New energy hydrogen production power supply integrated control system

Abstract

The invention relates to the technical field of battery control, in particular to a new energy hydrogen production power supply integrated control system, which comprises a demand prediction module for acquiring electrolytic bath operation data and real-time environmental parameters, calculating statistical characteristics of data including an average value and a standard deviation element by element, calculating a future trend based on the statistical characteristics, and obtaining an energy demand prediction value. According to the method, through real-time data analysis and trend prediction, the operation condition and the environment change of the electrolytic cell are grasped in advance, so that the future energy demand is accurately predicted, the prediction method is based on the statistical characteristics of historical data, the prediction model can be dynamically adjusted to adapt to the environment change, the accuracy and the response speed of energy management are improved, and the energy consumption is reduced. Through the technical means of real-time optimization and adjustment, fine matching of energy output and demands, a fine energy distribution strategy and dynamic adjustment are realized, and the method is more flexible and efficient in response to energy market fluctuation and user demand change.

Description

Technical Field

[0001] The present invention relates to the technical field of battery control, and in particular to an integrated control system for a new energy hydrogen production power source. Background Art

[0002] The field of battery control technology focuses on optimizing the performance, life and safety of battery systems, ranging from basic battery management systems (BMS) to complex integrated control strategies. Battery control technology not only includes monitoring the battery's state of charge and health, but also involves real-time data analysis to predict battery performance and failure. In addition, the battery control system is also responsible for balancing the charging and discharging process between battery cells, as well as optimizing the interface between the battery and other systems such as energy recovery systems and auxiliary power systems. Through these technologies, the efficiency and reliability of the battery can be significantly improved while extending its service life.

[0003] Among them, the new energy hydrogen production power integrated control system refers to the advanced control technology that integrates hydrogen production technology with the battery system. This system is mainly used to optimize the production, storage and utilization of hydrogen, especially in fuel cells and other hydrogen energy equipment. Through the integrated control system, the production of hydrogen and the demand for electricity can be managed more effectively, and efficient conversion and storage of energy can be achieved. The main uses of such systems include but are not limited to clean energy production, backup power systems, and energy integration in the field of renewable energy, which is of great significance to improving the flexibility and efficiency of energy use.

[0004] Existing battery control technologies have deficiencies in real-time data processing and prediction accuracy, which often results in the inability of energy management systems to efficiently respond to rapidly changing market demands and environmental conditions. In existing technologies, battery management systems focus on monitoring and basic battery protection, lacking advanced data analysis and prediction capabilities, which limits the scope of application and efficiency of battery systems in dynamic market environments. In addition, existing systems can often only adopt preset strategies and lack the ability to flexibly adjust the charge and discharge balance between battery cells and integration with other systems. These deficiencies may lead to battery performance degradation or even safety risks in emergency or non-standard operating situations, highlighting the limitations of existing technologies in efficient energy utilization and system reliability, and affecting the overall performance of battery systems and the economic benefits of users. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and propose a new energy hydrogen production power integrated control system.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: the new energy hydrogen production power integrated control system comprises:

[0007] The demand forecasting module collects the electrolyzer operation data and real-time environmental parameters, calculates the statistical characteristics of the data including the mean value and standard deviation element by element, and infers the future trend based on the statistical characteristics to obtain the energy demand forecast value;

[0008] The dynamic programming module receives the energy demand forecast value, combines the real-time data of the energy management unit, sets evaluation criteria for differentiated energy input combinations, adjusts multiple combinations to optimize energy output efficiency, and obtains an energy allocation strategy;

[0009] The strategy optimization module uses the energy allocation strategy to quantitatively adjust the storage capacity and output rate of the hydrogen storage device, evaluate the cost-effectiveness of the differentiated solution, and obtain the adjusted strategy refinement results;

[0010] The real-time optimization and adjustment module applies the adjusted strategy refinement results, continuously monitors the deviation between energy output and preset targets, dynamically adjusts the working parameters of the load regulator, performs real-time matching of energy output and demand, and establishes a real-time response optimization framework.

[0011] As a further solution of the present invention, the steps for obtaining the statistical characteristics of the mean value and the standard deviation are specifically as follows:

[0012] For the daily operation data of the electrolyzer, the daily average values ​​of the current, voltage and temperature parameters are calculated using the formula:

[0013]

[0014] Get the daily average current, daily average voltage, and daily average temperature;

[0015] in, represents the daily average of the parameter, n represents the number of data points, x i Represents the value of the i-th data point;

[0016] Based on the daily average current, daily average voltage and daily average temperature, the sum of squares of the deviations of each parameter from the average value is calculated using the formula:

[0017]

[0018] The current standard deviation, voltage standard deviation and temperature standard deviation are calculated;

[0019] Where σ represents the standard deviation of the parameter, n represents the number of data points, and x i Represents the value of the i-th data point;

[0020] The current standard deviation, voltage standard deviation and temperature standard deviation are combined, and the influence of multiple parameters on the performance of the electrolytic cell is referred to, and the formula is adopted:

[0021]

[0022] Calculate the combined standard deviation to obtain the statistical properties of the mean and standard deviation;

[0023] Where S represents the comprehensive standard deviation, σ x represents the standard deviation of the current, σ y Represents the standard deviation of voltage, σ z represents the standard deviation of temperature, a q , b q 、c q Represent the weight coefficients of current, voltage and temperature respectively, d q Represents an adjustment factor.

[0024] As a further solution of the present invention, the step of obtaining the energy demand forecast value is specifically as follows:

[0025] Based on the statistical properties of the mean and standard deviation, combined with the composite standard deviation and historical energy consumption data for the electrolyzers, the initial estimate of energy demand is adjusted using the formula:

[0026]

[0027] Calculate a preliminary energy demand estimate;

[0028] Where E represents the preliminary energy demand estimate, α w represents the weight associated with the standard deviation, β w Represents the linear influence coefficient of historical energy consumption, λ w represents the nonlinear adjustment coefficient of historical consumption, and H represents the average value of historical energy consumption;

[0029] Based on the preliminary energy demand estimate, with reference to the impact of real-time environmental parameters, the formula is used:

[0030] D=E·(1+γ w ·cos(T w )·+δ w ·log(1+M w ))

[0031] Refine the energy demand forecast and obtain the energy demand forecast value;

[0032] Where D represents the predicted energy demand, γ w Represents the cosine adjustment coefficient of temperature, T w Represents the real-time ambient temperature, δ w Represents the logarithmic adjustment factor of humidity, M w Represents the real-time ambient humidity.

[0033] As a further solution of the present invention, the steps of obtaining the energy allocation strategy are specifically as follows:

[0034] Receive the energy demand forecast value and use the formula:

[0035]

[0036] Calculate and obtain the initial energy allocation plan;

[0037] Among them, V represents the initial energy allocation plan, r x represents the basic adjustment coefficient, δ x Represents the historical consumption adjustment coefficient, H x Represents the historical average energy consumption;

[0038] Based on the initial energy allocation plan and combined with the real-time data of the energy management unit, the formula is adopted:

[0039] C=V·(1+k x ·log(1+U x ))

[0040] adjusting the energy allocation plan to obtain an adjusted energy allocation plan;

[0041] Among them, C represents the adjusted energy allocation plan, k x Represents the dynamic adjustment coefficient, U x Represents real-time data;

[0042] Based on the adjusted energy allocation scheme, the evaluation criteria for the differentiated energy input combinations are set using the formula:

[0043]

[0044] Calculate the comprehensive efficiency of each combination and generate energy allocation strategy;

[0045] Where F represents the energy allocation strategy, w i represents the efficiency weight of the i-th energy combination, C i represents the allocation value of the i-th energy in the adjusted energy allocation plan, σ i stands for efficiency adjustment factor.

[0046] As a further solution of the present invention, the step of obtaining the adjusted strategy refinement result is specifically as follows:

[0047] Using the energy allocation strategy, the formula is adopted:

[0048]

[0049] calculating a storage capacity adjustment of the hydrogen storage device to obtain an adjusted storage capacity;

[0050] Where H represents the adjusted storage capacity, s z represents the storage efficiency factor, η z represents the efficiency adjustment coefficient, ∈ z represents the basic adjustment parameter;

[0051] Based on the adjusted storage capacity, the formula is used:

[0052]

[0053] adjusting the output rate of the hydrogen storage device to obtain an adjusted output rate;

[0054] Where O represents the adjusted output rate, λ z represents the output rate adjustment coefficient, p z Represents the pressure regulation parameter, μ z represents the coefficient of the quadratic term of pressure;

[0055] Combining the adjusted storage capacity and the adjusted output rate, the formula is adopted:

[0056]

[0057] Evaluate the cost-effectiveness of differentiated solutions and generate adjusted strategy refinement results;

[0058] Among them, E represents the adjusted strategy optimization result, c z represents the cost coefficient, τ z Represents the cost adjustment parameter.

[0059] As a further solution of the present invention, the step of obtaining the real-time response optimization framework is specifically as follows:

[0060] Apply the adjusted strategy refinement results, by continuously monitoring the deviation of energy output from the preset target, using the formula:

[0061] Δ=KT s

[0062] Calculate the current deviation result;

[0063] Where Δ represents the current deviation, T s Represents a preset goal;

[0064] Based on the current deviation results, the formula is used:

[0065]

[0066] Dynamically adjust the working parameters of the load regulator to obtain adjusted working parameters;

[0067] Among them, P represents the adjusted working parameters, κ s represents the linear adjustment coefficient, β s represents the square root adjustment coefficient, γ s represents the quadratic adjustment coefficient;

[0068] Combined with the adjusted working parameters, the formula is adopted:

[0069]

[0070] Match energy output with demand in real time and establish a real-time response optimization framework;

[0071] Among them, M represents the real-time response optimization framework, e s Represents the base of natural logarithms.

[0072] Compared with the prior art, the advantages and positive effects of the present invention are:

[0073] In the present invention, the operating status and environmental changes of the electrolyzer are grasped in advance through real-time data analysis and trend prediction, so as to make accurate predictions of future energy demand. The prediction method is not only based on the statistical characteristics of historical data, but also can dynamically adjust the prediction model to adapt to environmental changes, thereby improving the accuracy and response speed of energy management. Through the technical means of real-time optimization and adjustment, a fine match between energy output and demand is achieved. The refined energy allocation strategy and dynamic adjustment are more flexible and efficient in responding to energy market fluctuations and changes in user demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 is a system flow chart of the present invention;

[0075] Figure 2 A flow chart of the steps for obtaining the statistical characteristics of the mean value and standard deviation of the present invention;

[0076] Figure 3 A flow chart of the steps for obtaining the energy demand prediction value of the present invention;

[0077] Figure 4 A flow chart of the steps for obtaining the energy allocation strategy of the present invention;

[0078] Figure 5 A flowchart of the steps for obtaining the adjusted strategy refinement results of the present invention;

[0079] Figure 6 Flow chart of the acquisition steps of the real-time response optimization framework of the present invention. DETAILED DESCRIPTION

[0080] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0081] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0082] Embodiment 1

[0083] See also Figure 1 , the new energy hydrogen power integrated control system includes:

[0084] The demand forecasting module collects the electrolyzer operation data and real-time environmental parameters, calculates the statistical characteristics of the data including the mean value and standard deviation element by element, and infers the future trend based on the statistical characteristics to obtain the energy demand forecast value;

[0085] The dynamic programming module receives the energy demand forecast value, combines it with the real-time data of the energy management unit, sets evaluation criteria for differentiated energy input combinations, adjusts multiple combinations to optimize energy output efficiency, and obtains energy allocation strategies;

[0086] The strategy optimization module uses the energy allocation strategy to quantitatively adjust the storage capacity and output rate of the hydrogen storage device, evaluate the cost-effectiveness of the differentiated solution, and obtain the adjusted strategy refinement results;

[0087] The real-time optimization and adjustment module applies the adjusted strategy refinement results, continuously monitors the deviation between energy output and preset targets, dynamically adjusts the working parameters of the load regulator, performs real-time matching of energy output and demand, and establishes a real-time response optimization framework.

[0088] The energy demand forecast value specifically refers to trend forecast, average value statistics, and standard deviation statistics. The energy allocation strategy includes optimization criteria, input combination, and output efficiency. The strategy refinement results include capacity adjustment, output rate change, and cost-effectiveness. The real-time response optimization framework includes energy output monitoring, preset target deviation adjustment, and load regulator parameter adjustment.

[0089] See also Figure 2, the steps to obtain the statistical characteristics of the mean and standard deviation are as follows:

[0090] For the daily operation data of the electrolyzer, the daily average values ​​of the current, voltage and temperature parameters are calculated using the formula:

[0091]

[0092] Get the daily average current, daily average voltage, and daily average temperature;

[0093] in, represents the daily average of the parameter, n represents the number of data points, x i Represents the value of the i-th data point;

[0094] Based on the daily average current, voltage and temperature, the sum of the squares of the deviations of each parameter from the average value is calculated using the formula:

[0095]

[0096] The current standard deviation, voltage standard deviation and temperature standard deviation are calculated;

[0097] Where σ represents the standard deviation of the parameter, n represents the number of data points, and x i Represents the value of the i-th data point;

[0098] The current standard deviation, voltage standard deviation and temperature standard deviation are combined, and the influence of multiple parameters on the performance of the electrolytic cell is referred to, and the formula is adopted:

[0099]

[0100] Calculate the combined standard deviation to obtain the statistical properties of the mean and standard deviation;

[0101] Where S represents the comprehensive standard deviation, σ x represents the standard deviation of the current, σ y Represents the standard deviation of voltage, σ z represents the standard deviation of temperature, a q , b q 、c q Represent the weight coefficients of current, voltage and temperature respectively, d q Represents an adjustment factor.

[0102] formula:

[0103]

[0104] in:

[0105] Daily average

[0106] n: number of data points

[0107] x i : The value of the i-th data point

[0108] Derivation process:

[0109] Suppose there is a set of current readings (in amperes) as follows: [10, 12, 11, 13, 12]. Calculate the average:

[0110] Determine the number of data points n = 5.

[0111] Use the formula to calculate the sum:

[0112] Calculate the average: ampere.

[0113] Example results:

[0114] The calculated average is 11.6 amps, representing the average amperage for a group of current readings.

[0115] formula:

[0116]

[0117] in:

[0118] σ: standard deviation

[0119] Parameter daily average

[0120] n: number of data points

[0121] x i : The value of the i-th data point

[0122] Derivation process:

[0123] Using the above data and results, calculate the standard deviation:

[0124] Using the above results ampere.

[0125] Compute the square of each data point's deviation from the mean:

[0126] (10-11.6) 2 =2.56

[0127] (12-11.6) 2 =0.16

[0128] (11-11.6) 2 =0.36

[0129] (13-11.6) 2 =1.96

[0130] (12-11.6) 2 =0.16

[0131] Total: 2.56+0.16+0.36+1.96+0.16=5.2

[0132] Calculate the standard deviation: ampere.

[0133] Example results:

[0134] The standard deviation is 1.14 amps, which indicates the variability in the current reading data.

[0135] formula:

[0136]

[0137] in:

[0138] S: comprehensive standard deviation

[0139] σ x , σ y , σ z : Represents the standard deviation of current, voltage and temperature respectively

[0140] a q , b q 、c q : Weight coefficient

[0141] d q : Adjustment coefficient

[0142] Derivation process:

[0143] Assume that the standard deviations of current, voltage, and temperature are 1.14 amps, 0.75 volts, and 1.05 degrees, respectively. Set the weight a q =0.5, b q =0.3, c q =0.2, adjustment coefficient d q =0.1:

[0144] Calculate the product of the weight and the standard deviation:

[0145] 0.5×(1.14) 2 =0.649

[0146] 0.3×(0.75) 2 =0.169

[0147] 0.2×(1.05) 2 =0.221

[0148] Calculate the adjustment factor part:

[0149] Comprehensive calculation:

[0150] Example results:

[0151] The combined standard deviation is 1.036, indicating the degree of variability in the differentiation parameters after reference to the weights.

[0152] See also Figure 3 ,The specific steps for obtaining the energy demand forecast value are:

[0153] Based on the statistical properties of the mean and standard deviation, combined with the composite standard deviation and the historical energy consumption data of the electrolyzer, the initial estimate of energy demand is adjusted using the formula:

[0154]

[0155] Calculate a preliminary energy demand estimate;

[0156] Where E represents the preliminary energy demand estimate, α w represents the weight associated with the standard deviation, β w Represents the linear influence coefficient of historical energy consumption, λ w represents the nonlinear adjustment coefficient of historical consumption, and H represents the average value of historical energy consumption;

[0157] Based on the preliminary energy demand estimate and referring to the impact of real-time environmental parameters, the formula is adopted:

[0158] D=E·(1+γ w ·cos(T w )+δ w ·log(1+M w ))

[0159] Refine the energy demand forecast and obtain the energy demand forecast value;

[0160] Where D represents the predicted energy demand, γ w Represents the cosine adjustment coefficient of temperature, T w Represents the real-time ambient temperature, δ w Represents the logarithmic adjustment factor of humidity, M w Represents the real-time ambient humidity.

[0161] formula:

[0162]

[0163] Parameter setting and analysis

[0164] α w : The weight associated with the standard deviation, assumed to be 0.7.

[0165] β w : The linear influence coefficient of historical energy consumption is assumed to be 1.5.

[0166] λ w : Nonlinear adjustment coefficient of historical consumption, assumed to be 0.05.

[0167] S: comprehensive standard deviation, assumed to be obtained from the associated device data, set to 3.0.

[0168] H: The average value of historical energy consumption, assumed to be 200 kWh.

[0169] Calculation process and examples

[0170] Calculate the weight multiplied by the standard deviation:

[0171] α w S = 0.7 × 3.0 = 2.1

[0172] Calculate the adjusted impact of historical energy consumption:

[0173]

[0174] Preliminary energy demand estimates are:

[0175] E=2.1+30=32.1kWh

[0176] The results represent an estimated preliminary energy demand of 32.1 kWh based on historical consumption and existing standard deviations.

[0177] formula:

[0178] D=E·(1+γ w ·cos(T w )+δ w ·log(1+M w ))

[0179] Parameter setting and analysis

[0180] E: Preliminary energy demand estimate, 32.1kWh.

[0181] γ w : The cosine adjustment coefficient of temperature, assumed to be 0.2.

[0182] T w : Real-time ambient temperature, assumed to be 30 degrees, the cosine value is calculated as cos(30°)=0.866.

[0183] δw : Logarithmic adjustment coefficient of humidity, assumed to be 0.1.

[0184] M w : Real-time ambient humidity, assumed to be 75%, converted to logarithmic input log(1+0.75)=log(1.75)≈0.559.

[0185] Calculation process and examples

[0186] The part that calculates the temperature cosine adjustment:

[0187] γ w ·cos(T w )=0.2×0.866=0.1732

[0188] Calculate the humidity logarithm adjustment part:

[0189] δ w ·log(1+M w )=0.1×0.559=0.0559

[0190] Energy demand is forecasted to be:

[0191] D=32.1·(1+0.1732+0.0559)=32.1×1.2291=

[0192] 39.46191 kWh

[0193] The results represent a predicted energy demand of 39.46 kWh with real-time temperature and humidity regulation.

[0194] See also Figure 4 ,The specific steps for obtaining the energy allocation strategy are:

[0195] Receive energy demand forecast using the formula:

[0196]

[0197] Calculate and obtain the initial energy allocation plan;

[0198] Among them, V represents the initial energy allocation plan, r x represents the basic adjustment coefficient, δ x Represents the historical consumption adjustment coefficient, H x Represents the historical average energy consumption;

[0199] Based on the initial energy allocation plan and combined with the real-time data of the energy management unit, the formula is adopted:

[0200] C=V·(1+k x ·log(1+U x ))

[0201] adjusting the energy allocation plan to obtain an adjusted energy allocation plan;

[0202] Among them, C represents the adjusted energy allocation plan, k x Represents the dynamic adjustment coefficient, U x Represents real-time data;

[0203] Based on the adjusted energy allocation plan, the evaluation criteria for the differentiated energy input combinations are set using the formula:

[0204]

[0205] Calculate the comprehensive efficiency of each combination and generate energy allocation strategy;

[0206] Where F represents the energy allocation strategy, w i represents the efficiency weight of the i-th energy combination, C i represents the allocation value of the i-th energy in the adjusted energy allocation plan, σ i stands for efficiency adjustment factor.

[0207] formula:

[0208]

[0209] Detailed explanation and derivation:

[0210] D: predicted energy demand value, assumed to be 500 units.

[0211] r x : Basic adjustment coefficient, reflecting the ratio of basic energy demand to supply, is assumed to be 1.05.

[0212] δ x : Historical consumption adjustment coefficient, adjust current demand with reference to historical data, assumed to be 0.03.

[0213] H x : The historical average energy consumption, assumed to be 400 units.

[0214] Calculation process:

[0215] Calculate the impact of historical energy consumption on the regulation factor:

[0216] Calculate the total adjustment factor:

[0217] Calculate the initial energy allocation plan: V = 500 1.65 = 825

[0218] Example results:

[0219] The initial energy allocation plan V is 825 units, which means that after referring to the impact of historical consumption, 825 units of energy should be allocated according to the current energy demand forecast.

[0220] formula:

[0221]

[0222] Detailed explanation and derivation:

[0223] V: Initial allocation plan, 825 units.

[0224] k x : Dynamic adjustment coefficient, referring to the impact of real-time data, assumed to be 0.02.

[0225] U x : Real-time data, such as the current energy utilization rate, assumed to be 50 (indicating 50%).

[0226] Calculation process:

[0227] Calculate the impact of real-time data on the allocation plan: k x ·log(1+U x )=0.02·log(1+50)=0.02·log(51)≈0.02·3.93=0.0786

[0228] Calculate the adjusted energy allocation:

[0229] C=825·(1+0.0786)=825·1.0786≈889.545

[0230] Example results:

[0231] The adjusted energy allocation plan C is 889.545 units, which means the amount of energy allocated after the initial plan is adjusted under the influence of real-time data.

[0232] formula:

[0233]

[0234] Detailed explanation and derivation:

[0235] w i : The efficiency weight of the ith energy combination, assumed to be 0.6 and 0.4 for the two energy combinations respectively.

[0236] C i : The allocation values ​​of multiple energy sources in the adjusted energy allocation plan are assumed to be 600 and 289.545 respectively.

[0237] σ i: Efficiency adjustment factor, assumed to be 0.1 and 0.2 for the two energy sources respectively.

[0238] Calculation process:

[0239] Calculate the overall efficiency of the first energy combination:

[0240] Calculate the overall efficiency of the second energy combination:

[0241] Total comprehensive efficiency: 361.47+117.14328=478.61328

[0242] Example results:

[0243] The energy allocation strategy F is 478.61328 units, which represents the total energy efficiency after comprehensive reference to the efficiency weight of the multi-energy combination and actual allocation.

[0244] See also Figure 5 , the specific steps for obtaining the adjusted strategy refinement results are:

[0245] Using the energy allocation strategy, the formula is adopted:

[0246]

[0247] calculating a storage capacity adjustment of the hydrogen storage device to obtain an adjusted storage capacity;

[0248] Where H represents the adjusted storage capacity, s z represents the storage efficiency factor, η z represents the efficiency adjustment coefficient, ∈ z represents the basic adjustment parameter;

[0249] Based on the adjusted storage capacity, the formula is used:

[0250]

[0251] adjusting the output rate of the hydrogen storage device to obtain an adjusted output rate;

[0252] Where O represents the adjusted output rate, λ z represents the output rate adjustment coefficient, p z Represents the pressure regulation parameter, μ z represents the coefficient of the quadratic term of pressure;

[0253] Combining the adjusted storage capacity and the adjusted output rate, the formula is used:

[0254]

[0255] Evaluate the cost-effectiveness of differentiated solutions and generate adjusted strategy refinement results;

[0256] Among them, E represents the adjusted strategy optimization result, c z represents the cost coefficient, τ z Represents the cost adjustment parameter.

[0257] formula:

[0258]

[0259] in:

[0260] H: Adjusted storage capacity.

[0261] F: Energy allocation strategy, assuming unit energy demand, such as 1000 units.

[0262] s z : Storage efficiency factor, which represents the amount of hydrogen that can be stored per unit of energy, assumed to be 0.8.

[0263] η z : Efficiency adjustment coefficient, representing an additional adjustment factor, assumed to be 0.05.

[0264] ∈ z : Basic adjustment parameters, avoiding the influence of the denominator being zero and adjusting the efficiency factor, assumed to be 0.01.

[0265] Calculation process:

[0266] Calculate the adjusted denominator:

[0267] Computational efficiency adjustments:

[0268] Adjusted storage capacity: H = 1000·(0.8+0.0769) = 1000·0.8769 = 876.9 units.

[0269] Result analysis:

[0270] The adjusted storage capacity is 876.9 units, indicating that hydrogen is stored efficiently per unit of energy, reflecting that the strategy adjustment has improved storage efficiency.

[0271] formula:

[0272]

[0273] in:

[0274] O: Adjusted output rate.

[0275] H: Adjusted storage capacity, 876.9 units.

[0276] λ z : Output rate adjustment coefficient, assumed to be 0.5.

[0277] p z : Pressure adjustment parameter, assumed to be (30 degrees).

[0278] μ z : Pressure quadratic term coefficient, assumed to be 0.1.

[0279] Calculation process:

[0280] Calculate the pressure-dependent adjustment term:

[0281] Calculate the effect of quadratic adjustment:

[0282] Adjusted output rate: O = 876.9 (0.5 0.866 + 0.1 0.274) ≈ 876.9.

[0283] (0.433+0.0274)=876.9·0.4604≈403.64

[0284] Result analysis:

[0285] The adjusted output rate is 403.64 units, indicating that the output efficiency of hydrogen has been significantly improved, optimizing the overall energy management efficiency.

[0286] formula:

[0287]

[0288] in:

[0289] K: Cost-effectiveness.

[0290] O: Output rate, 403.64 units.

[0291] H: storage capacity, 876.9 units.

[0292] c z : Cost coefficient, assumed to be 0.002.

[0293] τ z : Cost adjustment parameter, assumed to be 0.05.

[0294] Calculation process:

[0295] Calculate the cost factor: c z ·H 2 +τ z·H=0.002·876.9 2 +0.05·876.9≈1538.1842+43.845=1582.0292

[0297] Cost-effectiveness:

[0298] Result analysis:

[0299] The cost-effectiveness ratio is 0.255, which indicates the output benefit per unit cost. A high benefit value indicates that the solution is economically feasible.

[0300] See also Figure 6 ,The specific steps for obtaining the real-time response optimization framework are:

[0301] Apply the adjusted strategy to refine the results by continuously monitoring the deviation of energy output from the preset target, using the formula:

[0302] Δ=KT s

[0303] Calculate the current deviation result;

[0304] Where Δ represents the current deviation, T s Represents a preset goal;

[0305] Based on the current deviation results, the formula is used:

[0306]

[0307] Dynamically adjust the working parameters of the load regulator to obtain adjusted working parameters;

[0308] Among them, P represents the adjusted working parameters, κ s represents the linear adjustment coefficient, β s represents the square root adjustment coefficient, γ s represents the quadratic adjustment coefficient;

[0309] Combined with the adjusted working parameters, the formula is used:

[0310]

[0311] Match energy output with demand in real time and establish a real-time response optimization framework;

[0312] Among them, M represents the real-time response optimization framework, e s Represents the base of natural logarithms.

[0313] formula:

[0314] Δ=KT s

[0315] Parameter Description:

[0316] K: The adjusted strategy refinement result, for example, E = 250 units (assuming it is the amount of energy output)

[0317] T s : Preset target, such as T s = 200 units (assuming the desired energy output)

[0318] Calculation process:

[0319] Δ=250-200=50

[0320] The deviation value (Δ) indicates the amount by which the current energy output exceeds the preset target and is used for iterative adjustment.

[0321] formula:

[0322]

[0323] Parameter Description:

[0324] κ s : Linear adjustment coefficient, assumed to be 0.5

[0325] β s : Square root adjustment coefficient, assumed to be 0.3

[0326] γ s : Quadratic adjustment coefficient, assumed to be 0.1

[0327] Δ=50

[0328] Calculation process:

[0329]

[0330] P = 25 + 0.3 7.07 + 0.1 2500

[0331] P = 25 + 2.12 + 250

[0332] P = 277.12

[0333] The calculation result P represents the adjusted operating parameters, and the parameter values ​​will be used to adjust the energy output to better match the demand.

[0334] formula:

[0335]

[0336] Parameter Description:

[0337] e s : The base of the natural logarithm, approximately equal to 2.718

[0338] P = 277.12

[0339] Δ=50

[0340] Calculation process:

[0341]

[0342]

[0343]

[0344] M=277.12

[0345] The M value represents the optimal energy output adjustment of the system under given parameters and current deviations, ensuring real-time responsiveness.

[0346] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. New energy hydrogen production power integrated control system, characterized in that: The system comprises: The demand forecasting module collects the electrolyzer operation data and real-time environmental parameters, calculates the statistical characteristics of the data including the mean value and standard deviation element by element, and infers the future trend based on the statistical characteristics to obtain the energy demand forecast value; The dynamic programming module receives the energy demand forecast value, combines the real-time data of the energy management unit, sets evaluation criteria for differentiated energy input combinations, adjusts multiple combinations to optimize energy output efficiency, and obtains an energy allocation strategy; The strategy optimization module uses the energy allocation strategy to quantitatively adjust the storage capacity and output rate of the hydrogen storage device, evaluate the cost-effectiveness of the differentiated solution, and obtain the adjusted strategy refinement results; The real-time optimization and adjustment module applies the adjusted strategy refinement results, continuously monitors the deviation between energy output and preset targets, dynamically adjusts the working parameters of the load regulator, performs real-time matching of energy output and demand, and establishes a real-time response optimization framework.

2. The new energy hydrogen production power integrated control system according to claim 1 is characterized in that: The steps for obtaining the statistical characteristics of the mean value and the standard deviation are specifically as follows: For the daily operation data of the electrolyzer, the daily average values ​​of the current, voltage and temperature parameters are calculated using the formula: Get the daily average current, daily average voltage, and daily average temperature; in, represents the daily average of the parameter, n represents the number of data points, x i Represents the value of the i-th data point; Based on the daily average current, daily average voltage and daily average temperature, the sum of squares of the deviations of each parameter from the average value is calculated using the formula: The current standard deviation, voltage standard deviation and temperature standard deviation are calculated; Where σ represents the standard deviation of the parameter, n represents the number of data points, and x i Represents the value of the i-th data point; The current standard deviation, voltage standard deviation and temperature standard deviation are combined, and the influence of multiple parameters on the performance of the electrolytic cell is referred to, and the formula is adopted: Calculate the combined standard deviation to obtain the statistical properties of the mean and standard deviation; Where S represents the comprehensive standard deviation, σ x represents the standard deviation of the current, σ y Represents the standard deviation of voltage, σ z represents the standard deviation of temperature, a q 、b q 、c q Represent the weight coefficients of current, voltage and temperature respectively, d q Represents an adjustment factor.

3. The new energy hydrogen production power integrated control system according to claim 2 is characterized in that: The steps for obtaining the energy demand forecast value are specifically as follows: Based on the statistical properties of the mean and standard deviation, combined with the composite standard deviation and historical energy consumption data for the electrolyzers, the initial estimate of energy demand is adjusted using the formula: Calculate a preliminary energy demand estimate; Where E represents the preliminary energy demand estimate, α w represents the weight associated with the standard deviation, β w Represents the linear influence coefficient of historical energy consumption, λ w represents the nonlinear adjustment coefficient of historical consumption, and H represents the average value of historical energy consumption; Based on the preliminary energy demand estimate, with reference to the impact of real-time environmental parameters, the formula is used: D=E·(1+γ w ·cos(T w )+d w ·log(1+M w )) Refine the energy demand forecast and obtain the energy demand forecast value; Where D represents the predicted energy demand, γ w Represents the cosine adjustment coefficient of temperature, T w Represents the real-time ambient temperature, δ w Represents the logarithmic adjustment factor of humidity, M w Represents the real-time ambient humidity.

4. The new energy hydrogen production power integrated control system according to claim 3 is characterized in that: The steps for obtaining the energy allocation strategy are specifically as follows: Receive the energy demand forecast value and use the formula: Calculate and obtain the initial energy allocation plan; Among them, V represents the initial energy allocation plan, r x represents the basic adjustment coefficient, δ x Represents the historical consumption adjustment coefficient, H x Represents the historical average energy consumption; Based on the initial energy allocation plan and combined with the real-time data of the energy management unit, the formula is adopted: C=V·(1+k x ·log(1+U x )) adjusting the energy allocation plan to obtain an adjusted energy allocation plan; Among them, C represents the adjusted energy allocation plan, k x Represents the dynamic adjustment coefficient, U x Represents real-time data; Based on the adjusted energy allocation scheme, the evaluation criteria for the differentiated energy input combinations are set using the formula: Calculate the comprehensive efficiency of each combination and generate energy allocation strategy; Where F represents the energy allocation strategy, w i represents the efficiency weight of the i-th energy combination, C i represents the allocation value of the i-th energy in the adjusted energy allocation plan, σ i stands for efficiency adjustment factor.

5. The new energy hydrogen production power integrated control system according to claim 4 is characterized in that: The steps for obtaining the adjusted strategy refinement result are specifically as follows: Using the energy allocation strategy, the formula is adopted: calculating a storage capacity adjustment of the hydrogen storage device to obtain an adjusted storage capacity; Where H represents the adjusted storage capacity, s z represents the storage efficiency factor, η z represents the efficiency adjustment coefficient, ∈ z represents the basic adjustment parameter; Based on the adjusted storage capacity, the formula is used: adjusting the output rate of the hydrogen storage device to obtain an adjusted output rate; Where O represents the adjusted output rate, λ z represents the output rate adjustment coefficient, p z Represents the pressure regulation parameter, μ z represents the pressure quadratic term coefficient; Combining the adjusted storage capacity and the adjusted output rate, the formula is adopted: Evaluate the cost-effectiveness of differentiated solutions and generate adjusted strategy refinement results; Among them, K represents the adjusted strategy optimization result, c z represents the cost coefficient, τ z Represents the cost adjustment parameter.

6. The new energy hydrogen production power integrated control system according to claim 5 is characterized in that: The steps for obtaining the real-time response optimization framework are specifically as follows: Apply the adjusted strategy refinement results, by continuously monitoring the deviation of energy output from the preset target, using the formula: Δ=KT s Calculate the current deviation result; Where Δ represents the current deviation, T s Represents a preset goal; Based on the current deviation results, the formula is used: Dynamically adjust the working parameters of the load regulator to obtain adjusted working parameters; Among them, P represents the adjusted working parameters, κ s represents the linear adjustment coefficient, β s represents the square root adjustment coefficient, γ s represents the quadratic adjustment coefficient; Combined with the adjusted working parameters, the formula is adopted: Match energy output with demand in real time and establish a real-time response optimization framework; Among them, M represents the real-time response optimization framework, e s Represents the base of natural logarithms.

Images