Hydrogen purification method based on big data analysis and electronic equipment

Abstract

The invention is applicable to the technical field of equipment control, and provides a hydrogen purification method based on big data analysis and electronic equipment, and the hydrogen purification method comprises the following steps: acquiring real-time acquisition data of raw material gas in a hydrogen production cavity; the real-time acquisition data comprises first component information and flow data of the feed gas; performing data analysis on the real-time acquired data through a preset supervision model to obtain a valve control script corresponding to the hydrogen production cavity; controlling each valve to switch according to the valve switching time sequence so as to adsorb impurities in the raw material gas through an adsorber corresponding to each valve; and collecting the raw material gas adsorbed by all the valves to obtain target hydrogen with preset purity. By adopting the method, the adsorption effect of the adsorber corresponding to each valve can be improved, so that the purity of hydrogen in finished gas is improved, the accuracy of hydrogen production management can also be improved, repeated impurity adsorption is not needed, and the production efficiency of hydrogen is improved.

Description

Technical Field

[0001] The present application belongs to the field of equipment control technology, and in particular relates to a hydrogen purification method and electronic equipment based on big data analysis. Background Art

[0002] Hydrogen, as an important raw material in industrial applications, how to produce high-purity hydrogen has become the focus of people's attention. The existing hydrogen production technology is generally implemented by the Pressure Swing Adsorption (PSA) process. In the PSA process, a large number of valves need to be switched accurately and quickly to circulate the raw gas through multiple adsorbers to achieve the purpose of hydrogen purification. This requires the control system to be able to accurately switch the status of a large number of valves and ensure the reliability and stability of the switching process.

[0003] In the existing PSA process, the valve control technology generally involves workers adjusting the start-up status of each valve based on a preset timing relationship. However, in actual production, it is also necessary to adjust the control of components in the hydrogen production chamber according to changes in parameters such as the composition and flow rate of the raw gas. If the same script is used to control each valve, the accuracy of valve control may be reduced, thereby affecting the purity of the finished gas purified by hydrogen production, reducing production efficiency and product quality. Summary of the invention

[0004] The embodiments of the present application provide a hydrogen purification method and electronic equipment based on big data analysis, which can solve the control technology of valves in the existing PSA process. Generally, the staff adjusts the start-up status of each valve based on a preset timing relationship. However, in actual production, it is also necessary to change the composition, flow rate and other parameters of the raw gas, which will affect the control of the components in the hydrogen production chamber. If the same script is used to control each valve, the accuracy of valve control may be reduced, thereby affecting the purity of the finished gas purified by hydrogen production, reducing production efficiency and product quality.

[0005] In a first aspect, the present application embodiment provides a hydrogen purification method based on big data analysis, comprising:

[0006] Acquire real-time data of the raw gas in the hydrogen production chamber; the real-time data includes first component information and flow data of the raw gas; the hydrogen production chamber includes a plurality of valves;

[0007] The real-time collected data is analyzed by a preset supervisory model to obtain a valve control script corresponding to the hydrogen production chamber; the supervisory model is obtained by performing big data analysis on the historical data of the hydrogen production chamber; the valve control script is used to determine the valve switching timing of the hydrogen production chamber;

[0008] Controlling each of the valves to switch according to the valve switching timing, so as to adsorb impurities on the raw gas through the adsorber corresponding to each valve;

[0009] The raw gas obtained after adsorption by all the valves is collected to obtain target hydrogen with a preset purity.

[0010] In a possible implementation of the first aspect, controlling each valve to switch the valve according to the valve switching timing so as to adsorb impurities on the raw gas through an adsorber corresponding to each valve includes:

[0011] For the adsorber of the Nth valve, the adsorption calibration coefficient is determined according to the second component information of the raw gas when it flows through the N-1th valve and the first adsorption parameter corresponding to the N-1th valve; N is a positive integer greater than 1 and not greater than the total number of valves in the hydrogen production chamber; the adsorption calibration coefficient is:

[0012]

[0013] Among them, Adsob adj (N) is the adsorption calibration coefficient; Adsob(N-1) is the first adsorption parameter; Compent i [N-1] is the concentration value of the i-th gas in the second component information; BaseCom i is the expected concentration value of the i-th gas when the raw gas flows through the N-1-th valve; M is the total number of gases in the second component information; P is the total number of valves; Adsob(j) is the adsorption parameter corresponding to the j-th valve;

[0014] Performing parameter calibration on the expected adsorption parameter of the Nth valve according to the adsorption calibration coefficient to obtain a second adsorption parameter of the Nth valve;

[0015] When the raw gas flows through the Nth valve, the adsorber is controlled to perform an adsorption operation on the raw gas according to the second adsorption parameter.

[0016] In a possible implementation manner of the first aspect, for the adsorber of the Nth valve, determining the adsorption calibration coefficient according to the second component information of the raw gas when it flows through the N-1th valve and the first adsorption parameter corresponding to the N-1th valve includes:

[0017] According to the number of component detection modules deployed in the adsorption area corresponding to the N-1th valve, create a plurality of sub-threads corresponding to the number of modules; each sub-thread corresponds to one component detection module;

[0018] The original collected data corresponding to each component detection module is obtained through each sub-thread respectively, and the corresponding original collected data is processed in parallel by multiple sub-threads to obtain the second component information.

[0019] In a possible implementation manner of the first aspect, before determining the adsorption calibration coefficient for the adsorber of the Nth valve according to the second component information of the raw gas when it flows through the N-1th valve and the first adsorption parameter corresponding to the N-1th valve, the method further includes:

[0020] When the raw gas flows through the N-1th valve, the operating state of the adsorber of the Nth valve is set according to the expected adsorption parameter corresponding to the Nth valve; the expected adsorption parameter includes multiple dimensional indicators; the dimensional indicators include: gas pressure value, adsorption efficiency and regeneration efficiency;

[0021] Correspondingly, when the raw gas flows through the Nth valve, controlling the adsorber to perform an adsorption operation on the raw gas according to the second adsorption parameter includes:

[0022] Calculate the deviation value corresponding to each dimensional index between the expected adsorption parameter and the second adsorption parameter;

[0023] Determine the adjustment order corresponding to each of the dimensional indicators based on the order of the deviation values ​​corresponding to each of the dimensional indicators from large to small;

[0024] Based on the adjustment order, the operating state of the adsorber corresponding to each of the dimensional indicators is adjusted in sequence.

[0025] In a possible implementation manner of the first aspect, before the real-time collected data is analyzed by a preset supervision model to obtain a valve control script corresponding to the hydrogen production chamber, the method further includes:

[0026] Acquire test operation data corresponding to each valve of the hydrogen production chamber; the test operation data includes the state switching time and sealing coefficient of the valve in the test result before the start of hydrogen production;

[0027] Constructing a first switching timing curve and a second sealing timing curve corresponding to each valve through the historical operation data corresponding to the hydrogen production chamber;

[0028] Determine a first slope deviation between the first switching timing curve and the first coordinate according to the first coordinate corresponding to the first coordinate system of the state switching duration corresponding to the first switching timing curve; the first slope deviation is used to adjust the timing factor in the supervision model;

[0029] Determine a second slope deviation between the second sealing timing curve and the second coordinate according to a second coordinate of the sealing coefficient in a second coordinate system corresponding to the second sealing timing curve; the second slope deviation is used to adjust the valve thrust factor in the supervision model;

[0030] The supervision model is calibrated according to the first slope deviation and the second slope deviation corresponding to all valves.

[0031] In a possible implementation manner of the first aspect, before calibrating the supervision model according to the first slope deviation and the second slope deviation, the method further includes:

[0032] Calculating an aging coefficient corresponding to each of the valves according to the second slope deviation and the first slope deviation;

[0033] If any of the aging coefficients is greater than a preset aging threshold, first abnormal information corresponding to the valve is generated.

[0034] In a possible implementation of the first aspect, after collecting the raw gas obtained after adsorption by all the valves to obtain the target hydrogen with a preset purity, the method further includes:

[0035] Collect and output the air flow rate corresponding to the raw gas adsorbed by all the valves;

[0036] If the air flow rate is greater than a preset flow rate threshold, second abnormal information of valve leakage is generated.

[0037] In a second aspect, an embodiment of the present application provides a hydrogen purification device based on big data analysis, the device comprising:

[0038] A real-time acquisition unit is used to obtain real-time acquisition data of the raw gas in the hydrogen production chamber; the real-time acquisition data includes first component information and flow data of the raw gas; the hydrogen production chamber includes a plurality of valves;

[0039] A valve control script generating unit is used to perform data analysis on the real-time collected data through a preset supervisory model to obtain a valve control script corresponding to the hydrogen production chamber; the supervisory model is obtained by performing big data analysis on the historical data of the hydrogen production chamber; the valve control script is used to determine the valve switching timing of the hydrogen production chamber;

[0040] A valve control unit, used for controlling each of the valves to switch the valves according to the valve switching sequence, so as to adsorb impurities on the raw gas through the adsorber corresponding to each of the valves;

[0041] The purification unit is used to collect the raw gas obtained after adsorption by all the valves to obtain the target hydrogen with a preset purity.

[0042] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method as described in any one of the first aspects above when executing the computer program.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0044] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a drone, enables the drone to execute any of the methods described in the first aspect above.

[0045] Compared with the prior art, the embodiments of the present application have the following beneficial effects: by collecting real-time data of the raw gas during the process of hydrogen production and purification, and importing the real-time data into a supervised learning algorithm, a valve control script is generated so that the valve control script is consistent with the actual situation in the cavity, thereby improving the accuracy of valve control and the degree of matching with the hydrogen production scenario, and controlling each valve to switch according to the above-mentioned valve control script, and adsorbing impurities on the raw gas through the corresponding adsorber to improve the purity of hydrogen in the raw gas, and after the adsorption operation of the adsorbers corresponding to all valves, the corresponding raw gas is output as a finished gas to obtain the target hydrogen with a preset purity, so as to achieve the purpose of hydrogen purification. Compared with the existing hydrogen production technology, in the embodiment of the present application, the control of the valve is not controlled by a fixed timing logic. Instead, when hydrogen is produced and purified, the real-time collected data in the current cavity is imported into the supervision model to generate a valve control script that matches it. This can improve the matching degree between the valve control script and the actual scene, and then improve the accuracy of valve control, and then improve the adsorption effect of each valve corresponding to the adsorber, so as to improve the purity of hydrogen in the finished gas, and also improve the accuracy of hydrogen production management. There is no need for repeated impurity adsorption, thereby improving the production efficiency of hydrogen. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 It is a structural schematic diagram of a hydrogen production and purification system provided in one embodiment of the present application;

[0048] Figure 2 It is a schematic diagram of an implementation method of a hydrogen purification method based on big data analysis provided in an embodiment of the present application;

[0049] Figure 3 This is a specific implementation flow chart of S203 in a hydrogen purification method based on big data analysis provided in the second embodiment of the present application;

[0050] Figure 4 This is a specific implementation flow chart of S2033 in a hydrogen purification method based on big data analysis provided in the third embodiment of the present application;

[0051] Figure 5 This is a specific implementation flow chart of a hydrogen purification method based on big data analysis before S201 provided in the fourth embodiment of the present application;

[0052] Figure 6 This is a specific implementation flow chart of a hydrogen purification method based on big data analysis before S505 provided in the fifth embodiment of the present application;

[0053] Figure 7 This is a specific implementation flow chart of a hydrogen purification method based on big data analysis after S201 provided in the sixth embodiment of the present application;

[0054] Figure 8 It is a structural schematic diagram of a hydrogen purification device based on big data analysis provided in an embodiment of the present application;

[0055] Fig. 9 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0057] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0058] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0059] The hydrogen purification method based on big data analysis provided in the embodiment of the present application can be applied to the control equipment of the hydrogen production and purification system. For example, Figure 1 The structure diagram of the hydrogen production and purification system provided in one embodiment of the present application is shown. Figure 1 The hydrogen production and purification system includes a control device 11 and a hydrogen production chamber 12 for hydrogen purification. The hydrogen production chamber 12 includes a raw gas storage bin, an adsorption bin and a finished gas storage bin. The raw gas storage bin is used to store raw gas with low hydrogen purity. The number of the adsorption bins can be set according to actual conditions. For example, the hydrogen production chamber 12 provided in this embodiment includes 3 adsorption bins, or other numbers; the finished gas storage bin is used to store purified high-purity hydrogen, which can be output as finished gas. The gas flow can be controlled by a type of valve between each bin in the hydrogen production chamber 12 to achieve the purpose of pressure swing purification. The adsorption bin can also be provided with two types of valves to achieve pressure swing adsorption in the adsorption bin, which improves the flexibility of pressure swing adsorption and can also improve the utilization efficiency of the adsorption bin. Since pressure swing adsorption relies on the coordinated operation of valves between different bins to achieve the purpose of impurity adsorption through the corresponding adsorber in the adsorption bin, the control device 11 needs to accurately control the switch state of each valve according to the valve timing.

[0060] The control device 11 can establish a communication connection with the relevant components in the hydrogen production chamber 12. For example, the control device 11 can establish a communication connection with each valve on the hydrogen production chamber 12 to achieve the purpose of remotely controlling each valve; the control device 11 can also establish a communication connection with the adsorber in the adsorption bin, so as to control the adsorber to adsorb impurities on the gas with preset operating parameters. After the raw gas passes through the adsorption operation of the adsorbers corresponding to all valves, the raw gas obtained after the adsorption operation can be stored in the finished gas storage bin, that is, the target hydrogen with a preset purity is obtained.

[0061] See also Figure 2 , Figure 2A schematic diagram of a hydrogen purification method based on big data analysis provided in an embodiment of the present application is shown. The hydrogen purification method based on big data analysis is applied to the above-mentioned control device 11, that is, the execution subject of the embodiment of the present application can be the above-mentioned control device 11, wherein the control device 11 is specifically an electronic device, and the electronic device can be a computer, a laptop, a server, a smart phone and other electronic devices. For the convenience of description, the subsequent execution subject is explained by taking an electronic device as an example. Specifically, the method includes the following steps:

[0062] In S201, real-time collected data of the raw gas in the hydrogen production chamber is obtained; the real-time collected data includes first component information and flow data of the raw gas; the hydrogen production chamber includes a plurality of valves.

[0063] In this embodiment, the electronic device can obtain the above-mentioned real-time data through the data acquisition module in the hydrogen production chamber. The above-mentioned data acquisition module can be set in the raw gas storage bin or in any adsorption bin. The number and location of the specific data acquisition module can be set according to actual conditions. Optionally, the above-mentioned data acquisition module can be set on the valve on the pipeline between the above-mentioned bins, such as Figure 1 On a type of valve.

[0064] In some possible implementations, when the data acquisition module is set in the raw gas storage bin, the triggering timing of the above S201 is at the exact stage when the raw gas is ready for impurity adsorption, that is, before the impurity adsorption is performed, and the corresponding valve control script can be determined through this embodiment.

[0065] In some possible implementations, when the data acquisition module is disposed on an adsorption bin or on a pipeline between adsorption bins, the triggering timing of S201 is during the execution stage of impurity adsorption of the raw gas, that is, during the process of impurity adsorption, the original valve control script can be calibrated in real time through this embodiment, thereby improving the accuracy of the valve control script during operation.

[0066] In some possible implementations, the electronic device can collect the composition data of the raw gas at a preset time interval (such as every 1 minute) through a gas chromatograph, and use a vortex flowmeter to measure the flow of the raw gas in real time. After the collected data is pre-processed by denoising and normalization, the key features that affect the valve switching, such as hydrogen concentration, methane concentration and flow, are extracted to construct the above-mentioned real-time acquisition data set. Using the real-time acquisition data set, a support vector regression algorithm is used to establish a nonlinear mapping relationship model between the valve switching timing and duration and the raw gas parameters, that is, the subsequent supervision model. The model is deployed in the hydrogen production system, and the raw gas parameter data is received in real time. When it is detected that the hydrogen concentration changes exceeding the concentration threshold or the flow changes exceeding the preset amplitude threshold, the model calculation is triggered, so that the adjusted valve control script can be immediately obtained at the preset response time. The valve control script includes the valve timing and the duration of the valve state. According to the model calculation results, the control system immediately executes the valve switching operation, adjusts the switching timing to the optimal value of the model output, and the duration is also adjusted accordingly to adapt to the changes in the raw gas composition and flow.

[0067] In S202, the real-time collected data is analyzed by a preset supervisory model to obtain a valve control script corresponding to the hydrogen production chamber; the supervisory model is obtained by performing big data analysis on historical data of the hydrogen production chamber; the valve control script is used to determine the valve switching timing of the hydrogen production chamber.

[0068] In this embodiment, after the electronic device acquires the above-mentioned real-time acquisition data, it can import it into a preset supervision model, and the supervision model can automatically generate a valve control script that matches the current environment. Since the above-mentioned supervision model is generated by collecting a large amount of historical operation data and performing big data analysis on the historical operation data, it can achieve effective guidance on valve control and improve the accuracy of valve control. It should be noted that after each raw gas purification operation is completed, the electronic device can add the acquisition data acquired in this acquisition to the training set, and then the above-mentioned supervision model can be calibrated through the training set to improve the accuracy of the supervision model.

[0069] In some possible implementations, by preprocessing and feature extraction of real-time collected data, a data set that can be used for modeling is obtained. Based on the obtained data set, a supervised model, such as a support vector machine or a neural network, is used to establish a supervised optimization model for valve switching timing and duration. The electronic device deploys the established optimization model to the hydrogen production system, receives the collected data of the raw gas parameters in real time, and determines whether the raw gas parameters have changed. If it is detected that the raw gas parameters have changed, the changed parameters are input into the optimization model, and the adjusted valve control script is obtained through model calculation. According to the output results of the optimization model, the electronic device can adjust the valve switching timing and duration in time to adapt to the changing process conditions. Multiple valve switching plans are set in the hydrogen production chamber, and the optimal control plan under the current working conditions is determined by the pattern recognition algorithm according to the changing trends of parameters such as raw gas composition and flow rate. According to the judgment results, the control system switches to the optimal control plan in advance, reduces the transition time during the valve switching process, and improves the response speed and stability of the system. The key parameters such as temperature and pressure of the adsorber are monitored and analyzed in real time, and the reinforcement learning algorithm is used to dynamically optimize the adsorption and regeneration process through continuous trial and error and feedback. Based on the optimization results of the reinforcement learning algorithm, the control system adjusts the valve switching timing and duration in real time, improving the hydrogen purification efficiency and product quality by dynamically adapting to changes in process conditions.

[0070] In S203, each valve is controlled to switch according to the valve switching sequence, so that the raw gas is adsorbed with impurities by the adsorber corresponding to each valve.

[0071] In this embodiment, after determining the valve control script, the electronic device can control the switch state of each valve and the duration corresponding to each switch state based on the valve switching timing in the valve control script, and after the raw gas flows into the adsorption area corresponding to the valve, the corresponding adsorber can be turned on to adsorb impurities in the raw gas. It should be noted that if the data acquisition module is set in the adsorption bin, the above-mentioned valve control script can be calibrated, for example, the above-mentioned valve control timing can be calibrated, so as to improve the accuracy of the valve control script.

[0072] In a possible implementation, the electronic device can preset a variety of valve switching modes under different working conditions (the mode includes the step length of the control valve and the power value of the corresponding drive module), that is, different valves can correspond to one or more valve switching modes. The electronic device can use the K-means clustering algorithm to match the valve switching mode under the above-mentioned different working conditions according to the change trend of the raw gas parameters to obtain the corresponding valve switching mode, and switch to the valve switching mode in advance, such as controlling the valve drive module to operate at a preset power, or adjusting the step length, etc., to reduce the transition time of the valve switching, so that the system can respond quickly when facing changes in working conditions. For the operating parameters of the adsorber, the operating data can be collected based on the preset collection cycle, and the Q-learning reinforcement learning algorithm can be used to continuously try to adjust the valve switching timing and duration by setting the target range of temperature and pressure, and learn the optimal control strategy based on the feedback information of the adsorption effect. The learned strategy is used to guide the control system to adjust the valve operation in real time, while ensuring the adsorption effect, improving the purification efficiency and quality of hydrogen.

[0073] In S204, the raw gas obtained after adsorption by all the valves is collected to obtain target hydrogen with a preset purity.

[0074] In this embodiment, after the electronic device performs all adsorption operations, that is, after all adsorption bins and the adsorbers in the corresponding adsorption areas have performed adsorption operations on the impurities in the raw gas, it can obtain target hydrogen of a preset purity and store the target hydrogen in a finished gas storage bin. Subsequently, the hydrogen in the finished gas storage bin can be packaged as a product to obtain relevant high-purity hydrogen.

[0075] From the above, it can be seen that the embodiment of the present application provides a hydrogen purification method based on big data analysis, which collects real-time data of the raw gas during the hydrogen production and purification process, and imports the real-time data into the supervised learning algorithm to generate a valve control script, so that the valve control script is consistent with the actual situation in the cavity, thereby improving the accuracy of valve control and the matching degree with the hydrogen production scenario, and controls each valve to switch according to the above-mentioned valve control script, and adsorbs impurities on the raw gas through the corresponding adsorber to improve the purity of hydrogen in the raw gas, and after the adsorption operation of the adsorbers corresponding to all valves, the corresponding raw gas is output as a finished gas to obtain the target hydrogen with a preset purity, so as to achieve the purpose of hydrogen purification. Compared with the existing hydrogen production technology, in the embodiment of the present application, the control of the valve is not controlled by a fixed timing logic. Instead, when hydrogen is produced and purified, the real-time collected data in the current cavity is imported into the supervision model to generate a valve control script that matches it. This can improve the matching degree between the valve control script and the actual scene, and then improve the accuracy of valve control, and then improve the adsorption effect of each valve corresponding to the adsorber, so as to improve the purity of hydrogen in the finished gas, and also improve the accuracy of hydrogen production management. There is no need for repeated impurity adsorption, thereby improving the production efficiency of hydrogen.

[0076] Figure 3 The specific implementation flow chart of S203 in a hydrogen purification method based on big data analysis provided in the second embodiment of the present application is shown. Figure 3 As shown, relative to Figure 2 In the embodiment, a hydrogen purification method based on big data analysis provided in the embodiment of the present application is provided in S203, including S2031 to S2033, which are specifically described as follows:

[0077] In S2031, for the adsorber of the Nth valve, an adsorption calibration coefficient is determined according to the second component information of the raw gas when it flows through the N-1th valve and the first adsorption parameter corresponding to the N-1th valve; N is a positive integer greater than 1 and not greater than the total number of valves in the hydrogen production chamber; the adsorption calibration coefficient is:

[0078]

[0079] Among them, Adsob adj (N) is the adsorption calibration coefficient; Adsob(N-1) is the first adsorption parameter; Compent i [N-1] is the concentration value of the i-th gas in the second component information; BaseCom iis the expected concentration value of the i-th gas when the raw gas flows through the N-1-th valve; M is the total number of gases in the second component information; P is the total number of valves; Adsob(j) is the adsorption parameter corresponding to the j-th valve.

[0080] In this embodiment, when the raw gas passes through the valve of the previous adsorption bin, the electronic device can collect the second component information corresponding to the raw gas when passing through the adsorption bin, so as to determine whether there is a deviation between the current gas composition and the expected gas composition, and thus determine whether the current adsorption efficiency meets the requirements. The electronic device can calibrate the operating parameters of the adsorber in the adsorption area corresponding to the subsequent valve according to the component information collected by the valve of the previous adsorption sequence.

[0081] In this embodiment, the electronic device can calculate the adsorption deviation of different gas components respectively, that is, calculate the deviation between the concentration value of a certain gas in the second component information and the expected concentration value. The gas can be an impurity gas or hydrogen. According to the concentration value deviation corresponding to each gas, the corresponding adsorption deviation can be obtained, and the corresponding adsorption calibration coefficient can be determined according to the adsorption deviation. Among them, the above-mentioned adsorption calibration coefficient is also related to the adsorption parameter (i.e., the first adsorption parameter) corresponding to the adsorber of the previous adsorption order. If the value of the adsorption parameter is larger, its ability to calibrate abnormalities is stronger, so the subsequent adsorption calibration coefficient has a smaller value; conversely, if the value of the adsorption parameter is smaller, the ability to calibrate abnormalities is weaker, and the corresponding adsorption calibration coefficient has a larger value.

[0082] Further, as another embodiment of the present application, the above S2031 may include the following steps in the process of collecting the second component information:

[0083] In S2031.1, according to the number of component detection modules deployed in the adsorption area corresponding to the N-1th valve, a plurality of sub-threads corresponding to the number of modules are created; each sub-thread corresponds to one component detection module.

[0084] In this embodiment, when there are many types of gas impurities contained in the raw gas, one or more component detection modules can be configured according to the types of impurities. Different component detection modules can be used to collect concentration values, distribution density values, etc. of one or more impurities. The electronic device can configure a plurality of sub-threads corresponding to the number of modules corresponding to the above-mentioned component detection modules, and each thread is used to receive detection data fed back by a component detection module, that is, the original data for generating the second component information.

[0085] In S2031.2, the original collected data corresponding to each of the component detection modules is obtained through each sub-thread respectively, and the corresponding original collected data are processed in parallel by multiple sub-threads to obtain the second component information.

[0086] In this embodiment, the electronic device may be provided with multiple interfaces, and different interfaces are used to receive raw data sent by different component detection modules, wherein the raw data may be processed by corresponding sub-threads. Due to the parallel operation of multiple sub-threads, the raw data fed back by multiple component detection modules may be processed at the same time, thereby improving the efficiency of raw data processing, and then improving the efficiency of generating the second component information.

[0087] In the embodiment of the present application, since there are a large number of valves in the PSA and there are certain time limits for the coordination between the valves, the construction of the operating environment of the adsorber also requires a certain running time. In order to improve the management accuracy while achieving precise control of the adsorber, it is necessary to minimize the time required for related calculations. Therefore, by processing the original data in parallel through multiple threads, the time required for calculation can be reduced, thereby improving the accuracy of the adsorber control.

[0088] In S2032, the expected adsorption parameter of the Nth valve is calibrated according to the adsorption calibration coefficient to obtain a second adsorption parameter of the Nth valve.

[0089] In S2033, when the raw gas flows through the Nth valve, the adsorber is controlled to perform an adsorption operation on the raw gas according to the second adsorption parameter.

[0090] In this embodiment, after calculating the adsorption calibration coefficient for the adsorber, the electronic device can calibrate the desired operating parameters of the adsorber according to the calibrated adsorption coefficient, wherein the desired operating parameters of the adsorber may include characteristic values ​​of multiple dimensions, such as adsorption temperature, adsorption ambient pressure, and adsorbent dosage, etc. The electronic device can calculate the calibrated adsorption coefficients corresponding to different dimensions, and adjust the corresponding characteristic values ​​according to the calibrated adsorption coefficients of the corresponding dimensions, so as to obtain the corresponding second adsorption parameters after adjusting the characteristic values ​​of all dimensions, and when the raw gas flows through the adsorption area corresponding to the valve, the adsorber is controlled to operate in the state of the second adsorption parameter to adsorb impurities in the raw gas.

[0091] In one possible implementation, the electronic device may be provided with a calibration threshold. If it is detected that the above-mentioned adsorption calibration coefficient is less than or equal to the above-mentioned calibration threshold, it is identified as not requiring adjustment. Since the operating parameter calibration of the adsorber will affect the operating parameters of the adsorber, it is necessary to change the already stable adsorption environment, which may reduce the actual adsorption effect due to environmental changes. In order to avoid the above situation, in the scenario where the adsorption calibration coefficient is less than or equal to the above-mentioned calibration threshold, it is not necessary to adjust the operating parameters of the adsorber, that is, maintain the original adsorption parameters for operation; conversely, if it is detected that the adsorption calibration coefficient is greater than the above-mentioned calibration threshold, the calibrated second adsorption parameters may be determined, and the operating parameters of the adsorber may be set based on the calibrated second adsorption parameters.

[0092] In an embodiment of the present application, by collecting the corresponding second component information when the raw gas flows through the valve of the previous adsorption order, and calibrating the parameters of the adsorber of the next adsorption order according to the second component information, the accuracy of the operating parameters of the adsorber can be improved, thereby improving the purity of the target hydrogen.

[0093] Figure 4 The specific implementation flow chart of S2033 in a hydrogen purification method based on big data analysis provided in the third embodiment of the present application is shown. Figure 4 As shown, relative to Figure 3 In the embodiment, a hydrogen purification method based on big data analysis provided in the embodiment of the present application may include S401 before S2033, and the above S2033 may include S402 to S404, which are specifically described as follows:

[0094] Before determining the adsorption calibration coefficient for the adsorber of the Nth valve according to the second component information of the raw gas when it flows through the N-1th valve and the first adsorption parameter corresponding to the N-1th valve, the method further includes:

[0095] In S401, when the raw gas flows through the N-1th valve, the operating state of the adsorber of the Nth valve is set according to the expected adsorption parameters corresponding to the Nth valve; the expected adsorption parameters include multiple dimensional indicators; the dimensional indicators include: gas pressure value, adsorption efficiency and regeneration efficiency.

[0096] In this embodiment, it takes a certain amount of time for the adsorber to construct the corresponding adsorption environment in the adsorption area, such as raising the temperature of the adsorption area to a preset temperature value, or adjusting the air pressure of the adsorption area to a preset air pressure value, etc. In order to improve the timeliness and accuracy of the environment construction, after determining the valve control script, the environment of the adsorber in the adsorption area corresponding to each valve can be constructed according to the expected adsorption parameters recorded in the valve control script, that is, the operating state of the adsorber of each valve is set based on the expected adsorption parameters, so that a stable adsorption environment can be constructed in advance, such as setting the temperature value in the adsorption area to a preset value, so that the adsorbent in the adsorber can adsorb impurities at a preset adsorption efficiency, and the dosage of the adsorbent in the adsorber can be adjusted to adjust the regeneration efficiency of the overall adsorbent.

[0097] Correspondingly, when the raw gas flows through the Nth valve, controlling the adsorber to perform an adsorption operation on the raw gas according to the second adsorption parameter includes:

[0098] In S402, the deviation values ​​corresponding to the expected adsorption parameters and the second adsorption parameters in each dimensional index are calculated.

[0099] In S403, based on the order of the deviation values ​​corresponding to the dimensional indicators from large to small, the adjustment order corresponding to the dimensional indicators is determined.

[0100] In S404, based on the adjustment order, the operating state of the adsorber corresponding to each of the dimensional indicators is adjusted in sequence.

[0101] In this embodiment, the electronic device can adjust the expected adsorption parameters through the adsorption calibration coefficient, and the characteristics of different dimensions can be adjusted through different adsorption calibration coefficients. Therefore, the deviation values ​​corresponding to different dimensional indicators are different. The electronic device can calculate the deviation values ​​of the dimensional indicators corresponding to different dimensions, that is, calculate the difference between the dimensional indicator in the expected adsorption parameter and the dimensional indicator in the second adsorption parameter.

[0102] In this embodiment, since it takes a certain amount of time to construct the adsorption environment, the larger the above-mentioned deviation value is, the longer the corresponding time required is. Therefore, the electronic device can determine the adjustment order corresponding to each dimensional indicator according to the order of the deviation values ​​corresponding to different dimensional indicators from large to small. That is, the larger the deviation value of the dimensional indicator, the earlier the corresponding adjustment order is, and vice versa, the smaller the deviation value of the dimensional indicator, the later the corresponding adjustment order is; and according to the corresponding adjustment order, the operating parameters of the adsorber corresponding to each dimensional indicator are adjusted.

[0103] In an embodiment of the present application, before the raw gas enters the adsorption area of ​​the valve, the adsorption environment can be constructed first, and the adjustment order can be determined according to the deviation values ​​corresponding to the indicators of different dimensions. This can increase the probability that the adsorption environment is consistent with the environment corresponding to the second adsorption parameter when the raw gas enters the adsorption area, thereby improving the accuracy of control.

[0104] Figure 5 The specific implementation flow chart of a hydrogen purification method based on big data analysis provided in the fourth embodiment of the present application before S201 is shown. Figure 5 , relative to Figure 2-4 In any of the embodiments, the hydrogen purification method based on big data analysis provided in this embodiment further includes, before S201, S501 to S505, which are described in detail as follows:

[0105] In S501, the test operation data corresponding to each valve of the hydrogen production chamber is obtained; the test operation data includes the state switching time and the sealing coefficient of the valve in the test result before the start of hydrogen production.

[0106] In this embodiment, historical test operation data of each valve in the hydrogen production chamber is obtained, and the data includes parameters such as valve state switching time and sealing coefficient; based on the obtained historical test operation data, a valve performance evaluation model is established to evaluate the valve state switching time and sealing performance; before hydrogen production starts, the real-time test operation data of each valve is obtained, and the real-time data is input into the valve performance evaluation model for evaluation; the evaluation result of the valve performance evaluation model is compared with the preset threshold value to determine whether the switching time and sealing performance of each valve meet the standard; if the evaluation result shows that the valve switching time or sealing performance does not meet the standard, an early warning message is issued to prompt relevant personnel to inspect or replace the valve; based on the valve performance evaluation result, the hydrogen production process parameters are dynamically adjusted, such as adjusting the reaction temperature, pressure, etc., to adapt to the actual performance of the valve; the valve test evaluation results and the hydrogen production process parameter adjustment are recorded in the system log for subsequent analysis and optimization of the hydrogen production process.

[0107] In S502, a first switching timing curve and a second sealing timing curve corresponding to each valve are constructed according to the historical operation data corresponding to the hydrogen production chamber.

[0108] In this embodiment, historical operation data of the hydrogen production chamber is obtained, including changes in the switching status and sealing status of each valve over time; the acquired historical operation data is preprocessed to remove abnormal values ​​and invalid data to obtain valid valve status data; based on the preprocessed valve status data, the switching time point and sealing time point of each valve are extracted to form a time series; wherein the above-mentioned time series includes a first time series obtained based on the switching time point, and a second time series corresponding to the sealing coefficient, the above-mentioned first switching timing curve is constructed based on the first time series, and the above-mentioned second sealing timing curve is obtained according to the second time series.

[0109] In S503, a first slope deviation between the first switching timing curve and the first coordinate is determined according to the first coordinate corresponding to the first coordinate system corresponding to the state switching duration in the first switching timing curve; the first slope deviation is used to adjust the timing factor in the supervision model.

[0110] In this embodiment, the state switching duration is obtained by collecting data during the trial operation phase before hydrogen production, that is, it is the most capable of reflecting the current valve response speed of the hydrogen production system, and the line between the first coordinate and the most recently collected coordinate point in the first timing curve is connected as the slope corresponding to the first coordinate. Then, the first slope deviation is calculated based on the slope of the most recently collected coordinate point in the first timing curve and the slope corresponding to the first coordinate. The first slope deviation can be used to determine the duration required to control the valve to improve the accuracy of the valve switching timing.

[0111] In S504, a second slope deviation between the second sealing timing curve and the second coordinate is determined according to the second coordinate of the sealing coefficient in the second coordinate system corresponding to the second sealing timing curve; the second slope deviation is used to adjust the valve thrust factor in the supervision model.

[0112] In this embodiment, the valve may age during use, so its corresponding thrust may vary depending on the length of use, resulting in deviations in the actual moving position when the valve is pushed with the same force, thereby affecting the sealing of the valve. Therefore, the thrust of the above-mentioned valve can be calibrated by calculating the second slope deviation, thereby improving the accuracy of valve control.

[0113] In this embodiment, the sealing coefficient is obtained by collecting data in the trial operation phase before hydrogen production, that is, the expected sealing coefficient of the current valve of the hydrogen production system when the corresponding thrust is controlled is the best, and the line between the second coordinate and the coordinate point collected most recently in the second sealing timing curve is connected as the slope corresponding to the second coordinate. Then, the second slope deviation is calculated based on the slope of the coordinate point collected most recently in the second timing curve and the slope corresponding to the second coordinate.

[0114] In S505, the supervision model is calibrated according to the first slope deviation and the second slope deviation corresponding to all valves.

[0115] In this embodiment, the electronic device can calibrate the supervision model according to the above two slope deviations to improve the accuracy and timeliness of the model.

[0116] Figure 6 The specific implementation flow chart of a hydrogen purification method based on big data analysis provided in the fifth embodiment of the present application before S505 is shown. Figure 6 , relative to Figure 5 In the embodiment, a hydrogen purification method based on big data analysis provided in this embodiment further includes, before S505: S601 to S602, which are described in detail as follows:

[0117] In S601, the aging coefficient corresponding to each of the valves is calculated according to the second slope deviation and the first slope deviation.

[0118] In S602, if any of the aging coefficients is greater than a preset aging threshold, first abnormal information corresponding to the valve is generated.

[0119] In this embodiment, before performing the hydrogen production and purification operation, a pre-test process is executed, and the corresponding state switching duration and the corresponding sealing coefficient during valve control are collected, and the slope deviation between the timing curve constructed with historical data is calculated based on the above two coefficients. The slope deviation can be used to determine whether the valve operation is aged, and then the above aging coefficient can be calculated. The larger the values ​​of the above two slope deviations are, the larger the corresponding aging coefficient is. The above aging coefficient can be calculated based on a preset conversion function.

[0120] In this embodiment, if it is detected that the aging coefficient corresponding to any valve in the hydrogen production chamber is greater than the preset aging threshold, it means that the valve needs to be maintained, and then the first abnormal information of the valve corresponding to the aging coefficient greater than the aging threshold can be generated.

[0121] In the embodiment of the present application, the electronic device can monitor the aging degree of the valve through the above-mentioned slope deviation, so as to timely identify the valves that are aged and generate corresponding abnormal information, thereby improving the timeliness of aging detection of the hydrogen production system.

[0122] Figure 7 The specific implementation flow chart of a hydrogen purification method based on big data analysis provided in the sixth embodiment of the present application after S201 is shown. Figure 8 , relative to Figure 2-6 In any of the embodiments described above, the hydrogen purification method based on big data analysis provided in this embodiment further includes, after S201, S701 to S702, which are described in detail as follows:

[0123] In S701, the air flow rate corresponding to the raw gas adsorbed by all the valves is collected and output.

[0124] In S702, if the air flow rate is greater than the preset flow rate threshold, the second abnormal information of valve leakage is generated. In this embodiment, when the electronic device delivers the raw gas to the adsorption area corresponding to each valve, it can collect the air flow rate corresponding to the raw gas through the flow rate detection module on the valve. Since the deviation between the corresponding air flow rate and the flow rate threshold is small when there is no leakage or the valve is well sealed, it is closer to the preset flow rate threshold; on the contrary, if the above air flow rate is greater than the above flow rate threshold, there may be a leakage. At this time, the corresponding second abnormal information can be generated to prompt the administrator that the valve has a leakage, so as to realize automatic detection and identification of abnormalities.

[0125] In this embodiment, Figure 8 The structure diagram of a hydrogen purification device based on big data analysis provided by an embodiment of the present application is shown. The hydrogen purification device based on big data analysis includes various units for executing Figure 2 The steps implemented by the first device in the corresponding embodiment. For details, please refer to Figure 2 and Figure 2 For the convenience of explanation, only the parts related to this embodiment are shown.

[0126] See also Figure 8 , a hydrogen purification device based on big data analysis, including:

[0127] The real-time acquisition unit 81 is used to obtain the real-time acquisition data of the raw gas in the hydrogen production chamber; the real-time acquisition data includes the first component information and flow data of the raw gas; the hydrogen production chamber includes a plurality of valves;

[0128] The valve control script generating unit 82 is used to perform data analysis on the real-time collected data through a preset supervisory model to obtain a valve control script corresponding to the hydrogen production chamber; the supervisory model is obtained by performing big data analysis on the historical data of the hydrogen production chamber; the valve control script is used to determine the valve switching timing of the hydrogen production chamber;

[0129] A valve control unit 83, used for controlling each of the valves to switch the valves according to the valve switching sequence, so as to adsorb impurities on the raw gas through the adsorber corresponding to each valve;

[0130] The purification unit 84 is used to collect the raw gas obtained after adsorption by all the valves to obtain the target hydrogen with a preset purity.

[0131] It should be understood that Figure 8 In the structural block diagram of the device shown, each module is used to execute Figures 2 to 7 The steps in the corresponding embodiments, and for Figures 2 to 7 Each step in the corresponding embodiment has been explained in detail in the above embodiment. Figures 2 to 7 as well as Figures 2 to 7 The relevant descriptions in the corresponding embodiments are not repeated here.

[0132] Fig. 9 is a structural block diagram of an electronic device provided by another embodiment of the present application. Fig. 9 The electronic device 900 of this embodiment includes: a processor 910, a memory 920, and a computer program 930 stored in the memory 920 and executable on the processor 910, such as a program for a hydrogen purification method based on big data analysis. When the processor 910 executes the computer program 930, the steps in each embodiment of the hydrogen purification method based on big data analysis are implemented, such as Figure 2 Alternatively, the processor 910 implements the above when executing the computer program 930 Figure 8 The functions of each module in the corresponding embodiment are, for example, Figure 8 For details on the functions of the units 81 to 84, please refer to Figure 8 Related description in the corresponding embodiment.

[0133] Exemplarily, the computer program 930 may be divided into one or more modules, one or more modules are stored in the memory 920, and are executed by the processor 910 to complete the present application. One or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 930 in the electronic device 900. For example, the computer program 930 may be divided into various unit modules, and the specific functions of each module are as described above.

[0134] The electronic device 900 may include, but is not limited to, a processor 910 and a memory 920. Those skilled in the art will appreciate that Fig. 9 It is only an example of the electronic device 900 and does not constitute a limitation of the electronic device 900. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0135] The processor 910 may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0136] The memory 920 may be an internal storage unit of the electronic device 900, such as a hard disk or memory of the electronic device 900. The memory 920 may also be an external storage device of the electronic device 900, such as a plug-in hard disk, a smart memory card, a flash memory card, etc. equipped on the electronic device 900. Furthermore, the memory 920 may also include both an internal storage unit of the electronic device 900 and an external storage device.

[0137] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A hydrogen purification method based on big data analysis, characterized in that: include: Obtaining real-time data of raw gas in the hydrogen production chamber; The real-time collected data includes the first component information and flow data of the raw gas; The hydrogen production chamber includes a plurality of valves; The real-time collected data is analyzed by a preset supervision model to obtain a valve control script corresponding to the hydrogen production chamber; The supervision model is obtained by performing big data analysis based on historical data of the hydrogen production chamber; the valve control script is used to determine the valve switching timing of the hydrogen production chamber; Controlling each of the valves to switch according to the valve switching timing, so as to adsorb impurities on the raw gas through the adsorber corresponding to each valve; The raw gas obtained after adsorption by all the valves is collected to obtain target hydrogen with a preset purity.

2. The method for purifying hydrogen according to claim 1, characterized in that: The controlling each valve to switch the valve according to the valve switching timing so as to adsorb impurities on the raw gas through the adsorber corresponding to each valve includes: For the adsorber of the Nth valve, the adsorption calibration coefficient is determined according to the second component information of the raw gas when it flows through the N-1th valve and the first adsorption parameter corresponding to the N-1th valve; N is a positive integer greater than 1 and not greater than the total number of valves in the hydrogen production chamber; the adsorption calibration coefficient is: Among them, Adsob adj (N) is the adsorption calibration coefficient; Adsob(N-1) is the first adsorption parameter; Compent i [N-1] is the concentration value of the i-th gas in the second component information; BaseCom i is the expected concentration value of the i-th gas when the raw gas flows through the N-1-th valve; M is the total number of gases in the second component information; P is the total number of valves; Adsob(j) is the adsorption parameter corresponding to the j-th valve; Performing parameter calibration on the expected adsorption parameter of the Nth valve according to the adsorption calibration coefficient to obtain a second adsorption parameter of the Nth valve; When the raw gas flows through the Nth valve, the adsorber is controlled to perform an adsorption operation on the raw gas according to the second adsorption parameter.

3. The method for purifying hydrogen according to claim 2, characterized in that: For the adsorber of the Nth valve, the adsorption calibration coefficient is determined according to the second component information of the raw gas when it flows through the N-1th valve and the first adsorption parameter corresponding to the N-1th valve, including: According to the number of component detection modules deployed in the adsorption area corresponding to the N-1th valve, create a plurality of sub-threads corresponding to the number of modules; each sub-thread corresponds to one component detection module; The original collected data corresponding to each component detection module is obtained through each sub-thread respectively, and the corresponding original collected data is processed in parallel by multiple sub-threads to obtain the second component information.

4. The method for purifying hydrogen according to claim 2, characterized in that: Before determining the adsorption calibration coefficient for the adsorber of the Nth valve according to the second component information of the raw gas when it flows through the N-1th valve and the first adsorption parameter corresponding to the N-1th valve, the method further includes: When the raw gas flows through the N-1th valve, the operating state of the adsorber of the Nth valve is set according to the expected adsorption parameter corresponding to the Nth valve; the expected adsorption parameter includes multiple dimensional indicators; the dimensional indicators include: gas pressure value, adsorption efficiency and regeneration efficiency; Correspondingly, when the raw gas flows through the Nth valve, controlling the adsorber to perform an adsorption operation on the raw gas according to the second adsorption parameter includes: Calculate the deviation value corresponding to each dimensional index between the expected adsorption parameter and the second adsorption parameter; Determine the adjustment order corresponding to each of the dimensional indicators based on the order of the deviation values ​​corresponding to each of the dimensional indicators from large to small; Based on the adjustment order, the operating state of the adsorber corresponding to each of the dimensional indicators is adjusted in sequence.

5. The method for purifying hydrogen according to any one of claims 1 to 4, characterized in that: Before analyzing the real-time collected data through a preset supervision model to obtain a valve control script corresponding to the hydrogen production chamber, the method further includes: Acquire test operation data corresponding to each valve of the hydrogen production chamber; the test operation data includes the state switching time and sealing coefficient of the valve in the test result before the start of hydrogen production; Constructing a first switching timing curve and a second sealing timing curve corresponding to each valve through the historical operation data corresponding to the hydrogen production chamber; Determine a first slope deviation between the first switching timing curve and the first coordinate according to the first coordinate corresponding to the first coordinate system of the state switching duration corresponding to the first switching timing curve; the first slope deviation is used to adjust the timing factor in the supervision model; Determine a second slope deviation between the second sealing timing curve and the second coordinate according to a second coordinate of the sealing coefficient in a second coordinate system corresponding to the second sealing timing curve; the second slope deviation is used to adjust the valve thrust factor in the supervision model; The supervision model is calibrated according to the first slope deviation and the second slope deviation corresponding to all valves.

6. The method for purifying hydrogen according to claim 5, characterized in that: Before calibrating the supervision model according to the first slope deviation and the second slope deviation, the method further includes: Calculating an aging coefficient corresponding to each of the valves according to the second slope deviation and the first slope deviation; If any of the aging coefficients is greater than a preset aging threshold, first abnormal information corresponding to the valve is generated.

7. The method for purifying hydrogen according to any one of claims 1 to 4, characterized in that: After collecting the raw gas obtained after adsorption by all the valves to obtain the target hydrogen with a preset purity, the method further includes: Collect and output the air flow rate corresponding to the raw gas adsorbed by all the valves; If the air flow rate is greater than a preset flow rate threshold, second abnormal information of valve leakage is generated.

8. A hydrogen purification device based on big data analysis, characterized in that: include: A real-time data collection unit, used to obtain real-time data of the raw gas in the hydrogen production chamber; The real-time collected data includes the first component information and flow data of the raw gas; the hydrogen production chamber includes a plurality of valves; A valve control script generating unit is used to perform data analysis on the real-time collected data through a preset supervisory model to obtain a valve control script corresponding to the hydrogen production chamber; the supervisory model is obtained by performing big data analysis on the historical data of the hydrogen production chamber; the valve control script is used to determine the valve switching timing of the hydrogen production chamber; A valve control unit, used for controlling each of the valves to switch the valves according to the valve switching sequence, so as to adsorb impurities on the raw gas through the adsorber corresponding to each of the valves; The purification unit is used to collect the raw gas obtained after adsorption by all the valves to obtain the target hydrogen with a preset purity.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images