Self-adaptive optimization method and system for using amount of getter for aerospace helium purification
By optimizing getter dosage through multi-source data fusion and model predictive control algorithms, the waste and high cost caused by fixed getter dosage in aerospace helium purification systems are solved, achieving adaptive optimization of getter dosage and improving dehydrogenation stability and system intelligence.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-02-24
- Publication Date
- 2026-03-27
AI Technical Summary
The fixed amount of getter in existing aerospace helium purification systems leads to significant waste, high costs, and a lack of adaptability. It cannot be dynamically adjusted according to changes in inlet hydrogen concentration and getter performance, resulting in unstable dehydrogenation effects.
By employing multi-source data fusion technology, combining adsorption kinetics and getter capacity models, and utilizing model predictive control algorithms to optimize getter dosage, the system dynamically adjusts getter dosage by predicting future hydrogen concentration changes through real-time monitoring and historical data, and performs model parameter calibration to achieve adaptive optimization.
It significantly reduces getter consumption and operating costs, improves dehydrogenation stability and system intelligence, and ensures stable and efficient helium purification.
Smart Images
Figure CN121747759A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of gas separation and purification technology, and in particular to an adaptive optimization method and system for the dosage of getter used in aerospace helium purification. Background Technology
[0002] In the aerospace field, high-purity helium is an indispensable gas in critical applications such as rocket propellant loading and cryogenic equipment cooling. Currently, aerospace helium purification typically employs multi-stage purification processes, including adsorption purification, cryogenic purification, and chemisorption purification. Among these, chemisorption purification is often used to remove residual impurities such as hydrogen to meet the purity requirements of aerospace-grade helium.
[0003] Traditional chemisorption purification processes typically employ a fixed getter dosage, meaning the amount of getter is determined based on the worst-case scenario (e.g., the highest hydrogen concentration). While this method is simple and easy to implement, it has the following problems.
[0004] 1) Significant waste of getter: In actual operation, the hydrogen concentration in helium is usually far lower than that under the worst conditions, resulting in most of the getter's adsorption capacity not being fully utilized.
[0005] 2) High operating costs: High-efficiency dehydrogenation getters are expensive, and fixed dosage significantly increases operating costs.
[0006] 3) Lack of adaptability: It cannot dynamically adjust the amount of getter according to changes in the inlet hydrogen concentration and the decline in getter performance, resulting in unstable dehydrogenation effect.
[0007] In recent years, with the rapid development of IoT, big data, and AI technologies, some studies have begun to explore the application of these technologies to the optimized control of gas separation and purification processes. For example, sensor networks are used to monitor system status in real time, data mining techniques are used to analyze historical data, and machine learning algorithms are used to predict system behavior. However, most of these studies remain at the theoretical level and lack application in actual aerospace helium purification systems.
[0008] The existing technology has the following main drawbacks.
[0009] 1) Lack of precise control over the amount of getter: Traditional methods use a fixed amount of getter, which cannot be adjusted according to actual working conditions, resulting in serious waste of getter.
[0010] 2) Lack of real-time monitoring of getter performance: The inability to monitor the adsorption performance and remaining capacity of the getter in real time makes it difficult to optimize the adsorption process.
[0011] 3) Lack of comprehensive perception of system status: Control is based solely on limited sensor data, which fails to fully utilize system information.
[0012] 4) Lack of adaptive capability: It is difficult to adapt to changes in inlet hydrogen concentration and flow rate, resulting in unstable dehydrogenation effect.
[0013] Therefore, how to dynamically optimize the amount of getter, reduce consumption and operating costs, and improve dehydrogenation stability and system intelligence has become a technical problem that urgently needs to be solved in this field. Summary of the Invention
[0014] The purpose of this application is to provide an adaptive optimization method and system for the amount of getter used in aerospace helium purification, which can dynamically optimize the amount of getter, significantly reduce consumption and operating costs, and improve dehydrogenation stability and system intelligence.
[0015] To achieve the above objectives, this application provides the following solution.
[0016] In a first aspect, this application provides an adaptive optimization method for the amount of getter used in aerospace helium purification, the adaptive optimization method for the amount of getter used in aerospace helium purification includes the following steps.
[0017] Acquire multi-source data from the purification system, including real-time sensor data and historical background data.
[0018] The multi-source data is fused to obtain fused data.
[0019] Based on the fused data, the trend of hydrogen concentration at the outlet of the third-stage chemisorption purifier is predicted within a predetermined time period using a preset adsorption kinetics model and a getter capacity model. The adsorption kinetics model describes the adsorption rate of hydrogen on the getter, and the getter capacity model characterizes the remaining adsorption capacity of the getter.
[0020] An optimization problem is constructed with the goal of minimizing the amount of getter used and the constraint that the outlet hydrogen concentration does not exceed a set threshold. Based on the model predictive control algorithm, the optimal amount of getter added at the current moment is obtained.
[0021] Based on the optimal getter dosage at the current moment and the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier over a preset future period, the parameters of the adsorption kinetics model and / or the getter capacity model are calibrated and updated.
[0022] Optionally, the real-time sensor data includes: the inlet hydrogen concentration, outlet hydrogen concentration, getter bed temperature distribution, system pressure, and helium flow rate of the third-stage chemisorption purifier; the historical background data includes: the initial adsorption capacity of the getter, cumulative usage time, and batch information.
[0023] Optionally, the adsorption kinetic model is a function related to hydrogen concentration, temperature, and flow rate, constructed based on the Langmuir model, Freundlich model, or Toth model; the getter capacity model is a function related to usage time or cumulative treated gas volume, constructed based on a linear decay model or an exponential decay model.
[0024] Optionally, the model predictive control algorithm adopts a rolling optimization strategy, specifically including: in each control cycle, predicting the system behavior in the future time domain based on the current system state, solving the optimization problem in an optimization time domain, and outputting the first control quantity in the solution sequence as the actual injection quantity.
[0025] Optionally, a genetic algorithm or a particle swarm optimization algorithm may be used to calibrate and update the parameters of the adsorption kinetics model and / or the getter capacity model.
[0026] Optionally, the adaptive optimization method for the amount of getter used in aerospace helium purification further includes the following steps.
[0027] Based on the real-time remaining adsorption capacity calculated by the getter capacity model, when the real-time remaining adsorption capacity is lower than a preset safety threshold, a getter replacement warning signal is generated.
[0028] Secondly, this application provides an adaptive optimization system for the amount of getter used in aerospace helium purification. The adaptive optimization system for the amount of getter used in aerospace helium purification is used to implement the adaptive optimization method for the amount of getter used in aerospace helium purification as described in any one of the first aspects. The adaptive optimization system for the amount of getter used in aerospace helium purification includes the following modules.
[0029] The multi-source data acquisition module is used to acquire multi-source data from the purification system, including real-time sensor data and historical background data.
[0030] The data fusion module is communicatively connected to the multi-source data acquisition module and is used to fuse the multi-source data to obtain fused data.
[0031] The prediction module is used to predict the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier within a preset time period based on the fused data and using a preset adsorption kinetics model and getter capacity model. The adsorption kinetics model is used to describe the adsorption rate of hydrogen on the getter, and the getter capacity model is used to characterize the remaining adsorption capacity of the getter.
[0032] The optimization module is used to construct an optimization problem with the goal of minimizing the amount of getter and the constraint that the outlet hydrogen concentration does not exceed a set threshold. Based on the model predictive control algorithm, it solves the optimal amount of getter to be added at the current moment.
[0033] The calibration and update module is used to calibrate and update the parameters of the adsorption kinetics model and / or the getter capacity model based on the optimal getter dosage at the current moment and the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier in the future preset time period.
[0034] Optionally, the multi-source data acquisition module includes the following devices.
[0035] An online hydrogen analyzer is used to measure the hydrogen concentration at the inlet and outlet of the third-stage chemisorption purifier.
[0036] An array of getter bed temperature sensors is arranged inside the adsorption tower of the third-stage chemisorption purifier to measure the temperature distribution of the getter bed.
[0037] A pressure sensor is installed inside the adsorption tower of the third-stage chemisorption purifier to measure the system pressure.
[0038] A flow sensor is installed inside the adsorption tower of the third-stage chemical adsorption purifier to measure the helium flow rate.
[0039] A getter dosing system is installed on the third-stage chemical adsorption purifier to receive control commands and add getter.
[0040] The historical background data acquisition submodule is used to obtain the initial adsorption capacity, cumulative usage time, and batch information of the getter.
[0041] Optionally, the adaptive optimization system for the amount of getter used in aerospace helium purification also includes the following modules.
[0042] The early warning module is used to generate an early warning signal for replacing the getter when the real-time remaining adsorption capacity is calculated based on the getter capacity model.
[0043] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to implement the adaptive optimization method for the amount of getter used for aerospace helium purification as described in any one of the first aspects.
[0044] Based on the specific embodiments provided in this application, the following technical effects are disclosed.
[0045] This application provides an adaptive optimization method and system for getter dosage in aerospace helium purification. The method includes: acquiring multi-source data from the purification system, including real-time sensor data and historical background data; fusing the multi-source data to obtain fused data; eliminating data redundancy, compensating for the limitations of single data sources, improving data quality, and providing accurate data input for subsequent model prediction and optimization. Based on the fused data, using a preset adsorption kinetics model and getter capacity model, the method predicts the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier within a preset future time period; the adsorption kinetics model describes the adsorption rate of hydrogen on the getter; the getter capacity model characterizes the remaining adsorption capacity of the getter; this method allows for advance understanding of the dynamic changes in outlet hydrogen concentration, providing a forward-looking basis for subsequent getter dosage optimization and avoiding the risk of concentration exceeding limits. An optimization problem is constructed with the goal of minimizing getter dosage and the constraint that the outlet hydrogen concentration does not exceed a set threshold. Based on a model predictive control algorithm, the optimal getter dosage for the current moment is obtained. This minimizes getter dosage while ensuring helium purification meets standards (compliant outlet hydrogen concentration), reducing the operating cost of aerospace helium purification. Based on the optimal getter dosage at the current moment and the trend of outlet hydrogen concentration change of the third-stage chemisorption purifier over a preset future period, the parameters of the adsorption kinetics model and / or the getter capacity model are calibrated and updated. This enables dynamic adaptation of model parameters, improving model prediction accuracy and the reliability of optimization decisions, and ensuring the adaptive capability of the entire optimization method. Through the synergistic effect of each step, this application achieves precise optimization of getter dosage and stable purification effect, balancing cost control and operational reliability. It also possesses dynamic adaptive capability, continuously adapting to changes in the operation of the aerospace helium purification system, ensuring the long-term efficient, economical, and stable operation of the purification system. Attached Figure Description
[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0047] Figure 1 This is an application environment diagram of an adaptive optimization method for the dosage of getter in aerospace helium purification according to an embodiment of this application.
[0048] Figure 2 This is a flowchart illustrating an adaptive optimization method for the dosage of getter in aerospace helium purification, provided as an embodiment of this application.
[0049] Figure 3 This is a flowchart illustrating the steps of an adaptive optimization method for the dosage of getter in aerospace helium purification, provided in one embodiment of this application.
[0050] Figure 4 This is a schematic diagram of the functional modules of an adaptive optimization system for getter dosage in aerospace helium purification, provided as an embodiment of this application.
[0051] Figure 5 This is a system architecture diagram for adaptive optimization of getter dosage for aerospace helium purification, provided as an embodiment of this application.
[0052] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation
[0053] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0054] This application provides an adaptive optimization method and system for the amount of getter used in aerospace helium purification. To solve the problems of waste, high cost and lack of adaptability caused by the fixed amount of getter in the existing three-stage chemical adsorption purification process, this application adopts the following technical solution.
[0055] 1) System Architecture: The aerospace helium purification system comprises a first-stage adsorption purifier, a second-stage cryogenic purifier, and a third-stage chemisorption purifier connected in sequence. The third-stage chemisorption purifier includes an adsorption tower and a chemically active oxide reactor. The adsorption tower is filled with a highly efficient dehydrogenating getter and is equipped with a precise getter dosing system and a getter bed temperature sensor array. The system also includes a high-precision online hydrogen analyzer for measuring the hydrogen concentration at the inlet and outlet; a pressure gauge for measuring system pressure; a flow meter for measuring helium flow rate; and a historical background data acquisition submodule for acquiring the initial adsorption capacity, cumulative usage time, and batch information of the getter.
[0056] 2) Data fusion: Integrates data from multiple sensors (inlet hydrogen concentration, outlet hydrogen concentration, getter bed temperature, system pressure, and helium flow rate) and historical background data (initial adsorption capacity of getter, cumulative usage time, and batch information) to comprehensively perceive the system status.
[0057] 3) Adsorption kinetics modeling: Establish an adsorption rate model for hydrogen by the getter to describe the relationship between the adsorption rate and factors such as hydrogen concentration, temperature and flow rate, for example, using Langmuir, Freundlich or Toth adsorption models.
[0058] 4) Getter capacity modeling: Establish a model of the remaining adsorption capacity of the getter to describe the relationship between adsorption capacity and factors such as usage time, for example, by using a linear model or an exponential model.
[0059] 5) Model Predictive Control (MPC): Construct an optimization problem with the objective of minimizing getter dosage and the constraint of outlet hydrogen concentration. Use the MPC algorithm to calculate the optimal getter dosage and send it to the precision getter dosing system.
[0060] 6) Adaptive optimization: Periodically analyze historical data, evaluate the model's prediction accuracy, and use optimization algorithms (such as genetic algorithms or particle swarm optimization algorithms) to adjust the model parameters.
[0061] This application can dynamically optimize the amount of getter, significantly reduce consumption and operating costs, and improve dehydrogenation stability and system intelligence.
[0062] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0063] The adaptive optimization method for getter dosage in aerospace helium purification provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on another server. Terminal 102 can send the acquired multi-source data of the purification system to server 104. The multi-source data includes real-time sensor data and historical background data. After receiving the multi-source data, server 104 fuses the multi-source data to obtain fused data. Based on the fused data, using a preset adsorption kinetics model and getter capacity model, the server predicts the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier within a preset future time period. The adsorption kinetics model describes the adsorption rate of hydrogen on the getter. The getter capacity model characterizes the remaining adsorption capacity of the getter. An optimization problem is constructed with minimizing the amount of getter used as the optimization objective and the outlet hydrogen concentration not exceeding a set threshold as the constraint. Based on the model predictive control algorithm, the optimal getter dosage at the current moment is obtained. Based on the optimal getter dosage at the current moment and the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier within the preset future time period, the parameters of the adsorption kinetics model and / or the getter capacity model are calibrated and updated. Server 104 can feed back the calibrated and updated parameters to terminal 102. Furthermore, in some embodiments, the adaptive optimization method for the amount of getter used in aerospace helium purification can also be implemented independently by server 104 or terminal 102. For example, terminal 102 can directly perform adaptive optimization of the amount of getter used in aerospace helium purification based on multi-source data, or server 104 can obtain multi-source data from the data storage system and perform adaptive optimization of the amount of getter used in aerospace helium purification based on the multi-source data.
[0064] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, and tablets. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.
[0065] In one exemplary embodiment, such as Figure 2 As shown, an adaptive optimization method for the dosage of getter in aerospace helium purification is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the following steps are included.
[0066] S1: Acquire multi-source data from the purification system, including real-time sensor data and historical background data.
[0067] S2: The multi-source data is fused to obtain fused data.
[0068] S3: Based on the fused data, using a preset adsorption kinetics model and getter capacity model, predict the trend of hydrogen concentration change at the outlet of the third-stage chemical adsorption purifier within a preset future time period; the adsorption kinetics model is used to describe the adsorption rate of hydrogen on the getter; the getter capacity model is used to characterize the remaining adsorption capacity of the getter.
[0069] S4: Construct an optimization problem with the goal of minimizing the amount of getter and the constraint that the outlet hydrogen concentration does not exceed a set threshold. Based on the model predictive control algorithm, solve for the optimal amount of getter to be added at the current moment.
[0070] S5: Based on the optimal getter dosage at the current moment and the trend of hydrogen concentration change at the outlet of the third-stage chemical adsorption purifier in the future preset time period, calibrate and update the parameters of the adsorption kinetic model and / or the getter capacity model.
[0071] By implementing steps S1 to S5 above, this application integrates real-time sensor data and historical background data through a data fusion module to comprehensively perceive the system status. Based on the fused data, it predicts the future system status using an adsorption kinetics model and a getter capacity model. A model predictive control algorithm is employed to minimize getter dosage while ensuring the outlet hydrogen concentration, continuously calculating the optimal getter dosage. Furthermore, it achieves getter failure early warning and adaptive updating of model parameters. This application can dynamically optimize getter dosage, significantly reducing consumption and operating costs, and improving dehydrogenation stability and system intelligence.
[0072] As an optional implementation, in step S1, the real-time sensor data includes: the inlet hydrogen concentration, outlet hydrogen concentration, getter bed temperature distribution, system pressure, and helium flow rate of the third-stage chemical adsorption purifier; the historical background data includes: the initial adsorption capacity of the getter, the cumulative usage time, and batch information.
[0073] As an optional implementation, in step S3, the adsorption kinetic model is a function related to hydrogen concentration, temperature, and flow rate, constructed based on the Langmuir model, Freundlich model, or Toth model; the getter capacity model is a function related to usage time or cumulative treated gas volume, constructed based on a linear decay model or exponential decay model. The adsorption kinetic model is used to describe the adsorption rate of hydrogen on the getter; the getter capacity model is used to characterize the remaining adsorption capacity of the getter.
[0074] As an optional implementation, in step S4, the model predictive control algorithm adopts a rolling optimization strategy, specifically including: in each control cycle, predicting the system behavior in the future time domain based on the current system state, solving the optimization problem in an optimization time domain, and outputting the first control quantity in the solution sequence as the actual injection quantity.
[0075] As an optional implementation, in step S5, a genetic algorithm or particle swarm optimization algorithm is used to calibrate and update the parameters of the adsorption kinetics model and / or the getter capacity model.
[0076] As an optional implementation, the adaptive optimization method for the amount of getter used in aerospace helium purification further includes a failure early warning step.
[0077] Based on the real-time remaining adsorption capacity calculated by the getter capacity model, when the real-time remaining adsorption capacity is lower than a preset safety threshold, a getter replacement warning signal is generated.
[0078] like Figure 3 As shown, 1. Closed-loop control main cycle: The process begins with data fusion, then proceeds to model prediction and MPC (Model Predictive Control) optimization, and finally executes control commands. After completion, it enters the next cycle, forming a real-time closed loop of "perception-decision-execution".
[0079] 2. Parallel monitoring path (failure warning): In each cycle, the system checks the remaining capacity of the getter to provide early warning.
[0080] 3. Background adaptive path (model update): The system will periodically (e.g., daily or weekly) use accumulated historical data to calibrate the model parameters to ensure the long-term accuracy of predictions.
[0081] In one exemplary embodiment, such as Figure 4 As shown, an adaptive optimization system for the amount of getter used in aerospace helium purification is provided. The adaptive optimization system for the amount of getter used in aerospace helium purification is used to implement the adaptive optimization method for the amount of getter used in aerospace helium purification described above. The adaptive optimization system for the amount of getter used in aerospace helium purification includes the following modules.
[0082] Multi-source data acquisition module ( Figure 5 The SCADA system (i.e., the data acquisition and monitoring system) is used to acquire multi-source data from the purification system, including real-time sensor data and historical background data.
[0083] The data fusion module is communicatively connected to the multi-source data acquisition module and is used to fuse the multi-source data to obtain fused data.
[0084] The prediction module is used to predict the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier within a preset time period based on the fused data and using a preset adsorption kinetics model and getter capacity model. The adsorption kinetics model is used to describe the adsorption rate of hydrogen on the getter, and the getter capacity model is used to characterize the remaining adsorption capacity of the getter.
[0085] The optimization module is used to construct an optimization problem with the goal of minimizing the amount of getter and the constraint that the outlet hydrogen concentration does not exceed a set threshold. Based on the model predictive control algorithm, it solves the optimal amount of getter to be added at the current moment.
[0086] The calibration and update module is used to calibrate and update the parameters of the adsorption kinetics model and / or the getter capacity model based on the optimal getter dosage at the current moment and the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier in the future preset time period.
[0087] As an optional implementation, the multi-source data acquisition module includes the following devices.
[0088] An online hydrogen analyzer is used to measure the hydrogen concentration at the inlet and outlet of the third-stage chemisorption purifier.
[0089] An array of getter bed temperature sensors is arranged inside the adsorption tower of the third-stage chemisorption purifier to measure the temperature distribution of the getter bed.
[0090] A pressure sensor is installed inside the adsorption tower of the third-stage chemisorption purifier to measure the system pressure.
[0091] A flow sensor is installed inside the adsorption tower of the third-stage chemical adsorption purifier to measure the helium flow rate.
[0092] A getter dosing system is installed on the third-stage chemical adsorption purifier to receive control commands and add getter.
[0093] The historical background data acquisition submodule is used to obtain the initial adsorption capacity, cumulative usage time, and batch information of the getter.
[0094] As an optional implementation, the adaptive optimization system for getter usage in aerospace helium purification further includes: an early warning module, used to generate an early warning signal for getter replacement when the real-time remaining adsorption capacity is calculated based on the getter capacity model and the real-time remaining adsorption capacity is lower than a preset safety threshold.
[0095] The adaptive optimization system architecture for getter dosage in aerospace helium purification is as follows: Figure 5 As shown, Figure 5 The hardware infrastructure and data flow of this application are described, and it is shown how the intelligent optimization module can be integrated into an existing aerospace helium purification system.
[0096] The architecture is described below.
[0097] 1. Physical Layer (Aerospace Helium Purification System): This section demonstrates how helium sequentially passes through the first and second stages of purification before finally entering the core third-stage chemisorption purifier. This purifier is equipped with a precise getter dosing system and a temperature sensor array.
[0098] 2. Sensing layer: Various sensors (hydrogen analyzer, pressure / flow sensor, temperature array) collect process data in real time.
[0099] 3. Intelligent Core Layer (Data Fusion and Optimization Control Layer): This is the core of this application. It receives all data and forms a unified state perception through the data fusion module. Adsorption and capacity models are used for prediction, and the MPC optimizer calculates the optimal control command, ultimately driving the actuator (dosing system). The adaptive and early warning modules are responsible for the long-term reliable operation of the system.
[0100] The technical effects of this application are shown below.
[0101] 1) Reduced getter consumption: Compared with traditional methods, it can significantly reduce the amount of getter consumed and reduce operating costs (expected to be reduced by 10%-30%).
[0102] 2) Improve dehydrogenation efficiency: The getter dosage can be dynamically adjusted according to the system status to ensure that the purity of the outlet helium always meets the requirements.
[0103] 3) Extend the lifespan of the getter: By optimizing the adsorption process, the performance degradation of the getter is slowed down, thus extending its service life.
[0104] 4) Achieve automated control: Enables automated control and remote monitoring of the third-stage purifier, improving operational efficiency.
[0105] 5) Provide early warning of adsorbent failure: It can provide early warning based on the system status and replace the adsorbent in advance to prevent a decline in dehydrogenation efficiency.
[0106] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 6As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores multi-source data from the purification system. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements an adaptive optimization method for the amount of getter used in aerospace helium purification.
[0107] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0108] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method embodiments.
[0109] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use and processing of the relevant data are carried out in compliance with the relevant data protection laws and policies of the country where the location is located, and with the authorization granted by the owner of the corresponding device.
[0110] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
[0111] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchain. The processors involved in the embodiments provided in this application may be, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc.
[0112] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0113] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. An adaptive optimization method for the dosage of getter used in aerospace helium purification, characterized in that, The adaptive optimization method for the amount of getter used in aerospace helium purification includes: Acquire multi-source data from the purification system, including real-time sensor data and historical background data; The multi-source data is fused to obtain fused data; Based on the fused data, the trend of hydrogen concentration at the outlet of the third-stage chemical adsorption purifier is predicted within a preset time period using a pre-defined adsorption kinetics model and a getter capacity model. The adsorption kinetics model describes the adsorption rate of hydrogen on the getter, and the getter capacity model characterizes the remaining adsorption capacity of the getter. An optimization problem is constructed with the goal of minimizing the amount of getter used and the constraint that the outlet hydrogen concentration does not exceed a set threshold. Based on the model predictive control algorithm, the optimal amount of getter added at the current moment is obtained by solving the problem. Based on the optimal getter dosage at the current moment and the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier over a preset future period, the parameters of the adsorption kinetics model and / or the getter capacity model are calibrated and updated.
2. The adaptive optimization method for the dosage of getter for aerospace helium purification according to claim 1, characterized in that, The real-time sensor data includes: the inlet hydrogen concentration, outlet hydrogen concentration, getter bed temperature distribution, system pressure, and helium flow rate of the third-stage chemical adsorption purifier; the historical background data includes: the initial adsorption capacity of the getter, cumulative usage time, and batch information.
3. The adaptive optimization method for the dosage of getter for aerospace helium purification according to claim 1, characterized in that, The adsorption kinetic model is a function related to hydrogen concentration, temperature, and flow rate, constructed based on the Langmuir model, Freundlich model, or Toth model; the getter capacity model is a function related to usage time or cumulative treated gas volume, constructed based on the linear decay model or exponential decay model.
4. The adaptive optimization method for the dosage of getter for aerospace helium purification according to claim 1, characterized in that, The model predictive control algorithm adopts a rolling optimization strategy, which specifically includes: in each control cycle, predicting the system behavior in the future time domain based on the current system state, solving the optimization problem in an optimization time domain, and outputting the first control quantity in the solution sequence as the actual injection quantity.
5. The adaptive optimization method for the dosage of getter for aerospace helium purification according to claim 1, characterized in that, The parameters of the adsorption kinetics model and / or the getter capacity model are calibrated and updated using a genetic algorithm or a particle swarm optimization algorithm.
6. The adaptive optimization method for the dosage of getter for aerospace helium purification according to claim 1, characterized in that, The adaptive optimization method for the amount of getter used in aerospace helium purification also includes: Based on the real-time remaining adsorption capacity calculated by the getter capacity model, when the real-time remaining adsorption capacity is lower than a preset safety threshold, a getter replacement warning signal is generated.
7. An adaptive optimization system for getter dosage in aerospace helium purification, characterized in that, The adaptive optimization system for the amount of getter used in aerospace helium purification is used to implement the adaptive optimization method for the amount of getter used in aerospace helium purification as described in any one of claims 1-6. The adaptive optimization system for the amount of getter used in aerospace helium purification includes: A multi-source data acquisition module is used to acquire multi-source data from the purification system, including real-time sensor data and historical background data. The data fusion module is communicatively connected to the multi-source data acquisition module and is used to fuse the multi-source data to obtain fused data; The prediction module is used to predict the trend of hydrogen concentration at the outlet of the third-stage chemical adsorption purifier within a preset time period based on the fused data and using a preset adsorption kinetics model and getter capacity model. The adsorption kinetics model is used to describe the adsorption rate of hydrogen on the getter, and the getter capacity model is used to characterize the remaining adsorption capacity of the getter. The optimization module is used to construct an optimization problem with the goal of minimizing the amount of getter and the constraint that the outlet hydrogen concentration does not exceed a set threshold. Based on the model predictive control algorithm, it solves the optimal amount of getter at the current moment. The calibration and update module is used to calibrate and update the parameters of the adsorption kinetics model and / or the getter capacity model based on the optimal getter dosage at the current moment and the trend of hydrogen concentration change at the outlet of the third-stage chemisorption purifier in the future preset time period.
8. The adaptive optimization system for getter dosage in aerospace helium purification according to claim 7, characterized in that, The multi-source data acquisition module includes: An online hydrogen analyzer is used to measure the hydrogen concentration at the inlet and outlet of the third-stage chemisorption purifier. An array of getter bed temperature sensors is arranged inside the adsorption tower of the third-stage chemical adsorption purifier to measure the temperature distribution of the getter bed. A pressure sensor is installed inside the adsorption tower of the third-stage chemical adsorption purifier to measure the system pressure. A flow sensor is installed inside the adsorption tower of the third-stage chemical adsorption purifier to measure the helium flow rate. A getter dosing system is installed on the third-stage chemical adsorption purifier to receive control commands and add getter. The historical background data acquisition submodule is used to obtain the initial adsorption capacity, cumulative usage time, and batch information of the getter.
9. The adaptive optimization system for getter dosage in aerospace helium purification according to claim 7, characterized in that, The adaptive optimization system for getter dosage in aerospace helium purification also includes: The early warning module is used to generate an early warning signal for replacing the getter when the real-time remaining adsorption capacity is calculated based on the getter capacity model.
10. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the adaptive optimization method for the amount of getter used in aerospace helium purification as described in any one of claims 1-6.