Countercurrent extraction unit operation management and control system and method based on artificial intelligence

Abstract

The invention discloses a countercurrent extraction unit operation management and control system and method based on artificial intelligence, and relates to the technical field of countercurrent extraction unit operation management and control, and the method comprises the following steps: detecting the operation data and key parameters of a countercurrent extraction unit; based on the historical operation data and the key parameters, analyzing an optimal proportion between different operation data; performing intelligent control on the countercurrent extraction unit based on the optimal proportion; the method is used for solving the problem that the maximum extraction efficiency cannot be kept in real time due to the fact that an existing countercurrent extraction unit operation management and control technology depends too much on manual management and control and cannot balance different parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of countercurrent extraction unit operation control, and in particular to an artificial intelligence-based countercurrent extraction unit operation control system and method. Background Art

[0002] Countercurrent extraction unit operation control technology refers to the monitoring, adjustment and control of key parameters and operating conditions during the countercurrent extraction process to ensure the efficient operation of the extraction process, maximize the extraction efficiency, and ensure the stability and consistency of product quality. This technology aims to optimize the extraction process, improve production efficiency, reduce production costs, and ensure that the product meets the specified standards.

[0003] Existing countercurrent extraction unit operation control technology is usually manually controlled, by manually setting a series of parameters such as feed flow rate, circulation flow rate, heating temperature and system pressure. Different parameters influence each other and have an impact on the extraction efficiency. Therefore, how to balance different parameters to maximize the extraction efficiency, and the existing countercurrent extraction unit operation control technology cannot automatically control them based on the influence between different parameters, so the extraction efficiency cannot reach the maximum in real time. The existing countercurrent extraction unit operation control technology also has the problem of over-reliance on manual control and inability to balance different parameters, resulting in the inability to maintain the maximum extraction efficiency in real time. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the prior art to at least a certain extent, by detecting the operating data and key parameters of the countercurrent extraction unit, and then normalizing the operating data and key parameters based on the historical operating data and key parameters to obtain historical normalized data, grouping the historical operating data and key parameters based on the historical normalized data to obtain different historical data groups, and then analyzing the optimal ratio between the feed flow rate and the circulation flow rate based on the historical data group and the historical normalized data, and at the same time analyzing the optimal ratio between the heating temperature and the system pressure based on the historical data group and the historical normalized data, and then analyzing the relationship between the feed flow rate and the heating temperature based on the historical data group and the historical normalized data, and finally intelligently controlling the countercurrent extraction unit based on the optimal ratio, so as to solve the problem that the existing countercurrent extraction unit operation control technology is still too dependent on manual control and cannot balance different parameters, resulting in the inability to maintain the maximum extraction efficiency in real time.

[0005] To achieve the above objectives, in a first aspect, the present application provides an artificial intelligence-based countercurrent extraction unit operation control method, comprising the following steps: Test the operating data and key parameters of the countercurrent extraction unit; Analyze the optimal ratio between different operating data based on historical operating data and key parameters; Intelligent control of the countercurrent extraction unit based on the optimal ratio.

[0006] Furthermore, the operating data includes feed flow rate, circulation flow rate, heating temperature and system pressure, and the key parameter is extraction efficiency.

[0007] Further, analyzing the optimal ratio between different operating data based on historical operating data and key parameters includes the following sub-steps: Normalizing the operating data and key parameters based on historical operating data and key parameters to obtain historical normalized data; The historical operation data and key parameters are grouped based on the historical normalized data to obtain different historical data groups; Analyzing the optimal ratio between the feed flow rate and the circulation flow rate based on the historical data set and the historical normalized data; Analyze the optimal ratio between heating temperature and system pressure based on historical data groups and historical normalized data; The relationship between feed flow rate and heating temperature is analyzed based on the historical data set and the historical normalized data.

[0008] Furthermore, normalizing the operating data and the key parameters based on the historical operating data and the key parameters to obtain the historical normalized data includes the following sub-steps: Acquire historical data of the operation data and mark them as historical operation data, wherein the historical operation data also includes key parameters, and mark the feed flow rate, circulation flow rate, heating temperature, system pressure and extraction efficiency in the historical operation data as HF, HC, HT, HP and HE respectively; Get the minimum and maximum values ​​of HT, marked as HT min and HT max ; Get the minimum and maximum values ​​of HP, marked as HP min HP max ; Get the minimum and maximum values ​​of HE, marked as HE respectively min and HE max ; By normalizing the formula Calculate the normalized index of different operation history data, where R represents any one of HT, HP and HE, and RN, namely HTN, HPN and HEN, represent the HT normalized index, HP normalized index and HE normalized index respectively; Integrate HF, HC, HTN, HPN and HEN into historical normalized data.

[0009] Furthermore, grouping the historical operating data and key parameters based on the historical normalized data to obtain different historical data groups includes the following sub-steps: The historical data group includes a historical flow rate data group and a historical temperature and pressure data group; For any two historical normalized data, if the HF normalized index is equal and the HC normalized index is equal, they are classified as the same historical temperature and pressure data group; For any two historical normalized data, if the HP normalized index is equal and the HE normalized index is equal, they are classified into the same historical flow rate data group.

[0010] Further, analyzing the optimal ratio between the feed flow rate and the circulation flow rate based on the historical data set and the historical normalized data includes the following sub-steps: For any historical flow rate data group, calculate the average value of HEN, mark it as the average flow rate efficiency, find the historical flow rate data group with the largest average flow rate efficiency, and mark it as the reference flow rate data group; For the historical normalized data in the reference velocity data group, HF / HC is calculated, and the calculation result is marked as the velocity data ratio, and each velocity data ratio corresponds to a HEN; A plane rectangular coordinate system is established with the velocity data ratio as the X-axis and HEN as the Y-axis, named as the velocity ratio analysis chart, and the velocity data ratio and the corresponding HEN are entered into the velocity ratio analysis chart; Performing polynomial regression on the flow rate ratio analysis graph, and marking the curve obtained by the polynomial regression as a flow rate efficiency distribution curve; Find the highest point on the flow rate efficiency distribution curve, mark it as the flow rate best efficiency point, and mark the flow rate data ratio corresponding to the flow rate best efficiency point on the X-axis as the flow rate best ratio.

[0011] Further, analyzing the optimal ratio between the heating temperature and the system pressure based on the historical data set and the historical normalized data includes the following sub-steps: For any historical temperature and pressure data set, calculate the average value of HEN, mark it as the average temperature and pressure efficiency, find the historical temperature and pressure data set with the largest average temperature and pressure efficiency, and mark it as the reference temperature and pressure data set; For the historical normalized data in the reference temperature and pressure data set, HTN / HPN is calculated and the calculation result is marked as the temperature and pressure data ratio. Each temperature and pressure data ratio corresponds to a HEN. A plane rectangular coordinate system is established with the temperature-pressure data ratio as the X-axis and HEN as the Y-axis, named as the temperature-pressure ratio analysis diagram, and the temperature-pressure data ratio and the corresponding HEN are entered into the temperature-pressure ratio analysis diagram; Perform polynomial regression on the temperature-pressure ratio analysis graph, and mark the curve obtained by the polynomial regression as the temperature-pressure efficiency distribution curve; Find the highest point on the temperature-pressure efficiency distribution curve, mark it as the temperature-pressure optimal efficiency point, and mark the temperature-pressure data ratio corresponding to the temperature-pressure optimal efficiency point on the X-axis as the temperature-pressure optimal ratio.

[0012] Further, analyzing the relationship between the feed flow rate and the heating temperature based on the historical data set and the historical normalized data includes the following sub-steps: The historical data groups are numbered by the symbol G i Indicates, where i is a non-zero natural number and i is the serial number of G. i , find the HF and HTN in the historical normalized data with the largest HEN, and mark them as F i and TN i ; F i is the horizontal axis, TN i Establish a plane rectangular coordinate system for the vertical axis, named the velocity-temperature relationship diagram, and set F i and TN i Enter the flow rate temperature relationship diagram; A polynomial regression is performed on the flow velocity-temperature relationship diagram, and the function obtained by the polynomial regression is named the flow velocity-temperature relationship function.

[0013] Furthermore, intelligent control of the countercurrent extraction unit based on the optimal ratio includes the following sub-steps: Get the feed flow rate set by the user, marked as the target flow rate, represented by the symbol V; The optimal ratio of flow rate is represented by A, and the optimal ratio of temperature and pressure is represented by B; Calculate V / HC=A, solve HC, and get the optimal value of the circulation flow rate, which is marked as the optimal circulation flow rate; Substitute V into the velocity-temperature relationship function and mark the result obtained as the optimal normalized temperature, expressed as TZ. Solve for HT, which is marked as the optimal heating temperature; Calculate TZ / HP=B, solve HP, and get the optimal value of system pressure, marked as the optimal normalized pressure, expressed as PZ, through the formula Solve for HP, which is marked as the optimal pressure of the system; After the user sets the target flow rate, the circulation flow rate is automatically set to the optimal circulation flow rate, the heating temperature is automatically set to the optimal heating temperature, and the system pressure is automatically set to the optimal system pressure.

[0014] In a second aspect, the present application provides an artificial intelligence-based countercurrent extraction unit operation control system, including a data monitoring module, an optimal ratio analysis module and an intelligent control module; the data monitoring module and the intelligent control module are respectively connected to the optimal ratio analysis module data; The data monitoring module is used to detect the operating data and key parameters of the countercurrent extraction unit; The optimal ratio analysis module is used to analyze the optimal ratio between different operating data based on historical operating data and key parameters; The intelligent management and control module is used to intelligently manage the countercurrent extraction unit based on the optimal ratio.

[0015] The beneficial effects of the present invention are as follows: the operation data and key parameters of the countercurrent extraction unit are detected, and then the operation data and key parameters are normalized based on the historical operation data and key parameters to obtain historical normalized data, and the historical operation data and key parameters are grouped based on the historical normalized data to obtain different historical data groups. The advantage is that there are a variety of data in the countercurrent extraction unit that need to be managed, and the units and definitions of different operation data are different, so they cannot be directly used for comparison and analysis. Therefore, the operation data are unified into historical normalized data for de-outlining and quantity extraction through normalization processing, and then they are grouped, which is convenient for subsequent proportional analysis, thereby improving the rationality and effectiveness of the operation control of the countercurrent extraction unit; The present invention analyzes the optimal ratio between the feed flow rate and the circulation flow rate based on the historical data group and the historical normalized data, analyzes the optimal ratio between the heating temperature and the system pressure based on the historical data group and the historical normalized data, and then analyzes the relationship between the feed flow rate and the heating temperature based on the historical data group and the historical normalized data. Finally, the countercurrent extraction unit is intelligently controlled based on the optimal ratio. The advantage is that the optimal ratio and relationship between different operating data are analyzed, and then the optimal ratio and relationship are used to balance the different operating data in the operation control, so that the extraction efficiency is always kept at the maximum, thereby improving the effectiveness and efficiency of the operation control of the countercurrent extraction unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a functional block diagram of the system of the present invention; Figure 2 It is the flow rate ratio analysis diagram of the present invention; Figure 3 It is a temperature-pressure ratio analysis diagram of the present invention; Figure 4 It is the flow rate temperature relationship diagram of the present invention; Figure 5 The figure is a flow chart of the steps of the method of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1, please refer to Figure 1 As shown, the present application provides an artificial intelligence-based countercurrent extraction unit operation control system, including a data monitoring module, an optimal ratio analysis module and an intelligent control module; the data monitoring module and the intelligent control module are respectively connected to the optimal ratio analysis module data; The data monitoring module is used to detect the operating data and key parameters of the countercurrent extraction unit; the operating data include feed flow rate, circulation flow rate, heating temperature and system pressure, and the key parameter is extraction efficiency; In practical applications, the operating data is the data required to control the countercurrent extraction unit, which is usually set manually. The present embodiment aims to provide an intelligent and efficient control method for the management of the operating data, and to ensure that the extraction efficiency is always at the maximum value during the management process.

[0019] The optimal ratio analysis module is used to analyze the optimal ratio between different operating data based on historical operating data and key parameters; the optimal ratio analysis module includes a data normalization unit, a historical grouping unit, a flow rate analysis unit, a temperature and pressure analysis unit, and a flow rate and temperature analysis unit; The data normalization unit is used to normalize the operation data and key parameters based on the historical operation data and key parameters to obtain historical normalized data; The data normalization unit is configured with a data normalization strategy, which includes: Acquire historical data of the operation data and mark them as operation history data, the operation history data also includes key parameters, and mark the feed flow rate, circulation flow rate, heating temperature, system pressure and extraction efficiency in the operation history data as HF, HC, HT, HP and HE respectively; Get the minimum and maximum values ​​of HT, marked as HT min and HT max ; Get the minimum and maximum values ​​of HP, marked as HP min HP max ; Get the minimum and maximum values ​​of HE, marked as HE respectively min and HE max ; By normalizing the formula Calculate the normalized index of different operation history data, where R represents any one of HT, HP and HE, and RN, namely HTN, HPN and HEN, represent the HT normalized index, HP normalized index and HE normalized index respectively; Integrate HF, HC, HTN, HPN and HEN into historical normalized data; In actual applications, since the amount of historical data is too large, it is not convenient to display it in detail in this embodiment. Therefore, this embodiment only displays the obtained values ​​to promote the analysis process of this embodiment. Taking the heating temperature HT as an example, the HT is obtained. min and HT max 40℃ and 60℃ respectively. For any piece of operation history data, assuming that its HT is 45℃, the HT normalization index HTN is calculated to be 0.25. HT, HP and HE in each piece of operation history data are calculated and converted into HTN, HPN and HEN. Finally, HF, HC, HTN, HPN and HEN form a piece of historical normalization data. Since HF and HC are both flow rates, the units and meanings are the same, so there is no need for normalization. The historical grouping unit is used to group historical operation data and key parameters based on historical normalized data to obtain different historical data groups; The history grouping unit is configured with a history grouping strategy, which includes: The historical data group includes a historical flow rate data group and a historical temperature and pressure data group; For any two historical normalized data, if the HF normalized index is equal and the HC normalized index is equal, they are classified as the same historical temperature and pressure data group; For any two historical normalized data, if the HP normalized index is equal and the HE normalized index is equal, they are classified as the same historical flow rate data group; In practical applications, some historical normalized data in Table 1 are taken as an example: Table 1 Some historical normalized data

[0020] This embodiment only takes the determination process of the historical flow rate data group as an example to illustrate the historical grouping strategy, and only considers the HTN and HPN in Table 1, so HF, HC and HEN do not show specific values, and the symbol "——" represents the omitted value; wherein, numbers 1 to 5 are codes for historical normalized data, representing the first historical normalized data to the fifth historical normalized data. In this embodiment, A, B, C, D and E represent the first historical normalized data to the fifth historical normalized data in sequence. It is easy to see from Table 1 that the HTN of A and B is equal and HPN N is equal, so A and B are summarized as the same group of historical flow rate data, which is represented by α here. D and E have the same HTN and HPN, so D and E are summarized as the same group of historical flow rate data, which is represented by β here. α and β are different historical flow rate data groups. Then analyze C. It is easy to know from Table 1 that C has the same HTN and HPN as A and B, and A and B belong to α, so C is also included in α; the analysis process of the historical temperature and pressure data group is the same as the analysis process of the historical flow rate data group, so no specific explanation is given in this embodiment; The flow rate analysis unit is used to analyze the optimal ratio between the feed flow rate and the circulation flow rate based on the historical data group and the historical normalized data; The flow rate analysis unit is configured with a flow rate analysis strategy, which includes: For any historical flow rate data group, calculate the average value of HEN, mark it as the average flow rate efficiency, find the historical flow rate data group with the largest average flow rate efficiency, and mark it as the reference flow rate data group; For the historical normalized data in the reference velocity data group, HF / HC is calculated, and the calculation result is marked as the velocity data ratio, and each velocity data ratio corresponds to a HEN; See also Figure 2 As shown, a plane rectangular coordinate system is established with the velocity data ratio as the X-axis and HEN as the Y-axis, named as the velocity ratio analysis diagram, and the velocity data ratio and the corresponding HEN are entered into the velocity ratio analysis diagram; Performing polynomial regression on the flow rate ratio analysis graph, and marking the curve obtained by the polynomial regression as a flow rate efficiency distribution curve; Find the highest point on the flow rate efficiency distribution curve, mark it as the flow rate best efficiency point, and mark the flow rate data ratio corresponding to the flow rate best efficiency point on the X-axis as the flow rate best ratio; In practical applications, due to the large amount of data, this embodiment does not display specific data, but only displays the distribution of flow rate data ratio and HEN through the flow rate ratio analysis diagram. The average flow rate efficiency of the reference flow rate data group is the largest, which represents that the heating temperature and system pressure settings of the reference flow rate data group are the most reasonable. The results obtained by this analysis are closer to the real data, and the role of the reference temperature and pressure data group is the same; the flow rate ratio analysis diagram and flow rate efficiency distribution curve are constructed as shown in FIG. Figure 2As shown, the optimal flow rate ratio is found to be 0.34; The temperature and pressure analysis unit is used to analyze the optimal ratio between the heating temperature and the system pressure based on the historical data group and the historical normalized data; The temperature and pressure analysis unit is equipped with a temperature and pressure analysis strategy, which includes: For any historical temperature and pressure data set, calculate the average value of HEN, mark it as the average temperature and pressure efficiency, find the historical temperature and pressure data set with the largest average temperature and pressure efficiency, and mark it as the reference temperature and pressure data set; For the historical normalized data in the reference temperature and pressure data set, HTN / HPN is calculated and the calculation result is marked as the temperature and pressure data ratio. Each temperature and pressure data ratio corresponds to a HEN. See also Figure 3 As shown, a plane rectangular coordinate system is established with the temperature-pressure data ratio as the X-axis and HEN as the Y-axis, named as the temperature-pressure ratio analysis diagram, and the temperature-pressure data ratio and the corresponding HEN are entered into the temperature-pressure ratio analysis diagram; Perform polynomial regression on the temperature-pressure ratio analysis graph, and mark the curve obtained by the polynomial regression as the temperature-pressure efficiency distribution curve; Find the highest point on the temperature-pressure efficiency distribution curve, mark it as the temperature-pressure optimal efficiency point, and mark the temperature-pressure data ratio corresponding to the temperature-pressure optimal efficiency point on the X-axis as the temperature-pressure optimal ratio; In practical applications, the temperature-pressure ratio analysis diagram and temperature-pressure efficiency distribution curve are constructed as follows: Figure 3 As shown, the optimal temperature-pressure ratio is found to be 0.85; The flow rate and temperature analysis unit is used to analyze the relationship between the feed flow rate and the heating temperature based on the historical data group and the historical normalized data; The flow rate temperature analysis unit is equipped with a flow rate temperature analysis strategy, which includes: The historical data groups are numbered by the symbol G i Indicates, where i is a non-zero natural number and i is the serial number of G. i , find the HF and HTN in the historical normalized data with the largest HEN, and mark them as F i and TN i ; See also Figure 4 As shown, F i is the horizontal axis, TN i Establish a plane rectangular coordinate system for the vertical axis, named the velocity-temperature relationship diagram, and set F i and TN i Enter the flow rate temperature relationship diagram; Perform polynomial regression on the flow velocity-temperature relationship graph, and name the function obtained by the polynomial regression as the flow velocity-temperature relationship function; In practical applications, the extraction efficiency in each historical data set has a maximum value. When the extraction efficiency reaches the maximum, it means that the balance between the feed flow rate and the heating temperature reaches the best state in the historical data set. i and TN i The equilibrium relationship between the feed flow rate and the heating temperature under different conditions can be obtained; due to the large amount of data, this embodiment does not i and TN i The specific value of is specifically displayed, and it is simply displayed through the flow rate temperature relationship diagram; the flow rate temperature relationship diagram is constructed as follows Figure 4 As shown, the velocity-temperature relationship function obtained by regression is HT=0.2689×HF 2 -0.0303×HF-0.0151.

[0021] The intelligent control module is used to intelligently control the countercurrent extraction unit based on the optimal ratio; The intelligent management and control module is configured with intelligent management and control strategies, which include: Get the feed flow rate set by the user, marked as the target flow rate, represented by the symbol V; The optimal ratio of flow rate is represented by A, and the optimal ratio of temperature and pressure is represented by B; Calculate V / HC=A, solve HC, and get the optimal value of the circulation flow rate, which is marked as the optimal circulation flow rate; Substitute V into the velocity-temperature relationship function and mark the result obtained as the optimal normalized temperature, expressed as TZ. Solve for HT, which is marked as the optimal heating temperature; Calculate TZ / HP=B, solve HP, and get the optimal value of system pressure, marked as the optimal normalized pressure, expressed as PZ, through the formula Solve for HP, which is marked as the optimal pressure of the system; When the user sets the target flow rate, the circulation flow rate is automatically set to the optimal circulation flow rate, the heating temperature is automatically set to the optimal heating temperature, and the system pressure is automatically set to the optimal system pressure; In practical applications, in this embodiment, the target flow rate V set by the user is 1.2m / s, the optimal flow rate ratio A is 0.34, and the optimal temperature-pressure ratio B is 0.85. V / HC=A is calculated, that is, 1.2m / s / HC=0.34. The solution is HC, which is 3.5m / s. The calculation result is retained to one decimal place, and the optimal circulation flow rate is 3.5m / s. Substitute HF=V into the flow rate-temperature relationship function, and the optimal normalized temperature is 0.3358. The calculation result is retained to four decimal places. HT min and HT maxThe optimal heating temperature is 46.7℃, and the result is retained to one decimal place. TZ / HP=B, that is, 0.3358 / HP=0.85, and the optimal normalized pressure is 0.3951, and the result is retained to four decimal places. min 0.1MPa, HP max is 0.5MPa, and the optimal pressure is 0.25804MPa. When the user sets the target flow rate to 1.2m / s, the circulation flow rate is automatically set to 3.5m / s, the heating temperature is automatically set to 46.7℃, and the system pressure is automatically set to 0.25804MPa.

[0022] Example 2, please refer to Figure 5 As shown, the present application provides an artificial intelligence-based countercurrent extraction unit operation control method, comprising the following steps: Step S1, detecting the operating data and key parameters of the countercurrent extraction unit; the operating data include feed flow rate, circulation flow rate, heating temperature and system pressure, and the key parameter is extraction efficiency; Step S2, analyzing the optimal ratio between different operating data based on historical operating data and key parameters; Step S2 includes the following sub-steps: Step S201, normalizing the operating data and key parameters based on the historical operating data and key parameters to obtain historical normalized data; Step S201 includes the following sub-steps: Step S201.1, obtaining historical data of the operation data, marking it as historical operation data, the historical operation data also includes key parameters, and marking the feed flow rate, circulation flow rate, heating temperature, system pressure and extraction efficiency in the historical operation data as HF, HC, HT, HP and HE respectively; Step S201.2, obtaining the minimum and maximum values ​​of HT, marked as HT min and HT max ; Get the minimum and maximum values ​​of HP, marked as HP min HP max ; Get the minimum and maximum values ​​of HE, marked as HE respectively min and HE max ; Step S201.3, by normalization formula Calculate the normalized index of different operation history data, where R represents any one of HT, HP and HE, and RN, namely HTN, HPN and HEN, represent the HT normalized index, HP normalized index and HE normalized index respectively; Step S201.4, integrating HF, HC, HTN, HPN and HEN into historical normalized data; Step S202, grouping the historical operation data and key parameters based on the historical normalized data to obtain different historical data groups; Step S202 includes the following sub-steps: Step S202.1, the historical data set includes a historical flow rate data set and a historical temperature and pressure data set; Step S202.2: for any two historical normalized data, if the HF normalized index is equal and the HC normalized index is equal, they are classified into the same historical temperature and pressure data group; Step S202.3: for any two historical normalized data, if the HP normalized index is equal and the HE normalized index is equal, they are classified into the same historical flow rate data group; Step S203, analyzing the optimal ratio between the feed flow rate and the circulation flow rate based on the historical data group and the historical normalized data; Step S203 includes the following sub-steps: Step S203.1, for any historical flow rate data set, calculate the average value of HEN therein, mark it as the average flow rate efficiency, find the historical flow rate data set with the largest average flow rate efficiency, and mark it as the reference flow rate data set; Step S203.2, for the historical normalized data in the reference flow rate data group, calculate HF / HC, and mark the calculation result as a flow rate data ratio, each flow rate data ratio corresponds to a HEN; Step S203.3, establish a plane rectangular coordinate system with the flow rate data ratio as the X-axis and HEN as the Y-axis, name it a flow rate ratio analysis chart, and enter the flow rate data ratio and the corresponding HEN into the flow rate ratio analysis chart; Step S203.4, performing polynomial regression on the flow rate ratio analysis graph, and marking the curve obtained by the polynomial regression as a flow rate efficiency distribution curve; Step S203.5, find the highest point on the flow rate efficiency distribution curve, mark it as the flow rate best efficiency point, and mark the flow rate data ratio corresponding to the flow rate best efficiency point on the X-axis as the flow rate best ratio; Step S204, analyzing the optimal ratio between the heating temperature and the system pressure based on the historical data group and the historical normalized data; Step S204 includes the following sub-steps: Step S204.1, for any historical temperature and pressure data set, calculate the average value of HEN therein, mark it as the temperature and pressure average efficiency, find the historical temperature and pressure data set with the largest temperature and pressure average efficiency, and mark it as the reference temperature and pressure data set; Step S204.2, calculating HTN / HPN for the historical normalized data in the reference temperature and pressure data group, marking the calculation result as a temperature and pressure data ratio, each temperature and pressure data ratio corresponds to a HEN; Step S204.3, establish a plane rectangular coordinate system with the temperature-pressure data ratio as the X-axis and HEN as the Y-axis, name it as the temperature-pressure ratio analysis diagram, and enter the temperature-pressure data ratio and the corresponding HEN into the temperature-pressure ratio analysis diagram; Step S204.4, performing polynomial regression on the temperature-pressure ratio analysis graph, and marking the curve obtained by the polynomial regression as the temperature-pressure efficiency distribution curve; Step S204.5, finding the highest point on the temperature-pressure efficiency distribution curve, marking it as the temperature-pressure optimal efficiency point, and marking the temperature-pressure data ratio corresponding to the temperature-pressure optimal efficiency point on the X-axis as the temperature-pressure optimal ratio; Step S205, analyzing the relationship between the feed flow rate and the heating temperature based on the historical data set and the historical normalized data; Step S205 includes the following sub-steps: Step S205.1, number the historical data groups, using the symbol G i Indicates, where i is a non-zero natural number and i is the serial number of G. i , find the HF and HTN in the historical normalized data with the largest HEN, and mark them as F i and TN i ; Step S205.2, with F i is the horizontal axis, TN i Establish a plane rectangular coordinate system for the vertical axis, named the velocity-temperature relationship diagram, and set F i and TN i Enter the flow rate temperature relationship diagram; Step S205.3, performing polynomial regression on the flow velocity-temperature relationship graph, and naming the function obtained by the polynomial regression as the flow velocity-temperature relationship function; Step S3, intelligently controlling the countercurrent extraction unit based on the optimal ratio; Step S3 includes the following sub-steps: Step S301, obtaining the feed flow rate set by the user, marked as the target flow rate, represented by the symbol V; Step S302, the optimal flow rate ratio is represented by A, and the optimal temperature-pressure ratio is represented by B; Step S303, calculate V / HC=A, solve HC, and obtain the optimal value of the circulation flow rate, which is marked as the optimal circulation flow rate; Step S304, substitute V into the velocity-temperature relationship function, and mark the result obtained as the optimal normalized temperature, expressed as TZ, through the formula Solve for HT, which is marked as the optimal heating temperature; Step S305, calculate TZ / HP=B, solve HP, and obtain the optimal value of system pressure, marked as the optimal normalized pressure, expressed as PZ, through the formula Solve for HP, which is marked as the optimal pressure of the system; Step S306, after the user sets the target flow rate, the circulation flow rate is automatically set to the optimal circulation flow rate, the heating temperature is automatically set to the optimal heating temperature, and the system pressure is automatically set to the optimal system pressure.

[0023] Embodiment 3, the present application provides a structural schematic diagram of an electronic device, which may include: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in a method for operating and controlling a countercurrent extraction unit based on artificial intelligence are executed to achieve the following functions: detecting the operating data and key parameters of the countercurrent extraction unit; analyzing the optimal ratio between different operating data based on historical operating data and key parameters; and intelligently controlling the countercurrent extraction unit based on the optimal ratio.

[0024] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0025] Example 4. The present application also provides a computer-readable storage medium. The present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned artificial intelligence-based countercurrent extraction unit operation control method are executed to achieve the following functions: detecting the operating data and key parameters of the countercurrent extraction unit; analyzing the optimal ratio between different operating data based on historical operating data and key parameters; and intelligently controlling the countercurrent extraction unit based on the optimal ratio.

[0026] Through the description of the above implementation methods, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on such an understanding, the above technical solutions can be essentially or partly contributed to the prior art in the form of software products, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and include several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0027] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0028] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for controlling the operation of a countercurrent extraction unit based on artificial intelligence, characterized in that: The steps include: Test the operating data and key parameters of the countercurrent extraction unit; Analyze the optimal ratio between different operating data based on historical operating data and key parameters; Intelligent control of the countercurrent extraction unit based on the optimal ratio.

2. The method for controlling the operation of a countercurrent extraction unit based on artificial intelligence according to claim 1, characterized in that: The operating data include feed flow rate, circulation flow rate, heating temperature and system pressure, and the key parameter is extraction efficiency.

3. The operation control method of a countercurrent extraction unit based on artificial intelligence according to claim 2 is characterized in that: Analyzing the optimal ratio between different operating data based on historical operating data and key parameters includes the following sub-steps: Normalizing the operating data and key parameters based on historical operating data and key parameters to obtain historical normalized data; The historical operation data and key parameters are grouped based on the historical normalized data to obtain different historical data groups; Analyzing the optimal ratio between the feed flow rate and the circulation flow rate based on the historical data set and the historical normalized data; Analyze the optimal ratio between heating temperature and system pressure based on historical data groups and historical normalized data; The relationship between feed flow rate and heating temperature is analyzed based on the historical data set and the historical normalized data.

4. The method for controlling the operation of a countercurrent extraction unit based on artificial intelligence according to claim 3, characterized in that: Normalizing the operating data and key parameters based on the historical operating data and key parameters to obtain the historical normalized data includes the following sub-steps: Acquire historical data of the operation data and mark them as operation history data, wherein the operation history data also includes key parameters, and mark the feed flow rate, circulation flow rate, heating temperature, system pressure and extraction efficiency in the operation history data as HF, HC, HT, HP and HE respectively; Get the minimum and maximum values ​​of HT, marked as HT min and HT max ; Get the minimum and maximum values ​​of HP, marked as HP min HP max ; Get the minimum and maximum values ​​of HE, marked as HE respectively min and HE max ; By normalizing the formula Calculate the normalized index of different operation history data, where R represents any one of HT, HP and HE, and RN, namely HTN, HPN and HEN, represent the HT normalized index, HP normalized index and HE normalized index respectively; Integrate HF, HC, HTN, HPN and HEN into historical normalized data.

5. The method for controlling the operation of a countercurrent extraction unit based on artificial intelligence according to claim 4, characterized in that: The historical operation data and key parameters are grouped based on the historical normalized data to obtain different historical data groups, including the following sub-steps: The historical data group includes a historical flow rate data group and a historical temperature and pressure data group; For any two historical normalized data, if the HF normalized index is equal and the HC normalized index is equal, they are classified as the same historical temperature and pressure data group; For any two historical normalized data, if the HP normalized index is equal and the HE normalized index is equal, they are classified into the same historical flow rate data group.

6. The method for controlling the operation of a countercurrent extraction unit based on artificial intelligence according to claim 5, characterized in that: Analyzing the optimal ratio between the feed flow rate and the circulation flow rate based on the historical data set and the historical normalized data includes the following sub-steps: For any historical flow rate data group, calculate the average value of HEN, mark it as the average flow rate efficiency, find the historical flow rate data group with the largest average flow rate efficiency, and mark it as the reference flow rate data group; For the historical normalized data in the reference velocity data group, HF / HC is calculated, and the calculation result is marked as the velocity data ratio, and each velocity data ratio corresponds to a HEN; A plane rectangular coordinate system is established with the velocity data ratio as the X-axis and HEN as the Y-axis, named as the velocity ratio analysis chart, and the velocity data ratio and the corresponding HEN are entered into the velocity ratio analysis chart; Performing polynomial regression on the flow rate ratio analysis graph, and marking the curve obtained by the polynomial regression as a flow rate efficiency distribution curve; Find the highest point on the flow rate efficiency distribution curve, mark it as the flow rate best efficiency point, and mark the flow rate data ratio corresponding to the flow rate best efficiency point on the X-axis as the flow rate best ratio.

7. The method for controlling the operation of a countercurrent extraction unit based on artificial intelligence according to claim 6, characterized in that: Analyzing the optimal ratio between heating temperature and system pressure based on the historical data set and historical normalized data includes the following sub-steps: For any historical temperature and pressure data set, calculate the average value of HEN, mark it as the average temperature and pressure efficiency, find the historical temperature and pressure data set with the largest average temperature and pressure efficiency, and mark it as the reference temperature and pressure data set; For the historical normalized data in the reference temperature and pressure data set, HTN / HPN is calculated and the calculation result is marked as the temperature and pressure data ratio. Each temperature and pressure data ratio corresponds to a HEN. A plane rectangular coordinate system is established with the temperature-pressure data ratio as the X-axis and HEN as the Y-axis, named as the temperature-pressure ratio analysis diagram, and the temperature-pressure data ratio and the corresponding HEN are entered into the temperature-pressure ratio analysis diagram; Perform polynomial regression on the temperature-pressure ratio analysis graph, and mark the curve obtained by the polynomial regression as the temperature-pressure efficiency distribution curve; Find the highest point on the temperature-pressure efficiency distribution curve, mark it as the temperature-pressure optimal efficiency point, and mark the temperature-pressure data ratio corresponding to the temperature-pressure optimal efficiency point on the X-axis as the temperature-pressure optimal ratio.

8. The method for controlling the operation of a countercurrent extraction unit based on artificial intelligence according to claim 7, characterized in that: Analyzing the relationship between feed flow rate and heating temperature based on the historical data set and historical normalized data includes the following sub-steps: The historical data groups are numbered by the symbol G i Indicates, where i is a non-zero natural number and i is the serial number of G. i , find the HF and HTN in the historical normalized data with the largest HEN, and mark them as F i and TN i ; F i is the horizontal axis, TN i Establish a plane rectangular coordinate system for the vertical axis, named the velocity-temperature relationship diagram, and set F i and TN i Enter the flow rate temperature relationship diagram; A polynomial regression is performed on the flow velocity-temperature relationship diagram, and the function obtained by the polynomial regression is named the flow velocity-temperature relationship function.

9. The method for controlling the operation of a countercurrent extraction unit based on artificial intelligence according to claim 8, characterized in that: Intelligent control of the countercurrent extraction unit based on the optimal ratio includes the following sub-steps: Get the feed flow rate set by the user, marked as the target flow rate, represented by the symbol V; The optimal ratio of flow rate is represented by A, and the optimal ratio of temperature and pressure is represented by B; Calculate V / HC=A, solve HC, and get the optimal value of the circulation flow rate, which is marked as the optimal circulation flow rate; Substitute V into the velocity-temperature relationship function and mark the result obtained as the optimal normalized temperature, expressed as TZ. Solve for HT, which is marked as the optimal heating temperature; Calculate TZ / HP=B, solve HP, and get the optimal value of system pressure, marked as the optimal normalized pressure, expressed as PZ, through the formula Solve for HP, which is marked as the optimal pressure of the system; After the user sets the target flow rate, the circulation flow rate is automatically set to the optimal circulation flow rate, the heating temperature is automatically set to the optimal heating temperature, and the system pressure is automatically set to the optimal system pressure.

10. An artificial intelligence-based countercurrent extraction unit operation control system, used to implement an artificial intelligence-based countercurrent extraction unit operation control method according to any one of claims 1 to 9, characterized in that: It includes a data monitoring module, an optimal ratio analysis module and an intelligent management and control module; the data monitoring module and the intelligent management and control module are respectively connected to the optimal ratio analysis module data; The data monitoring module is used to detect the operating data and key parameters of the countercurrent extraction unit; The optimal ratio analysis module is used to analyze the optimal ratio between different operating data based on historical operating data and key parameters; The intelligent management and control module is used to intelligently manage the countercurrent extraction unit based on the optimal ratio.

Images