demand forecast results for the stage; According to the methanol supply scheme, a corresponding number of target independent power generation units are controlled to perform methanol pumping, wherein the methanol supply scheme includes methanol pumping schemes for multiple target independent power generation units, and the multiple target independent power generation units are multiple parallel independent power generation units; For the methanol reforming process of the multiple target independent power generation units, a two-way optimization feedback mechanism is used to adaptively and dynamically adjust the reforming process of the reforming reactor to obtain an optimal reforming scheme; Prepare hydrogen-rich gas according to the optimal reforming scheme, transport the generated hydrogen-rich gas to the fuel cells of each independent power generation unit for power supply, and monitor the change of power demand in real time during the power generation process to add or remove independent power generation units; Wherein, for the methanol reforming process of the multiple target independent power generation units, the reforming process of the reforming reactor is adaptively and dynamically adjusted by using a two-way optimization feedback mechanism to obtain an optimal reforming scheme, including: Real-time monitoring of key operating indicators of each target independent power generation unit reforming reactor, wherein the key operating indicators include positive indicators and negative indicators; Based on the key operating indicators, a reorganization decision matrix is ​​constructed: ;in, represents the value of the i-th power generation unit on the j-th index; The reorganization decision matrix is ​​weighted and normalized to assign weights to each key operating indicator. , and get the standard decision matrix: V ， * ， ； Among them, V is the standard decision matrix, is the standardized value, is the key indicator weight; The ideal solution and negative ideal solution of each key operating indicator are calculated and obtained, and the reorganization scheme is optimized based on the ideal solution and negative ideal solution in combination with the standard decision matrix to obtain the optimal reorganization scheme.

2. A distributed methanol power generation method according to claim 1, characterized in that: According to the electricity demand forecast results of the said stage, methanol supply analysis is carried out to generate a methanol supply plan, including: Calculate the total power demand and power demand for each period based on the stage power demand forecast results; Calculating the maximum power generation capacity of each unit based on the power generation efficiency, methanol inventory and delivery rate limit of the plurality of independent power generation units; Based on the total power demand and the power demand in each time period, the independent power generation units are matched to generate a parallel power generation plan, wherein the parallel power generation plan includes the number of independent power generation units participating in power generation and corresponding power generation indicators; According to the parallel power generation scheme, the methanol demand of each independent power generation unit is calculated to generate the methanol supply scheme.

3. A distributed methanol power generation method according to claim 1, characterized in that: According to the ideal solution and the negative ideal solution, combined with the standard decision matrix, a reorganization scheme is optimized to obtain an optimal reorganization scheme, including: Based on the standard decision matrix, calculating the distance between each power generation unit and the ideal solution and the negative ideal solution to obtain a relative distance; According to the relative distance, the relative proximity is calculated, and the power generation states are sorted based on this, and the reforming scheme corresponding to the current optimal power generation unit is selected as the initial optimal scheme; According to the two-way optimization feedback mechanism, the initial optimal solution is corrected and adjusted to obtain the optimal reorganization solution.

4. A distributed methanol power generation method as claimed in claim 3, characterized in that: According to the two-way optimization feedback mechanism, the initial optimal solution is corrected and adjusted to obtain the optimal reorganization solution, including: The two-way optimization feedback mechanism is embedded with a two-way tuning model, and the two-way tuning model includes a value evaluation network and an advantage evaluation network; The initial optimal solution is used as a state vector and input into the two-way tuning model, the value evaluation network performs solution value evaluation to obtain the comprehensive value of the solution, and the advantage evaluation network outputs the corresponding action advantage for each adjustment action; According to the comprehensive value of the scheme and the action advantage, the action value is calculated, and the adjustment action with the maximum action value is selected as the current optimization strategy. The initial optimal scheme is corrected and adjusted to obtain the optimal reorganization scheme.

5. A distributed methanol power generation method as claimed in claim 4, characterized in that: According to the comprehensive value of the scheme and the advantages of the action, the action value is calculated, including: The action value is calculated by combining the value evaluation network and the advantage evaluation network: ； Specifically, the initial optimal solution is represented as the state vector , input into the bidirectional tuning model; the state vector It contains the key performance indicators of the initial solution and the current operating environment of the solution. Then, the value evaluation network analyzes the input state vector and outputs the comprehensive value of the solution. , and the advantage evaluation network is based on the state vector and regulating actions , output the action advantage of each action ;in, is the action value, To adjust the action, The comprehensive value of the solution, For Action action advantage.

6. A distributed methanol power generation method as claimed in claim 5, characterized in that: The method of preparing hydrogen-rich gas according to the optimal reforming scheme includes: Optimizing the operating parameters of the remaining target independent power generation units according to the optimal reforming scheme of the optimal power generation unit; When the relative proximity of all target independent power generation units approaches the optimal value, the scheme adjustment is stopped, and hydrogen-rich gas is prepared according to the adjusted scheme.

7. A distributed methanol power generation device, characterized in that: The device comprises a plurality of independent power generation units, each of which comprises a methanol storage tank, a methanol pump, a reforming reactor and a fuel cell, and is used to perform a distributed methanol power generation method according to any one of claims 1 to 6, wherein the device comprises: An electricity demand forecasting module, which is used to forecast the electricity demand in stages according to the historical electricity usage data, grid load information and real-time environmental factors of the target area, and obtain the forecast results of the electricity demand in stages; A methanol supply analysis module, which is used to perform methanol supply analysis and generate a methanol supply plan based on the power demand forecast result of the stage; A methanol pumping module, the methanol pumping module is used to control a corresponding number of target independent power generation units to perform methanol pumping according to the methanol supply scheme, wherein the methanol supply scheme includes methanol pumping schemes for multiple target independent power generation units, and the multiple target independent power generation units are multiple parallel independent power generation units; A reforming process optimization module, wherein the reforming process optimization module is used to adaptively and dynamically adjust the reforming process of the reforming reactor according to the methanol reforming process of the multiple target independent power generation units by using a two-way optimization feedback mechanism to obtain an optimal reforming scheme; A power supply module, wherein the power supply module is used to prepare hydrogen-rich gas according to the optimal reforming scheme, transport the generated hydrogen-rich gas to the fuel cells of each independent power generation unit for power supply, and during the power generation process, monitor the change in power demand in real time and add or remove independent power generation units.

Images