Artificial intelligence-based nanofiltration membrane preparation method and system

Abstract

The application provides a nanofiltration membrane preparation method and system based on artificial intelligence, and relates to the technical field of intelligent manufacturing. The nanofiltration membrane preparation method based on artificial intelligence comprises the following steps: controlling a maturation equipment to pretreat raw materials and an auxiliary oil based on preset maturation parameters; predicting a performance score of a nanofiltration membrane obtained by processing the pretreated raw materials by a production equipment according to first production parameters of the production equipment; adjusting the first production parameters according to the performance score to obtain second production parameters; and controlling the production equipment to process the pretreated raw materials according to the second production parameters to obtain a hollow fiber nanofiltration membrane. The application can improve the efficiency of nanofiltration membrane preparation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent manufacturing, and particularly relates to a nanofiltration membrane preparation method and system based on artificial intelligence. BACKGROUND

[0002] At present, with the development of data science, some enterprises or organizations tend to improve productivity and efficiency of production equipment maintenance in a production environment through data analysis. In the preparation process of nanofiltration membranes, a curing device is usually used to cure raw materials, and a production device is used to process the materials after curing to obtain hollow fiber nanofiltration membranes. In order to improve the preparation efficiency, the current method usually assists in formulating a preparation strategy based on digital control technology. However, this method has insufficient adaptability to dynamic changes in production parameters in the preparation process, which easily leads to the problem of low preparation efficiency. SUMMARY

[0003] In view of the above, it is necessary to provide a nanofiltration membrane preparation method and system based on artificial intelligence to solve the technical problems of low consistency of finished hollow fiber nanofiltration membranes and low preparation efficiency.

[0004] The present application provides a nanofiltration membrane preparation method based on artificial intelligence, applied to an electronic device, wherein the electronic device is communicatively connected to a curing device and a production device, and the method comprises the following steps: controlling the curing device to pretreat raw materials and an additive oil based on preset curing parameters; predicting a performance score of a nanofiltration membrane obtained by processing the pretreated raw materials by the production device according to first production parameters of the production device obtained in real time according to the first production parameters; adjusting the first production parameters to obtain second production parameters according to the performance score; and controlling the production device to process the pretreated raw materials according to the second production parameters to obtain a hollow fiber nanofiltration membrane.

[0005] In some embodiments, the step of predicting the performance score of the nanofiltration membrane obtained by processing the pretreated raw materials by the production device according to the first production parameters of the production device obtained in real time comprises the following steps: determining target production parameters from a plurality of batches of historical production parameters according to the first production parameters; and determining the performance score of the nanofiltration membrane based on a pre-trained evaluation model according to the target production parameters.

[0006] In some embodiments, the training the evaluation model comprises: obtaining a plurality of batches of historical data and label data; the historical data comprises historical production parameters, porosity, tensile strength and energy consumption; the label data is used to indicate a performance score of a nanofiltration membrane corresponding to each batch of historical data; determining a reward value corresponding to the historical data of any one batch according to the historical data of the any one batch; inputting the historical production parameters of any one batch to a pre-constructed initial evaluation model to obtain a predicted performance score output by the initial evaluation model; determining a first loss value of the initial evaluation model based on the reward value, the predicted performance score and the label data; updating the initial evaluation model based on a back propagation algorithm until the first loss value meets a preset condition, stopping updating the initial evaluation model, and obtaining an evaluation model trained to a convergent state.

[0007] In some embodiments, the determining the reward value corresponding to the historical data of any one batch according to the historical data of the any one batch comprises: performing weighted summation calculation on the porosity, the tensile strength and the energy consumption in the historical data according to a preset weight parameter to obtain the reward value corresponding to the historical data of the any one batch; the calculation method of the reward value satisfies the following relationship: Reward = a * porosity + β * tensile strength - γ * energy consumption; wherein, Reward represents the reward value corresponding to the historical data of the any one batch; a represents a first weight in the weight parameter, the first weight being used to represent an influence degree of the porosity on the reward value; β represents a second weight in the weight parameter, the second weight being used to represent an influence degree of the tensile strength on the reward value; γ represents a third weight in the weight parameter, the third weight being used to represent an influence degree of the energy consumption on the reward value.

[0008] In some embodiments, the determining the first loss value of the initial evaluation model based on the reward value, the predicted performance score and the label data comprises: wherein, Loss1 represents the first loss value of the initial evaluation model; i represents an index of a batch of historical data, m represents a number of batches of historical data; e represents a natural constant; Reward i represents the reward value corresponding to the historical data of the i-th batch; S i represents the label data of the i-th batch; S ′ i represents the predicted performance score determined based on the historical data of the i-th batch.

[0009] In some embodiments, the adjusting the first production parameter according to the performance score to obtain a second production parameter comprises: determining a score mean value according to the performance scores corresponding to the historical data of the plurality of batches; and adjusting the first production parameter according to a ratio of the performance score to the score mean value to obtain a second production parameter.

[0010] The application further provides a nanofiltration membrane preparation system based on artificial intelligence, which comprises an electronic device, the electronic device being communicatively connected to a maturation device and a production device; the electronic device is configured to control the maturation device to pretreat raw materials and auxiliary oil based on preset maturation parameters; the electronic device is further configured to predict a performance score of a nanofiltration membrane obtained by processing the pretreated raw materials by the production device based on a first production parameter of the production device obtained in real time; the electronic device is further configured to adjust the first production parameter based on the performance score to obtain a second production parameter; and the electronic device is further configured to control the production device to process the pretreated raw materials based on the second production parameter to obtain a hollow fiber nanofiltration membrane.

[0011] In some embodiments, the electronic device is further configured to determine a target production parameter from the historical production parameters of the plurality of batches based on the first production parameter; and the electronic device is further configured to determine the performance score of the nanofiltration membrane based on a pre-trained evaluation model based on the target production parameter.

[0012] In some embodiments, the electronic device is further configured to obtain historical data and label data of a plurality of batches; the historical data comprises historical production parameters, porosity, tensile strength and energy consumption; the label data is used to indicate the performance score of the nanofiltration membrane corresponding to the historical data of each batch; the electronic device is further configured to determine a reward value corresponding to the historical data of any one batch based on the historical data of the any one batch; the electronic device is further configured to input the historical production parameters of the any one batch into a pre-constructed initial evaluation model to obtain a predicted performance score output by the initial evaluation model; the electronic device is further configured to determine a first loss value of the initial evaluation model based on the reward value, the predicted performance score and the label data; and the electronic device is further configured to update the initial evaluation model based on a back propagation algorithm until the first loss value meets a preset condition, stop updating the initial evaluation model, and obtain an evaluation model trained to a convergent state.

[0013] In some embodiments, the electronic device is further configured to: calculate a weighted sum of the porosity, the tensile strength, and the energy consumption in the historical data according to a preset weight parameter to obtain a reward value corresponding to the historical data of the arbitrary batch; and the calculation method of the reward value satisfies the following relationship: Reward = a * porosity + β * tensile strength - γ * energy consumption, where Reward represents the reward value corresponding to the historical data of the arbitrary batch, a represents a first weight in the weight parameter, the first weight is used to represent the influence degree of the porosity on the reward value, β represents a second weight in the weight parameter, the second weight is used to represent the influence degree of the tensile strength on the reward value, and γ represents a third weight in the weight parameter, the third weight is used to represent the influence degree of the energy consumption on the reward value.

[0014] From the above technical solutions, it can be seen that the embodiments of the present application realize precise regulation and control of the mixing and ripening process of raw materials and auxiliary oil (for example, polytetrafluoroethylene / oil agent) in the preparation process of nanofiltration membranes through multi-modal perception, adaptive decision-making, and digital twin verification. Compared with the static ripening process, the ripening efficiency and ripening uniformity can be improved, and the energy consumption can be controlled in real time. In addition, multi-scale modeling is performed on the historical production parameters of the production equipment, and the real-time acquired production parameters are processed according to the evaluation model to realize efficient closed-loop control, thereby further improving the preparation efficiency of polytetrafluoroethylene hollow fiber nanofiltration membranes. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is an application scenario diagram of a nanofiltration membrane preparation method based on artificial intelligence provided by an embodiment of the present application.

[0016] Figure 2 is a flowchart of a nanofiltration membrane preparation method based on artificial intelligence provided by an embodiment of the present application.

[0017] Figure 3 is a functional module diagram of a nanofiltration membrane preparation system based on artificial intelligence provided by an embodiment of the present application.

[0018] Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to more clearly understand the purpose, features and advantages of the present application, the present application will be described in detail below in conjunction with the drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict. In the following description, a large number of specific details are set forth in order to fully understand the present application, and the described embodiments are only part of the embodiments of the present application, not all embodiments.

[0020] In addition, the terms "first", "second", etc. are used only for descriptive purposes and do not connote or imply relative importance or a quantity of the indicated technical features. Thus, features with "first", "second" designations can include one or more of the features implicitly or explicitly. In the description of the present application, the meaning of "a plurality" is two or more, unless otherwise expressly specified.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0022] The embodiments of the present application provide a method for preparing a nanofiltration membrane based on artificial intelligence, which can be applied to one or more electronic devices. The electronic device is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions. The hardware thereof includes, but is not limited to, a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0023] The electronic device can be any electronic product that can interact with a customer, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive Internet Protocol Television (IPTV), a smart wearable device, etc.

[0024] The electronic device can also include a network device and / or a customer device. The network device includes, but is not limited to, a single network server, a server group composed of multiple network servers, or a cloud composed of a large number of hosts or network servers based on cloud computing.

[0025] The network in which the electronic device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0026] As Figure 1The diagram illustrates an application scenario of an AI-based nanofiltration membrane preparation method according to an embodiment of this application. This AI-based nanofiltration membrane preparation method can be applied to an electronic device 100. The electronic device 100 is communicatively connected to a curing device 200 and a production device 300. Specifically, the electronic device 100 controls the curing device 200 to pretreat raw materials and auxiliary oils based on preset curing parameters. The electronic device 100 also predicts the performance score of the nanofiltration membrane obtained after processing the pretreated raw materials using the production device 300 according to first production parameters acquired in real time. The electronic device 100 further adjusts the first production parameters based on the performance score to obtain second production parameters. Finally, the electronic device 100 controls the production device to process the pretreated raw materials according to the second production parameters to obtain a hollow fiber nanofiltration membrane.

[0027] like Figure 2 The diagram shown is a flowchart of an artificial intelligence-based nanofiltration membrane preparation method according to an embodiment of this application. The order of steps in the flowchart can be changed, and some steps can be omitted, depending on different requirements. The artificial intelligence-based nanofiltration membrane preparation method provided in this embodiment includes the following steps.

[0028] S20 controls the maturation equipment to pre-treat raw materials and auxiliary oils based on preset maturation parameters.

[0029] In some embodiments, the raw material can be polytetrafluoroethylene (PTFE), and the auxiliary oil can be paraffin oil. PTFE is a polymer with a low coefficient of friction, non-adhesive properties, high temperature resistance, and corrosion resistance. Specifically, PTFE can be applied to the treatment of highly polluting industrial wastewater containing oil and solvents. For example, PTFE can be used for landfill leachate treatment, water reuse in the steel industry, wastewater treatment in the dyeing and electroplating industries, and wastewater treatment in the chemical industry. PTFE can address the problems of insufficient oil resistance and fouling resistance in membrane bioreactors made of polyvinylidene fluoride (PVDF), thereby improving the efficiency of industrial wastewater treatment. Specifically, compared to polyvinylidene fluoride (PVDF), polytetrafluoroethylene (PTFE) has more stable hydrophilicity; nanofiltration membranes made of PTFE are manufactured through a stretching process, resulting in a higher open-cell ratio of the nanofiltration membrane fibers compared to those made of PVDF, leading to higher flux and higher fiber strength; furthermore, PTFE can be stored dry when the system is shut down, making it easier to store compared to PVDF which is stored wet.

[0030] In an embodiment of the present application, during the preparation of the hollow fiber nanofiltration membrane, the polytetrafluoroethylene needs to be subjected to aging treatment to further improve its performance and stability. The aging equipment is used to mix the polytetrafluoroethylene with the auxiliary oil, so as to age the polytetrafluoroethylene material by using the auxiliary oil, and the crystalline structure and physical properties thereof are changed by controlling the temperature and time. The aging treatment can eliminate the crystalline defects in the polytetrafluoroethylene material, improve the order of the crystal structure, and thus improve the mechanical properties and durability. In addition, the aging can also remove the residual solvent and impurities in the polytetrafluoroethylene material, and ensure the purity and stability thereof.

[0031] S21, according to the first production parameter of the production equipment obtained in real time, predicting the performance score of the nanofiltration membrane obtained by processing the pretreated raw material according to the first production parameter control of the production equipment.

[0032] In an embodiment of the present application, the production equipment is used to process the polytetrafluoroethylene subjected to aging treatment, and obtain a hollow fiber nanofiltration membrane with polytetrafluoroethylene as a support layer. Specifically, the production equipment is used to perform pressure blanking, pushing, degreasing, stretching, shaping, wrapping, sintering, hydrophilic modification, and drying treatment on the polytetrafluoroethylene subjected to aging treatment, and obtain a hollow fiber nanofiltration membrane with polytetrafluoroethylene as a support layer. Specifically, after the hydrophilic modification, the production equipment is also used to treat the membrane wire by using a solution containing polyethyleneimine, polyvinyl alcohol, sodium hydroxide, and water; then the membrane wire is lifted to remove the excess solution inside the membrane wire based on gravity; and finally, the membrane wire is subjected to solidification treatment by using a solution containing butanedial, polyethylene glycol, and diglycidyl ether before drying.

[0033] In some embodiments, the performance score of the nanofiltration membrane obtained by processing the pretreated raw material according to the first production parameter control of the production equipment includes: determining the target production parameter from a plurality of batches of historical production parameters according to the first production parameter; and determining the performance score of the nanofiltration membrane based on the pre-trained evaluation model according to the target production parameter.

[0034] In some embodiments, the method further comprises training the evaluation model, and the training the evaluation model comprises: obtaining a plurality of batches of historical data and label data; the historical data comprises historical production parameters, porosity, tensile strength, and energy consumption; the label data is used to indicate a performance score of a nanofiltration membrane corresponding to each batch of historical data; determining a reward value corresponding to the historical data of any one batch according to the historical data of the any one batch; inputting the historical production parameters of any one batch to a pre-constructed initial evaluation model to obtain a predicted performance score output by the initial evaluation model; determining a first loss value of the initial evaluation model based on the reward value, the predicted performance score, and the label data; updating the initial evaluation model based on a back propagation algorithm until the first loss value meets a preset condition, stopping updating the initial evaluation model, and obtaining the evaluation model trained to a convergent state.

[0035] In some embodiments, the determining the reward value corresponding to the historical data of any one batch comprises: performing weighted summation calculation on the porosity, the tensile strength, and the energy consumption in the historical data according to a preset weight parameter to obtain the reward value corresponding to the historical data of the any one batch; and the calculation method of the reward value satisfies the following relationship: Reward = a * porosity + β * tensile strength - γ * energy consumption; wherein, Reward represents the reward value corresponding to the historical data of the any one batch; a represents a first weight in the weight parameter, and the first weight is used to represent an influence degree of the porosity on the reward value; β represents a second weight in the weight parameter, and the second weight is used to represent an influence degree of the tensile strength on the reward value; γ represents a third weight in the weight parameter, and the third weight is used to represent an influence degree of the energy consumption on the reward value.

[0036] In some embodiments, the determining the first loss value of the initial evaluation model based on the reward value, the predicted performance score, and the label data comprises: wherein, Loss1 represents the first loss value of the initial evaluation model; i represents an index of a batch of historical data, and m represents a number of batches of historical data; e represents a natural constant; Reward i represents the reward value corresponding to the historical data of the i-th batch; S i represents the label data of the i-th batch; S ′ i represents the predicted performance score determined based on the historical data of the i-th batch.

[0037] S22, adjusting the first production parameter according to the performance score to obtain a second production parameter.

[0038] In some embodiments, the adjusting the first production parameter according to the performance score to obtain a second production parameter comprises: determining a score mean value according to the performance scores corresponding to the historical data of the plurality of batches; and adjusting the first production parameter according to a ratio of the performance score to the score mean value to obtain a second production parameter.

[0039] S23, controlling the production equipment to process the pretreated raw material according to the second production parameter to obtain the hollow fiber nanofiltration membrane.

[0040] In some embodiments, the production equipment forms a microporous structure by preforming polytetrafluoroethylene through a push-pull process, bidirectional stretching, high-temperature sintering, and setting to stabilize the crystalline state, thereby ensuring the strength of the hollow fiber nanofiltration membrane.

[0041] From the above technical solutions, it can be seen that the embodiments of the present application realize precise regulation and control of the mixing and ripening process of raw materials and auxiliary oil (for example, polytetrafluoroethylene / oil agent) in the preparation process of nanofiltration membranes through multi-modal perception, adaptive decision-making, and digital twin verification. Compared with the static ripening process, the ripening efficiency and ripening uniformity can be improved, and the energy consumption can be controlled in real time. In addition, multi-scale modeling is performed on the historical production parameters of the production equipment, and the real-time obtained production parameters are processed according to the evaluation model to realize efficient closed-loop control, thereby further improving the preparation efficiency of the polytetrafluoroethylene hollow fiber nanofiltration membrane.

[0042] Please refer to Figure 3 , Figure 3 is a functional module diagram of a nanofiltration membrane preparation system based on artificial intelligence provided by an embodiment of the present application. The nanofiltration membrane preparation system based on artificial intelligence 500 comprises an electronic device 100, which is communicatively connected to a ripening device 200 and a production equipment 300. The modules / units referred to in the present application refer to a series of computer readable instruction segments that can be executed by a processor 13 and can complete a fixed function, which are stored in a memory 12. In the present embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0043] The electronic device 100 is configured to control the ripening device 200 to pretreat the raw material and the auxiliary oil based on the preset ripening parameters.

[0044] The electronic device 100 is further configured to predict a performance score of a nanofiltration membrane obtained by processing the pretreated raw material by the production equipment 300 according to the first production parameter of the production equipment 300 obtained in real time.

[0045] The electronic device 100 is further configured to adjust the first production parameter according to the performance score to obtain a second production parameter.

[0046] The electronic device 100 is further configured to control the production equipment 300 to process the pretreated raw material according to the second production parameter, so as to obtain the hollow fiber nanofiltration membrane.

[0047] In some embodiments, the electronic device 100 is further configured to determine a target production parameter from a plurality of batches of historical production parameters according to the first production parameter; and the electronic device 100 is further configured to determine a performance score of the nanofiltration membrane based on a pre-trained evaluation model according to the target production parameter.

[0048] In some embodiments, the electronic device 100 is further configured to obtain a plurality of batches of historical data and label data; the historical data comprises historical production parameters, porosity, tensile strength and energy consumption; the label data is used to indicate a performance score of a nanofiltration membrane corresponding to each batch of historical data; the electronic device 100 is further configured to determine a reward value corresponding to any one batch of historical data according to the any one batch of historical data; the electronic device 100 is further configured to input any one batch of historical production parameters into a pre-constructed initial evaluation model to obtain a predicted performance score output by the initial evaluation model; the electronic device 100 is further configured to determine a first loss value of the initial evaluation model based on the reward value, the predicted performance score and the label data; and the electronic device 100 is further configured to update the initial evaluation model based on a back propagation algorithm until the first loss value meets a preset condition, stop updating the initial evaluation model, and obtain an evaluation model trained to a convergent state.

[0049] In some embodiments, the electronic device 100 is further configured to perform weighted summation calculation on the porosity, the tensile strength and the energy consumption in the historical data according to a preset weight parameter, so as to obtain a reward value corresponding to the any one batch of historical data; and a calculation method of the reward value satisfies the following relationship: Reward = a * porosity + β * tensile strength - γ * energy consumption; wherein, Reward represents the reward value corresponding to the any one batch of historical data; a represents a first weight in the weight parameter, and the first weight is used to represent an influence degree of the porosity on the reward value; β represents a second weight in the weight parameter, and the second weight is used to represent an influence degree of the tensile strength on the reward value; and γ represents a third weight in the weight parameter, and the third weight is used to represent an influence degree of the energy consumption on the reward value.

[0050] Please refer to Figure 4Fig. 1 is a structural schematic diagram of an electronic device provided in an embodiment of the present application. The electronic device 100 comprises a memory 12 and a processor 13. The memory 12 is configured to store computer readable instructions, and the processor 13 is configured to execute the computer readable instructions stored in the memory to implement the artificial intelligence-based nanofiltration membrane preparation method in any of the above embodiments.

[0051] In an embodiment of the present application, the electronic device 100 further comprises a bus, a computer program stored in the memory 12 and executable on the processor 13, for example, an artificial intelligence-based nanofiltration membrane preparation program.

[0052] Figure 4 Only the electronic device 100 with the memory 12 and the processor 13 is shown, and those skilled in the art can understand that, Figure 4 The structure shown does not constitute a limitation on the electronic device 100, and can comprise fewer or more components than shown, or combine certain components, or different component arrangements.

[0053] In combination with Figure 2 The memory 12 in the electronic device 100 stores a plurality of computer readable instructions to implement the artificial intelligence-based nanofiltration membrane preparation method, and the processor 13 can execute the plurality of instructions to achieve: controlling a maturation device to pretreat raw materials and an additive oil based on a preset maturation parameter; predicting a performance score of a nanofiltration membrane obtained by processing the pretreated raw materials by a production device according to a first production parameter of the production device; adjusting the first production parameter to obtain a second production parameter according to the performance score; and controlling the production device to process the pretreated raw materials according to the second production parameter to obtain a hollow fiber nanofiltration membrane.

[0054] Specifically, the processor 13 can refer to the description of the specific implementation method of the above instructions Figure 3 for the description of related steps in corresponding embodiments, which will not be repeated here.

[0055] Those skilled in the art can understand that the schematic diagram is only an example of the electronic device 100 and does not constitute a limitation on the electronic device 100. The electronic device 100 can be a bus structure or a star structure, and the electronic device 100 can further comprise more or fewer other hardware or software than shown, or different component arrangements, for example, the electronic device 100 can further comprise an input / output device, a network access device, etc.

[0056] It should be noted that the electronic device 100 is only an example, and other existing or future electronic products, such as those adaptable to the present application, should also be included in the protection scope of the present application and are hereby incorporated by reference.

[0057] The memory 12 includes at least one type of readable storage medium, which can be non-volatile or volatile. The readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. The memory 12 can be an internal storage unit of the electronic device 100 in some embodiments, such as a mobile hard disk of the electronic device 100. The memory 12 can also be an external storage device of the electronic device 100 in other embodiments, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 100. The memory 12 can be used to store application software and various data installed in the electronic device 100, such as the code of an artificial intelligence-based nanofiltration membrane preparation program, and can also be used to temporarily store data that has been output or will be output.

[0058] The processor 13 can be composed of an integrated circuit in some embodiments, such as a single packaged integrated circuit or a plurality of packaged integrated circuits with the same or different functions, including one or more combinations of a central processing unit (CPU), a microprocessor, a digital processing chip, a graphics processor, and various control chips, etc. The processor 13 is the control unit of the electronic device 100, which connects all components of the electronic device 100 through various interfaces and lines, executes programs or modules stored in the memory 12 (such as an artificial intelligence-based nanofiltration membrane preparation program, etc.), and calls data stored in the memory 12 to perform various functions of the electronic device 100 and process data.

[0059] The processor 13 executes the operating system and various application programs installed in the electronic device 100. The processor 13 executes the application programs to implement the steps in each of the above artificial intelligence-based nanofiltration membrane preparation method embodiments, such as Figure 2 the steps shown.

[0060] For example, the computer program can be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules / units can be a series of computer-readable instruction segments that can complete a specific function, which are used to describe the execution process of the computer program in the electronic device 100.

[0061] The integrated units in the form of software function modules can be stored in a computer readable storage medium. The software function modules are stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to execute part of the artificial intelligence-based nanofiltration membrane preparation method described in various embodiments of the present application.

[0062] The modules / units integrated in the electronic device 100, if implemented in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiments can also be implemented by a computer program to instruct related hardware devices to complete, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the above-mentioned various method embodiments can be implemented.

[0063] The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, and other memories, etc.

[0064] Further, the computer readable storage medium can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function, etc.; and the data storage area can store data created according to the use of the blockchain node, etc.

[0065] The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one arrow is used in the Figure 4 However, it does not mean that there is only one bus or only one type of bus. The bus is arranged to realize the connection and communication between the memory 12, the at least one processor 13, etc.

[0066] The embodiment of the present application further provides a computer readable storage medium (not shown in the figure), which stores computer readable instructions, and the computer readable instructions are executed by a processor in an electronic device to implement the artificial intelligence-based nanofiltration membrane preparation method in any of the above embodiments.

[0067] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the above-described device embodiments are merely illustrative, and the division of the modules can be different. For example, the division of the modules is merely a logical function division, and there can be another division manner in actual implementation.

[0068] The modules described as separated components can or can not be physically separated, and the components displayed as modules can or can not be physical units, i.e., can be located in one place or distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0069] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0070] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The plurality of units or devices stated in the specification can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names and do not represent any particular order.

[0071] Finally, it should be noted that the above embodiments are merely used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for preparing nanofiltration membranes based on artificial intelligence, applied to electronic devices, wherein the electronic devices are communicatively connected to curing equipment and production equipment, characterized in that, The method includes: The maturation equipment is controlled based on preset maturation parameters to pre-treat raw materials and auxiliary oils; Based on the first production parameters acquired in real time from the production equipment, the method predicts the performance score of the nanofiltration membrane obtained after processing the pretreated raw materials by controlling the production equipment according to the first production parameters. This includes: determining target production parameters from historical production parameters of multiple batches based on the first production parameters; and determining the performance score of the nanofiltration membrane based on a pre-trained evaluation model according to the target production parameters. The first production parameters indicate the parameters by which the production equipment processes the pretreated raw materials using multiple processes, including pressing, pushing, degreasing, stretching, shaping, wrapping, sintering, hydrophilic modification, and drying. The method also includes training the evaluation model, which involves: acquiring historical data and tag data from multiple batches; the historical data includes historical production parameters, porosity, tensile strength, and energy consumption; and the tag data indicates the nanofiltration membrane corresponding to the historical data of each batch. Performance scoring; determining the reward value corresponding to the historical data of any batch based on the historical data of any batch; inputting the historical production parameters of any batch into a pre-built initial evaluation model to obtain the predicted performance score output by the initial evaluation model; determining the first loss value of the initial evaluation model based on the reward value, the predicted performance score, and the label data; updating the initial evaluation model based on the backpropagation algorithm until the first loss value meets a preset condition, stopping the update of the initial evaluation model, and obtaining an evaluation model trained to a convergent state; the step of determining the reward value corresponding to the historical data of any batch based on the historical data of any batch includes: performing a weighted summation calculation on the porosity, tensile strength, and energy consumption in the historical data according to preset weight parameters to obtain the reward value corresponding to the historical data of any batch; the calculation method of the reward value satisfies the following relationship: Reward = α Porosity + β Tensile strength — γ Energy consumption; where Reward represents the reward value corresponding to any batch of historical data; α represents the first weight in the weighting parameters, which is used to characterize the influence of porosity on the reward value; β represents the second weight in the weighting parameters, which is used to characterize the influence of tensile strength on the reward value; γ represents the third weight in the weighting parameters, which is used to characterize the influence of energy consumption on the reward value; determining the first loss value of the initial evaluation model based on the reward value, the predicted performance score, and the label data includes: Where Loss1 represents the first loss value of the initial evaluation model; i represents the batch index of the historical data; m represents the number of batches of historical data; e represents the natural constant; Reward i This represents the reward value corresponding to the historical data of the i-th batch. This represents the label data for the i-th batch; This represents the prediction performance score determined based on historical data from the i-th batch. The first production parameter is adjusted based on the performance score to obtain the second production parameter; Based on the second production parameters, the production equipment is controlled to process the pretreated raw materials to obtain hollow fiber nanofiltration membranes.

2. The method for preparing nanofiltration membranes based on artificial intelligence as described in claim 1, characterized in that, The step of adjusting the first production parameter based on the performance score to obtain the second production parameter includes: The average score is determined based on the performance scores corresponding to historical data from multiple batches. The first production parameter is adjusted based on the ratio of the performance score to the average score to obtain the second production parameter.

3. A nanofiltration membrane preparation system based on artificial intelligence, characterized in that, The system includes electronic devices that are communicatively connected to the curing equipment and the production equipment; The electronic device is used to control the maturation equipment to pre-treat the raw materials and auxiliary oils based on preset maturation parameters; The electronic device is further configured to predict, based on real-time acquired first production parameters of the production equipment, the performance score of the nanofiltration membrane obtained after controlling the production equipment to process the pretreated raw materials according to the first production parameters, including: determining target production parameters from historical production parameters of multiple batches based on the first production parameters; determining the performance score of the nanofiltration membrane based on the target production parameters and a pre-trained evaluation model; wherein, the first production parameters indicate the parameters by which the production equipment processes the pretreated raw materials based on multiple processes, including pressing, pushing, degreasing, stretching, shaping, wrapping, sintering, hydrophilic modification, and drying; the method further includes training the evaluation model, which includes: acquiring historical data and tag data of multiple batches; the historical data includes historical production parameters, porosity, tensile strength, and energy consumption; the tag data is used to indicate the historical data corresponding to each batch. The process involves: evaluating the performance of the nanofiltration membrane; determining the reward value corresponding to the historical data of any given batch; inputting the historical production parameters of any given batch into a pre-built initial evaluation model to obtain the predicted performance score output by the initial evaluation model; determining the first loss value of the initial evaluation model based on the reward value, the predicted performance score, and the label data; updating the initial evaluation model based on the backpropagation algorithm until the first loss value meets a preset condition, at which point the updating of the initial evaluation model stops, resulting in an evaluation model trained to a convergent state; the determination of the reward value corresponding to the historical data of any given batch includes: performing a weighted summation calculation on the porosity, tensile strength, and energy consumption in the historical data according to preset weight parameters to obtain the reward value corresponding to the historical data of any given batch; the calculation method of the reward value satisfies the following relationship: Reward = α Porosity + β Tensile strength — γ Energy consumption; where Reward represents the reward value corresponding to any batch of historical data; α represents the first weight in the weighting parameters, which is used to characterize the influence of porosity on the reward value; β represents the second weight in the weighting parameters, which is used to characterize the influence of tensile strength on the reward value; γ represents the third weight in the weighting parameters, which is used to characterize the influence of energy consumption on the reward value; determining the first loss value of the initial evaluation model based on the reward value, the predicted performance score, and the label data includes: Where Loss1 represents the first loss value of the initial evaluation model; i represents the batch index of the historical data; m represents the number of batches of historical data; e represents the natural constant; Reward i This represents the reward value corresponding to the historical data of the i-th batch. This represents the label data for the i-th batch; This represents the prediction performance score determined based on historical data from the i-th batch. The electronic device is also used to adjust the first production parameter according to the performance score to obtain the second production parameter; The electronic device is also used to control the production equipment to process the pretreated raw materials according to the second production parameters to obtain a hollow fiber nanofiltration membrane.

Images