Air separation plant intelligent working condition adjusting system based on multi-point temperature and pressure monitoring

Abstract

The embodiment of the invention provides an air separation equipment intelligent working condition adjusting system based on multi-point temperature and pressure monitoring, relates to the technical field of air separation, and can realize automatic working condition adjustment of a purification system. The system includes: a plurality of internal temperature sensors; a plurality of internal pressure sensors; a regeneration data collection device which collects the internal temperature data and the internal pressure data and performs preprocessing; the reconstruction device is used for reconstructing a three-dimensional temperature field and a three-dimensional pressure field of the adsorber; the feature engineering device is used for extracting a three-dimensional temperature chromatography matrix and a three-dimensional pressure chromatography matrix of the adsorber; the working condition adjusting model is regenerated, the three-dimensional temperature chromatography matrix, the three-dimensional pressure chromatography matrix and the current working condition are calculated, and a working condition adjusting instruction is output; the main controller is used for sending out a working condition adjusting signal; the executing mechanism adjusts the working condition of the adsorber according to the working condition adjusting signal.

Description

Technical Field

[0001] The present invention relates to the technical field of air separation, and in particular, to an intelligent operating condition adjustment system for an air separation device based on multi-point temperature and pressure monitoring. Background Art

[0002] An air separation device can liquefy and rectify air, and finally separate it into oxygen, nitrogen and other useful gases, which is simply called an air separation device. Generally, a purification system is included in the air separation device to remove substances such as water, carbon dioxide, and hydrocarbons in the air output by the precooling system. Generally, two adsorbers are provided in the purification system, one is in the purification stage and the other is in the regeneration stage. The regeneration stage includes multiple regeneration working conditions. In the prior art, the working condition adjustment is generally performed by manual experience, which cannot guarantee the purification and regeneration performance of the purification system, thus affecting the final air separation quality. Summary of the Invention

[0003] In view of this, an embodiment of the present invention provides an intelligent operating condition adjustment system for an air separation device based on multi-point temperature and pressure monitoring, which can realize the automatic working condition adjustment of the purification system.

[0004] To achieve the above object, the present invention provides an intelligent operating condition adjustment system for an air separation device based on multi-point temperature and pressure monitoring.

[0005] The air separation device in the embodiment of the present invention includes: a purification system, the purification system includes: two adsorbers and an electric heater, and each adsorber is in the purification stage or the regeneration stage; the intelligent operating condition adjustment system for the air separation device includes: a plurality of internal temperature sensors arranged inside the two adsorbers; a plurality of internal pressure sensors fixed inside the two adsorbers; a regeneration data collection device that collects the internal temperature data and internal pressure data detected in real time by the internal temperature sensors in the adsorbers in the regeneration stage and performs preprocessing; a reconstruction device that reconstructs the three-dimensional temperature field of the adsorber according to the internal temperature data after preprocessing, and reconstructs the three-dimensional pressure field of the adsorber according to the internal pressure data after preprocessing; a feature engineering device that extracts the three-dimensional temperature tomography matrix of the adsorber from the three-dimensional temperature field, and extracts the three-dimensional pressure tomography matrix of the adsorber from the three-dimensional pressure field; a regeneration working condition adjustment model, which is a pre-trained machine learning model, calculates the input three-dimensional temperature tomography matrix, the three-dimensional pressure tomography matrix and the currently recorded working condition, and outputs a command to maintain the current working condition or a command to adjust the working condition; a main controller that sends out a working condition adjustment signal after receiving the adjustment working condition command; an actuator that adjusts the working condition of the adsorber in the regeneration stage according to the received working condition adjustment signal.

[0006] Preferably, the intelligent operating condition adjustment system of the air separation plant further includes: an inlet temperature sensor arranged at the inlet of the adsorber, an outlet temperature sensor and an outlet pressure sensor arranged at the outlet of the adsorber, a sensing data processing device in communication with the inlet temperature sensor, the outlet temperature sensor and the outlet pressure sensor, and a control confirmation device in communication with the sensing data processing device; after receiving the operating condition adjustment instruction, the main controller sends a request for operating condition adjustment confirmation to the control confirmation device, and the current operating condition identifier is carried in the request for operating condition adjustment confirmation; the control confirmation device receives the request for operating condition adjustment confirmation, determines whether the sensing data transmitted by the inlet temperature sensor, the outlet temperature sensor and the outlet pressure sensor meets the pre-configured necessary conditions for adjusting the current operating condition, and returns the determination result to the main controller; the main controller receives the determination result; if the determination result indicates that the necessary conditions for adjusting the current operating condition are met, an operating condition adjustment signal is sent; if the determination result indicates that the necessary conditions for adjusting the current operating condition are not met, an artificial intervention signal is sent to the management unit.

[0007] Preferably, after the actuator adjusts the operating condition of the adsorber in the regeneration stage according to the operating condition adjustment signal, the purification system operates according to the default operating parameters of the adjusted operating condition pre-configured; the default operating parameters include: the heating temperature of the electric heater, the blowing flow rate of the waste nitrogen gas from the cold box.

[0008] Preferably, after the actuator adjusts the operating condition of the adsorber in the regeneration stage according to the operating condition adjustment signal, a notice of adjustment completion is returned to the main controller, the main controller sends a notice of adjustment success to the regeneration operating condition adjustment model, and the regeneration operating condition adjustment model updates the record of the current operating condition locally.

[0009] Preferably, the intelligent operating condition adjustment system of the air separation device further includes: a working parameter regression model communicated with the regeneration operating condition adjustment model, where the working parameter regression model is a pre-trained machine learning regression model; the regeneration operating condition adjustment model calculates the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, and the current operating condition. If the calculation result matches the abnormal working mode pre-configured for the current operating condition, it sends a working parameter calculation request to the working parameter regression model; the working parameter calculation request carries the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, the current operating condition, and the matched abnormal working mode; the working parameter regression model outputs the target working parameters for coping with the abnormal working mode according to the received working parameter calculation request, and sends a working parameter update instruction carrying the target working parameters to the main controller; after receiving the working parameter update instruction, the main controller sends a parameter adjustment signal carrying the target working parameters to the actuator; the target working parameters include: the heating temperature of the electric heater, the blowing flow rate of the waste nitrogen gas; the actuator operates the purification system according to the target working parameters in the parameter adjustment signal, and returns a change completion notice to the main controller after the operation is completed; after receiving the change completion notice, the main controller returns a change success notice to the working parameter regression model; after receiving the change success notice, the working parameter regression model sends a working parameter update notice carrying the target working parameters to the regeneration operating condition adjustment model; the regeneration operating condition adjustment model calculates the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, the current operating condition, and the target working parameters to perform the operating condition adjustment judgment after the working parameter update.

[0010] Preferably, the intelligent operating condition adjustment system of the air separation device further includes: a plurality of humidity sensors fixed inside the adsorber; a plurality of adsorbate detection devices installed at different positions near the outlet of the adsorber; a purification data collection device that collects the internal temperature data detected in real time by the internal temperature sensor in the adsorber during the purification stage, the internal humidity data detected in real time by the humidity sensor, and the adsorbate front position data collected by the adsorbate detection device and performs preprocessing; a feature extraction device that splices the preprocessed internal temperature data, the internal humidity data, and the adsorbate front position data into purification features; a purification decision model, which is a machine learning model trained in advance, calculates the input purification features, and outputs a default working signal or an emergency switching signal; the emergency switching signal carries the remaining regeneration duration of the adsorber in the regeneration stage, and is used to indicate that the two adsorbers are switched between the purification stage and the regeneration stage within the remaining regeneration duration; a rearrangement device that communicates with the purification decision model and the regeneration operating condition adjustment model, and calculates the execution duration of each to-be-executed operating condition of the adsorber in the regeneration stage and the target working parameters of each to-be-executed operating condition in the emergency switching state according to the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, and current operating condition of the adsorber in the regeneration stage transmitted by the regeneration operating condition adjustment model, and the remaining regeneration duration transmitted by the purification decision model; generates an emergency switching instruction carrying the execution duration and the target working parameters and sends it to the main controller; after receiving the emergency switching instruction, the main controller sends the execution duration and the target working parameters in the emergency switching instruction to the actuator, so that the execution structure performs corresponding operations on the purification system; the main controller also sends an emergency switching notification carrying the execution duration and the target working parameters to the regeneration operating condition adjustment model, and the regeneration operating condition adjustment model calculates the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, current operating condition, the execution duration, and the target working parameters of the adsorber in the regeneration stage to perform the operating condition adjustment judgment in the emergency switching state.

[0011] Preferably, for the adsorber in the purification stage, the control confirmation device obtains the sensing data of the purified air collected by the outlet temperature sensor and the outlet pressure sensor, and judges whether the sensing data meets the design index; if it does not meet the design index, it sends an alarm signal to the main controller; after receiving the alarm signal, the main controller sends a high-temperature regeneration instruction to the actuator, so that the actuator changes the purification system to the high-temperature regeneration mode; the main controller also sends a high-temperature regeneration notification to the regeneration operating condition adjustment model, so that the regeneration operating condition adjustment model performs the operating condition adjustment judgment in the high-temperature regeneration mode.

[0012] Preferably, the feature engineering device cuts the three-dimensional temperature field into a plurality of parallel cross-sections, arranges the temperature values of each parallel cross-section into a temperature vector, and combines the temperature vectors of the plurality of parallel cross-sections into the three-dimensional temperature tomography matrix; the feature engineering device cuts the three-dimensional pressure field into a plurality of parallel cross-sections, arranges the pressure values of each parallel cross-section into a pressure vector, and combines the pressure vectors of the plurality of parallel cross-sections into the three-dimensional pressure tomography matrix.

[0013] Preferably, the operating conditions of the adsorber in the regeneration stage are, in sequence: pressure relief condition, heating condition, cold blow condition, pressurization condition, or, preparation for pressure relief condition, pressure relief condition, preparation for heating condition, heating condition, cold blow condition, preparation for pressurization condition, pressurization condition, preparation for switching condition, switching condition.

[0014] Preferably, the necessary condition for adjusting the pressure relief condition is that the air pressure at the outlet of the adsorber is less than the first pressure threshold; the necessary condition for adjusting the heating condition is that the air temperature at the outlet of the adsorber is greater than the first temperature threshold; the necessary condition for adjusting the cold blow condition is that the absolute value of the difference between the air temperatures at the outlet and inlet of the adsorber is less than the preset second temperature threshold; the necessary condition for adjusting the pressurization condition is that the air pressure at the outlet of the adsorber is greater than the second pressure threshold.

[0015] According to the technical solution of the present invention, one embodiment of the above invention has the following advantages or beneficial effects: It can accurately sense the working environment of the purification system and precisely calculate the timing of operating condition adjustment through sensor technology for multi-point temperature and pressure monitoring, automatic control technology, and artificial intelligence technology, avoiding the defects of relying on manual experience to adjust operating conditions, and contributing to the improvement of air separation quality and efficiency.

[0016] The further effects of the above non-conventional optional methods will be described in conjunction with specific embodiments below. Description of the Drawings

[0017] The drawings are used to better understand the present invention and do not constitute an improper limitation to the present invention. Among them: Figure 1 is a schematic diagram of the main components of the air separation equipment; Figure 2 is a schematic diagram of the structure of the intelligent operating condition adjustment system for the air separation equipment based on multi-point temperature and pressure monitoring of the present invention; Figure 3 is the first schematic diagram of the operating condition flow of the present invention; Figure 4 is the second schematic diagram of the operating condition flow of the present invention. Detailed Embodiments

[0018] The following describes exemplary embodiments of the present invention with reference to the accompanying drawings. Various details of the embodiments of the present invention are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness.

[0019] Figure 1 is a schematic diagram of the main components of an air separation plant, as Figure 1 shown, the air separation plant may include an air filter, an air compression system, a precooling system, a purification system, a heat exchange system, a turboexpander, a rectification system, etc. The functions of these parts are known technologies and will not be introduced here.

[0020] Figure 2 is a schematic diagram of the intelligent operating condition adjustment system of the air separation plant based on multi-point temperature and pressure monitoring of the present invention. Refer to Figure 2 .

[0021] In specific applications, the purification system in the air separation plant includes: two adsorbers and an electric heater. Each adsorber is in the purification stage or the regeneration stage and can be switched between the purification stage and the regeneration stage. The purification stage is used to adsorb adsorbates such as water, carbon dioxide, and hydrocarbons in the air to be treated, and the regeneration stage is used to restore the adsorption function of the adsorber adsorbed with adsorbates. The adsorber is generally a double-bed structure, with activated alumina in the lower layer and molecular sieve in the upper layer. The intelligent operating condition adjustment system of the air separation plant includes the following parts.

[0022] A plurality of internal temperature sensors are arranged inside the two adsorbers, and thermocouples, infrared thermal imagers, etc. can be used. A plurality of internal pressure sensors are fixed inside the two adsorbers, which can be barometric pressure sensors.

[0023] The regeneration data collection device is used to collect the internal temperature data and internal pressure data detected in real time by the internal temperature sensors in the adsorber during the regeneration stage and perform preprocessing such as data cleaning and standardization.

[0024] The reconstruction device is used to reconstruct the three-dimensional temperature field of the adsorber according to the internal temperature data after preprocessing, and reconstruct the three-dimensional pressure field of the adsorber according to the internal pressure data after preprocessing. In practical applications, the reconstruction device can perform the reconstruction of the three-dimensional temperature field and pressure field based on known data differences and reconstruction algorithms. More preferably, the reconstruction device can implement the above reconstruction based on a mature machine learning model to obtain a more accurate three-dimensional temperature field and pressure field model.

[0025] The feature engineering device is used to extract the three-dimensional temperature tomography matrix of the adsorber from the three-dimensional temperature field and extract the three-dimensional pressure tomography matrix of the adsorber from the three-dimensional pressure field. In the embodiment of the present invention, the feature engineering device cuts the three-dimensional temperature field into multiple parallel cross-sections, arranges the temperature values of each parallel cross-section into a temperature vector, and combines the temperature vectors of multiple parallel cross-sections into the three-dimensional temperature tomography matrix; the feature engineering device cuts the three-dimensional pressure field into multiple parallel cross-sections, arranges the pressure values of each parallel cross-section into a pressure vector, and combines the pressure vectors of multiple parallel cross-sections into the three-dimensional pressure tomography matrix.

[0026] The regeneration condition adjustment model is a pre-trained machine learning model, which can adopt a traditional classification model or a pre-trained large language model. The regeneration condition adjustment model is used to calculate the input three-dimensional temperature tomography matrix, the three-dimensional pressure tomography matrix and the currently recorded working condition, and output a maintain current condition instruction or an adjust condition instruction. The maintain current condition instruction indicates that no condition adjustment is required, and the adjust condition instruction indicates that an adjustment to the next condition needs to be executed. The main controller is used to send out a condition adjustment signal outward after receiving the adjust condition instruction, and the actuator can adjust the working condition of the adsorber in the regeneration stage according to the received condition adjustment signal. The above condition adjustment method of the regeneration condition adjustment model is the condition adjustment judgment logic in the default state.

[0027] Through the above steps, it is possible to realize the automatic adjustment of the working conditions of the purification system by using multi-point temperature and pressure sensing, automatic control technology and artificial intelligence technology, thereby improving the accuracy of condition adjustment. The temperature sensors and pressure sensors arranged inside the adsorber can capture more accurate real-time temperature and pressure data, and have better monitoring performance compared with the outlet sensing method in the prior art. In the above process, the reconstruction device is used to reconstruct the three-dimensional temperature field and three-dimensional pressure field models based on the monitored temperature and pressure data, and mature three-dimensional reconstruction machine learning models can be used to enrich the temperature data and pressure data, which helps to improve the condition classification performance of the regeneration condition adjustment model. Furthermore, the feature engineering device extracts a large amount of temperature and pressure distribution data from the three-dimensional model to form the three-dimensional temperature tomography matrix and three-dimensional pressure tomography matrix input into the model, ensuring the accuracy of model calculation.

[0028] See Figure 3 and Figure 4 , in one embodiment, there can be two cases for the working condition sequence of the adsorber in the regeneration stage. One is that the working conditions are in turn: pressure relief condition, heating condition, cold blow condition, pressurization condition. The other is that on the basis of the first one, a preparation condition and a switching condition are added, and the working conditions are in turn: preparation for pressure relief condition, pressure relief condition, preparation for heating condition, heating condition, cold blow condition, preparation for pressurization condition, pressurization condition, preparation for switching condition, switching condition.

[0029] As a preferred solution, the intelligent operating condition adjustment system of the air separation plant further includes: an inlet temperature sensor arranged at the inlet of the adsorber, an outlet temperature sensor and an outlet pressure sensor arranged at the outlet of the adsorber, a sensing data processing device communicating with the inlet temperature sensor, the outlet temperature sensor and the outlet pressure sensor, and a control confirmation device communicating with the sensing data processing device.

[0030] After receiving the operating condition adjustment instruction, the main controller sends a request for operating condition adjustment confirmation to the control confirmation device, and the current operating condition identifier is carried in the request for operating condition adjustment confirmation; the control confirmation device receives the request for operating condition adjustment confirmation, and judges whether the sensing data transmitted by the inlet temperature sensor, the outlet temperature sensor and the outlet pressure sensor meets the pre-configured adjustment necessary conditions for the current operating condition (i.e., the minimum conditions required to execute the operating condition adjustment), and returns the judgment result to the main controller; the main controller receives the judgment result; if the judgment result indicates that the adjustment necessary conditions for the current operating condition are met, it means that the calculation result of the regeneration operating condition adjustment model is correct, and then a signal for operating condition adjustment is sent; if the judgment result indicates that the adjustment necessary conditions for the current operating condition are not met, it means that the calculation result of the regeneration operating condition adjustment model may be incorrect, and then an artificial intervention signal is sent to the management unit. In this way, the main controller can use the control confirmation device and the external sensors connected thereto to perform a necessity check on the temperature and pressure at the inlet and outlet of the adsorber, thereby avoiding mistakes in control decisions and improving the reliability of the control system.

[0031] Exemplarily, the adjustment necessary conditions for the pressure relief operating condition are: the air pressure at the outlet of the adsorber is less than the first pressure threshold; the adjustment necessary conditions for the heating operating condition are: the air temperature at the outlet of the adsorber is greater than the first temperature threshold; the adjustment necessary conditions for the cold blow operating condition are: the absolute value of the difference between the air temperature at the outlet and the inlet of the adsorber is less than the preset second temperature threshold; the adjustment necessary conditions for the pressurization operating condition are: the air pressure at the outlet of the adsorber is greater than the second pressure threshold.

[0032] Preferably, after the actuator adjusts the operating condition of the adsorber in the regeneration stage according to the operating condition adjustment signal, the purification system operates according to the default operating parameters of the adjusted operating condition pre-configured; the default operating parameters may include: the heating temperature of the electric heater, the blowing flow rate of the waste nitrogen gas from the cold box.

[0033] In one embodiment, after the actuator adjusts the operating condition of the adsorber in the regeneration stage according to the operating condition adjustment signal, it returns a notice of adjustment completion to the main controller, the main controller returns a notice of adjustment success to the regeneration operating condition adjustment model, and the regeneration operating condition adjustment model updates the record of the current operating condition locally for subsequent calculations.

[0034] In an embodiment of the present invention, the intelligent operating condition adjustment system of the air separation plant further includes: a working parameter regression model in communication with the regeneration operating condition adjustment model, where the working parameter regression model is a machine learning regression model pre-trained, which can be a traditional regression model or a pre-trained large language model.

[0035] The regeneration operating condition adjustment model calculates the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, and the current operating condition. If the calculation result matches an abnormal operating mode pre-configured for the current operating condition (such as a low-temperature mode occurring during the heating operation), it sends a working parameter calculation request to the working parameter regression model; the working parameter calculation request carries the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, the current operating condition, and the matching abnormal operating mode. The working parameter regression model regresses and calculates the target working parameters for dealing with the abnormal operating mode according to the received working parameter calculation request, and sends a working parameter update instruction carrying the target working parameters to the master controller; after receiving the working parameter update instruction, the master controller sends a parameter adjustment signal carrying the target working parameters to the actuator; the target working parameters include: the heating temperature of the electric heater, the blowing flow rate of the waste nitrogen gas. The actuator operates the purification system according to the target working parameters in the parameter adjustment signal, and returns a change completion notice to the master controller after the operation is completed; after receiving the change completion notice, the master controller returns a change success notice to the working parameter regression model; after receiving the change success notice, the working parameter regression model sends a working parameter update notice carrying the target working parameters to the regeneration operating condition adjustment model; the regeneration operating condition adjustment model calculates the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, the current operating condition, and the target working parameters to execute the operating condition adjustment judgment logic after the working parameter update. Through the above steps, the regeneration operating condition adjustment model can detect the abnormal mode, the working parameter regression model can execute the update calculation of the working parameters, and the master controller can drive the update of the working parameters, so as to realize the dynamic update of the working parameters during the operating condition maintenance process, which is beneficial to optimizing the operation process and operation quality through the change of the working parameters. The above operating condition adjustment method of the regeneration operating condition adjustment model is to execute the operating condition adjustment judgment logic after the working parameter update, which is different from the operating condition adjustment judgment logic in the default state.

[0036] In an alternative technical solution, the intelligent operating condition adjustment system of the air separation plant of the present invention further includes: a plurality of humidity sensors fixed inside the adsorber, and a plurality of adsorbate detection devices installed at different positions near the outlet of the adsorber, and also includes the following parts.

[0037] The purified data collection device is used to collect the internal temperature data detected in real time by the internal temperature sensor in the adsorber during the purification stage, the internal humidity data detected in real time by the humidity sensor, and the adsorbate front position data collected by the adsorbate detection device and perform preprocessing; the above front refers to the front end face where the adsorbate arrives (i.e., the end face closest to the adsorber outlet). The feature extraction device is used to splice the preprocessed internal temperature data, internal humidity data, and adsorbate front position data into purified features. The purification decision model is a pre-trained machine learning model, which is used to calculate the input purified features and output a default working signal or an emergency switching signal. The default working signal indicates that no emergency treatment needs to be performed, and the emergency switching signal indicates that it is in an emergency switching state and the adsorber needs to be switched between the purification stage and the regeneration stage within a short time. The remaining regeneration duration of the adsorber in the regeneration stage is carried in the emergency switching signal, which is used to indicate the switching between the purification stage and the regeneration stage of the two adsorbers within the remaining regeneration duration.

[0038] The rearrangement device communicates with the purification decision model and the regeneration condition adjustment model. It can calculate the execution duration of each to-be-executed condition of the adsorber in the regeneration stage and the target working parameters of each to-be-executed condition in the emergency switching state according to the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix and current condition of the adsorber in the regeneration stage transmitted by the regeneration condition adjustment model, and the remaining regeneration duration transmitted by the purification decision model; generate an emergency switching instruction carrying the execution duration and the target working parameters and send it to the main controller. The rearrangement device can be implemented by using traditional algorithms or machine learning models.

[0039] After receiving the emergency switching instruction, the main controller sends the execution duration and the target working parameters in the emergency switching instruction to the actuator, so that the execution structure performs corresponding operations on the purification system; the main controller also sends an emergency switching notice carrying the execution duration and the target working parameters to the regeneration condition adjustment model, and the regeneration condition adjustment model calculates the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, current condition, the execution duration and the target working parameters of the adsorber in the regeneration stage to execute the condition adjustment judgment logic in the emergency switching state. The condition adjustment judgment logic in the emergency switching state is different from the condition adjustment judgment logic in the default state.

[0040] Through the above steps, for the adsorber in the purification stage, sensors inside the adsorber can be used to monitor emergency situations such as high temperature (which can cause a serious decline in adsorption capacity and result in impurities in the output gas), high humidity (which can cause irreversible damage to the molecular sieve), and adsorbate breakthrough (i.e., the adsorbate approaches the outlet of the adsorber). The rearrangement device calculates the execution duration of each working condition for response (usually shortening the duration of each working condition) and the working parameters, and finally the main controller drives the implementation, so as to complete the regeneration of the adsorber and the stage switch within a short time, and effectively respond to the above emergency situations. Correspondingly, the regeneration working condition adjustment model executes the working condition adjustment judgment logic in the emergency switch state, and generally completes the working condition adjustment according to the execution duration of each working condition calculated by the rearrangement device.

[0041] In addition, in the embodiment of the present invention, for the adsorber in the purification stage, the control confirmation device acquires the sensing data of the purified air collected by the outlet temperature sensor and the outlet pressure sensor, and judges whether the sensing data meets the design index; if it does not meet the design index, it sends an alarm signal to the main controller; after receiving the alarm signal, the main controller sends a high-temperature regeneration instruction to the actuator, so that the actuator changes the purification system to the high-temperature regeneration mode; the main controller also sends a high-temperature regeneration notice to the regeneration working condition adjustment model, so that the regeneration working condition adjustment model executes the working condition adjustment judgment in the high-temperature regeneration mode. The above high-temperature regeneration mode has higher regeneration intensity and efficiency compared with the conventional regeneration mode. In the above process, if the outlet sensor monitors that the purified gas does not meet the design index (such as the existence of free water, unqualified temperature, etc.), it means that the conventional regeneration model cannot meet the operation requirements, then the high-temperature regeneration model is started to improve the purification and regeneration quality. At this time, the regeneration working condition adjustment model can execute the working condition adjustment judgment logic in the high-temperature regeneration mode. In practical applications, in addition to executing the working condition adjustment judgment logic in the default state, the regeneration working condition adjustment model can also execute the working condition adjustment judgment logic after the working parameters are updated, the working condition adjustment judgment logic in the emergency switch state, and the working condition adjustment judgment logic in the high-temperature regeneration mode.

[0042] In the technical solution of the present invention, through the sensor technology of multi-point temperature and pressure monitoring, automatic control technology and artificial intelligence technology, the working environment of the purification system can be accurately sensed and the timing of working condition adjustment can be accurately calculated, avoiding the defects of relying on manual experience to adjust the working conditions, and contributing to the improvement of air separation quality and efficiency.

[0043] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent operating condition adjustment system for an air separation plant based on multi-point temperature and pressure monitoring, the air separation plant comprising: Purification system, the purification system includes: two adsorbers and an electric heater, each adsorber being in a purification stage or a regeneration stage; characterized in that, the intelligent operating condition adjustment system of the air separation equipment includes: A plurality of internal temperature sensors arranged inside the two adsorbers; A plurality of internal pressure sensors fixed inside the two adsorbers; A regeneration data collection device that collects the internal temperature data detected in real time by the internal temperature sensors and the internal pressure data detected in real time by the internal pressure sensors in the adsorbers during the regeneration stage and performs preprocessing; A reconstruction device that reconstructs the three-dimensional temperature field of the adsorber based on the internal temperature data after preprocessing, and reconstructs the three-dimensional pressure field of the adsorber based on the internal pressure data after preprocessing; A feature engineering device that extracts the three-dimensional temperature tomography matrix of the adsorber from the three-dimensional temperature field, and extracts the three-dimensional pressure tomography matrix of the adsorber from the three-dimensional pressure field; A regeneration operating condition adjustment model, which is a pre-trained machine learning model, calculates the input three-dimensional temperature tomography matrix, the three-dimensional pressure tomography matrix, and the pre-recorded current operating condition, and outputs a maintain current operating condition instruction or an adjustment operating condition instruction; A main controller that sends out an operating condition adjustment signal after receiving the adjustment operating condition instruction; An actuator that adjusts the operating condition of the adsorber in the regeneration stage according to the received operating condition adjustment signal.

2. The intelligent operating condition adjustment system for the air separation plant according to claim 1, characterized in that It further includes: An inlet temperature sensor arranged at the inlet of the adsorber, an outlet temperature sensor and an outlet pressure sensor arranged at the outlet of the adsorber, a sensing data processing device in communication with the inlet temperature sensor, the outlet temperature sensor and the outlet pressure sensor, and a control confirmation device in communication with the sensing data processing device; After receiving the adjustment operating condition instruction, the main controller sends a working condition adjustment confirmation request to the control confirmation device, and the current working condition identifier is carried in the working condition adjustment confirmation request; The control confirmation device receives the working condition adjustment confirmation request, judges whether the sensing data transmitted by the inlet temperature sensor, the outlet temperature sensor and the outlet pressure sensor meets the pre-configured adjustment necessary conditions for the current working condition, and returns the judgment result to the main controller; The main controller receives the judgment result; if the judgment result indicates that the adjustment necessary conditions for the current working condition are met, an operating condition adjustment signal is sent; If the judgment result indicates that the adjustment necessary conditions for the current working condition are not met, an artificial intervention signal is sent to the management unit.

3. The intelligent operating condition adjustment system for the air separation equipment according to claim 2, characterized in that, After the actuator adjusts the operating condition of the adsorber in the regeneration stage according to the operating condition adjustment signal, the purification system operates according to the default working parameters of the adjusted operating condition; The default working parameters include: the heating temperature of the electric heater, the blowing flow rate of the waste nitrogen gas from the cold box.

4. The intelligent operating condition adjustment system for the air separation plant according to claim 3, wherein After the actuator adjusts the operating condition of the adsorber in the regeneration stage according to the operating condition adjustment signal, it returns an adjustment completion notice to the main controller, the main controller returns an adjustment success notice to the regeneration operating condition adjustment model, and the regeneration operating condition adjustment model locally updates the record of the current operating condition.

5. The intelligent operating condition adjustment system for the air separation equipment according to claim 4, characterized in that, It further includes: A working parameter regression model communicating with the regeneration condition adjustment model, where the working parameter regression model is a pre-trained machine learning regression model; The regeneration condition adjustment model calculates the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, and the current working condition. If the calculation result matches an abnormal working mode pre-configured for the current working condition, it sends a working parameter calculation request to the working parameter regression model; the working parameter calculation request carries the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, the current working condition, and the matched abnormal working mode; The working parameter regression model outputs target working parameters for coping with the abnormal working mode according to the received working parameter calculation request, and sends a working parameter update instruction carrying the target working parameters to the main controller; after receiving the working parameter update instruction, the main controller sends a parameter adjustment signal carrying the target working parameters to the actuator; the target working parameters include: the heating temperature of the electric heater, the blowing-in flow rate of the waste nitrogen gas; The actuator operates the purification system according to the target working parameters in the parameter adjustment signal, and returns a change completion notice to the main controller after the operation is completed; after receiving the change completion notice, the main controller returns a change success notice to the working parameter regression model; after receiving the change success notice, the working parameter regression model sends a working parameter update notice carrying the target working parameters to the regeneration condition adjustment model; the regeneration condition adjustment model calculates the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, the current working condition, and the target working parameters to perform the working condition adjustment judgment after the working parameter update.

6. The intelligent operating condition adjustment system for air separation equipment according to claim 5, wherein It also includes: Multiple humidity sensors fixed inside the adsorber; Multiple adsorbate detection devices installed at different positions near the outlet of the adsorber; A purification data collection device that collects the internal temperature data detected in real time by the internal temperature sensor in the adsorber during the purification stage, the internal humidity data detected in real time by the humidity sensor, and the adsorbate front position data collected by the adsorbate detection device and performs preprocessing; A feature extraction device that splices the preprocessed internal temperature data, internal humidity data, and adsorbate front position data into purification features; A purification decision model, which is a pre-trained machine learning model, calculates the input purification features, and outputs a default working signal or an emergency switching signal; the emergency switching signal carries the remaining regeneration duration of the adsorber in the regeneration stage, and is used to indicate to switch between the purification stage and the regeneration stage for the two adsorbers within the remaining regeneration duration; The rearrangement device communicates with the purification decision-making model and the regeneration condition adjustment model, calculates the execution duration of each to-be-executed condition of the adsorber in the regeneration stage and the target working parameters of each to-be-executed condition in the emergency switching state according to the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix and current condition of the adsorber in the regeneration stage transmitted by the regeneration condition adjustment model, and the remaining regeneration duration transmitted by the purification decision-making model; Generates an emergency switching instruction carrying the execution duration and the target working parameters and sends it to the master controller; After receiving the emergency switching instruction, the master controller sends the execution duration and the target working parameters in the emergency switching instruction to the actuator, so that the actuator performs corresponding operations on the purification system; the master controller also sends an emergency switching notice carrying the execution duration and the target working parameters to the regeneration condition adjustment model, and the regeneration condition adjustment model calculates the current three-dimensional temperature tomography matrix, three-dimensional pressure tomography matrix, current condition, the execution duration and the target working parameters of the adsorber in the regeneration stage to perform the condition adjustment judgment in the emergency switching state.

7. The intelligent operating condition adjustment system for the air separation equipment according to claim 6, characterized in that, For the adsorber in the purification stage, the control confirmation device acquires the sensing data of the purified air collected by the outlet temperature sensor and the outlet pressure sensor, and judges whether the sensing data meets the design indexes; If it does not meet the design indexes, sends an alarm signal to the master controller; After receiving the alarm signal, the master controller sends a high-temperature regeneration instruction to the actuator, so that the actuator changes the purification system to the high-temperature regeneration mode; the master controller also sends a high-temperature regeneration notice to the regeneration condition adjustment model, so that the regeneration condition adjustment model performs the condition adjustment judgment in the high-temperature regeneration mode.

8. The intelligent operating condition adjustment system for the air separation equipment according to claim 7, characterized in that The feature engineering device cuts the three-dimensional temperature field into multiple parallel cross-sections, arranges the temperature values of each parallel cross-section into a temperature vector, and combines the temperature vectors of multiple parallel cross-sections into the three-dimensional temperature tomography matrix; The feature engineering device cuts the three-dimensional pressure field into multiple parallel cross-sections, arranges the pressure values of each parallel cross-section into a pressure vector, and combines the pressure vectors of multiple parallel cross-sections into the three-dimensional pressure tomography matrix.

9. The intelligent operating condition adjustment system for the air separation equipment according to claim 2, characterized in that, The working conditions of the adsorber in the regeneration stage are in turn: pressure relief condition, heating condition, cold blow condition, pressurization condition, or, preparation for pressure relief condition, pressure relief condition, preparation for heating condition, heating condition, cold blow condition, preparation for pressurization condition, pressurization condition, preparation for switching condition, switching condition.

10. The intelligent operating condition adjustment system for air separation equipment according to claim 9, wherein, The necessary condition for adjusting the pressure relief condition is that the air pressure at the outlet of the adsorber is less than the first pressure threshold; the necessary condition for adjusting the heating condition is that the air temperature at the outlet of the adsorber is greater than the first temperature threshold; the necessary condition for adjusting the cold blow condition is that the absolute value of the difference between the air temperature at the outlet and the inlet of the adsorber is less than the preset second temperature threshold; the necessary condition for adjusting the pressurization condition is that the air pressure at the outlet of the adsorber is greater than the second pressure threshold.

Images