Non-intervention type electric hydrogen thermal coupling system regulation potential quantification method and system

Abstract

The invention discloses a non-intervention type electro-hydrogen thermal coupling system regulation potential quantification method and system. The method comprises the steps that historical and current operation data of all devices of a system are acquired; establishing an electro-hydrogen thermal coupling external characteristic model comprising a state space and an action space, wherein the state space is a product of the action space and the sensitivity matrix; based on the historical operation data, constructing an initial sensitivity matrix under different typical working conditions; based on the current operation data, performing recursive updating on the sensitivity matrix under each typical working condition; based on the current working condition parameters, self-adaptive smooth weights corresponding to the typical working conditions are calculated, and weighted fusion is carried out on the updated sensitivity matrixes under the typical working conditions to obtain a sensitivity matrix corresponding to the current working condition; and according to the external characteristic model and the sensitivity matrix corresponding to the current working condition, calculating to obtain an instantaneous adjustment potential, an interval adjustment potential and a comprehensive adjustment potential of the electro-hydrogen thermal coupling system. According to the invention, the regulation potential evaluation precision and reusability of the electro-hydrogen thermal coupling system can be improved.

Description

Technical Field

[0001] This invention belongs to the field of regulating potential quantification of electro-hydrogen-thermal coupling systems, and in particular relates to a non-interventional method and system for regulating potential quantification of electro-hydrogen-thermal coupling systems. Background Technology

[0002] Chemical industrial parks are accelerating the construction of distributed energy systems that couple electricity, hydrogen, and heat to address the dual constraints of fluctuating renewable energy sources and continuous energy consumption in process industries. However, existing potential assessments typically rely on on-site scrambling experiments or high-intensity offline simulations, which present problems such as high intervention risks, high costs, lack of replicability, and conflicts with production safety. Furthermore, most methods focus on a single energy channel, neglecting the bidirectional coupling of electrolyzers and fuel cells and the cross-time peak shifting constraints of hydrogen / thermal energy storage. They lack adaptively updated models under different operating conditions, making it difficult to provide unified indicators and capacity curves that can be directly used for scheduling and trading. Moreover, black-box models have poor interpretability and lack robust mechanisms against data quality and model drift. Therefore, there is an urgent need to establish a non-interventional method for quantifying the external characteristic adjustment potential of an electro-hydrogen-thermal coupling system. Based solely on historical / online operating data, this method adaptively identifies the adjustment sensitivity matrix under mechanistic constraints, uniformly constructs the instantaneous potential, interval potential, and comprehensive potential index of electrical power, hydrogen, and thermal power, and outputs capability curves constrained by equipment, safety, and inventory. This enables low-risk, replicable, interpretable, market-oriented, and dispatch-oriented potential assessment, thereby improving the flexibility and economy of chemical industrial parks in supporting the power grid. Summary of the Invention

[0003] To address the issues of poor interpretability of black-box models and lack of robust mechanisms for data quality and model drift in existing technologies, this invention provides a non-interventional method and system for quantifying the regulation potential of an electro-hydrogen thermal coupling system.

[0004] To achieve the above-mentioned objectives, the present invention specifically adopts the following technical solution.

[0005] In a first aspect, the present invention discloses a method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system, comprising: Acquire historical and current operating parameters of the electro-hydrogen-thermal coupling system, as well as historical and current operating data of each device in the system; An electro-hydrogen-thermal coupling external characteristic model is established, including a state space and an action space, and a sensitivity matrix is ​​introduced. The input of the electro-hydrogen-thermal coupling external characteristic model is the action space and the sensitivity matrix, and the output is the state space, which is the product of the action space and the sensitivity matrix. Based on the historical operating parameters of the system, the historical operating data of each device, and the external characteristic model of the electro-hydrogen-thermal coupling, the initial sensitivity matrix under different typical operating conditions is calculated; based on the current operating data, the sensitivity matrix under each typical operating condition is recursively updated; based on the current operating parameters, the adaptive smoothing weight corresponding to each typical operating condition is calculated; based on the adaptive smoothing weight, the updated sensitivity matrix under each typical operating condition is weighted and fused to obtain the sensitivity matrix corresponding to the current operating condition. Based on the external characteristic model and the sensitivity matrix corresponding to the current operating condition, the instantaneous regulation potential, interval regulation potential, and comprehensive regulation potential of the electro-hydrogen thermal coupling system are calculated.

[0006] More preferably, The system includes various devices such as electrolyzers, fuel cells, boilers, and thermal energy storage devices. The electro-hydrogen-thermal coupling external characteristic model is as follows:

[0007] in, For state space, For the action space, K This is the sensitivity matrix; The state space With action space Specifically: ,

[0008] Where, Δ P Δ represents the power exchanged between the electro-hydrogen thermal coupling system and the power grid. N For hydrogen production, Δ Q For heating capacity; To adjust the power of the controllable electrolytic cell, For controllable power adjustment of fuel cells, For the controllable heat regulation power of the boiler, For controllable thermal energy storage and power regulation, It provides controllable power exchange regulation for the power grid.

[0009] More preferably, The initial sensitivity matrix is ​​calculated in the following manner: The historical operating data is time-aligned, and then steady-state segments, fluctuation segments, and outlier samples are identified and differential samples are extracted. The initial sensitivity matrix is ​​solved by weighted constrained least squares with physical priors. K 0, the specific solution method is as follows:

[0010] in, K Let be the sensitivity matrix to be solved. K 0 represents the solution to the least squares model, i.e., the initial sensitivity matrix to be obtained; w t For robust weights, they are determined based on the type of the differenced samples; For the first t The amount of change in the adjustment action of each device in the action space at any given moment. For the first t The changes in each state in the state space at any given time; λ is the regularization coefficient.

[0011] More preferably, The recursive update of the sensitivity matrix under various typical operating conditions based on current operating data specifically includes: The sensitivity matrix is ​​updated online using recursive least squares, and the result of each update is projected onto the set of physical constraints. The calculation method is as follows:

[0012]

[0013]

[0014] in, , They are respectively t time, t The sensitivity matrix at time +1; It is a convex projection operator on the constraint set, used to ensure that the updated sensitivity matrix satisfies the physical prior constraints; This is the recursive least squares gain matrix, used to determine the sensitivity matrix for the current sample pair. The updated weights enable online learning capabilities to adapt to changes in operating conditions. for t The covariance matrix at time t is used to describe the sensitivity matrix. The parameter uncertainty is controlled, and the recursive least squares update magnitude is controlled; It is a numerically stable term, and ; for t The covariance matrix at time +1; It is a forgetting factor and satisfies This is used to improve the model's adaptability to changes in operating conditions.

[0015] More preferably, The adaptive smoothing weights corresponding to each typical operating condition are determined as follows:

[0016]

[0017]

[0018] in, For the first j Adaptive smoothing weights corresponding to typical operating conditions J This represents the total number of typical operating conditions. , The first j , No. k The adaptive smoothing weights before normalization correspond to the typical operating conditions. This is the parameter vector corresponding to the current operating condition. The first obtained through clustering j The central parameter vector of a typical working condition This is the weight matrix of parameters for each operating condition under typical operating conditions. For the current working conditions and the first j Weighted distance between typical operating conditions This is a smoothing factor used to adjust the sensitivity of the weights to changes in operating conditions.

[0019] More preferably, The instantaneous regulation potential of the electro-hydrogen thermal coupling system is the maximum achievable output change within the feasible region of the action space, and is specifically determined as follows:

[0020] in, Ω represents the instantaneous adjustment potential, and Ω represents the set of device constraints in the electro-hydrogen-thermal coupling system. The aforementioned range adjustment potential refers to the adjustment potential within a preset adjustment period. T Within the timeframe, the summation of all changes in the state space at each corresponding moment is expressed as:

[0021] in, φ This represents potential for range-based adjustment.

[0022] More preferably, The comprehensive adjustment potential is determined as follows:

[0023] in, To comprehensively regulate potential, and Let be the weight coefficient, and satisfy... It is used to balance the adjustment needs of instantaneous adjustment and range adjustment; , These are the normalized benchmark values ​​for instantaneous regulation potential and interval regulation potential, respectively, used to characterize the upper limit of the corresponding potential indicators under the structural and equipment constraints of the electro-hydrogen-thermal coupling system.

[0024] Secondly, the present invention discloses a non-interventional electro-hydrogen thermal coupling system regulation potential quantification system based on the aforementioned method, including a data acquisition module, an electro-hydrogen thermal coupling external characteristic model construction module, a sensitivity matrix calculation module, and an electro-hydrogen thermal coupling system regulation potential quantification module. The data acquisition module acquires historical and current operating parameters of the electro-hydrogen-thermal coupling system, as well as historical and current operating data of each device in the system. The module for constructing the electro-hydrogen-thermal coupling external characteristic model establishes an electro-hydrogen-thermal coupling external characteristic model including a state space and an action space, and introduces a sensitivity matrix; the input of the electro-hydrogen-thermal coupling external characteristic model is the action space and the sensitivity matrix, and the output is the state space, and the state space is the product of the action space and the sensitivity matrix; The sensitivity matrix calculation module calculates the initial sensitivity matrix under different typical operating conditions based on the historical operating parameters of the system, the historical operating data of each device, and the electro-hydrogen-thermal coupling external characteristic model; it recursively updates the sensitivity matrix under each typical operating condition based on the current operating data; it calculates the adaptive smoothing weight corresponding to each typical operating condition based on the current operating parameters; and it performs weighted fusion on the updated sensitivity matrix under each typical operating condition based on the adaptive smoothing weight to obtain the sensitivity matrix corresponding to the current operating condition. The regulation potential quantification module of the electro-hydrogen thermal coupling system calculates the instantaneous regulation potential, interval regulation potential, and comprehensive regulation potential of the electro-hydrogen thermal coupling system based on the external characteristic model and the sensitivity matrix corresponding to the current operating condition.

[0025] Thirdly, the present invention provides a terminal, including a processor and a storage medium; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of the first aspects of the present invention.

[0026] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects of the present invention.

[0027] The beneficial effects of this invention are compared with those of the prior art: This invention, without altering the system state or injecting control signals, employs a non-interventional modeling approach based on mechanism-data fusion and a constrained recursive identification method to acquire and adaptively update the regulation sensitivity matrix. It constructs instantaneous potential, interval potential, and a weighted comprehensive potential index for electrical power, hydrogen, and thermal power. This enables a rapid, non-disruptive, interpretable, robust, and cross-condition adaptive assessment of the regulation potential of the electro-hydrogen-thermal coupling system in chemical industrial parks. This improves the accuracy and reusability of potential assessment, supports the scheduling optimization of the electro-hydrogen-thermal coupling system in chemical industrial parks, and facilitates spot / ancillary service market pricing, thereby enhancing the flexible regulation capabilities and economic efficiency of chemical industrial parks. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of the process for quantifying the regulation potential of the non-interventional electro-hydrogen thermal coupling system of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this invention.

[0030] like Figure 1 As shown, this invention discloses a method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system, comprising: Step 1: Obtain the historical and current operating parameters of the electro-hydrogen-thermal coupling system, as well as the historical and current operating data of each device in the system; The devices in the electro-hydrogen thermal coupling system include an electrolyzer, a fuel cell, a boiler, and a thermal energy storage device. Step 2: Establish an electro-hydrogen-thermal coupling external characteristic model including state space and action space, and introduce a sensitivity matrix; the input of the electro-hydrogen-thermal coupling external characteristic model is the action space and the sensitivity matrix, and the output is the state space, and the state space is the product of the action space and the sensitivity matrix; The electro-hydrogen-thermal coupling external characteristic model is as follows:

[0031] in, For state space, For the action space, K This is the sensitivity matrix; The state space and action space are specifically as follows: ,

[0032] Where, Δ P Δ represents the power exchanged between the electro-hydrogen thermal coupling system and the power grid. N For hydrogen production, Δ Q For heating capacity, To adjust the power of the controllable electrolytic cell, For controllable power adjustment of fuel cells, For the controllable heat regulation power of the boiler, For controllable thermal energy storage and power regulation, It provides controllable power exchange regulation for the power grid.

[0033] Step 3: Based on the historical operating parameters of the system, the historical operating data of each device, and the external characteristic model of the electro-hydrogen-thermal coupling, calculate the initial sensitivity matrix under different typical operating conditions; based on the current operating data, recursively update the sensitivity matrix under each typical operating condition; based on the current operating parameters, calculate the adaptive smoothing weight corresponding to each typical operating condition; based on the adaptive smoothing weight, perform weighted fusion on the updated sensitivity matrix under each typical operating condition to obtain the sensitivity matrix corresponding to the current operating condition. The initial sensitivity matrix is ​​calculated in the following manner: The historical operating data is time-aligned, and then steady-state segments, fluctuation segments, and outlier samples are identified and differential samples are extracted. The initial sensitivity matrix is ​​solved by weighted constrained least squares with physical priors. K 0, the specific solution method is as follows:

[0034] in, w t Robust weights are determined based on the type of the differenced sample. When the differenced sample belongs to a steady-state segment, the robust weights are... w t The value range is (0.7, 1.0]. When the difference sample belongs to a fluctuating segment, the robust weights are... w t The value range is (0.1, 0.7]. When the difference sample belongs to the outlier, the robust weights... w t The value range is (0, 0.1]. For the first t The amount of change in the adjustment action of each device in the action space at any given moment. For the first t The changes in each state in the state space at any given time; λ is the regularization coefficient.

[0035] The recursive update of the sensitivity matrix under various typical operating conditions based on current operating data specifically includes: The sensitivity matrix is ​​updated online using recursive least squares, and the result of each update is projected onto the set of physical constraints. The calculation method is as follows:

[0036]

[0037]

[0038] in, , They are respectively t time, t The sensitivity matrix at time +1; It is a convex projection operator on the constraint set, used to ensure that the updated sensitivity matrix satisfies the physical prior constraints; This is the recursive least squares gain matrix, used to determine the sensitivity matrix for the current sample pair. The updated weights enable online learning capabilities to adapt to changes in operating conditions. for t The covariance matrix at time t is used to describe the sensitivity matrix. The parameter uncertainty is controlled, and the recursive least squares update magnitude is controlled; It is a numerically stable term, and ; for t The covariance matrix at time +1 This is a forgetting factor used to improve the model's adaptability to changes in operating conditions.

[0039] The adaptive smoothing weights corresponding to each typical operating condition are determined as follows:

[0040]

[0041]

[0042] in, For the first j Adaptive smoothing weights corresponding to typical operating conditions , The first j , No. k The adaptive smoothing weights before normalization correspond to the typical operating conditions. This is the parameter vector corresponding to the current operating condition. The first obtained through clustering jThe central parameter vector of a typical working condition This is the weight matrix of parameters for each operating condition under typical operating conditions. For the current working conditions and the first j Weighted distance between typical operating conditions This is a smoothing factor used to adjust the sensitivity of the weights to changes in operating conditions.

[0043] Step 4: Based on the external characteristic model and the sensitivity matrix corresponding to the current operating condition, calculate the instantaneous regulation potential, interval regulation potential, and comprehensive regulation potential of the electro-hydrogen-thermal coupling system.

[0044] The instantaneous regulation potential of the electro-hydrogen thermal coupling system is the maximum achievable output change within the feasible region of the action space, and is specifically determined as follows:

[0045] in, Ω represents the instantaneous adjustment potential, and Ω represents the set of device constraints in the electro-hydrogen-thermal coupling system. The aforementioned range adjustment potential refers to the adjustment potential within a preset adjustment period. T Within the timeframe, the summation of all changes in the state space at each corresponding moment is expressed as:

[0046] in, φ This represents potential for range-based adjustment.

[0047] The comprehensive adjustment potential is determined as follows:

[0048] in, To comprehensively regulate potential, and Let be the weight coefficient, and satisfy... It is used to balance the adjustment needs of instantaneous adjustment and range adjustment; , These are the normalized benchmark values ​​for instantaneous regulation potential and interval regulation potential, respectively, used to characterize the upper limit of the corresponding potential indicators under the structural and equipment constraints of the electro-hydrogen-thermal coupling system.

[0049] The present invention also discloses a non-interventional electro-hydrogen thermal coupling system regulation potential quantification system based on the aforementioned method, including a data acquisition module, an electro-hydrogen thermal coupling external characteristic model construction module, a sensitivity matrix calculation module, and an electro-hydrogen thermal coupling system regulation potential quantification module; The data acquisition module acquires historical and current operating parameters of the electro-hydrogen-thermal coupling system, as well as historical and current operating data of each device in the system. The module for constructing the electro-hydrogen-thermal coupling external characteristic model establishes an electro-hydrogen-thermal coupling external characteristic model including a state space and an action space, and introduces a sensitivity matrix; the input of the electro-hydrogen-thermal coupling external characteristic model is the action space and the sensitivity matrix, and the output is the state space, and the state space is the product of the action space and the sensitivity matrix; The sensitivity matrix calculation module calculates the initial sensitivity matrix under different typical operating conditions based on the historical operating parameters of the system, the historical operating data of each device, and the electro-hydrogen-thermal coupling external characteristic model; it recursively updates the sensitivity matrix under each typical operating condition based on the current operating data; it calculates the adaptive smoothing weight corresponding to each typical operating condition based on the current operating parameters; and it performs weighted fusion on the updated sensitivity matrix under each typical operating condition based on the adaptive smoothing weight to obtain the sensitivity matrix corresponding to the current operating condition. The regulation potential quantification module of the electro-hydrogen thermal coupling system calculates the instantaneous regulation potential, interval regulation potential, and comprehensive regulation potential of the electro-hydrogen thermal coupling system based on the external characteristic model and the sensitivity matrix corresponding to the current operating condition.

[0050] Example 1: like Figure 1 As shown in this embodiment, a method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system includes the following steps: Step 1: Obtain the historical and current operating parameters of the electro-hydrogen-thermal coupling system, as well as the historical and current operating data of each device in the system; The devices in the electro-hydrogen thermal coupling system include an electrolyzer, a fuel cell, a boiler, and a thermal energy storage device. The operating data includes: electrolyzer regulation power, fuel cell regulation power, boiler heat regulation power, thermal energy storage regulation power, and grid exchange regulation power, as well as the hydrogen production, heating power, and grid exchange power corresponding to each regulation power. The operating parameters include ambient temperature, load, and electricity price.

[0051] Step 2: Establish an electro-hydrogen-thermal coupling external characteristic model including state space and action space, and introduce a sensitivity matrix; the input of the electro-hydrogen-thermal coupling external characteristic model is the action space and the sensitivity matrix, and the output is the state space, and the state space is the product of the action space and the sensitivity matrix; In step 2, the state space for: (1) in, For the electro-hydrogen thermal coupling system to exchange power with the power grid, For hydrogen production, This refers to the heating capacity.

[0052] The action space for: (2) in, To adjust the power of the controllable electrolytic cell, For controllable power adjustment of fuel cells, For controllable heat regulation power of a controllable boiler, For controllable thermal energy storage and power regulation, It provides controllable power exchange regulation for the power grid.

[0053] The input-output relationship of the electro-hydrogen-thermal coupling external characteristic model is as follows: (3) in, , , The sensitivity matrix was adjusted by fitting historical data with mechanistic constraints.

[0054] Step 3: Based on the historical operating parameters of the system, the historical operating data of each device, and the external characteristic model of the electro-hydrogen-thermal coupling, calculate the initial sensitivity matrix under different typical operating conditions; based on the current operating data, recursively update the sensitivity matrix under each typical operating condition; based on the current operating parameters, calculate the adaptive smoothing weight corresponding to each typical operating condition; based on the adaptive smoothing weight, perform weighted fusion on the updated sensitivity matrix under each typical operating condition to obtain the sensitivity matrix corresponding to the current operating condition. The adjustment sensitivity matrix To obtain the result using a non-interventional adaptive estimation method, the specific calculation method includes: Step 301: Based on the historical operating parameters of the system, the historical operating data of each device, and the external characteristic model of the electro-hydrogen-thermal coupling, calculate the initial sensitivity matrix under different typical operating conditions; First, using a clustering algorithm, the historical operating data is divided into categories based on operating parameters including ambient temperature, load, and electricity price. J Typical operating conditions; For each typical operating condition, without injecting control signals, historical operating data is time-aligned and steady-state segments, fluctuation segments, and outlier samples are identified, and differential samples are extracted. ,in, For the first t The amount of change in the adjustment action of each device in the action space at any given moment. For the first tThe changes in each state in the time-space are considered; a difference sample set is constructed based on the difference samples, where the difference samples corresponding to steady-state segments are used as the main effective samples, and the difference samples corresponding to fluctuating segments and abnormal samples are weakened or suppressed through robust weights; based on the difference sample set, the initial sensitivity matrix under each typical working condition is solved by weighted constrained least squares with physical priors. First, use a conservative weighting. This reflects the steady-state degree and reliability of each difference segment. Secondly, it uses a set of physical prior constraints to embody mechanistic constraints such as equipment capacity, monotonicity, and coupling relationships. Finally, it utilizes regularization terms. Characterizes the smoothness and boundedness of external properties within the physical range.

[0055] Specifically, a steady-state segment refers to a segment of operating data in which the system's operating state changes slowly and the relationship between equipment adjustment actions and state responses is stable within a given time window.

[0056] A fluctuation segment refers to a data segment in which the system is still within the normal operating range, but the state variables exhibit moderate fluctuations due to load disturbances, price changes, or the coordinated adjustment of multiple devices.

[0057] Abnormal samples refer to operational data that does not conform to the normal operating mechanism or statistical characteristics of the system.

[0058] Stable weighting The weight of the differential sample is determined based on its type, specifically according to the stability, noise level, and physical feasibility of each segment. The weight of a steady-state segment is greater than that of a fluctuating segment, which in turn is greater than the weight of anomaly samples with excessively large residuals, and the weight of anomaly samples approaches zero. Preferably, the weight of a steady-state segment ranges from 0.7 to 1.0; the weight of a fluctuating segment ranges from 0.1 to 0.7; and the weight of anomaly samples ranges from 0 to 0.1. Fluctuating segments and anomaly samples are not used as the primary modeling basis; they only participate in the weighting through robust weights to improve the robustness of the sensitivity matrix estimation to noise, disturbances, and anomaly data.

[0059] The equipment capacity constraints in the constraint set are used to reflect the adjustable capacity limitations of various types of equipment within their rated capacity and safe operating range, including: 1) The regulating power of the electrolytic cell shall not exceed its maximum allowable regulating power; 2) The output power of the fuel cell shall not exceed the rated power; 3) The heating power of the electric boiler shall not exceed its rated heating power; 4) The charging and discharging power and energy level of thermal energy storage and hydrogen storage devices should be within their allowable upper and lower limits.

[0060] Monotonicity constraints are used to reflect the fundamental causal relationship and directional characteristics between regulatory actions and state responses in a system. These include: 1) When the power of the electrolyzer is increased, the hydrogen production should increase accordingly; 2) As the output power of the fuel cell increases, the hydrogen consumption should also increase; 3) When the power of an electric boiler is increased, the heating power should be increased monotonically; 4) When the heat release power of thermal energy storage increases, the external heat supply capacity should be enhanced.

[0061] Coupling constraints are used to reflect the energy conversion and mutual influence relationships between different energy carriers within an electro-hydrogen-thermal coupling system. These include: 1) Equipment such as electrolytic cells and electric boilers are related to both electrical power and hydrogen or thermal power, and their adjustment actions will affect multiple state variables at the same time. 2) Fuel cells consume hydrogen and generate some waste heat while outputting electrical power; 3) The charging and discharging behavior of thermal energy storage devices will affect the instantaneous heating capacity of the system and its regulation potential in subsequent periods; 4) Changes in the exchange power between the system and the power grid will affect the operating status of the hydrogen side and the thermal side through electrical coupling.

[0062] The initial sensitivity matrix The specific calculation formula is as follows: (4) in, K Let be the sensitivity matrix to be solved. K 0 represents the solution to the least squares model, i.e., the initial sensitivity matrix to be obtained; For a stable weighting, The regularization coefficient is... This is the sensitivity matrix.

[0063] Step 302: Based on the current operating data, recursively update the sensitivity matrix for each typical operating condition; Specifically, recursive least squares is used for online updates, and the results are projected onto the set of physical constraints at each step. To adapt to changes in operating conditions, the specifics are as follows: (5) (6) (7) in, , They are respectively t time, t The sensitivity matrix at time +1; It is a forgetting factor and satisfies This is used to improve the model's adaptability to changes in operating conditions; It is a numerically stable term, and ; It is a convex projection operator on the constraint set, used to ensure that the updated sensitivity matrix satisfies physical prior constraints such as capacity, monotonicity, and coupling relationship; for t The covariance matrix at time t is used to describe the sensitivity matrix. The parameter uncertainty is controlled, and the recursive least squares update magnitude is controlled; This is the recursive least squares gain matrix, used to determine the sensitivity matrix for the current sample pair. The updated weights enable online learning capabilities to adapt to changes in operating conditions.

[0064] Step 303: Based on the current operating condition parameters, calculate the adaptive smoothing weights corresponding to each typical operating condition. Based on the adaptive smoothing weights, perform weighted fusion on the updated sensitivity matrices under each typical operating condition to obtain the sensitivity matrix corresponding to the current operating condition. Specifically as follows: (8) (9) (10) in, This is the sensitivity matrix corresponding to the current operating condition; J This represents the total number of typical operating conditions. This is a vector of operating parameters, including ambient temperature, load, and electricity price. For the first j Adaptive smoothing weights for various operating conditions, used for adaptive smoothing across temperature, load, electricity price, and other operating conditions. For the updated number j The local sensitivity matrix under various operating conditions.

[0065] Specifically, adaptive smoothing weights Determine as follows: The parameter vector corresponding to the current operating condition is , No. j The central parameter vector for a typical working condition is So, what are the current working conditions and the first... j Weighted distance between typical working conditions for: (11) in, This is a weight matrix of parameters such as temperature, load, and electricity price under typical operating conditions, representing the degree of influence of operating condition parameters, including temperature, load, and electricity price, on the external characteristics of the system.

[0066] Based on the working condition distance, a non-negative mapping function for the weights is constructed, and the first... j Adaptive smoothing weights for typical working conditions Specifically, the nonnegative mapping function can be constructed as an exponential similarity function: (12) in, This is a smoothing factor used to adjust the sensitivity of the weights to changes in operating conditions.

[0067] The weights for all typical operating conditions are normalized to obtain the final adaptive smoothing weights: (13) in, For the first j Adaptive smoothing weights corresponding to typical operating conditions J This represents the total number of typical operating conditions. , The first j , No. k Adaptive smoothing weights before normalization for a typical operating condition.

[0068] Step 4: Based on the external characteristic model and the sensitivity matrix corresponding to the current operating condition, calculate the instantaneous regulation potential, interval regulation potential, and comprehensive regulation potential of the electro-hydrogen-thermal coupling system.

[0069] Specifically, based on the aforementioned external characteristic model and the final sensitivity matrix, combined with The range of values ​​for each element is determined, and the adjustable ranges of electrical power, hydrogen production, and thermal power under the constraints of each system device set are calculated, thereby obtaining the instantaneous adjustment potential, the interval adjustment potential, and the comprehensive adjustment potential.

[0070] The instantaneous adjustment potential Defined as the maximum achievable output change within the feasible region of the action space: (14) Wherein, Ω represents the set of equipment constraints in the electro-hydrogen-thermal coupling system of the chemical industrial park.

[0071] The interval adjustment potential Defined as a preset adjustment period Within, the cumulative sum of all changes in the state space at each time step is as follows: (15) The comprehensive potential index Defined as: (16) (17) in, and Let be the weight coefficient, and satisfy... It is used to balance the adjustment needs of instantaneous adjustment and range adjustment; , These are normalized benchmark values ​​for instantaneous regulation potential and interval regulation potential, respectively, used to characterize the upper limit of the corresponding potential index under the structural and equipment constraints of the electro-hydrogen-thermal coupling system. Preferably, the maximum value in historical operating data can be taken.

[0072] Example 2: To verify the effectiveness of the method of the present invention, a case study analysis was conducted using an electro-hydrogen-thermal coupling system in a chemical industrial park. The equipment and constraints are as follows: The electrolyzer has a rated capacity of 20MW; the fuel cell has a rated capacity of 10MW; the electric boiler has a capacity of 60MW; the thermal energy storage is 40MWh (initial value 20MWh, range [5, 40]MWh); the hydrogen storage is 8t (initial value 5t, range [1, 8]t, industrial hydrogen load 1200Nm3 / h); the time resolution is Δt = 1min. After the above steps, steady-state segments of 90 days of historical data were screened and weighted / recursive least squares identification with mechanistic constraints was performed. The sensitivity matrix K under the current operating conditions is shown in the table below: Table 1 Sensitivity Matrix K

[0073] The feasible domain of the device's actions: , , , , .

[0074] Based on the sensitivity matrix K in Table 1 and the feasible region of equipment operation, the instantaneous power regulation potential ΔPg is calculated to be ±11.8MW, the instantaneous hydrogen regulation potential ΔNh is ±2680Nm3 / h, and the instantaneous heating regulation potential ΔQt is ±20MW.

[0075] Using a 1-hour interval, the interval regulation potentials for electric power, hydrogen, and heating were further calculated to be ±10.85MWh, ±2460Nm3, and ±8.6MWh, respectively.

[0076] Finally, with an instantaneous score of 0.992 and an interval score of 0.748, and weights α1 and α2 of 0.6 and 0.4 respectively, the comprehensive index C is calculated to be 0.89.

[0077] Example 3: An embodiment of the present invention provides a terminal, including a processor and a storage medium; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of Embodiment 1.

[0078] Example 4: The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the embodiments.

[0079] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0081] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0082] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading the present invention, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the scope of protection of the pending claims of the invention.

Claims

1. A method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system, characterized in that, include: Acquire the historical and current operating parameters of the electro-hydrogen thermal coupling system, as well as the historical and current operating data of each device in the system; establish an external characteristic model of the electro-hydrogen thermal coupling including state space and action space, and introduce a sensitivity matrix; The input to the electro-hydrogen-thermal coupling external characteristic model is the action space and the sensitivity matrix, and the output is the state space, which is the product of the action space and the sensitivity matrix. Based on the historical operating parameters of the system, the historical operating data of each device, and the electro-hydrogen-thermal coupling external characteristic model, the initial sensitivity matrix under different typical operating conditions is calculated. Based on the current operating data, the sensitivity matrix under each typical operating condition is updated recursively. Based on the current operating parameters, the adaptive smoothing weights corresponding to each typical operating condition are calculated. Based on the adaptive smoothing weights, the sensitivity matrices under each typical operating condition are weighted and fused to obtain the sensitivity matrix corresponding to the current operating condition. According to the external characteristic model and the sensitivity matrix corresponding to the current operating condition, the instantaneous regulation potential, interval regulation potential and comprehensive regulation potential of the electro-hydrogen-thermal coupling system are calculated.

2. The method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system according to claim 1, characterized in that: The system includes various devices such as electrolyzers, fuel cells, boilers, and thermal energy storage devices. The electro-hydrogen-thermal coupling external characteristic model is as follows: in, For state space, For the action space, K This is the sensitivity matrix; The state space With action space Specifically: ， Where, Δ P Δ represents the power exchanged between the electro-hydrogen thermal coupling system and the power grid. N For hydrogen production, Δ Q For heating capacity; To adjust the power of the controllable electrolytic cell, For controllable power adjustment of fuel cells, For the controllable heat regulation power of the boiler, For controllable thermal energy storage and power regulation, It provides controllable power exchange regulation for the power grid.

3. The method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system according to claim 1, characterized in that: The initial sensitivity matrix is ​​calculated in the following manner: The historical operating data is time-aligned, and then steady-state segments, fluctuation segments, and outlier samples are identified and differential samples are extracted. The initial sensitivity matrix is ​​solved by weighted constrained least squares with physical priors. K 0, the specific solution method is as follows: in, K Let be the sensitivity matrix to be solved. K 0 represents the solution to the least squares model, i.e., the initial sensitivity matrix to be obtained; w t For robust weights, they are determined based on the type of the differenced samples; For the first t The amount of change in the adjustment action of each device in the action space at any given moment. For the first t The changes in each state in the state space at any given time; λ is the regularization coefficient.

4. The method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system according to claim 3, characterized in that: The recursive update of the sensitivity matrix under various typical operating conditions based on current operating data specifically includes: The sensitivity matrix is ​​updated online using recursive least squares, and the result of each update is projected onto the set of physical constraints. The calculation method is as follows: in, , They are respectively t time, t The sensitivity matrix at time +1; It is a convex projection operator on the constraint set, used to ensure that the updated sensitivity matrix satisfies the physical prior constraints; This is the recursive least squares gain matrix, used to determine the sensitivity matrix for the current sample pair. The updated weights enable online learning capabilities to adapt to changes in operating conditions. for t The covariance matrix at time t is used to describe the sensitivity matrix. The parameter uncertainty is controlled, and the recursive least squares update magnitude is controlled; It is a numerically stable term, and ; for t The covariance matrix at time +1; It is a forgetting factor and satisfies This is used to improve the model's adaptability to changes in operating conditions.

5. The method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system according to claim 4, characterized in that: The adaptive smoothing weights corresponding to each typical operating condition are determined as follows: in, For the first j Adaptive smoothing weights corresponding to typical operating conditions J This represents the total number of typical operating conditions. , The first j , No. k The adaptive smoothing weights before normalization correspond to the typical operating conditions. This is the parameter vector corresponding to the current operating condition. The first obtained through clustering j The central parameter vector of a typical working condition This is the weight matrix of parameters for each operating condition under typical operating conditions. For the current working conditions and the first j Weighted distance between typical operating conditions This is a smoothing factor used to adjust the sensitivity of the weights to changes in operating conditions.

6. The method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system according to claim 4, characterized in that: The instantaneous regulation potential of the electro-hydrogen thermal coupling system is the maximum achievable output change within the feasible region of the action space, and is specifically determined as follows: in, Ω represents the instantaneous adjustment potential, and Ω represents the set of device constraints in the electro-hydrogen-thermal coupling system. The aforementioned range adjustment potential refers to the adjustment potential within a preset adjustment period. T Within the timeframe, the summation of all changes in the state space at each corresponding moment is expressed as: in, φ This represents potential for range-based adjustment.

7. The method for quantifying the regulation potential of a non-interventional electro-hydrogen thermal coupling system according to claim 6, characterized in that: The comprehensive adjustment potential is determined as follows: in, To comprehensively adjust potential, and Let be the weight coefficient, and satisfy... It is used to balance the adjustment needs of instantaneous adjustment and range adjustment; , These are the normalized benchmark values ​​for instantaneous regulation potential and interval regulation potential, respectively, used to characterize the upper limit of the corresponding potential indicators under the structural and equipment constraints of the electro-hydrogen-thermal coupling system.

8. A non-interventional system for quantifying the regulatory potential of an electro-hydrogen thermal coupling system based on the method of any one of claims 1-7, comprising a data acquisition module, an electro-hydrogen thermal coupling external characteristic model construction module, a sensitivity matrix calculation module, and an electro-hydrogen thermal coupling system regulatory potential quantification module, characterized in that: The data acquisition module acquires historical and current operating parameters of the electro-hydrogen-thermal coupling system, as well as historical and current operating data of each device in the system. The module for constructing the electro-hydrogen-thermal coupling external characteristic model establishes an electro-hydrogen-thermal coupling external characteristic model including a state space and an action space, and introduces a sensitivity matrix; the input of the electro-hydrogen-thermal coupling external characteristic model is the action space and the sensitivity matrix, and the output is the state space, and the state space is the product of the action space and the sensitivity matrix; The sensitivity matrix calculation module calculates the initial sensitivity matrix under different typical operating conditions based on the historical operating parameters of the system, the historical operating data of each device, and the electro-hydrogen-thermal coupling external characteristic model. Based on the current operating data, the sensitivity matrix under each typical operating condition is updated recursively. Based on the current operating parameters, the adaptive smoothing weights corresponding to each typical operating condition are calculated. Based on the adaptive smoothing weights, the sensitivity matrices under each typical operating condition are weighted and fused to obtain the sensitivity matrix corresponding to the current operating condition. The regulation potential quantification module of the electro-hydrogen thermal coupling system calculates the instantaneous regulation potential, interval regulation potential, and comprehensive regulation potential of the electro-hydrogen thermal coupling system based on the external characteristic model and the sensitivity matrix corresponding to the current operating condition.

9. A terminal, comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1-7.

Images