Cryogenic air separation reflux control method and related apparatus

Abstract

The application is suitable for the technical field of deep cooling nitrogen production, and particularly relates to a deep cooling air separation reflux control method and related device. The method comprises the following steps: obtaining production control data and production process data chain of air in a separation process; determining a separation condition chain based on the production control data and the production process data chain; wherein the separation condition chain is used to reflect the change degree of component data of the air under the influence of separation parameter setting corresponding to each separation process in the separation process; determining a separation control strategy based on the separation condition chain, the production process data chain and the production control data; wherein the separation control strategy comprises a first strategy for reflecting that a product with incomplete separation is washed again or a second strategy for reflecting that a product with complete separation is stored in a storage tank. The deep cooling air separation reflux control method provided by the application can improve the production efficiency of oxygen, nitrogen, argon and other production products.

Description

Technical Field

[0001] This application belongs to the field of cryogenic nitrogen production technology, and in particular relates to a cryogenic air separation and reflux control method and related apparatus. Background Technology

[0002] Cryogenic air separation is a primary method for the industrial production of high-purity oxygen, nitrogen, liquid oxygen, and liquid nitrogen. A typical process includes: air compression, heat exchange, primary precooling, secondary precooling, gas purification (removal of moisture and carbon dioxide using molecular sieves), main heat exchange, washing in a scrubbing tower (circulating tower), distillation in a re-distillation tower, and final separation in a separation tower. The product is then sent to a liquid oxygen storage tank or vaporizer. The scrubbing tower and subsequent multi-tower distillation sequence (scrubbing tower-re-distillation tower-separation tower) are the core process sections for separating oxygen, nitrogen, and argon.

[0003] In related technologies and actual industrial operations, due to fluctuations in the composition of the raw material air (e.g., changes in argon content), disturbances in the input cooling capacity, and a decrease in the mass transfer efficiency of the tower, the purity of the product exiting the separation tower may sometimes be slightly lower than the lower limit of the specification. This results in the presence of substandard products. In such cases, the substandard products are directly vented to increase the purity of the product stored in the liquid oxygen storage tank. Consequently, the separation process of substandard products undergoing multiple washings is wasted. Because the energy consumption of the air compression step during the separation reflux process is enormous, and the significant waste of material and cooling capacity ultimately affects the air compressor load and the output of other products, resulting in low production efficiency for oxygen, nitrogen, and argon. Summary of the Invention

[0004] This application provides a method and apparatus for controlling the reflux of cryogenic air separation, which can improve the current problem of low production efficiency for products such as oxygen, nitrogen, and argon.

[0005] In a first aspect, embodiments of this application provide a method for controlling the separation and recirculation of cryogenic air, including: Acquire production control data and production process data chain of air during the separation process; wherein, the production control data is used to reflect the separation parameter settings during the separation process, and the production process data chain is used to reflect the changes in air composition data; Based on the production control data and the production process data chain, a separation status chain is determined; wherein, the separation status chain is used to reflect the degree of change of air composition data under the influence of the separation parameter settings corresponding to each separation step during the separation process; Based on the separation status chain, the production process data chain, and the production control data, a separation control strategy is determined; wherein, the separation control strategy includes a first strategy for reflecting the rewashing of products with incomplete air separation or a second strategy for reflecting the storage of products with complete air separation into storage tanks.

[0006] The technical solutions described in this application embodiment have at least the following technical effects: The cryogenic air separation reflux control method provided in this application first acquires production control data reflecting the separation parameter settings during the separation process and a production process data chain reflecting changes in air component data. Based on the production control data and the production process data chain, a separation status chain is determined to reflect the degree of change in air component data under the influence of the separation parameter settings at each separation step. Finally, based on the separation status chain, the production process data chain, and the production control data, a separation control strategy is determined, including a first strategy for rewashing incompletely separated air products and a second strategy for storing completely separated air products in a storage tank. This method can effectively construct a separation status chain reflecting the actual separation efficiency of each tower by comparing the degree of component change in each separation step in the production control data and the actual production process data chain. This analysis logic based on the comparison of efficiency deviations across the entire process can effectively reduce the problem of misjudging complete separation due to temporary stability of local tower conditions (such as washing towers or re-distillation towers). Only when the separation status chain indicates that the purity of the product at the separation tower outlet is lower than the preset start-up threshold does it mean that air separation is incomplete. Under this condition, the precise timing for activating the first strategy is determined based on the separation status chain and the production process data chain, and reflux control is executed. When the separation status chain indicates that the product purity meets the termination threshold, the second strategy is executed. This control method eliminates the need to directly vent or return unqualified products to the compressor inlet to re-run the entire process. It directly eliminates the energy waste and long response delays caused by the inability to accurately determine the timing of recovering incompletely separated products in traditional solutions, significantly improving the energy utilization efficiency and product qualification rate of the air separation unit. Since the separation control strategy is triggered only when the separation status chain accurately indicates that separation is incomplete, and the local circulation through reflux and re-separation in the scrubbing tower can truly reflect the reprocessing effect of unqualified products, it effectively reduces the misjudgment and ineffective circulation processing caused by local component fluctuations in the separation tower in traditional solutions, keeping the energy consumption, response time, and false trigger rate of reflux control within a more optimal range.

[0007] In one possible implementation of the first aspect, determining the separation status chain based on the production control data and the production process data chain includes: Based on the production control data, a baseline condition chain is determined; wherein the baseline condition chain is used to reflect the degree of influence of each separation step on the composition data of air under standard conditions; Based on the production process data chain, an actual situation chain is determined; wherein, the actual situation chain is used to reflect the degree of influence of each separation step on the composition data of air during the actual separation process; The separation condition chain is determined by comparing the actual condition chain with the benchmark condition chain according to the same separation process steps.

[0008] In one possible implementation of the first aspect, determining the baseline condition chain based on the production control data includes: Based on the production control data, multiple first feature items and corresponding first feature item data corresponding to each separation step in the production control data are extracted from the historical production database; wherein, the first feature item refers to the types of components inside the air after a complete separation step, and the first feature item data refers to the specific component data corresponding to the first feature item. Based on multiple first feature items, a matching analysis is performed between the i-th first feature item data and the (i+1)-th first feature item data to obtain the i-th first influence degree; wherein, the i-th first influence degree is used to reflect the degree of influence of the i-th separation step on the composition data of air under standard conditions; Multiple first degree of influence are constructed into a baseline condition chain in the order of the separation steps.

[0009] In one possible implementation of the first aspect, determining the actual status chain based on the production process data chain includes: Based on the production process data chain, multiple second feature items and corresponding second feature item data are determined for each separation step; wherein, the second feature item refers to the types of components inside the air after a complete separation step in the actual separation process, and the second feature item data refers to the specific component data corresponding to the second feature item. Based on multiple second feature items, a matching analysis is performed between the i-th second feature item data and the (i+1)-th second feature item data to obtain the i-th second influence degree; wherein, the i-th second influence degree is used to reflect the degree of influence of the i-th separation step on the composition data of air in the actual separation process; Multiple degrees of the second influence are constructed into a chain of actual conditions in the order of the separation steps.

[0010] In one possible implementation of the first aspect, determining the separation control strategy based on the separation status chain, the production process data chain, and the production control data includes: Based on the separation status chain and the production control data, characteristic process data is determined; wherein, the characteristic process data is used to reflect the data in the production control data that needs to be adjusted; Based on the production process data chain, the separation component data is determined; wherein, the separation component data is used to reflect the component data of the product after a complete separation process; Based on the separated component data and the production process data chain, a comparison result is determined; wherein, the comparison result is used to reflect either a first result of incomplete separation of air during the separation process or a second result of complete separation of air during the separation process; Based on the comparison results, the separation status chain, the separated component data, the characteristic process data, and the production process data chain, a separation control strategy is determined.

[0011] In one possible implementation of the first aspect, determining the characteristic process data based on the separation status chain and the production control data includes: From the separation status chain, determine the feature chain node data that is less than the preset change threshold of the corresponding separation step; Based on the feature chain node data, the corresponding feature process data is determined from the production control data.

[0012] In one possible implementation of the first aspect, determining the separation control strategy based on the comparison results, the separation status chain, the separated component data, the characteristic process data, and the production process data chain includes: When the comparison result reflects the first result, adjustment control data is determined based on the separation status chain, the separation component data, the characteristic process data, and the production process data chain; wherein, the adjustment control data is used to reflect the adjusted production control data; Based on the feature process data and the adjustment control data, the separation control strategy is confirmed to be the first strategy; When the comparison result reflects the second result, the separation control strategy is confirmed to be the second strategy.

[0013] In one possible implementation of the first aspect, determining the adjustment control data based on the separation status chain, the separated component data, the characteristic process data, and the production process data chain includes: Based on the first node of the separation component data and the production process data chain, updated component data is determined; wherein, the updated component data is used to reflect the component data of the mixed gas formed by the incompletely separated product re-entering the scrubbing tower and the new round of air entering the scrubbing tower. Based on the separation status chain, the updated component data, and the characteristic process data, adjustment control data are determined.

[0014] In one possible implementation of the first aspect, determining the adjustment control data based on the separation status chain, the updated component data, and the characteristic process data includes: Based on the separation status chain and the characteristic process data, first adjustment data is determined; wherein, the first adjustment data is used to reflect the adjustment data corresponding to the characteristic process data, which is used to offset the difference between the degree of influence of the separation steps corresponding to the standard conditions and the actual separation process on the composition data of air. Based on the first node of the updated component data and the production process data chain, component differences are determined; wherein, the component differences are used to reflect the component differences between the updated component data and the air that entered the scrubbing tower in the previous round. Based on the component differences, second adjustment data is determined from the historical production database; wherein the second adjustment data is used to reflect the degree of influence of the updated component data on the component data of air as adjustment data for the separation step corresponding to the separation condition chain; The adjustment control data is obtained by weighting and summing the first adjustment data and the second adjustment data.

[0015] Secondly, embodiments of this application provide a cryogenic air separation and recirculation system, comprising: The acquisition unit is used to acquire production control data and production process data chain of air during the separation process; wherein, the production control data is used to reflect the separation parameter settings during the separation process, and the production process data chain is used to reflect the changes in air composition data; The first analysis unit is used to determine the separation status chain based on the production control data and the production process data chain; wherein, the separation status chain is used to reflect the degree of change of air composition data under the influence of the separation parameter settings corresponding to each separation step during the separation process; The second analysis unit is used to determine a separation control strategy based on the separation status chain, the production process data chain, and the production control data; wherein the separation control strategy includes a first strategy for reflecting the rewashing of products with incomplete air separation or a second strategy for reflecting the storage of products with complete air separation into a storage tank.

[0016] Thirdly, embodiments of this application provide a cryogenic air separation and recirculation device, including a separation and recirculation device group and a control device. The separation and recirculation device group is electrically connected to the control device. The control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the method described in any of the first aspects above.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the first aspects above.

[0018] Fifthly, embodiments of this application provide a computer program that, when run on a separation and reflux device assembly, causes the separation and reflux device assembly to perform the cryogenic air separation and reflux method described in any of the first aspects above.

[0019] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art 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.

[0021] Figure 1 This is a schematic flowchart of a cryogenic air separation and reflux control method provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the implementation process of a cryogenic air separation and reflux control method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a cryogenic air separation and reflux control system provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of the control device of the cryogenic air separation and reflux control equipment provided in one embodiment of this application. Detailed Implementation

[0022] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0023] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0024] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0025] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0026] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0028] In related technologies, during actual industrial operation, fluctuations in the composition of the raw material air (e.g., changes in argon content), disturbances in the input cooling capacity, and a decrease in the mass transfer efficiency of the tower can sometimes cause the purity of the product at the outlet of the separation tower to be slightly lower than the lower limit of the specification. This results in the appearance of substandard products. In such cases, the substandard products are directly released to increase the purity of the product stored in the liquid oxygen storage tank. Consequently, the separation process of the substandard products undergoing multiple washings is wasted. Because the energy consumption of the air compression step during the separation reflux process is huge, and the large amount of material and cooling capacity is wasted, it ultimately affects the air compressor load and the output of other products, resulting in low production efficiency for oxygen, nitrogen, and argon.

[0029] To address the aforementioned issues, this application provides a cryogenic air separation reflux control method and related apparatus. The method first acquires production control data reflecting separation parameter settings during the separation process and a production process data chain reflecting changes in air component data. Based on the production control data and the production process data chain, a separation status chain is determined to reflect the degree of change in air component data under the influence of separation parameter settings at each separation step. Finally, based on the separation status chain, the production process data chain, and the production control data, a separation control strategy is determined, including a first strategy for rewashing incompletely separated air products and a second strategy for storing completely separated air products in a storage tank. This method effectively constructs a separation status chain reflecting the actual separation efficiency of each tower by comparing the degree of component change in each separation step in the production control data and the actual production process data chain. This analysis logic based on comparing the efficiency deviation of the entire process effectively reduces the problem of misjudging complete separation due to temporary stability in the operating conditions of local towers (such as washing towers or re-distillation towers). Only when the separation status chain indicates that the purity of the product at the separation tower outlet is lower than the preset start-up threshold does it mean that air separation is incomplete. Under this condition, the precise timing for activating the first strategy is determined based on the separation status chain and the production process data chain, and reflux control is executed. When the separation status chain indicates that the product purity meets the termination threshold, the second strategy is executed. This control method eliminates the need to directly vent or return unqualified products to the compressor inlet to re-run the entire process. It directly eliminates the energy waste and long response delays caused by the inability to accurately determine the timing of recovering incompletely separated products in traditional solutions, significantly improving the energy utilization efficiency and product qualification rate of the air separation unit. Since the separation control strategy is triggered only when the separation status chain accurately indicates that separation is incomplete, and the local circulation through reflux and re-separation in the scrubbing tower can truly reflect the reprocessing effect of unqualified products, it effectively reduces the misjudgment and ineffective circulation processing caused by local component fluctuations in the separation tower in traditional solutions, keeping the energy consumption, response time, and false trigger rate of reflux control within a more optimal range.

[0030] The cryogenic air separation and recirculation control method provided in this application embodiment can be applied to cryogenic air separation and recirculation equipment. In this case, the cryogenic air separation and recirculation equipment is the executing entity of the cryogenic air separation and recirculation control method provided in this application embodiment. This application embodiment does not impose any restrictions on the specific type of cryogenic air separation and recirculation equipment.

[0031] The cryogenic air separation and reflux equipment includes a separation and reflux unit assembly and a control unit. The separation and reflux unit assembly is electrically connected to the control unit. The separation and reflux unit assembly includes a distillation column assembly, a pipeline delivery system, detection components, and execution components. The distillation column assembly includes a scrubbing column, a re-distillation column, and a separation column. The scrubbing column is used to wash and purify the feed air, and simultaneously perform gas-liquid contact re-separation on the refluxed non-conforming products. The top of the scrubbing column is equipped with a return port and a spray distributor, and the bottom is equipped with a liquid phase outlet and a collection tank. The interior of the scrubbing column is filled with a structured packing layer to increase the gas-liquid contact area. The feed inlet of the re-distillation column is connected to the bottom liquid phase outlet of the scrubbing column, used to receive the washed material and perform preliminary distillation separation. The feed inlet of the separation column is connected to the top gas phase outlet of the re-distillation column, used to perform final distillation separation on the material, producing high-purity oxygen, nitrogen, or liquid products. The bottom or side outlet of the separation column is equipped with a product outlet. The pipeline delivery system includes a feed line, a product line, a reflux line, and a return line. The feed line connects the outlet of the upstream main heat exchanger to the lower part of the scrubbing tower. The product line connects the product outlet of the separation tower to the product storage tank, and is equipped with a three-way switching valve for switching between normal output and reflux output. The reflux line connects the bypass outlet of the three-way switching valve to the return port at the top of the scrubbing tower, and is equipped with a pneumatic shut-off valve, a reflux regulating valve, a mass flow meter, and a check valve sequentially along the flow direction. The return line connects the liquid phase outlet at the bottom of the scrubbing tower to the feed inlet of the re-distillation tower and the separation tower, and is equipped with a cryogenic booster pump and a flow splitting valve assembly. The detection components include an online purity analyzer, a mass flow meter, a differential pressure transmitter, a temperature sensor, and a feed component analyzer. The online purity analyzer is located on the product outlet line of the separation tower to obtain real-time product purity values. The mass flow meter is located on the reflux line to obtain the instantaneous flow rate of the reflux medium. The high-pressure and low-pressure ends of the differential pressure transmitter are connected to the upper and lower parts of the packing layer of the scrubbing tower, respectively, to obtain the differential pressure value of the packing section of the scrubbing tower. Temperature sensors are installed at multiple theoretical tray positions in the scrubbing tower, re-distillation tower, and separation tower to obtain temperature distribution data within the towers. A feed component analyzer is installed on the feed line between the main heat exchanger outlet and the scrubbing tower inlet to obtain real-time data on the argon, oxygen, and nitrogen content in the feed air. The actuators include a three-way switching valve, a reflux regulating valve, a pneumatic shut-off valve, a cryogenic booster pump, and a spray pump. The three-way switching valve is a pneumatic single-acting actuator, and its fault reset position is the normal output position connected to the product storage tank. The reflux regulating valve is a pneumatic diaphragm regulating valve used to adjust the reflux flow rate according to the control device commands. The cryogenic booster pump is a variable frequency centrifugal pump used to pressurize the reseparated product at the bottom of the scrubbing tower and deliver it to the feed inlet of the re-distillation tower or separation tower. The spray pump is connected to the spray distributor at the top of the scrubbing tower to supply the scrubbing liquid. Its frequency converter is electrically connected to the control device to achieve linkage adjustment of the spray volume.The control device can be a programmable logic controller (PLC), a distributed control system (DCS), or an industrial computer (IPC) equipped with a dedicated control program.

[0032] To better understand the cryogenic air separation and recirculation control method provided in the embodiments of this application, the specific implementation process of the cryogenic air separation and recirculation control method provided in the embodiments of this application will be described by way of example below.

[0033] Figure 1 and Figure 2 A schematic flowchart of the cryogenic air separation and reflux control method provided in this application embodiment is shown. Please refer to [link / reference]. Figure 1 and Figure 2 The cryogenic air separation and reflux control methods include: S100, acquire production control data and production process data chain of air during the separation process; wherein, the production control data is used to reflect the separation parameter settings during the separation process, and the production process data chain is used to reflect the changes in air composition data.

[0034] In cryogenic air separation, production control data refers to the set of various process parameters set by operators or automatic control systems. These parameters include, but are not limited to, the operating pressure of each distillation column, the temperature at the top and bottom of the column, the reflux ratio, the expansion rate of the expander, the hot-end temperature difference of each heat exchanger, and the material flow rates entering and exiting each column. The production process data chain, on the other hand, is a sequence of data recording changes in the concentration of air and its components (mainly oxygen, nitrogen, and argon) along the temporal or spatial order of the process flow. This production process data chain can be obtained through continuous sampling at multiple key nodes in the process pipeline (such as the air inlet, the top of the lower column, the upper column extraction outlet, and the argon fraction extraction outlet) using online chromatographs, trace oxygen analyzers, and other detection equipment. The data is then organized into a data set with a clear sequential relationship according to the progression of the process flow.

[0035] For example, the data can be recorded starting from the components of the air after it passes through the pre-purification system, and then sequentially recording the component concentrations after entering the lower column, being extracted from different trays in the upper column, and undergoing argon distillation, forming a data chain that includes the changes in oxygen content, nitrogen content, and argon content as the process progresses.

[0036] S200, based on production control data and production process data chain, determines the separation status chain; wherein, the separation status chain is used to reflect the degree of change of air composition data under the influence of the separation parameter settings corresponding to each separation step in the separation process.

[0037] The separation status chain can be understood as a quantitative evaluation sequence, where each element corresponds to a specific separation process (e.g., bottom column distillation, top column stripping, argon column separation, etc.). Each value in this sequence characterizes the actual separation effect achieved by the process under the existing separation parameter settings, specifically reflected in the comparison between the change in air component concentration before and after the process and the theoretically expected change. A high separation status value indicates high separation efficiency and that the component change is closer to the ideal process, while a low separation status value indicates low separation efficiency, which may be due to fluctuations in the feed air component (e.g., changes in argon content), disturbances in the cold input, decreased mass transfer efficiency of the column, or equipment internal component failure.

[0038] For example, production control data can be used to determine the impact of each separation step on air composition data under standard conditions. Then, the production process data chain can be used to determine the impact of each separation step on air composition data during actual separation. Finally, the impact of each separation step on air composition data under standard conditions and during actual separation is compared in the same type of separation and recirculation step to obtain the final separation status chain. Alternatively, production control data and the production process data chain can be input into a learning model, which outputs the corresponding separation status chain. The training process of the learning model can use the processed data from the production control data, production process data chain, and corresponding separation status chain as the training dataset, and then input the training dataset into the learning model for training, ultimately obtaining the learning model. And so on, but not limited to these examples.

[0039] In one possible implementation, in step S200, based on the production control data and the production process data chain, a separation status chain is determined, including: S210, Based on production control data, determine the baseline condition chain; wherein, the baseline condition chain is used to reflect the degree of influence of each separation step on the composition data of air under standard conditions.

[0040] A baseline condition chain is understood to be a sequence of theoretically expected component changes for each separation step, obtained under ideal or standard process conditions, based on currently set production control data and through theoretical calculations or fitting of historical best data. The baseline condition chain enables the expected performance of each process in the separation system under current parameter settings. The generation of the baseline condition chain relies on a process model or an empirical database (i.e., a historical production database).

[0041] For example, production control data can be used to extract the types of components in the air after a complete separation step, along with the specific component data corresponding to each type, from a historical production database covering historical separation processes. Then, based on multiple types, a matching process is performed between the i-th and (i+1)-th specific data points to determine the impact of the corresponding separation step. Finally, the impact of each separation step is determined step by step, forming the baseline condition chain. Alternatively, given a lower column pressure, temperature, and reflux ratio, the gas-liquid balance equation can be used to calculate the oxygen content in the nitrogen at the top of the column and the nitrogen content in the liquid oxygen at the bottom of the column after one theoretical equilibrium of the feed air in the lower column. This yields the theoretical decrease in oxygen concentration after passing through the lower column, and this decrease compared to the previous separation step represents the baseline impact of that step.

[0042] In one possible implementation, step S210 involves determining a baseline condition chain based on production control data, including: S211, based on production control data, extract multiple first characteristic items and corresponding first characteristic item data corresponding to each separation step in the production control data from the historical production database; wherein, the first characteristic item refers to the types of components inside the air after a complete separation step, and the first characteristic item data refers to the specific component data corresponding to the first characteristic item.

[0043] It is understandable that the historical production database stores complete records of multiple past air separation production processes, including control parameters and detailed performance data for each process step. The primary characteristic item refers to a key indicator used to characterize the separation effect of a particular separation step. For example, for a distillation step, the characteristic item could be the decrease in oxygen concentration, the increase in nitrogen concentration, or relative volatility. Based on the currently acquired production control data (such as pressure, temperature, reflux ratio, etc.), a search is performed in the historical production database to find the production batches historically most similar to the current control parameters. From these similar batches, multiple primary characteristic items and their specific numerical data corresponding to each separation step that needs to be evaluated are extracted; these constitute the primary characteristic items and their data.

[0044] S212, based on multiple first feature items, perform same-item matching analysis between the i-th first feature item data and the (i+1)-th first feature item data to obtain the i-th first influence degree; wherein, the i-th first influence degree is used to reflect the degree of influence of the i-th separation step on the composition data of air under standard conditions.

[0045] It can be understood that for the i-th separation step (e.g., the lower column distillation step), the change in its state before and after is described by two data items: the i-th first characteristic item data (e.g., the oxygen content of the feed air) and the (i+1)-th first characteristic item data (e.g., the oxygen content in the nitrogen at the top of the lower column). Same-item matching analysis refers to comparing the values ​​of the same characteristic item (e.g., oxygen content) before and after this step, calculating its change value or rate of change. Since data from multiple batches are extracted from the historical database, multiple samples of the oxygen content difference before and after this step can be obtained. Statistical processing of these samples yields a statistic that represents the degree of first influence of the i-th separation step on the air component data under standard conditions.

[0046] S213, construct a baseline state chain by arranging multiple first degree of influence in the order of separation steps.

[0047] It can be understood that after calculating the first degree of influence of the first separation step, the second separation step, and the Nth separation step, these values ​​are arranged according to the actual order in which air flows through each separation step, forming a data sequence. Each node in this sequence corresponds to a specific separation step, and the value of the node represents the degree of component change that should be achieved under standard conditions for that step.

[0048] This setup, utilizing historical big data to define the impact level under standard conditions, ensures that the benchmark determination does not rely on potentially inaccurate theoretical models but is based on statistical regularities from actual production experience, resulting in higher reliability and engineering applicability. Through matching with the same project and statistical processing, the randomness and measurement noise of single historical data are eliminated, obtaining a statistically significant and robust standard impact level, providing a reliable benchmark value for subsequent comparisons. Furthermore, the benchmark condition chain stores the expected performance of each step under the standard process path in a structured and sequential manner, laying the data structure foundation for efficient and automatic point-by-point comparisons with subsequent actual condition chains.

[0049] S220, based on the production process data chain, determines the actual condition chain; wherein, the actual condition chain is used to reflect the degree of influence of each separation step on the composition data of air during the actual separation process.

[0050] It is understandable that the actual condition chain is directly calculated based on the production process data chain acquired in real time by online monitoring equipment. It reflects the actual degree of component change achieved in each separation step under the current real operating environment, which is subject to various disturbances (such as changes in ambient temperature, equipment performance degradation, etc.). It should be noted that the calculation method of the actual condition chain is similar to that of the baseline condition chain, but the data source is different. For example, for the lower column separation step, the corresponding elements in the actual condition chain can be directly obtained by comparing the measured oxygen content of the lower column inlet air with the measured oxygen content at the lower column top nitrogen outlet in the production process data chain.

[0051] In one possible implementation, in step S220, determining the actual status chain based on the production process data chain includes: S221, based on the production process data chain, determine multiple second characteristic items and corresponding second characteristic item data corresponding to each separation step; wherein, the second characteristic item refers to the types of components inside the air after a complete separation step in the actual separation process, and the second characteristic item data refers to the specific component data corresponding to the second characteristic item.

[0052] It is understood that the production process data chain contains a series of component data obtained through real-time monitoring. For each separation step, a second characteristic item corresponding to the input and output of that step needs to be identified from this data chain. It should be noted that the second characteristic item and the first characteristic item in step S211 can be the same type of physical quantity (such as oxygen concentration and nitrogen concentration), and the second characteristic item data originates from a real-time online analyzer. For example, for the lower column separation step, the data point of oxygen content in the inlet air is located from the production process data chain as the input second characteristic item data, and the data point of nitrogen-oxygen content at the top of the lower column is located as the output second characteristic item data.

[0053] S222, based on multiple second feature items, perform same-item matching analysis between the i-th second feature item data and the (i+1)-th second feature item data to obtain the i-th second influence degree; wherein, the i-th second influence degree is used to reflect the degree of influence of the i-th separation step on the composition data of air in the actual separation process.

[0054] It is understandable that the step of obtaining the i-th second degree of influence can be obtained by a similar method as the step S212 in obtaining the i-th first degree of influence, which will not be elaborated here.

[0055] S223, constructs a chain of actual conditions by separating multiple second degree of influence in the order of the separation steps.

[0056] It is understandable that the steps to construct the actual situation chain can be obtained by similar methods to those used in step S213 to construct the baseline situation chain, and will not be elaborated here.

[0057] This setup, based on real-time monitoring data, objectively and truthfully reflects the current dynamic separation performance of the process system, providing a data foundation for analyzing the differences between the baseline and actual conditions. The long-sequence data chain generated in real-time is parsed and labeled according to the separation steps, clearly defining the data items corresponding to the inputs and outputs of each step, thus preparing the data for calculating the actual impact. Direct and rapid calculation using real-time data yields an actual impact that accurately reflects the dynamic separation performance under current operating conditions, with minimal delay and maximum field representativeness. The actual condition chain dynamically presents the system's current separation performance in a format and sequence fully compatible with the baseline condition chain, making direct point-by-point comparison a structured and automated operation.

[0058] S230, based on the comparison between the actual condition chain and the reference condition chain according to the same separation process steps, the separation condition chain is determined.

[0059] It's understandable that the separation status chain is neither the actual status chain nor the baseline status chain itself, but rather a sequence of comparative results between the two. For each separation process step, the actual impact level corresponding to the same separation step is compared with the baseline impact level, and the final ratio is the chain node data corresponding to the separation status chain. It can be explained that when the actual impact level is consistent with the baseline impact level, it indicates that the separation status of that step is good; when the actual impact level is lower than the baseline impact level, it indicates that the separation efficiency of that step has decreased; conversely, if the actual impact level is abnormally higher than the baseline impact level, it may indicate that insufficient separation in the preceding steps has led to excessive load or instrument malfunction in the subsequent steps.

[0060] This setup provides a repeatable benchmark independent of real-time data, giving a clear scale for subsequent comparisons of actual data and enabling the quantification of deviations between actual and theoretical performance. The separation condition chain directly quantifies the gap between the actual performance of each process and the standard expectation, accurately identifying specific sections with insufficient or excessive separation capabilities, providing clear direction for subsequent targeted adjustments to control parameters.

[0061] S300, based on the separation status chain, the production process data chain, and the production control data, determines the separation control strategy; wherein, the separation control strategy includes a first strategy for reflecting the rewashing of products with incomplete air separation or a second strategy for reflecting the storage of products with complete air separation into storage tanks.

[0062] For example, after obtaining the separation status chain, production process data chain, and original production control data, the system comprehensively judges the final effect of the entire separation process and the efficiency of intermediate links. If the separation status chain shows that the separation status of each process is generally low, or the component concentration of the last node of the production process data chain (i.e., the final product) does not meet the product specification requirements (e.g., excessive residual oxygen in nitrogen, excessive argon content in liquid oxygen, etc.), this indicates that the air has not been completely separated. In this case, the system should select the first strategy, that is, send the incompletely separated product (such as nitrogen with insufficient purity or impure liquid oxygen) back into the scrubbing tower (usually the upper tower or the crude argon tower) through the reflux pipeline for secondary distillation to improve the product extraction rate and purity. Conversely, if the separation status chain shows that the status of each process is good and the concentration of the final product meets the preset product quality standards, the second strategy is selected, and the qualified product is transported to the product storage tank for storage through pipeline.

[0063] This setup, by acquiring control parameters and real-time component data chains, provides complete input information for subsequent evaluation of the actual separation effect of each process step, making the separation process status quantifiable and traceable. Based on multi-dimensional real-time data and evaluation results, the automatic decision-making regarding product flow direction achieves closed-loop intelligent control of the separation process. This reduces the possibility of non-conforming products contaminating storage tanks and improves overall product yield through reflux and re-separation. By decomposing the complex multi-stage separation process into a series of individually evaluable steps, with the separation effect of each step expressed by a quantifiable index, a direct diagnostic basis is provided for identifying inefficient separation processes and making individual adjustments to those steps.

[0064] In one possible implementation, in step S300, a separation control strategy is determined based on the separation status chain, the production process data chain, and the production control data, including: S310, based on the separation status chain and production control data, determine the characteristic process data; wherein, the characteristic process data is used to reflect the data in the production control data that needs to be adjusted.

[0065] It is understandable that the separation condition chain has identified the processes where actual performance deviates from baseline performance. Characteristic process data attributes these deviations to specific adjustable production control parameters. For example, if the actual oxygen drop rate in the lower column is lower than the baseline value, the cause might be an insufficient reflux ratio, an excessively low reboiler temperature, or an excessive feed rate. By combining current production control data (lower column reflux ratio setpoint, reboiler temperature setpoint, air inlet flow rate valve position, etc.) with a pre-established fault-parameter mapping knowledge base, the deviation in separation condition is located at one or more specific control parameters. These identified control parameters, considered the main root causes of performance deviations, constitute the characteristic process data.

[0066] In one possible implementation, in step S310, characteristic process data is determined based on the separation status chain and production control data, including: S311, determine the feature chain node data from the separation status chain that is less than the preset change threshold of the corresponding separation step.

[0067] It is understandable that for each node in the separation status chain (i.e., the corresponding separation step), there exists a pre-defined threshold for change. This threshold reflects the allowable normal fluctuation range of performance for that step. Feature chain node data consists of nodes whose actual performance (i.e., the values ​​of the separation status chain nodes) lags behind this threshold. When the separation status value of a certain separation step falls below the pre-defined lower limit for that step, that node is marked as a feature chain node, and its corresponding value is the feature chain node data.

[0068] S312, based on the feature link point data, determines the corresponding feature process data from the production control data.

[0069] It is understandable that feature chain node data indicates specific processes with poor performance. The performance of each process is affected by its own control parameters and by upstream and downstream processes. Through a pre-established process-parameter association mapping table, feature chain node data can be mapped to a set of the most relevant production control parameters. These mapped parameters are the feature process data.

[0070] This setup, through threshold comparison, automatically filters out substandard process nodes that require attention, reducing wasted analytical resources on processes with normal fluctuations and focusing on the truly problematic links. It accurately attributes process-level performance issues to adjustable parameters at the equipment level, providing specific and actionable targets for subsequent control adjustments, achieving a leap from diagnosis to prescription.

[0071] S320, based on the production process data chain, determines the separation component data; wherein, the separation component data is used to reflect the component data of the product after a complete separation process.

[0072] It is understandable that the production process data chain includes component data for the entire process, from the air inlet to the outlets of each product. Separation component data specifically refers to the data at the last node of this data chain, that is, the real-time component concentration of the final product (such as product nitrogen, product liquid oxygen, crude argon, etc.) after all separation processes. This data is the direct basis for determining whether the entire separation process meets product specifications.

[0073] S330, based on the separation component data and the production process data chain, determines the comparison result; wherein, the comparison result is used to reflect the first result of incomplete separation of air during the separation process or the second result of complete separation of air during the separation process.

[0074] Understandably, the comparison result is a logical judgment obtained by comparing the separated component data with preset product quality thresholds. If all key indicators in the separated component data (such as the oxygen content in nitrogen, the hydrocarbon content in liquid oxygen, etc.) are better than or equal to the product quality standard, then the second result of complete separation is obtained. Conversely, if any key indicator fails to meet the standard (such as the residual oxygen content in the product nitrogen exceeding the permissible value), then the first result of incomplete separation is obtained.

[0075] S340 determines the separation control strategy based on the comparison results, separation status chain, separation component data, characteristic process data, and production process data chain.

[0076] It is understandable that determining the final control strategy is a decision-making process involving the fusion of multiple information sources. The comparison results determine the general direction of the strategy: if the second result is complete separation, the second strategy of storing the gas in the storage tank is executed; if the first result is incomplete separation, it is necessary to further utilize the separation status chain, characteristic process data, separated component data, and production process data chain to comprehensively calculate an optimized adjustment scheme, i.e., the specific content of the first strategy. For example, when the nitrogen purity is insufficient, the system will not simply reflux all the gas, but will determine that the problem is mainly in the lower column based on the poor separation status of the lower column and the good status of the upper column. Therefore, it will choose to reflux some of the impure nitrogen to the lower column inlet and simultaneously increase the reflux ratio setpoint of the lower column.

[0077] This setup allows for precise identification of problems and adjustments, tracing back from macroscopic process performance deviations to specific, operable control parameters. It provides a direct operational object for formulating subsequent control strategies. Separation component data serves as a quantitative evaluation of the final effect of the entire separation process, determining product qualification and providing the most direct basis for subsequent strategy selection. The comparison results transform continuous component concentration data into discrete, binary decision states, simplifying the branching logic of subsequent control strategy selection and making automated decisions clear and unambiguous. By comprehensively utilizing information from five dimensions, control strategy formulation is not a simple open-loop switching process, but a targeted, quantitatively based closed-loop optimization decision based on a comprehensive understanding of the system state.

[0078] In one possible implementation, in step S340, a separation control strategy is determined based on the comparison results, the separation status chain, the separated component data, the characteristic process data, and the production process data chain, including: S341, when the comparison result reflects the first result, the adjustment control data is determined based on the separation status chain, separation component data, characteristic process data and production process data chain; wherein, the adjustment control data is used to reflect the adjusted production control data.

[0079] It is understandable that when the comparison result is the first result of incomplete separation, the system enters the decision branch of backflow and reseparation.

[0080] For example, the component data reflecting the mixture formed by the re-entry of incompletely separated products into the scrubbing tower and the new batch of air into the scrubbing tower can be determined by the first node of the separation component data and production process data chain. Then, adjustment control data can be determined based on the separation status chain, updated component data, and characteristic process data. Alternatively, the separation status chain, separated component data, characteristic process data, and production process data chain can be input into the learning model, and the learning model can output the corresponding adjustment control data, and so on, but not limited to these.

[0081] In one possible implementation, in step S341, adjustment control data is determined based on the separation status chain, separation component data, characteristic process data, and production process data chain, including: S3411, based on the first chain node of the separation component data and production process data chain, determine the updated component data; wherein, the updated component data is used to reflect the component data of the mixed gas formed by the incompletely separated product re-entering the scrubbing tower and the new round of air entering the scrubbing tower.

[0082] It is understandable that during a reflux operation, the incompletely separated products will mix with fresh air from the upstream purification system at the scrubbing tower inlet via the reflux pipeline, and the updated component data will be the composition of this mixed gas. In other words, the composition of the mixed gas is calculated by weighting the current composition data of the fresh air and the composition data of the impure product that needs to be refluxed, based on the flow ratio of the two.

[0083] S3412, based on the separation status chain, updated component data, and characteristic process data, determines the adjustment control data.

[0084] Understandably, the separation status chain provides information on performance bottlenecks at each stage of the existing process flow, indicating which processes need improvement. Updated component data identifies the new composition of the mixed gas entering the scrubbing tower, which alters the material and gas-liquid balance within the tower. Characteristic process data reflects which parameters require adjustment. Calculating the control data adjustment is a multi-objective, multi-variable optimization problem. The optimization objective is, under the condition of updated component data input, to improve the separation status chain at each stage by adjusting the parameters corresponding to the characteristic process data, ultimately ensuring product quality.

[0085] For example, adjustment data reflecting the difference between the degree of influence of the separation steps corresponding to the characteristic process data on the air composition data under standard conditions and in the actual separation process can be determined by using the separation status chain and characteristic process data. Then, based on the first chain node of the updated composition data and production process data, adjustment data reflecting the composition difference between the updated composition data and the air entering the scrubbing tower in the previous round can be determined. Using this difference, adjustment data reflecting the degree of influence of the updated composition data on the air composition data assigned to the separation steps corresponding to the separation status chain can be determined from the historical production database. Finally, the adjustment control data is determined by weighting and summing these two adjustment data. Alternatively, the separation status chain, updated composition data, and characteristic process data can be input into the learning model, and the learning model can output the corresponding adjustment control data, etc., but not limited to these methods.

[0086] This setup allows the calculation of updated component data to provide a quantitative basis for assessing the impact of reflux on the inlet conditions of the separation system. This enables subsequent adjustment controls to take this change into account and reduce new disturbances introduced by reflux. This method integrates the nonlinear effects of reflux, existing performance bottlenecks, and adjustable parameters within a single computational framework. This ensures that the determination of adjustment control data is not an isolated single-parameter correction, but rather a system-level collaborative optimization that conforms to material balance and separation principles.

[0087] In one possible implementation, in step S3412, adjustment control data is determined based on the separation status chain, updated component data, and characteristic process data, including: S34121, Based on the separation status chain and characteristic process data, determine the first adjustment data; wherein, the first adjustment data is used to reflect the adjustment data corresponding to the characteristic process data, which is used to offset the difference between the degree of influence of the corresponding separation steps in the standard case and the actual separation process on the composition data of air.

[0088] It is understandable that a node in the separation condition chain with poor performance (actual impact level lower than the baseline impact level) indicates a decrease in the actual separation capacity of that process. The purpose of the first adjustment data is to calculate how much the characteristic process data needs to be adjusted to compensate for this capacity decrease and restore the process to the baseline performance level.

[0089] For example, if it is known that for the lower column, for every 0.01 increase in the reflux ratio, the oxygen decline rate increases by approximately 0.5%. If the current lower column oxygen decline rate is 2% lower than the baseline, then the first adjustment data suggests increasing the reflux ratio by 0.04, which is the first adjustment data.

[0090] S34122, Based on the first chain node of the updated component data and the production process data chain, determine the component difference; wherein, the component difference is used to reflect the component difference between the updated component data and the air that entered the scrubbing tower in the previous round.

[0091] It's understandable that the composition of the air that entered the scrubbing tower in the previous cycle is the first node in the production process data chain, which is the composition of the fresh air. The composition difference directly compares the updated mixed gas composition (considering recirculation) with the original fresh air composition, which can quantify the degree of contamination of the feed gas due to the recirculation operation.

[0092] S34123, Based on component differences, determine second adjustment data from the historical production database; wherein the second adjustment data is used to reflect the degree of influence of the updated component data on the component data of air as adjustment data for the separation step corresponding to the separation condition chain.

[0093] It is understandable that differences in composition (changes in feed composition) can affect the performance of each downstream separation step. For example, a decrease in feed oxygen content can affect the material balance in the lower column, potentially achieving the same separation effect without adjusting the reflux ratio. The second adjustment data aims to identify this feedforward compensation pattern from historical data. Specifically, it searches the historical production database for batches with feed compositions similar to the updated composition data, batches that achieved good final separation results without specific adjustments to characteristic process parameters. The second adjustment data analyzes the deviation of process parameters for each separation step from the current setpoint in these historical batches. This parameter setting deviation constitutes the second adjustment data.

[0094] S34124, the adjustment control data is obtained by weighting and summing the first adjustment data and the second adjustment data.

[0095] It is understandable that the first adjustment data (feedback compensation) and the second adjustment data (feedforward compensation) may point to the same process parameter, but their adjustment directions and magnitudes may differ, and they may even conflict with each other. The weight allocation can be dynamically set based on the confidence level of the separation condition chain (feedback weight) and the confidence level of historical matching (feedforward weight), or it can be directly obtained from a preset database. For example, when the performance deviation shown by the separation condition chain is very significant, the feedback weight is large; when the matching cases in the historical database are very perfect, the feedforward weight is large.

[0096] With such settings, the first adjustment data focuses on filling in the weak links. Its goal is to calculate the minimum parameter adjustment amount required to restore the process with poor performance to the normal level using the existing process model, which has clear physical meaning and engineering interpretability. The component difference quantifies the degree of change in the feed composition of the system caused by the reflux operation. This change essentially brings back the burden of incomplete separation to the system, which is an external disturbance that needs to be digested through subsequent adjustments. The second adjustment data utilizes the feedforward control law in historical production experience, enabling the system to actively and pre-emptively adjust process parameters when facing feed disturbances, rather than passively responding until the disturbance reaches the product end, thus improving the predictability and dynamic response speed of control. By weighted fusion of feedback and feedforward control commands, both the true attenuation of the current equipment performance and the strategies for dealing with feed changes in historical experience are considered, making the final adjustment control data more robust and balanced, and enhancing the adaptability of the control strategy under complex working conditions.

[0097] S342. Based on the characteristic process data and the adjustment control data, confirm that the separation control strategy is the first strategy.

[0098] It can be understood that after determining the adjustment control data, the specific content of the first strategy of the separation control strategy is also clear. The confirmation process is to compare the adjustment control data with the characteristic process data and convert the deviation amount into a control signal for the actuator. At the same time, the first strategy will include a valve switching instruction to switch the valve on the product pipeline to the reflux state, so that the incompletely separated product returns to the inlet of the washing tower through the reflux pipeline.

[0099] S343. When the comparison result reflects the second result, confirm that the separation control strategy is the second strategy.

[0100] It can be understood that when the comparison result is the second result of complete separation, that is, when the product is determined to be qualified and no reflux is required. The core instruction of the second strategy is to close all valves on the reflux paths, blocking the reflux channel of the unqualified gas, and at the same time, open the transfer valve leading to the product storage tank to start sending the qualified, high-purity product (liquid oxygen, liquid nitrogen or gaseous nitrogen) into the storage tank. It should be noted that if the system has been in the reflux mode before, the switch from the reflux mode to the product sending mode is executed.

[0101] With this setup, the first strategy is concretized into a series of executable control commands, covering all actions of parameter adjustment and flow path switching, directly driving the production unit into the reflux and re-separation working mode. Determining the control data is an optimization process based on multi-source information fusion and model-based reasoning, ensuring the targeting and effectiveness of the adjustments and reducing the time and resource waste from repeated trial and error. The second strategy concisely and explicitly executes the product collection action, improving production efficiency, reducing unnecessary recycling of qualified products, and lowering operating energy consumption, provided that product quality is guaranteed.

[0102] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0103] Corresponding to the cryogenic air separation and recirculation control method in the above embodiments, this application also provides a cryogenic air separation and recirculation control system. Each module of the cryogenic air separation and recirculation control system can implement each step of the cryogenic air separation and recirculation control method. Figure 3 A structural block diagram of the cryogenic air separation and reflux control system provided in an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0104] Reference Figure 3 The cryogenic air separation and reflux system includes: The acquisition unit is used to acquire production control data and production process data chain of air during the separation process; wherein, the production control data is used to reflect the separation parameter settings during the separation process, and the production process data chain is used to reflect the changes in air composition data.

[0105] The first analysis unit is used to determine the separation status chain based on production control data and production process data chain; wherein, the separation status chain is used to reflect the degree of change of air composition data under the influence of the separation parameter settings corresponding to each separation step during the separation process.

[0106] The second analysis unit is used to determine the separation control strategy based on the separation status chain, the production process data chain, and the production control data. The separation control strategy includes a first strategy to reflect the rewashing of products with incomplete air separation or a second strategy to reflect the storage of products with complete air separation into storage tanks.

[0107] It should be noted that the information interaction and execution process between the above systems / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0108] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0109] This application also provides a cryogenic air separation and recirculation device, which includes a separation and recirculation device group and a control device, wherein the separation and recirculation device group and the control device are electrically connected. Figure 4 This is a schematic diagram of the structure of the control device 4 provided in one embodiment of this application. Figure 4 As shown, the control device 4 in this embodiment includes: at least one processor 40 ( Figure 4 Only one is shown in the image), at least one memory 41 ( Figure 4 (Only one is shown in the image) and a computer program 42 stored in the at least one memory 41 and executable on the at least one processor 40, wherein when the processor 40 executes the computer program 42, it causes the control device 4 to perform the steps in any of the above-described embodiments of the cryogenic air separation and reflux method, or causes the control device 4 to perform the functions of each module / unit in the above-described embodiments of the system.

[0110] For example, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 42 in the control device 4.

[0111] The control device 4 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The control device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that... Figure 4This is merely an example of control device 4 and does not constitute a limitation on control device 4. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0112] The processor 40 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0113] In some embodiments, the memory 41 may be an internal storage unit of the control device 4, such as a hard disk or memory of the control device 4. In other embodiments, the memory 41 may be an external storage device of the control device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the control device 4. Furthermore, the memory 41 may include both internal storage units and external storage devices of the control device 4. The memory 41 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0114] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0115] This application provides a computer program product that, when run on a cryogenic air separation and reflux device, enables the cryogenic air separation and reflux device to perform the steps described in any of the above method embodiments.

[0116] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a cryogenic air separation and recirculation device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0117] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0118] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0119] In the embodiments provided in this application, it should be understood that the disclosed cryogenic air separation and recirculation system can be implemented in other ways. For example, the cryogenic air separation and recirculation system embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0121] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for controlling the reflux of cryogenic air separation, characterized in that, include: Acquire production control data and production process data chain of air during the separation process; wherein, the production control data is used to reflect the separation parameter settings during the separation process, and the production process data chain is used to reflect the changes in air composition data; Based on the production control data and the production process data chain, a separation status chain is determined; wherein, the separation status chain is used to reflect the degree of change of air composition data under the influence of the separation parameter settings corresponding to each separation step during the separation process; Based on the separation status chain, the production process data chain, and the production control data, a separation control strategy is determined; wherein, the separation control strategy includes a first strategy for reflecting the rewashing of products with incomplete air separation or a second strategy for reflecting the storage of products with complete air separation into storage tanks.

2. The cryogenic air separation and reflux control method as described in claim 1, characterized in that, The step of determining the separation status chain based on the production control data and the production process data chain includes: Based on the production control data, a baseline condition chain is determined; wherein the baseline condition chain is used to reflect the degree of influence of each separation step on the composition data of air under standard conditions; Based on the production process data chain, an actual situation chain is determined; wherein, the actual situation chain is used to reflect the degree of influence of each separation step on the composition data of air during the actual separation process; The separation condition chain is determined by comparing the actual condition chain with the benchmark condition chain according to the same separation process steps.

3. The cryogenic air separation and reflux control method as described in claim 2, characterized in that, The determination of the baseline condition chain based on the production control data includes: Based on the production control data, multiple first feature items and corresponding first feature item data corresponding to each separation step in the production control data are extracted from the historical production database; wherein, the first feature item refers to the types of components inside the air after a complete separation step, and the first feature item data refers to the specific component data corresponding to the first feature item. Based on multiple first feature items, a matching analysis is performed between the i-th first feature item data and the (i+1)-th first feature item data to obtain the i-th first influence degree; wherein, the i-th first influence degree is used to reflect the degree of influence of the i-th separation step on the composition data of air under standard conditions; Multiple first degree of influence are constructed into a baseline condition chain in the order of the separation steps.

4. The cryogenic air separation and reflux control method as described in claim 2, characterized in that, The determination of the actual status chain based on the production process data chain includes: Based on the production process data chain, multiple second feature items and corresponding second feature item data are determined for each separation step; wherein, the second feature item refers to the types of components inside the air after a complete separation step in the actual separation process, and the second feature item data refers to the specific component data corresponding to the second feature item. Based on multiple second feature items, a matching analysis is performed between the i-th second feature item data and the (i+1)-th second feature item data to obtain the i-th second influence degree; wherein, the i-th second influence degree is used to reflect the degree of influence of the i-th separation step on the composition data of air in the actual separation process; The multiple degrees of the second influence are constructed into a chain of actual conditions in the order of the separation steps.

5. The cryogenic air separation and reflux control method as described in claim 1, characterized in that, The step of determining the separation control strategy based on the separation status chain, the production process data chain, and the production control data includes: Based on the separation status chain and the production control data, characteristic process data is determined; wherein, the characteristic process data is used to reflect the data in the production control data that needs to be adjusted; Based on the production process data chain, the separation component data is determined; wherein, the separation component data is used to reflect the component data of the product after a complete separation process; Based on the separated component data and the production process data chain, a comparison result is determined; wherein, the comparison result is used to reflect either a first result of incomplete separation of air during the separation process or a second result of complete separation of air during the separation process; Based on the comparison results, the separation status chain, the separated component data, the characteristic process data, and the production process data chain, a separation control strategy is determined.

6. The cryogenic air separation and reflux control method as described in claim 5, characterized in that, The determination of characteristic process data based on the separation status chain and the production control data includes: From the separation status chain, determine the feature chain node data that is less than the preset change threshold of the corresponding separation step; Based on the feature chain node data, the corresponding feature process data is determined from the production control data.

7. The cryogenic air separation and reflux control method as described in claim 6, characterized in that, The step of determining a separation control strategy based on the comparison results, the separation status chain, the separated component data, the characteristic process data, and the production process data chain includes: When the comparison result reflects the first result, adjustment control data is determined based on the separation status chain, the separation component data, the characteristic process data, and the production process data chain; wherein, the adjustment control data is used to reflect the adjusted production control data; Based on the feature process data and the adjustment control data, the separation control strategy is confirmed to be the first strategy; When the comparison result reflects the second result, the separation control strategy is confirmed to be the second strategy.

8. The cryogenic air separation and reflux control method as described in claim 6, characterized in that, The determination of adjustment control data based on the separation status chain, the separated component data, the characteristic process data, and the production process data chain includes: Based on the first node of the separation component data and the production process data chain, updated component data is determined; wherein, the updated component data is used to reflect the component data of the mixed gas formed by the incompletely separated product re-entering the scrubbing tower and the new round of air entering the scrubbing tower. Based on the separation status chain, the updated component data, and the characteristic process data, adjustment control data are determined.

9. The cryogenic air separation and reflux control method as described in claim 8, characterized in that, The determination of adjustment control data based on the separation status chain, the updated component data, and the characteristic process data includes: Based on the separation status chain and the characteristic process data, first adjustment data is determined; wherein, the first adjustment data is used to reflect the adjustment data corresponding to the characteristic process data, which is used to offset the difference between the degree of influence of the separation steps corresponding to the standard conditions and the actual separation process on the composition data of air. Based on the first node of the updated component data and the production process data chain, component differences are determined; wherein, the component differences are used to reflect the component differences between the updated component data and the air that entered the scrubbing tower in the previous round. Based on the component differences, second adjustment data is determined from the historical production database; wherein the second adjustment data is used to reflect the degree of influence of the updated component data on the component data of air as adjustment data for the separation step corresponding to the separation condition chain; The adjustment control data is obtained by weighting and summing the first adjustment data and the second adjustment data.

10. A cryogenic air separation and reflux device, characterized in that, The method includes a separation reflux device assembly and a control device, wherein the separation reflux device is electrically connected to the control device, and the control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method as described in any one of claims 1 to 9.

Images