CN-122022392-A - Water electrolysis system configuration optimization method and platform based on multi-source data collaborative computing

CN122022392ACN 122022392 ACN122022392 ACN 122022392ACN-122022392-A

Abstract

The invention discloses a configuration optimization method and a configuration optimization platform for a water electrolysis system based on multi-source data collaborative computing, wherein the configuration optimization method and the configuration optimization platform comprise the steps of collecting multi-dimensional operation parameters of equipment such as an electrolytic tank, a gas-liquid separator and the like through a cross-domain data collaborative processing system, transmitting the multi-dimensional operation parameters in real time, calling a water electrolysis multi-field coupling simulation model to dynamically simulate an operation state, iteratively adjusting the configuration parameters by combining a guide matrix increment updating algorithm, calculating equipment proportion through a load adaptation model to determine a configuration feasible domain, establishing a mapping relation between the parameters and the operation state through multi-source data cross-validation, carrying out multi-round screening on schemes in the feasible domain, dynamically adjusting equipment grouping, connection modes and linkage logic, and finally determining an optimization configuration scheme adapting to different scenes, and the platform is orderly linked through six functional units to realize data collection, simulation operation, parameter updating, scheme optimization and execution of closed loops of landing, so that the device is guaranteed to operate efficiently and stably under complex working conditions.

Inventors

LIU HEQING
MENG XIN
HE MINGZHI
ZHANG CHANGWEI

Assignees

四川大学

Dates

Publication Date: 20260512
Application Date: 20260409

Claims (10)

1. A configuration optimization method of a water electrolysis system based on multi-source data collaborative calculation is characterized by comprising the following steps of S1, collecting gas yield of an electrolytic tank, processing capacity of a gas-liquid separator, gas purity detection value, alkali liquid flow data and load fluctuation related parameters in the operation process of the water electrolysis system through a cross-domain data collaborative processing system, constructing a multi-dimensional data collection matrix and transmitting in real time, S2, calling a water electrolysis multi-field coupling simulation model to dynamically simulate collected data to generate multi-field distribution characteristic data of the operation state of the device, iteratively adjusting an initial configuration parameter matrix by combining a water electrolysis guide matrix increment updating algorithm, S3, carrying out preliminary calculation on the quantity proportion of the electrolytic tank and the separator under different operation conditions based on an electrolytic device load adaptation model, determining a feasible domain range of configuration parameters, S4, extracting calibration characteristic parameters affecting configuration optimization through the cross-domain data collaborative processing system, establishing a mapping relation between the parameters and the operation state of the device, S5, carrying out multi-wheel screening on a configuration scheme in the feasible domain by combining the water electrolysis guide matrix increment updating algorithm, dynamically adjusting the electrolytic tank, a connection branch circuit and an auxiliary configuration mode, and a linkage configuration device and a final configuration optimizing mode are formed according to a linkage configuration result.
2. The water electrolysis system configuration optimization method based on multi-source data collaborative computing according to claim 1, wherein the S2 water electrolysis multi-field coupling simulation model expression is: Wherein: For the multi-field coupling simulation result matrix, For the weight coefficient of the i-th monitoring point, The electric field gradient vector for the i-th monitoring point, The gas density gradient vector for the ith monitoring point, For the multiple field coupling coefficients, The temperature field distribution value for the ith monitoring point, As a function of the time variable, Is the alkali liquor flowing viscosity coefficient of the ith monitoring point, Is the total number of monitoring points.
3. The water electrolysis guide matrix incremental update algorithm based on multi-source data collaborative computing according to claim 1, wherein the S2 water electrolysis guide matrix incremental update algorithm expression is: Wherein: for the incrementally updated steering matrix, For the initial steering matrix to be used, Is a matrix of units which is a matrix of units, In order to update the step size coefficients, In the case of a multi-source data delta matrix, A matrix of data weights is used for the data, The 2-norm of the data delta matrix, To configure a parameter projection matrix.
4. The water electrolysis system configuration optimization method based on multi-source data collaborative computing according to claim 1, wherein the electrolytic device load adaptation model expression in S3 is: Wherein: for the purpose of adapting the coefficients to the load, For the total gas production of the system, In order to adjust the coefficient of the load, As the influence coefficient of the j-th load fluctuation, For the magnitude of the j-th load fluctuation, In order to be able to measure the number of load fluctuation types, For the total number of electrolytic cells, Is the rated gas production rate of a single electrolytic tank, In order for the separator to process the efficiency coefficient, The ratio of the electrolytic tank to the separator is adapted to the coefficient.
5. The method for optimizing configuration of a water electrolysis system based on multi-source data collaborative computing according to claim 1, wherein the data cross-validation model expression of the cross-domain data collaborative processing system in S4 is: Wherein: In order to cross-validate the result value, The actual value of the I-th sample point for the kth class of data, The predicted value of the I-th sampling point for the kth class of data, As the weight coefficient of the actual value, For the weight coefficient of the predicted value, The number of data classes to be used in the method, For a single type of data sample point number, To verify the correction coefficients.
6. The configuration optimization method of the water electrolysis system based on the multi-source data collaborative computing according to claim 1, wherein the configuration scheme multi-round screening model expression in S5 is: Wherein: In order to screen out the optimal configuration scheme, In order to configure the feasible region of the scheme, The weight coefficients of purity deviation, yield deviation and cost deviation are respectively obtained, For the purity bias value of scheme s, As the value of the yield bias of scheme s, As the cost offset value for scheme s, The coefficients are adapted for the optimization of scheme s.
7. The configuration optimization method of the water electrolysis system based on the multi-source data collaborative calculation is characterized by comprising the following steps of S31, extracting rated gas yield, maximum purity fluctuation value and maximum processing capacity core parameters of a gas-liquid separator of an electrolysis tank under different load working conditions through a cross-domain data collaborative processing system, classifying and storing according to working condition types, S32, inputting the classified parameters into a load adaptation model of an electrolysis device, setting constraint conditions of different proportioning combinations, calculating load adaptation coefficients and operation state parameters under each combination, S33, sorting calculation results, eliminating proportioning combinations with the adaptation coefficients exceeding a preset range, reserving configuration parameter sets meeting basic operation requirements, S34, combining simulation results of the water electrolysis multi-field coupling simulation model, and performing secondary screening on the reserved configuration parameter sets to further reduce the feasible domain range.
8. The configuration optimization method of the water electrolysis system based on the multi-source data collaborative calculation is characterized by comprising the following steps of S41, classifying and analyzing collected operation data of an electrolytic tank, operation data of a separator, purity detection data and alkali liquid flow data by a cross-domain data collaborative processing system, extracting time sequence features and amplitude features of different types of data, S42, establishing association rules among the different types of data, constructing a data association matrix through a water electrolysis guide matrix incremental updating algorithm, identifying data abnormal values and marking, S43, checking marked abnormal data based on the association matrix, judging effectiveness of the abnormal data by combining historical operation data with simulation model results, removing ineffective abnormal data, S44, establishing a nonlinear mapping relation between parameters and device operation states according to the checked effective data, and providing data support for configuration optimization.
9. The configuration optimization method of the water electrolysis system based on the multi-source data collaborative calculation according to claim 1 is characterized in that the method comprises the following steps of S51, based on the mapping relation established by S4, performing initial iteration update on configuration schemes in a feasible domain by utilizing a water electrolysis guiding matrix increment update algorithm, adjusting the corresponding relation between the grouping number of the electrolytic cells and separators, S52, calling a water electrolysis multi-field coupling simulation model to perform operation simulation on the updated configuration schemes, obtaining a purity fluctuation curve, a yield output curve and a load adaptation curve of each scheme, S53, sorting the schemes according to the index priority and the index priority according to the comprehensive evaluation index of the simulation curve calculation scheme, and reserving the top 20% of high-quality schemes, and S54, performing multi-round iteration optimization on the high-quality schemes, and dynamically adjusting the linkage logic and branch connection mode of auxiliary equipment to form a final candidate configuration scheme set.
10. The water electrolysis system configuration optimization platform based on multi-source data collaborative computing is characterized by being applied to the water electrolysis system configuration optimization method based on multi-source data collaborative computing according to claim 1, and comprises a multi-source data cross-domain acquisition and transmission unit, a water electrolysis multi-field coupling simulation operation unit, a guide matrix increment updating processing unit, a load adaptation parameter calculation unit, a configuration scheme intelligent screening and optimization unit and a configuration result output and execution unit, wherein the multi-source data cross-domain acquisition and transmission unit acquires operation parameters of an electrolytic tank, a gas-liquid separator and auxiliary equipment through different kinds of sensors, the operation parameters are transmitted to the water electrolysis multi-field coupling simulation operation unit after data encoding processing, the water electrolysis multi-field coupling simulation operation unit receives data and then carries out multi-field dynamic simulation, a simulation result is synchronized to the guide matrix increment updating processing unit and the load adaptation parameter calculation unit, the guide matrix increment updating processing unit carries out iterative adjustment on an initial configuration matrix, the load adaptation coefficients under different working conditions are calculated, the two results are input into the configuration scheme intelligent screening and optimization unit together, the configuration scheme intelligent screening and the optimization unit carries out intelligent screening and optimization unit to carry out configuration and multi-wheel screening on the configuration result, the control scheme is converted into an optimal configuration result, and the control result is output to the control result, and the control result is sent to the control module.

Description

Water electrolysis system configuration optimization method and platform based on multi-source data collaborative computing Technical Field The invention relates to the field of multi-source data processing and engineering optimization of a water electrolysis technology, in particular to a water electrolysis system configuration optimization method and platform based on multi-source data collaborative computing, multi-physical field simulation modeling and intelligent algorithm based on computer multi-source data collaborative computing. Background The water electrolysis technology is used as a core supporting means for clean energy conversion and storage, is widely applied to the fields of hydrogen energy preparation, energy network peak regulation and the like, and the device operation efficiency and configuration rationality directly determine the energy conversion efficiency, operation stability and comprehensive cost control effect. Along with the development of the water electrolysis system to large-scale, intelligent and multi-working condition adaptation, the operation data of a single dimension cannot meet the requirement of accurate configuration, the cooperative utilization of multi-source cross-domain data and the accurate depiction of multi-physical field coupling relation become the key of improving the configuration optimization level of the device. In the prior art, multi-source data are integrated by optimizing multi-dependent computer data processing means aiming at the configuration of a water electrolysis system, the running state of a device is simulated by means of a computer multi-field coupling simulation model, and configuration parameters are adjusted by combining a preset algorithm. For example, partial schemes are used for generating a configuration scheme adapting to a single working condition by collecting basic data such as the voltage, the current, the temperature and the electrolyte concentration of an electrolytic tank and utilizing a computer system to carry out simple statistical analysis, and other schemes are used for attempting to provide theoretical support for parameter adjustment by repeating the coupling action of an electric field and a temperature field through a computer simulation model. However, the prior art is still obviously insufficient due to the fact that on one hand, the method is limited by single computer data processing logic and low multi-source data fusion precision, collaborative linkage processing of cross-domain data (such as power grid load data, environment temperature and humidity data and device history operation data) is difficult to achieve, so that the support of data on configuration optimization is insufficient, on the other hand, the existing computer multi-field coupling simulation model is multi-focusing single physical field or few two-field coupling, simulation dimension is incomplete, a simulation iterative algorithm is crude, a multi-field dynamic interaction rule cannot be accurately captured, and therefore the configuration parameter adjustment lacks accurate computer simulation support, and is difficult to adapt to complex and changeable operation conditions. In addition, part of schemes still rely on manual experience to correct configuration parameters, only the deep analysis processing is carried out through simple data recording instead of a computer system, the subjectivity of parameter adjustment is strong, the response speed is low, and the running stability and the energy conversion efficiency of the device are further reduced. Therefore, how to construct a set of efficient multi-source data collaborative processing and multi-field coupling simulation modeling scheme, and solve the problems of the prior art that the configuration of a computer-aided water electrolysis system is optimized by optimizing the computer data processing flow and iterative algorithm logic, and the accurate and intelligent adaptation of the configuration scheme is realized, is a technical problem to be solved urgently in the current water electrolysis technology field, and is also the core research direction of the invention. Disclosure of Invention In order to overcome the defects and shortcomings in the prior art, the invention provides a water electrolysis system configuration optimization method and platform based on multi-source data collaborative computing. The technical scheme adopted by the invention is that the configuration optimization method of the water electrolysis system based on multi-source data cooperative calculation comprises the following steps: S1, acquiring the gas yield of an electrolytic tank, the processing capacity of a gas-liquid separator, a gas purity detection value, alkali liquor flow data and load fluctuation related parameters in the operation process of a water electrolysis system through a cross-domain data cooperative processing system, constructing a multi-dimensional data acquisition matrix and transmittin