Hydrogen storage cylinder inflation and deflation regulation and control method based on numerical simulation and machine learning

Through numerical simulation and machine learning, the charging and deflation control logic of hydrogen storage bottles is optimized, and the temperature fluctuation problem during the charging and deflation process of hydrogen storage bottles is solved, and rapid and accurate control is achieved, which improves safety and efficiency.

CN118940639APending Publication Date: 2024-11-12DALIAN BOILER & PRESSURE VESSEL INSPECTION & TESTING INST CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411121488.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

During the filling and degassing process of hydrogen storage bottles, temperature fluctuations may be exceeded by the safety range due to gas compression/expansion and thermal energy conversion. The existing technology relies on bottle valve sensor monitoring to ensure that the temperature in the entire space is within the safe range, and the consumption of filling and degassing is optimized. Duration.

Method used

Using numerical simulation and machine learning methods, by constructing a flow-thermal coupled simulation model and neural network model, analyzing the working conditions and historical data of hydrogen storage bottles, optimizing the charging and deflation control logic, ensuring the evolution law of temperature and flow fields, and realizing Fast and accurate control.

Benefits of technology

It improves the safety of hydrogen storage bottles and the efficiency of the filling and deflation process, ensures that the entire space temperature of the filling and deflation process is within the safe range, and shortens the optimization time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940639A_ABST
    Figure CN118940639A_ABST
Patent Text Reader

Abstract

The invention provides a hydrogen storage cylinder inflation and deflation regulation and control method based on numerical simulation and machine learning, and the method comprises the steps: analyzing the inflation and deflation operation condition of a hydrogen storage cylinder, and obtaining a condition analysis result and historical data; constructing a flow-thermal coupling simulation model according to the three-dimensional model of the hydrogen storage bottle, and performing a simulation model simulation test to obtain a simulation result; the simulation result is verified according to historical data, and a flow field evolution rule and a temperature field evolution rule in the hydrogen storage cylinder in the inflation and deflation process are obtained; integrating the simulation result and historical data into a data set; constructing a neural network model, and training and verifying the neural network model through the data set; the working condition analysis result is calculated according to the trained neural network model, and inflation and deflation control logic is obtained; and the inflation and deflation control logic is optimized according to the flow field evolution law and the temperature field evolution law. According to the method, the optimal control logic of inflation and deflation of the hydrogen storage cylinder is accurately obtained, and the safety of the hydrogen storage cylinder and the high efficiency of the inflation and deflation process are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of hydrogen storage bottle filling and discharging optimization, and in particular to a hydrogen storage bottle filling and discharging control method based on numerical simulation and machine learning. Background Art

[0002] High-pressure on-board hydrogen storage bottles are the most widely used hydrogen storage method for hydrogen fuel cell vehicles at this stage because of their advantages such as low cost, low energy consumption, and fast filling and discharging speed. The safe and efficient use of high-pressure hydrogen storage bottles has become an important prerequisite for the large-scale commercialization of hydrogen fuel cell vehicles. Among them, the rapid filling and discharging process of hydrogen storage bottles is an important link in its practical application. This process must simultaneously meet the requirements of the filling and discharging rate and the safe operating temperature range of the hydrogen storage bottle (-40℃~85℃). However, during the filling and discharging process, due to gas compression / expansion, conversion between kinetic / thermal energy, and the Joule-Thomson effect, the temperature in the hydrogen storage bottle fluctuates significantly and is likely to exceed the safe temperature range.

[0003] At present, the temperature of hydrogen storage bottles during the filling and discharging process is only monitored by bottle valve sensors. However, the temperature distribution inside the bottle is uneven, and only monitoring the bottle mouth temperature cannot ensure that the entire space is within a safe temperature range. In addition, the volume, working environment and charging conditions of hydrogen storage bottles are complex and diverse, which affect the evolution and distribution of temperature during the charging and discharging process of hydrogen storage bottles. The temperature distribution in the entire space of the hydrogen storage bottle can be obtained by numerical simulation methods, but optimizing the charging and discharging rate by testing a large number of working conditions will be time-consuming. Therefore, it is very necessary to design a hydrogen storage bottle charging and discharging control method based on numerical simulation and machine learning. Summary of the invention

[0004] The purpose of the present invention is to provide a hydrogen storage bottle charging and deflation control method based on numerical simulation and machine learning, so as to quickly and accurately obtain the optimal control logic of hydrogen storage bottle charging and deflation, and improve the safety of hydrogen storage bottles and the efficiency of the charging and deflation process.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] A method for controlling the filling and discharging of a hydrogen storage bottle based on numerical simulation and machine learning comprises the following steps:

[0007] Analyze the charging and discharging operating conditions of the hydrogen storage bottle, and obtain the operating condition analysis results and historical data respectively;

[0008] A flow-heat coupling simulation model is constructed based on the three-dimensional model of the hydrogen storage bottle, and a simulation test is carried out based on the flow-heat coupling simulation model to obtain simulation results;

[0009] The simulation results were verified based on historical data, and the evolution laws of the flow field and temperature field in the hydrogen storage bottle during the filling and discharging process were obtained respectively;

[0010] Integrate simulation results and historical data into a data set; the data set includes a training set and a validation set;

[0011] Build a neural network model, train the neural network model through the training set, and test and verify the trained neural network model based on the verification set;

[0012] The working condition analysis results are calculated according to the trained neural network model to obtain the charging and discharging control logic;

[0013] The charging and discharging control logic is optimized according to the flow field evolution laws and temperature field evolution laws.

[0014] Optionally, the fluid-heat coupling simulation model includes a turbulence model and a heat transfer model.

[0015] Optionally, the operating condition analysis results include: the working environment temperature of the hydrogen storage bottle, the working environment humidity, the medium temperature, the initial pressure of filling and discharging, and the target pressure.

[0016] Optionally, the historical data includes: data type, data collection location and time series.

[0017] Optionally, the neural network model includes input parameters and output parameters; the input parameters are the results of the operating condition analysis, and the output parameters are the quantitative relationship between the rate and time during the inflation and deflation process.

[0018] Optionally, the inflation and deflation control logic is an expression of the rate changing with time during the inflation and deflation process.

[0019] Optionally, the charging and discharging control logic is optimized according to the flow field evolution law and the temperature field evolution law, and the specific steps are as follows:

[0020] According to the flow field evolution law and the temperature field evolution law, the local measurement data time series of pressure and temperature in the inflation and deflation process are obtained respectively, and the inflation and deflation control logic is optimized based on the local measurement data time series.

[0021] Optionally, the flow field evolution law is the evolution law of the velocity and pressure in the axial direction with the filling and deflation time; the temperature field evolution law is the evolution law of the temperature field in the axial direction, the bottle mouth temperature and the bottle tail temperature with the filling and deflation time.

[0022] According to the specific embodiment provided by the present invention, the present invention discloses the following technical effects: the method for regulating and controlling the filling and discharging of a hydrogen storage bottle based on numerical simulation and machine learning provided by the present invention comprises: constructing a flow-heat coupling simulation model according to the three-dimensional model of the hydrogen storage bottle, and conducting simulation tests according to the flow-heat coupling simulation model to obtain simulation results; analyzing the filling and discharging operating conditions of the hydrogen storage bottle to obtain the operating condition analysis results, and obtaining historical data according to the operating condition analysis results; verifying the simulation results according to the historical data to obtain the flow field evolution law and the temperature field evolution law in the hydrogen storage bottle during the filling and discharging process; integrating the simulation results and the historical data into a data set; the data set includes a training set and a verification set; constructing a neural network model, training the neural network model through the training set, and testing and verifying the trained neural network model according to the verification set; calculating the operating condition analysis results according to the trained neural network model to obtain the filling and discharging control logic; optimizing the filling and discharging control logic according to the flow field evolution law and the temperature field evolution law. The method quickly and accurately obtains the optimal control logic for the filling and discharging of the hydrogen storage bottle, and improves the safety of the hydrogen storage bottle and the efficiency of the filling and discharging process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0024] Figure 1 This is a flow chart of a method for controlling the filling and discharging of a hydrogen storage bottle based on numerical simulation and machine learning according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0027] like Figure 1 As shown, an embodiment of the present invention provides a method for controlling the filling and discharging of a hydrogen storage bottle based on numerical simulation and machine learning, comprising the following steps:

[0028] Step 100: Analyze the charging and discharging operating conditions of the hydrogen storage bottle to obtain operating condition analysis results and historical data;

[0029] Specifically, the operating condition analysis results include: the working environment temperature of the hydrogen storage bottle, the working environment humidity, the medium temperature, the initial pressure and target pressure of filling and discharging; the historical data include: data type, data collection location and time series.

[0030] Step 200: construct a flow-heat coupling simulation model based on the three-dimensional model of the hydrogen storage bottle, and conduct simulation tests based on the flow-heat coupling simulation model to obtain simulation results; the specific steps are: construct a three-dimensional geometric model of the hydrogen storage bottle according to the parameters of the hydrogen storage bottle to be charged and discharged, analyze the coupling characteristics of its internal flow field and temperature field, and construct a flow-heat coupling simulation model for charging and discharging the hydrogen storage bottle according to the coupling characteristics. The flow-heat coupling simulation model includes a turbulence model and a heat transfer model.

[0031] Specifically, the parameters of the hydrogen storage bottle include: bottle wall thickness, fiber layer thickness, thermal conductivity, liner thickness, material thermal conductivity, volume, length and diameter and other detailed parameters.

[0032] Step 300: verify the simulation results according to historical data, and obtain the flow field evolution law and temperature field evolution law in the hydrogen storage bottle during the filling and discharging process respectively; the specific steps are: determine the time series of pressure and temperature in the simulation test according to the historical data, and verify the simulation results according to the time series of pressure and temperature, and perform data analysis on the simulation results to obtain the flow field evolution law and temperature field evolution law in the hydrogen storage bottle during the filling and discharging process.

[0033] Specifically, the flow field evolution law is the evolution law of the velocity and pressure in the axial direction with the filling and deflation time; the temperature field evolution law is the evolution law of the temperature field in the axial direction, the bottle mouth temperature and the bottle tail temperature with the filling and deflation time.

[0034] Step 400: Integrate the simulation results and historical data into a data set; the data set includes a training set and a validation set;

[0035] Step 500: construct a neural network model, train the neural network model through a training set, and test and verify the trained neural network model based on a verification set; the specific steps are: use the ambient temperature, medium temperature, initial pressure of inflation and deflation, upper and lower limits of inflation and deflation rate, upper and lower limits of target pressure, and upper and lower limits of safety temperature as input parameters of the neural network model, and use the quantitative relationship between the rate change over time during the inflation and deflation process as the output parameter of the neural network model, train the neural network model through a training set, and test and verify the trained neural network model through a verification set.

[0036] Step 600: Calculate the operating condition analysis results according to the trained neural network model to obtain the charging and discharging control logic; the specific steps are: input the actual operating condition parameters (hydrogen storage bottle volume, ambient temperature, medium temperature and charging and discharging target pressure, etc.) into the trained neural network model for calculation, optimize the charging and discharging rate according to the charging and discharging rate, target pressure and safe temperature range, and obtain the optimal control logic of the charging and discharging rate in the whole charging and discharging process.

[0037] Specifically, the optimal control logic of the inflation and deflation rate is an expression of the rate changing with time during the inflation and deflation process.

[0038] Step 700: Optimize the inflation and deflation control logic according to the flow field evolution law and the temperature field evolution law. The specific steps are: obtain the local measurement data time series of pressure and temperature during the inflation and deflation process according to the flow field evolution law and the temperature field evolution law, and optimize the inflation and deflation control logic with the local measurement data time series.

[0039] The beneficial effects of the present invention are as follows:

[0040] 1) The initial and boundary conditions in the process of analyzing different working conditions were determined to ensure the applicability and accuracy of the method;

[0041] 2) It can effectively solve the problem of being unable to obtain the full-space temperature field during the hydrogen storage bottle charging and discharging process;

[0042] 3) The optimal control logic for charging and discharging hydrogen storage bottles can be obtained quickly and accurately, and the safety of hydrogen storage bottles and the efficiency of the charging and discharging process can be improved.

[0043] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0044] The present invention uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for controlling the filling and discharging of a hydrogen storage bottle based on numerical simulation and machine learning, characterized in that: The steps include: Analyze the charging and discharging operating conditions of the hydrogen storage bottle to obtain operating condition analysis results and historical data; Constructing a flow-heat coupling simulation model according to the three-dimensional model of the hydrogen storage bottle, and performing a simulation test according to the flow-heat coupling simulation model to obtain a simulation result; The simulation results are verified according to the historical data, and the flow field evolution law and the temperature field evolution law in the hydrogen storage bottle during the filling and discharging process are obtained respectively; Integrate the simulation results and the historical data into a data set; the data set includes a training set and a validation set; Constructing a neural network model, training the neural network model using the training set, and testing and verifying the trained neural network model using the verification set; The working condition analysis result is calculated according to the trained neural network model to obtain the charging and discharging control logic; The charging and discharging control logic is optimized according to the flow field evolution law and the temperature field evolution law.

2. The method for controlling the filling and discharging of a hydrogen storage bottle based on numerical simulation and machine learning according to claim 1 is characterized in that: The fluid-heat coupling simulation model includes a turbulence model and a heat transfer model.

3. The method for controlling the filling and discharging of hydrogen storage bottles based on numerical simulation and machine learning according to claim 1 is characterized in that: The working condition analysis results include: the working environment temperature, working environment humidity, medium temperature, initial pressure and target pressure of the hydrogen storage bottle.

4. The method for controlling the filling and discharging of a hydrogen storage bottle based on numerical simulation and machine learning according to claim 1 is characterized in that: The historical data includes: data type, data collection location and time series.

5. The method for controlling the filling and discharging of hydrogen storage bottles based on numerical simulation and machine learning according to claim 1 is characterized in that: The neural network model includes input parameters and output parameters; the input parameters are the operating condition analysis results, and the output parameters are the quantitative relationship between the rate and time during the inflation and deflation process.

6. The method for controlling the filling and discharging of a hydrogen storage bottle based on numerical simulation and machine learning according to claim 1 is characterized in that: The inflation and deflation control logic is an expression of the rate changing with time during the inflation and deflation process.

7. The method for controlling the filling and discharging of hydrogen storage bottles based on numerical simulation and machine learning according to claim 1 is characterized in that: The charging and discharging control logic is optimized according to the flow field evolution law and the temperature field evolution law, and the specific steps are as follows: According to the flow field evolution law and the temperature field evolution law, local measurement data time series of pressure and temperature in the inflation and deflation process are obtained respectively, and the inflation and deflation control logic is optimized by the local measurement data time series.

8. The method for controlling the filling and discharging of hydrogen storage bottles based on numerical simulation and machine learning according to claim 1 is characterized in that: The flow field evolution law is the evolution law of the velocity and pressure in the axial direction with the filling and deflation time; the temperature field evolution law is the evolution law of the temperature field in the axial direction, the bottle mouth temperature and the bottle tail temperature with the filling and deflation time.