Nitrogen generation regulation and control system, method and device and storage medium

Abstract

The embodiment of the invention provides a nitrogen generation regulation and control system, method and device and a storage medium, the system comprises a gas inlet unit, a gas generation unit and a processor, and the gas inlet unit comprises a gas inlet channel, a first sensing unit group, a second sensing unit group, compression equipment, cooling equipment and drying equipment. The processor is configured to obtain gas characteristics of the original gas from the first sensing unit group; generating compression parameters according to the gas characteristics of the original gas; controlling compression equipment to treat the original gas according to the compression parameters to obtain first intermediate gas; acquiring gas characteristics of the first intermediate gas from the second sensing unit group; generating a cooling parameter and a drying parameter according to the gas characteristics of the first intermediate gas; controlling cooling equipment and drying equipment to treat the first intermediate gas according to the cooling parameters and the drying parameters to obtain second intermediate gas. The gas generation unit is configured to generate nitrogen based on the second intermediate gas.

Description

Technical Field

[0001] This specification relates to the technical field of nitrogen production, and particularly to a nitrogen production regulation system, method, device, and storage medium. Background Art

[0002] In the technical field of nitrogen production equipment, the pretreatment sub-equipment is the core link to ensure nitrogen production efficiency and nitrogen quality. In the prior art, the pretreatment sub-equipment usually includes components such as an air compressor, a cooler, a refrigerated dryer, and a filter, which are responsible for compressing, cooling, drying, and filtering air or industrial waste gas. However, in the existing pretreatment sub-equipment during the working stages of compression, cooling, drying, etc., the parameters in each stage (such as compression pressure, cooling temperature) are mostly fixedly set or adjusted depending on manual experience, and cannot be dynamically optimized according to the real-time working conditions.

[0003] In view of this, it is desirable to provide an improved nitrogen production regulation system, method, device, and storage medium, which can improve the nitrogen production efficiency, shorten the nitrogen production cycle, and ensure the nitrogen production quality by adjusting the parameters of the compression equipment, cooling equipment, and drying equipment in the pretreatment sub-equipment. Summary of the Invention

[0004] One or more embodiments of this specification provide a nitrogen production regulation system, including an intake unit, a gas production unit, and a processor. The intake unit includes an intake channel, a first sensor unit group, a second sensor unit group, a compression device, a cooling device, and a drying device; the processor is configured to: execute a nitrogen production regulation method; the gas production unit is configured to produce nitrogen based on the second intermediate gas.

[0005] One or more embodiments of this specification provide a nitrogen production regulation method, which includes: obtaining the gas characteristics of the raw gas from the first sensor unit group; generating compression parameters according to the gas characteristics of the raw gas; controlling the compression device to process the raw gas according to the compression parameters to obtain a first intermediate gas; obtaining the gas characteristics of the first intermediate gas from the second sensor unit group; generating cooling parameters and drying parameters according to the gas characteristics of the first intermediate gas; controlling the cooling device and the drying device to process the first intermediate gas according to the cooling parameters and the drying parameters to obtain a second intermediate gas; controlling the gas production unit to produce nitrogen based on the second intermediate gas.

[0006] One or more embodiments of this specification provide a nitrogen production regulation device, including a processor, and the processor is used to execute the nitrogen production regulation method as described in any one of the above.

[0007] One or more embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the nitrogen production regulation method described in any of the above items. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described by way of exemplary embodiments, which will be described in detail through the accompanying drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0009] Figure 1 is a schematic system diagram of a nitrogen production regulation system shown in some embodiments of this specification;

[0010] Figure 2 is an exemplary flowchart of a nitrogen production regulation method shown in some embodiments of this specification;

[0011] Figure 3 is an exemplary schematic diagram of generating cooling parameters and drying parameters shown in some embodiments of this specification;

[0012] Figure 4 is an exemplary flowchart of controlling the operation of a recovery unit shown in some embodiments of this specification. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] To more clearly illustrate the technical solutions of the embodiments of this specification, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the drawings represent the same structures or operations.

[0014] Flowcharts are used in this specification to illustrate the operations performed by the systems according to the embodiments of this specification. It should be understood that the operations before or after do not necessarily need to be executed precisely in sequence. Instead, the steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0015] Figure 1 is a schematic system diagram of a nitrogen production regulation system shown in some embodiments of this specification.

[0016] In some embodiments, the nitrogen production regulation system 100 may include an intake unit 110, a gas generation unit 120, and a processor 130.

[0017] The intake unit 110 refers to the unit module that collects the raw gas and enters the nitrogen production regulation system. In some embodiments, the intake unit 110 may include an intake channel 111, a first sensor unit group 112, a second sensor unit group 113, a compression device 114, a cooling device 115, and a drying device 116.

[0018] The intake channel 111 refers to the gas channel that collects the raw gas and enters the nitrogen production regulation system.

[0019] In some embodiments, the first sensor unit group 112 may be configured to collect the physical quantities of the raw gas. For example, the first sensor unit group 112 may include a flow sensor, a temperature sensor, a humidity sensor, a pressure sensor, etc.

[0020] In some embodiments, the second sensor unit group 113 may be configured to collect the physical quantities of the first intermediate gas. For example, the second sensor unit group 113 may include a flow sensor, a temperature sensor, a humidity sensor, a pressure sensor, etc.

[0021] In some embodiments, the second sensor unit group 113 may further include an oil content sensor. The oil content sensor refers to a sensor used to detect the oil content in the gas. The oil content can affect the dew point of the first intermediate gas, thereby affecting the subsequent cooling parameters to be determined.

[0022] By detecting the oil content in the first intermediate gas, when determining the cooling parameters subsequently, the oil content can be taken into account, thereby improving the accuracy of the determined cooling parameters.

[0023] The compression device 114 refers to a device used to compress the gas and increase the gas pressure. In some embodiments, the compression device 114 may include a piston-type compression device, a screw-type compression device, etc.

[0024] The cooling device 115 refers to a device used to reduce the temperature of the compressed gas. In some embodiments, the cooling device 115 may include a refrigerated dryer, an air cooler, etc.

[0025] The drying device 116 refers to a device used to dry the gas. In some embodiments, the drying device 116 may include an adsorption dryer, a refrigerated dryer, etc.

[0026] The gas production unit 120 refers to the unit module for nitrogen production. In some embodiments, the gas production unit 120 may be configured to produce nitrogen based on the second intermediate gas.

[0027] In some embodiments, the nitrogen production regulation system 100 may further include a recovery unit 140 and a third sensor unit group 150.

[0028] The recovery unit 140 refers to the unit module for recovering and separating gases. In some embodiments, the recovery unit 140 may be configured to recover and separate gases.

[0029] For more information about the separated gas, refer to Figure 4 the relevant description.

[0030] The third sensing unit group 150 refers to the sensor combination for processing the separated gas. In some embodiments, the third sensing unit group 150 may be configured to collect the local component characteristics of the separated gas. For example, the third sensing unit group 150 may include semiconductor gas sensors, electrochemical sensors, thermal conductivity sensors, etc.

[0031] In some embodiments, the sensors in the third sensing unit group 150 may also be configured to detect and measure specific gas components. For example, collect the content of gas components with low chemical inertness and identifiable concentrations in the separated gas. Among them, the identifiable concentration refers to the concentration that the sensor can detect.

[0032] The processor 130 refers to a computing device that processes instructions, processes data, and executes operations, etc. In some embodiments, the processor 130 may be configured to obtain the gas characteristics of the raw gas from the first sensing unit group; generate compression parameters according to the gas characteristics of the raw gas; control the compression device to process the raw gas according to the compression parameters to obtain the first intermediate gas; obtain the gas characteristics of the first intermediate gas from the second sensing unit group; generate cooling parameters and drying parameters according to the gas characteristics of the first intermediate gas; control the cooling device and the drying device to process the first intermediate gas according to the cooling parameters and the drying parameters to obtain the second intermediate gas.

[0033] For more descriptions of the components of the nitrogen production regulation system, refer to Figures 2 - 4 the relevant description.

[0034] It should be noted that the above descriptions of the nitrogen production regulation system and its modules are only for convenience of description and do not limit this specification to the scope of the exemplified embodiments. It can be understood that for those skilled in the art, after understanding the principle of the system, they may, without departing from this principle, make any combination of the various modules, or form a subsystem and connect it with other modules. In some embodiments, Figure 1 the intake unit, the gas generation unit, the processor, the recovery unit, and the third sensing unit group disclosed in

[0035] Figure 2 is an exemplary flowchart of a nitrogen production regulation method shown in some embodiments of this specification. As Figure 2 shown, process 200 includes the following steps. In some embodiments, process 200 can be executed by a processor.

[0036] Step 210, obtain the gas characteristics of the raw gas from the first sensor unit group.

[0037] The raw gas refers to the raw materials used for nitrogen production. For example, air, industrial gas, etc. In some embodiments, the raw gas can be obtained in various ways. For example, using a suction fan to extract air, obtaining it from a factory, etc.

[0038] In some embodiments, the gas characteristics may include the flow rate, pressure, temperature, humidity, etc. of the gas.

[0039] Step 220, generate compression parameters according to the gas characteristics of the raw gas.

[0040] The compression parameters refer to the working parameters of the compression equipment. For example, the pressure value that the raw gas needs to reach after compression, the rotation speed of the compression equipment, etc.

[0041] In some embodiments, the processor can construct a first data table based on historical experience and historical production data. The first data table includes historical gas characteristics, historical compression parameters, and their corresponding relationships. In some embodiments, the processor can, based on the current gas characteristics, query the first data table to determine the same or similar historical gas characteristics, and determine the corresponding historical compression parameters as the current compression parameters.

[0042] In some embodiments, the processor is further configured to determine the loss distribution, and generate compression parameters based on the loss distribution and the gas characteristics of the raw gas.

[0043] The loss distribution refers to the distribution of pressure losses at various preset points in the compression equipment during the process of the raw gas entering the compression equipment from the outside. The materials, sizes, etc. corresponding to different preset points may be different, and different preset points may have different resistance values. Therefore, after the raw gas passes through the preset points, there may be a situation of pressure loss due to the existence of resistance.

[0044] In some embodiments, the loss distribution can be determined through the following steps:

[0045] Step S1, determine multiple preset points on the pipeline in the compression equipment.

[0046] The preset points are pre-selected points. For example, multiple points in the intake passage of the compression device or in the compressed air pipe. There may be a preset distance between adjacent preset points. The preset points and the preset distance are preset values and can be set according to actual needs.

[0047] In some embodiments, the preset distance may be negatively correlated with the pipeline complexity.

[0048] The pipeline complexity is used to characterize the complexity of the pipeline. In some embodiments, the pipeline complexity can be determined based on the number of bends in the pipeline. The more the number of bends, the higher the pipeline complexity and the shorter the preset distance can be.

[0049] Step S2, install a pressure gauge at the preset points.

[0050] Step S3, apply pressure to the pipeline and obtain the pressure values at each preset point based on the pressure gauge.

[0051] Step S4, determine the pressure loss value at the preset point based on the pressure difference between adjacent pressure gauges at the preset point.

[0052] Exemplarily, apply a pressure of 500 Pa to the inlet of the pipeline. The pressure value monitored by the pressure sensor corresponding to the first preset point closest to the inlet is 499 Pa, and the pressure value monitored by the pressure sensor corresponding to the second preset point second closest to the inlet is 497 Pa. Then the pressure loss value at the first preset point is 1 Pa, and the pressure loss value at the second preset point is 2 Pa.

[0053] Step S5, repeat steps S3 and S4. The processor counts the multiple pressure loss values corresponding to each preset point and calculates their average value. The processor can determine this average value as the final pressure loss value at this preset point.

[0054] In some embodiments, the number of repetitions and the pressure applied are preset values and can be set according to actual needs.

[0055] Step S6, construct a set of the final pressure loss values at each preset point to obtain the loss distribution.

[0056] In some embodiments, the processor can determine the compression parameters by vector matching based on the loss distribution and the gas characteristics of the original gas.

[0057] In some embodiments, the processor may construct a compression vector based on the current gas characteristics, altitude, loss distribution, compressor type, maximum temperature allowed by the cooler, and target nitrogen concentration. The altitude refers to the altitude where the compressor is located and can be queried through a third-party database. The compressor type refers to the type of the compressor, for example, piston type, screw type, etc. The maximum temperature allowed by the cooler refers to the maximum temperature of the fluid allowed to enter the cooler. The compressor type and the maximum temperature allowed by the cooler can be obtained from the manufacturer. The target nitrogen concentration refers to the concentration of the finally obtained nitrogen, and the target nitrogen concentration is a preset value and can be set according to actual needs.

[0058] The processor may construct a first vector library based on historical data. The first vector library includes a plurality of first feature vectors and their corresponding first vector tags. The processor may construct a first feature vector based on the historical gas characteristics, historical altitude, historical loss distribution, historical compressor type, historical maximum temperature allowed by the cooler, and historical target nitrogen concentration in the historical data. The first vector tag includes the historical compression parameters corresponding to the first feature vector.

[0059] In some embodiments, the processor may select the data in the historical data where the obtained nitrogen purity reaches the target nitrogen purity requirement and the nitrogen production duration is lower than the preset duration, and construct it as a feature vector based on the corresponding historical gas characteristics, historical altitude, historical loss distribution, historical compressor type, historical maximum temperature allowed by the cooler, and historical target nitrogen concentration. The processor may use the pressure value subsequently monitored by the pressure sensor of the second sensing unit group for this data as the first vector tag.

[0060] In some embodiments, the processor may, based on the compression vector, through vector matching, match the first feature vector with the highest similarity pair in the first vector library, and determine the historical compression parameters corresponding to the first feature vector as the current compression parameters.

[0061] In some embodiments, the processor may generate the compression parameters based on the loss distribution, gas characteristics of the raw gas, and the first content distribution.

[0062] For more content about the first content distribution, reference can be made to the relevant description in step 310.

[0063] In some embodiments, the compression vector may further include the first content distribution, and the first feature vector may further include the corresponding historical first content distribution.

[0064] The compressibility of different gas molecules and the load on the compressor are different. When determining the compression parameters, by considering the composition of the raw gas and the first content distribution, the accuracy of determining the compression parameters can be improved, and a better compression effect can be achieved when subsequently compressing the raw gas.

[0065] Due to the pressure loss of the raw gas caused by pipeline friction, the pressure of the raw gas gradually decreases during the flow process, resulting in the compression effect not reaching the expected level after the compression equipment pressurizes the raw gas. Therefore, when determining the compression parameters, by considering the loss distribution, the compression parameters can be determined based on the actual situation during the flow process of the raw gas, which is beneficial to improving the accuracy of determining the compression parameters. Determining the compression parameters through vector matching can improve the efficiency of determining the compression parameters, and combined with the actual nitrogen production data in historical data, it can improve the accuracy of determining the compression parameters.

[0066] Step 230, according to the compression parameters, control the compression equipment to process the raw gas to obtain a first intermediate gas.

[0067] The first intermediate gas refers to the gas after the raw gas is compressed by the compression equipment.

[0068] Step 240, obtain the gas characteristics of the first intermediate gas from the second sensor unit group.

[0069] Step 250, generate cooling parameters and drying parameters according to the gas characteristics of the first intermediate gas.

[0070] The cooling parameters refer to the operating parameters of the cooling equipment. In some embodiments, the cooling parameters may include the temperature of the cooling medium, the temperature of the first intermediate gas after cooling, etc.

[0071] The drying parameters refer to the operating parameters of the drying equipment. In some embodiments, the drying parameters may include the refrigerant evaporation temperature of the refrigerated dryer, and the adsorbent regeneration cycle and adsorbent regeneration temperature of the adsorption dryer, etc.

[0072] In some embodiments, the processor can construct a second data table based on historical experience and historical production data. The second data table includes the corresponding historical gas characteristics, historical cooling parameters, historical drying parameters of the historical first intermediate gas and their corresponding relationships. In some embodiments, the processor can, based on the current gas characteristics of the first intermediate gas, query the second data table to determine the same or similar historical gas characteristics, and determine the corresponding historical cooling parameters and historical drying parameters as the current cooling parameters and drying parameters.

[0073] Step 260, according to the cooling parameters and the drying parameters, control the cooling equipment and the drying equipment to process the first intermediate gas to obtain a second intermediate gas.

[0074] The second intermediate gas refers to the gas used for nitrogen production after the first intermediate gas is cooled and dried.

[0075] Step 270: Control the gas generation unit to generate nitrogen based on the second intermediate gas. For more information about the gas generation unit, reference can be made to Figure 1 the relevant description.

[0076] In some embodiments, the gas generation unit can generate nitrogen in various ways. For example, it can adopt cryogenic air separation for nitrogen generation, molecular sieve air separation for nitrogen generation, membrane air separation for nitrogen generation, etc.

[0077] The nitrogen generation regulation system and method provided in some embodiments of this specification can automatically detect the gas characteristics of the raw gas and automatically generate compression parameters, automatically detect the gas characteristics of the first intermediate gas and automatically generate cooling parameters and drying parameters, which can improve the degree of automation in preprocessing the raw gas. And it can automatically regulate parameters such as compression parameters, cooling parameters, and drying parameters according to the gas characteristics, which is beneficial to improving the accuracy and efficiency of preprocessing and providing high-quality gas for subsequent nitrogen generation.

[0078] Figure 3 is an exemplary flowchart for generating cooling parameters and drying parameters shown in some embodiments of this specification. As Figure 3 shown, process 300 includes the following steps. In some embodiments, process 300 can be executed by a processor.

[0079] Step 310: Determine the first content distribution of the raw gas.

[0080] The first content distribution refers to the composition components of the raw gas and the proportion of each component. For example, the composition components can include nitrogen, oxygen, carbon dioxide, water vapor, etc., and the first content distribution also includes the proportion of each component in the raw gas.

[0081] In some embodiments, the processor can obtain the first content distribution in various ways. For example, obtain user input, look up a table, etc.

[0082] Exemplarily, when the raw gas is air, the processor can construct a third data table based on historical data or a third-party database. The third data table can include geographical location, air quality, weather conditions, the first content distribution and their corresponding relationships. The processor can determine the first content distribution by querying the third data table based on the current geographical location, air quality, and weather conditions. The geographical location refers to the location where the air is collected. For example, a province, etc. The air quality can include different pm values. The weather conditions can include sunny, cloudy, rainy, etc.

[0083] Exemplarily, when the raw gas is an industrial gas, the processor may construct a fourth data table based on historical data or a third-party database. The fourth data table may include industrial reactant types, feed gas components, process operating conditions, the first content distribution, and their corresponding relationships. The processor may determine the first content distribution by querying the fourth data table based on the current industrial reactant types, feed gas components, and process operating conditions. The industrial reaction type refers to the type of chemical reaction in industrial production, such as ammonia synthesis, petroleum cracking, steel smelting, etc. The feed gas components refer to the components of the gaseous raw materials participating in the reaction in industrial production, such as hydrogen, nitrogen, hydrocarbon gases, etc. The process operating conditions refer to the conditions for carrying out the reaction in industrial production, such as high-pressure synthesis, high-temperature cracking, etc.

[0084] In some embodiments, the first content distribution further includes the oil content.

[0085] The oil content refers to the content of oil in the raw gas. The oil content can be obtained by an oil sensor. For the updated content of the oil sensor, reference can be made to the relevant description in step 240.

[0086] By determining the oil content and adjusting the compression parameters according to the oil content during the compression of the raw gas, the gasification or residue of the oil during compression can be effectively reduced, thereby reducing the pollution caused by the oil to subsequent equipment and processes.

[0087] Step 320, generate a dew point probability distribution according to the first content distribution and the gas characteristics of the first intermediate gas.

[0088] The dew point refers to the temperature at which a gas cools to the point where the first drop of liquid appears under a certain air pressure.

[0089] The dew point probability is used to characterize the probability that the compressed gas appears the first drop of liquid at different temperatures when the compressed gas is cooled to a preset temperature range.

[0090] The dew point probability distribution is used to characterize the distribution of the dew point probability within the preset temperature range. In some embodiments, the dew point probability is negatively correlated with the temperature. The dew point probability distribution can be a preset value.

[0091] The preset temperature range is a preset value and can be set according to actual needs. The dew point probability can be obtained from historical data or experimental data.

[0092] Exemplarily, the preset temperature range is from -40°C to -70°C, and the dew point probability distribution is [(-40°C, G1), (-41°C, G2), …, (-70°C, G n )]. G1…G n is the dew point probability at the corresponding temperature.

[0093] In some embodiments, the processor may construct a dew point vector based on the first content distribution and the gas characteristics of the first intermediate gas.

[0094] In some embodiments, the processor may construct a second vector library based on historical data or experimental data. The second vector library includes second feature vectors and their corresponding second vector tags.

[0095] The second feature vectors include the historical first content distribution of the historical original gas in the historical data or experimental data and the historical gas characteristics of the corresponding historical first intermediate gas of the historical original gas. The second vector tag is the historical dew point probability distribution corresponding to the second feature vector. In some embodiments, the processor may determine the actual dew point corresponding to the historical gas when the subsequent historical first intermediate gas is cooled under certain pressure conditions. In some embodiments, when the processor determines the historical dew point probability distribution corresponding to the historical first intermediate gas, the probability corresponding to the actual dew point is set to 1, and the probabilities corresponding to the remaining temperatures are set to 0. Exemplarily, the preset temperature range is from -40°C to -70°C, the actual dew point corresponding to the historical gas is -50°C, and the second vector tag is [(-40°C, 0), (-41°C, 0), …, (-50°C, 1), …, (-70°C, 0)].

[0096] In some embodiments, the processor may, based on the dew point vector, through vector matching, match the second feature vector with the highest similarity in the second vector library, and determine the corresponding historical dew point probability distribution as the current dew point probability distribution. The processor may calculate the similarity through a preset algorithm, such as cosine distance, Euclidean distance, etc.

[0097] In some embodiments, the processor may generate a dew point probability distribution based on the first content distribution and the gas characteristics of the first intermediate gas, based on a dew point prediction model.

[0098] The dew point prediction model refers to a model for determining the dew point probability distribution. In some embodiments, the dew point prediction model is a machine learning model. For example, a neural network model (Neural Networks, NN), etc.

[0099] In some embodiments, the input of the dew point prediction model further includes the oil content of the first intermediate gas.

[0100] For more content regarding the oil content, reference may be made to the relevant description in step 310.

[0101] When the oil content is high, in order to fully condense the oil into a liquid state for removal, it is necessary to lower the temperature of the first intermediate gas to a lower level, thus requiring a cooling medium with a lower temperature to improve the oil removal effect.

[0102] When determining the dew point probability distribution, by considering the oil content, the oil content is also taken into account when determining the cooling parameter based on the dew point probability distribution subsequently, so that the determined cooling parameter can effectively improve the condensation efficiency of the oil content, thereby enhancing the oil removal effect. This is conducive to reducing the oil residue in the gas subsequently, improving the purity of nitrogen and the stability of equipment operation.

[0103] In some embodiments, the processor may train the dew point prediction model based on the first sample data set.

[0104] The first sample data set includes the first training sample and its corresponding first label.

[0105] In some embodiments, the first training sample includes the sample first content distribution and the sample gas characteristics of the sample first intermediate gas. The first label is the dew point probability distribution corresponding to each first training sample.

[0106] In some embodiments, the processor may, in advance, through a series of experiments, change the first content distribution and the gas characteristics, and accurately measure the dew point corresponding to different first content distributions and gas characteristics based on the experiments, construct the dew point probability distribution based on the dew point, determine the collected first content distribution and gas characteristics as the first training sample, and determine the corresponding dew point probability distribution as the first training label corresponding to the first training sample.

[0107] Exemplarily, the preset temperature range is from -40°C to -70°C, and the experimentally accurately measured dew point is -50°C. The processor can, through exhaustion, set the probability corresponding to the measured dew point to 1, and set the probabilities of the remaining dew points to 0, that is, the processor constructs the first training label as [(-40°C, 0), (-41°C, 0), …, (-50°C, 1), …, (-70°C, 0)]. The preset temperature range can be set based on manual experience.

[0108] In some embodiments, the processor may perform multiple rounds of iteration. At least one round of iteration includes: selecting one or more first training samples from the first sample data set, inputting the one or more first training samples into the initial dew point prediction model to obtain the model prediction output corresponding to the one or more first training samples; according to the model prediction output corresponding to the one or more first training samples and the first label of the one or more first training samples, substituting them into the formula of the predefined loss function to calculate the value of the loss function; according to the value of the loss function, reversely update the model parameters in the initial dew point prediction model; this step can be performed using various methods. For example, it can be updated based on the gradient descent method. When the iteration end condition is satisfied, the iteration ends, and the trained dew point prediction model is obtained.

[0109] Determining the dew point probability distribution through the dew point prediction model can improve the accuracy and efficiency of determining the dew point probability distribution. When training the dew point prediction model, experimental data is utilized, which can improve the accuracy of the dew point prediction model.

[0110] Step 330: Generate cooling parameters and drying parameters based on the first content distribution and the dew point probability distribution.

[0111] In some embodiments, the processor can generate cooling parameters and drying parameters based on the first content distribution and the dew point probability distribution through a parameter prediction model.

[0112] The parameter prediction model refers to a model used to determine cooling parameters and drying parameters.

[0113] In some embodiments, the parameter prediction model may include a cooling parameter determination layer, a drying method determination layer, and a drying parameter determination layer.

[0114] The cooling parameter determination layer refers to a model used to determine cooling parameters. In some embodiments, the cooling parameter determination layer is a machine learning model. For example, a neural network model (Neural Networks, NN), etc. For more content about cooling parameters, reference can be made to the relevant description in step 250.

[0115] The input of the cooling parameter determination layer includes the first content distribution, the sample gas characteristics of the first intermediate gas, and the sample dew point probability distribution, and the output includes cooling parameters.

[0116] In some embodiments, the processor can train the cooling parameter determination layer based on the second sample data set.

[0117] The second sample data set includes second training samples and their corresponding second labels.

[0118] In some embodiments, the second training samples include the sample first content distribution of the sample raw gas, the sample gas characteristics of the sample first intermediate gas corresponding to the sample raw gas, and the sample dew point probability distribution. The second label is the cooling parameter corresponding to the sample first intermediate gas.

[0119] In some embodiments, the processor can set different cooling parameters through preliminary experiments. After actually producing nitrogen using the second intermediate gas cooled by different cooling parameters, determine the corresponding nitrogen purity and nitrogen production duration. Select historical data where the nitrogen purity reaches the target nitrogen purity requirement and the nitrogen production duration is lower than the preset duration, and use the first content distribution, dew point probability distribution, and gas characteristics corresponding to this historical data as the second training samples. Determine the corresponding cooling parameter as the second label.

[0120] The drying method determination layer refers to a model used to determine the drying method. In some embodiments, the drying method determination layer is a machine learning model. For example, a neural network model (Neural Networks, NN), etc.

[0121] The inputs of the drying method determination layer include the first content distribution, the sample gas characteristics of the first intermediate gas, the sample dew point probability distribution, and the cooling parameter, and the output includes the drying method.

[0122] In some embodiments, the processor can train the drying method determination layer based on the third sample dataset.

[0123] The third sample dataset includes third training samples and their corresponding third labels.

[0124] In some embodiments, the third training samples include the sample first content distribution of the sample raw gas, the sample gas characteristics of the sample first intermediate gas, the sample dew point probability distribution, and the sample cooling parameter. The third label is the drying method corresponding to the sample first intermediate gas.

[0125] In some embodiments, the processor can set different drying methods through preliminary experiments. After actually producing nitrogen using the second intermediate gas dried by different drying methods, the corresponding nitrogen purity and nitrogen production duration are determined. The historical data with the nitrogen purity reaching the target nitrogen purity requirement and the nitrogen production duration lower than the preset duration is selected, and the first content distribution, dew point probability distribution, gas characteristics, and cooling parameter corresponding to this historical data are used as the third training samples. The corresponding drying method is determined as the third label.

[0126] The drying parameter determination layer refers to a model used to determine the drying parameters. In some embodiments, the drying parameter determination layer is a machine learning model. For example, a neural network model (Neural Networks, NN), etc. For more content about the cooling parameter, reference can be made to the relevant description in step 250.

[0127] The inputs of the drying parameter determination layer include the first content distribution, the sample gas characteristics of the first intermediate gas, the sample dew point probability distribution, the cooling parameter, and the drying method, and the output includes the drying parameters.

[0128] In some embodiments, the processor can train the drying parameter determination layer based on the fourth sample dataset.

[0129] The fourth sample dataset includes fourth training samples and their corresponding fourth labels.

[0130] In some embodiments, the fourth training sample includes the sample first content distribution of the sample raw gas, the sample gas characteristics of the sample first intermediate gas, the sample dew point probability distribution, the sample cooling parameter, and the sample drying method. The fourth label is the drying parameter corresponding to the sample first intermediate gas.

[0131] In some embodiments, the processor can set different drying parameters through preliminary experiments. After actually producing nitrogen using the second intermediate gas dried with different drying parameters, determine the corresponding nitrogen purity and nitrogen production duration. Select historical data where the nitrogen purity meets the target nitrogen purity requirement and the nitrogen production duration is lower than the preset duration, and use the first content distribution, dew point probability distribution, gas characteristics, cooling parameter, and drying method corresponding to this historical data as the fourth training sample. Determine its corresponding drying parameter as the fourth label.

[0132] In some embodiments, the cooling parameter determination layer, the drying method determination layer, and the drying parameter determination layer can be trained separately or jointly. The training processes of the cooling parameter determination layer, the drying method determination layer, and the drying parameter determination layer are similar to the training process of the dew point prediction model. For the training processes of the cooling parameter determination layer, the drying method determination layer, and the drying parameter determination layer, reference can be made to the relevant descriptions of the training process of the dew point prediction model.

[0133] In some embodiments, the output of the cooling parameter determination layer can be used as the input of the drying method determination layer, and the output of the drying method determination layer can be used as the input of the drying parameter determination layer.

[0134] In some embodiments, the training samples for joint training include the sample first content distribution of the sample raw gas, the sample gas characteristics of the sample first intermediate gas, and the sample dew point probability distribution, and the label is the corresponding cooling parameter of the sample first intermediate gas in the training sample. The processor can input the sample first content distribution, the sample gas characteristics of the sample first intermediate gas, and the sample dew point probability distribution into the initial cooling parameter determination layer to obtain the cooling parameter output by the cooling parameter determination layer. Use the cooling parameter as the training sample, and input it together with the sample first content distribution, the sample gas characteristics of the sample first intermediate gas, and the sample dew point probability distribution into the initial drying method determination layer to obtain the drying method output by the drying method determination layer. Use the drying method as the training sample, and input it together with the sample first content distribution, the sample gas characteristics of the sample first intermediate gas, the sample dew point probability distribution, and the cooling parameter into the initial drying parameter determination layer to obtain the drying parameter output by the drying parameter determination layer. Construct a loss function based on the drying parameter and the label corresponding to the training sample, and according to the value of the loss function, reversely update the model parameters in the initial cooling parameter determination layer, the drying method determination layer, and the drying parameter determination layer to obtain the trained cooling parameter determination layer, drying method determination layer, and drying parameter determination layer.

[0135] In actual production, parameters such as the humidity, temperature, and pressure of the raw gas may change dynamically due to environmental changes or raw material fluctuations. The processor can predict the dew point corresponding to the first intermediate gas when cooling the first intermediate gas, and obtain the dew point probability distribution. When determining the cooling parameters and drying parameters subsequently, more robust cooling parameters and drying parameters can be obtained, improving the response ability of the nitrogen production control system to fluctuations in the composition and gas characteristics of the raw gas, thereby expanding the applicable range of the nitrogen production control system. At the same time, the dew point probability distribution can quantify the risks of different dew points occurring. For example, different oil contents in the raw gas may result in different dew points for the first intermediate gas. By considering the dew point probability distribution, redundant designs can be carried out for the cooling parameters and drying parameters, enhancing the ability of the designed cooling parameters and drying parameters to cope with risks, thereby effectively reducing the impact of sudden operating conditions during subsequent nitrogen production on process stability and ensuring the quality of nitrogen production.

[0136] Figure 4 is an exemplary flowchart showing the operation of the control recovery unit according to some embodiments of the present specification. As Figure 4 shown, process 400 includes the following steps. In some embodiments, process 400 can be executed by a processor.

[0137] Step 410, obtaining the local component characteristics of the separated gas from the third sensor unit group.

[0138] The separated gas refers to the remaining gas obtained by separating nitrogen from the second intermediate gas based on the gas production unit. In some embodiments, the separated gas may include methane (CH4), hydrogen (H2), carbon monoxide (CO), hydrogen sulfide (H2S), carbon dioxide (CO2), helium (He), etc.

[0139] For more information about the second intermediate gas, reference can be made to Figure 2 the relevant description.

[0140] The local component characteristics refer to the quantitative or qualitative information of some gas components in the separated gas. In some embodiments, the local component characteristics may include gas types, gas proportions, etc.

[0141] Merely by way of example, the local component characteristics of combustible gases such as methane (CH4) and hydrogen (H2) can be obtained based on semiconductor gas sensors.

[0142] Merely by way of example, the local component characteristics of gases such as carbon monoxide (CO), hydrogen sulfide (H2S), oxygen (O2), and nitrogen dioxide (NO2) can be obtained based on electrochemical sensors.

[0143] Merely by way of example, the local component characteristics of gases such as hydrogen (H2), helium (He), and carbon dioxide (CO2) can be obtained based on thermal conductivity sensors.

[0144] Step 420, predict the second content distribution of the separated gas based on the local component characteristics and the first content distribution of the original gas.

[0145] For more information about the original gas and the first content distribution, please refer to Figures 2 - 3 the relevant description.

[0146] The second content distribution refers to the gas components in the separated gas and the content distribution of different gases.

[0147] In some embodiments, the processor may construct a demand feature vector based on the local component characteristics of the separated gas and the first content distribution of the original gas, and based on the demand feature vector, predict the second content distribution of the separated gas through a third vector database.

[0148] In some embodiments, the third vector database includes multiple groups of reference demand feature vectors and their corresponding reference second content distributions. For example, the third vector database may construct reference demand feature vectors based on the first content distribution of the original gas and the corresponding local component characteristics of the separated gas in the historical production data, and use the actual second content distribution corresponding to the local component characteristics of the separated gas and the first content distribution of the original gas as the reference second content distribution corresponding to the reference demand feature vector.

[0149] In some embodiments, the processor may manually annotate the second content distribution based on partial local component characteristics and the first content distribution of the separated gas. The processor may also obtain the first content distribution of the original gas based on a preset table, then obtain the separated gas based on the nitrogen production operation, determine the local component characteristics of the separated gas based on sensors such as semiconductor gas sensors, electrochemical sensors, and thermal conductivity sensors, and then construct the local component characteristics and the first content distribution into a reference demand feature vector, and cluster it with the reference demand feature vector constructed based on the local component characteristics and the first content distribution with manual annotation. For each cluster obtained by clustering, use the second content distribution with the largest proportion as the reference second content distribution corresponding to all reference demand feature vectors in the cluster. For more information about the preset table, please refer to Figure 3 the relevant description.

[0150] In some embodiments, the processor may construct a target vector based on the current first content distribution and local component characteristics, select a reference demand feature vector that meets the preset requirements, and use its corresponding reference second content distribution as the second content distribution. The preset requirements may include that the vector similarity between the reference demand feature vector and the target vector is higher than a preset similarity threshold, etc. Among them, the vector similarity may be negatively correlated with the vector distance between the target vector and the reference demand feature vector, and the vector distance may be determined based on cosine distance, Euclidean distance, etc. The preset similarity threshold is set according to experience.

[0151] In some embodiments of the present specification, due to the high cost of manual annotation, by manually annotating some data and then annotating another part of the data based on clustering, the manual annotation cost can be reduced, and the vector database can be enriched, thereby improving the prediction accuracy of the second content distribution.

[0152] In some embodiments, the processor can also predict the second content distribution of the separated gas according to the local component characteristics and the first content distribution through a content prediction model.

[0153] The content prediction model refers to a model used to predict the second content distribution of the separated gas. In some embodiments, the content prediction model can be a machine learning model. For example, a Recurrent Neural Network (RNN).

[0154] In some embodiments, the input of the content prediction model can include local component characteristics and the first content distribution. In some embodiments, the output of the content prediction model can be the second content distribution.

[0155] In some embodiments, the content prediction model can be trained by multiple fifth training samples with fifth labels. Among them, each group of fifth training samples is the sample historical local component characteristics of the sample separated gas and the sample historical first content distribution of the sample original gas. The sample separated gas is the remaining gas after nitrogen production separation of the sample original gas, and the corresponding fifth label is the sample historical second content distribution of the sample separated gas.

[0156] The fifth training samples can be obtained based on experiments. In some embodiments, the sample historical first content distribution of the sample original gas and the sample separated gas can be obtained in advance based on a series of experiments, and semiconductor gas sensors, electrochemical sensors, and thermal conductivity sensors are used to determine the sample historical local component characteristics in the sample separated gas.

[0157] For more content on the sensor determining the sample historical local component characteristics in the sample separated gas, reference can be made to the relevant description above. In some embodiments, the processor can construct the fifth training samples based on the integration of the above-mentioned sensor data.

[0158] In some embodiments, the fifth label can be based on a gas chromatograph sensor detecting the sample separated gas, and the gas components and the content distribution of different gases in the obtained sample separated gas are used as the fifth label of the fifth training sample.

[0159] For more content on the training process of the content prediction model, reference can be made to Figure 3 the relevant description of the training process of the dew point prediction model in

[0160] In some embodiments, the inputs of the content prediction model may further include cooling parameters and drying parameters. For more information about the cooling parameters and drying parameters, reference can be made to Figure 2 the relevant description.

[0161] In some embodiments of the present specification, through the cooling parameters and drying parameters, they can be combined with the first content distribution, and the second content distribution can be deduced through chemical reactions and the like, thereby improving the prediction accuracy of the second content distribution.

[0162] Step 430, according to the second content distribution, determine whether it is necessary to recover and separate the gas.

[0163] In some embodiments, in response to the content of a specific gas (e.g., oxygen) in the second content distribution being not less than a preset threshold, the processor may determine that it is necessary to recover and separate the gas. Among them, the preset threshold can be set based on experiments. For example, in response to the oxygen content in the second content distribution being not less than 30%, the processor determines that it is necessary to recover and separate the gas.

[0164] Step 440, when it is necessary to recover and separate the gas, control the recovery unit to operate.

[0165] In some embodiments, in response to the need to recover and separate the gas, the processor may control the recovery unit to operate and recover and separate the gas.

[0166] For more information about the recovery unit, reference can be made to Figure 1 the relevant description.

[0167] In some embodiments of the present specification, through the recovery unit and the third sensing unit group, the separated gas can be recovered and processed, thereby realizing the sustainable utilization of nitrogen production resources and improving the nitrogen production efficiency.

[0168] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to the present specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to the present specification. Such modifications, improvements, and corrections are proposed in the present specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of the present specification.

[0169] Finally, it should be understood that the embodiments described in the present specification are only used to illustrate the principles of the embodiments of the present specification. Other deformations may also fall within the scope of the present specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of the present specification can be considered to be in agreement with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to the embodiments explicitly introduced and described in the present specification.

Claims

1. A nitrogen production control system, comprising an intake unit, a gas generation unit, and a processor, wherein the intake unit includes an intake channel, a first sensor unit group, a second sensor unit group, a compression device, a cooling device, and a drying device; The processor is configured to: Obtain the gas characteristics of the raw gas from the first sensor unit group; Generate compression parameters according to the gas characteristics of the raw gas; Control the compression device to process the raw gas according to the compression parameters to obtain a first intermediate gas; Obtain the gas characteristics of the first intermediate gas from the second sensor unit group; Generate cooling parameters and drying parameters according to the gas characteristics of the first intermediate gas; Control the cooling device and the drying device to process the first intermediate gas according to the cooling parameters and the drying parameters to obtain a second intermediate gas; The gas generation unit is configured to produce nitrogen based on the second intermediate gas.

2. The system according to claim 1, wherein The processor is further configured to: Determine the loss distribution; Generate the compression parameters based on the loss distribution and the gas characteristics of the raw gas.

3. The system according to claim 1, characterized in that, The processor is further configured to: Determine the first content distribution of the raw gas; Generate a dew point probability distribution according to the first content distribution and the gas characteristics of the first intermediate gas; Generate the cooling parameters and the drying parameters based on the first content distribution and the dew point probability distribution.

4. The system according to claim 1, characterized in that The system further includes a recovery unit and a third sensor unit group; The third sensor unit group is configured to collect the local component characteristics of the separated gas, and the recovery unit is configured to recover the separated gas; The processor is further configured to: Obtain the local component characteristics of the separated gas from the third sensor unit group; Predict the second content distribution of the separated gas based on the local component characteristics and the first content distribution of the raw gas; Judge whether it is necessary to recover the separated gas according to the second content distribution; When it is necessary to recover the separated gas, control the recovery unit to operate.

5. A nitrogen production regulation method, characterized in that, The method includes: Obtain the gas characteristics of the raw gas from the first sensor unit group; Generate compression parameters according to the gas characteristics of the raw gas; Control the compression device to process the raw gas according to the compression parameters to obtain a first intermediate gas; Obtain the gas characteristics of the first intermediate gas from the second sensor unit group; Generate cooling parameters and drying parameters according to the gas characteristics of the first intermediate gas; Control the cooling device and the drying device to process the first intermediate gas according to the cooling parameters and the drying parameters to obtain a second intermediate gas; Control the gas generation unit to produce nitrogen based on the second intermediate gas.

6. The method according to claim 5, wherein The generating compression parameters according to the gas characteristics of the raw gas includes: Determine the loss distribution; Generate the compression parameters based on the loss distribution and the gas characteristics of the raw gas.

7. The method according to claim 5, characterized in that, The generating cooling parameters and drying parameters according to the gas characteristics of the first intermediate gas includes: Determine the first content distribution of the raw gas; Generate a dew point probability distribution according to the first content distribution and the gas characteristics of the first intermediate gas; Generate the cooling parameter and the drying parameter based on the first content distribution and the dew point probability distribution.

8. The method according to claim 5, wherein The method further includes: Obtain the local component characteristics of the separated gas from the third sensing unit group; Predict the second content distribution of the separated gas based on the local component characteristics and the first content distribution of the original gas; Judge whether it is necessary to recover the separated gas according to the second content distribution; Control the operation of the recovery unit in response to the need to recover the separated gas.

9. A nitrogen production regulation device, comprising a processor, where the processor is used to execute the nitrogen production regulation method according to any one of claims 5 to 8.

10. A computer-readable storage medium, where the storage medium stores computer instructions, and when a computer reads the computer instructions in the storage medium, the computer executes the nitrogen production regulation method according to any one of claims 5 to 8.

Images