High-precision intelligent large-flux filtering method and system based on real-time monitoring

Abstract

The invention discloses a high-precision intelligent large-flux filtering method and system based on real-time monitoring, and the method comprises the steps: carrying out the real-time monitoring of a fluid, and obtaining a real-time data flow; analyzing the real-time data flow by using a dynamic interactive comprehensive analysis algorithm to obtain an analysis result, and generating a filtering optimization parameter based on the analysis result; preliminarily separating particulate matters in the fluid based on the filtering optimization parameters to obtain clean fluid and separated particulate matters, and monitoring the obtained clean fluid in real time to obtain state parameters of the clean fluid; updating and optimizing the filtering optimization parameters based on the state parameters to obtain updated and optimized filtering parameters; and optimizing the updated and optimized filtering parameters in combination with historical data of the cleaning fluid to obtain final filtering parameters. According to the method, accurate optimization of the filtering parameters is ensured, unnecessary adjustment and redundant processing are reduced, the optimized parameters are generated through efficient calculation, and the operation efficiency of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of high-flux filtering, and in particular to a high-precision intelligent high-flux filtering method and system based on real-time monitoring. Background Art

[0002] In the field of filtration technology, traditional filtration systems mainly rely on fixed parameter design and manual adjustment, and their operating efficiency and adaptability are limited, especially when dealing with complex fluid components or dynamically changing working environments, there are significant deficiencies. Specifically, in the prior art, key parameters such as the pore size, pressure and flow rate of the filter are usually set by fixed empirical values, and cannot be adjusted in real time according to the actual fluid characteristics, resulting in unstable filtration accuracy. In addition, when the traditional system improves the filtration accuracy, it is often accompanied by a significant reduction in flux, which is difficult to meet the needs of large-scale industrial filtration. At the same time, the prior art lacks real-time monitoring and optimization feedback mechanisms for the filtration state, and the system cannot capture the changing characteristics of the fluid in time. When problems such as blockage and reduced efficiency occur, manual intervention is often required, resulting in low operating efficiency. In other words, in intelligent high-flux filtration, the inability to accurately analyze the fluid state data leads to technical problems such as the inability to adjust the filtration parameters in time and inaccurate adjustment of the filtration parameters. Summary of the invention

[0003] The embodiments of the present invention provide a high-precision intelligent large-flux filtering method and system based on real-time monitoring to solve the above-mentioned technical problems in the prior art.

[0004] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not a general review, nor is it intended to identify key / important components or to describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0005] According to a first aspect of an embodiment of the present invention, a high-precision intelligent large-flux filtering method based on real-time monitoring is provided.

[0006] In one embodiment, the high-precision intelligent high-throughput filtering method based on real-time monitoring includes: Performing real-time monitoring on the fluid to be filtered to obtain monitoring data, and converting the monitoring data into a continuous electronic signal and outputting it as a real-time data stream; Analyzing the real-time data stream using a dynamic interactive comprehensive analysis algorithm to obtain analysis results, and generating filtering optimization parameters based on the analysis results; Preliminarily separating the particles in the fluid based on the filtration optimization parameters to obtain a clean fluid and separated particles, and monitoring the obtained clean fluid in real time to obtain the state parameters of the clean fluid; Based on the state parameters, the filtration optimization parameters are updated and optimized while balancing the flux and the filtration accuracy to obtain updated and optimized filtration parameters; and the updated and optimized filtration parameters are optimized in combination with the historical data of the clean fluid to obtain the final filtration parameters, and the filtration adjustment is performed based on the final filtration parameters.

[0007] In one embodiment, real-time monitoring of the fluid to be filtered to obtain monitoring data, and converting the monitoring data into a continuous electronic signal and outputting the signal as a real-time data stream comprises: Using pre-configured sensors to monitor the fluid to be filtered in real time to obtain monitoring data; wherein the monitoring data includes particle concentration, particle size distribution and chemical composition; The monitoring data is amplified by a signal amplification circuit and then converted into analog-to-digital form to obtain a continuous electronic signal as a real-time data stream.

[0008] In one embodiment, the filtration optimization parameters include filtration pore size, filtration pressure and filtration flow rate; and the real-time data stream is analyzed using a dynamic interactive comprehensive analysis algorithm to obtain analysis results, and the filtration optimization parameters generated based on the analysis results include: Through dynamic feature distribution modeling, the multi-dimensional characteristics of real-time data streams are converted into feature distribution functions; Based on the feature distribution function, a dynamic interaction mapping function is constructed, and a comprehensive evolution analysis is performed on the dynamic interaction mapping function to generate the time evolution quantity of the feature; Based on the time evolution of the feature, a recursive optimization function is constructed, and filtering optimization parameters are generated in real time according to the recursive optimization function.

[0009] In one embodiment, the state parameters include: residual concentration of particles in the clean fluid, fluid flow rate, and pressure difference across the filter; and, based on the state parameters, the filtration optimization parameters are updated and optimized under the condition of balancing flux and filtration accuracy, and the updated and optimized filtration parameters include: Compare the residual concentration of particles in the clean fluid with a pre-configured target concentration, and if the comparison result shows that the residual concentration of particles in the clean fluid is higher than the target concentration, reduce the filter aperture; otherwise, maintain or increase the filter aperture; Based on the adjusted filter aperture, the filter area of ​​the fluid is determined, and the fluid flow rate is adjusted according to the filter area; the filter pressure is adjusted according to the pressure difference at both ends of the filter and the predetermined pressure difference adjustment coefficient.

[0010] In one embodiment, the updated and optimized filtering parameters are optimized in combination with the historical data of the cleaning fluid, and the final filtering parameters include: A time series algorithm is used to perform trend analysis on historical data of the cleaning fluid to obtain a trend optimization sequence value; and based on the trend optimization sequence value, the updated and optimized filtering parameters are optimized to obtain the final filtering parameters.

[0011] According to a second aspect of an embodiment of the present invention, a high-precision intelligent large-flux filtration system based on real-time monitoring is provided.

[0012] In one embodiment, the high-precision intelligent high-flux filtration system based on real-time monitoring includes: A real-time monitoring module, used to monitor the fluid to be filtered in real time, obtain monitoring data, and convert the monitoring data into a continuous electronic signal and output it as a real-time data stream; An intelligent analysis module, used to analyze the real-time data stream using a dynamic interactive comprehensive analysis algorithm, obtain analysis results, and generate filtering optimization parameters based on the analysis results; An adaptive filtering module is used to perform preliminary separation of particles in the fluid based on the filtering optimization parameters to obtain clean fluid and separated particles, and to perform real-time monitoring of the obtained clean fluid to obtain state parameters of the clean fluid; A balance control module, used to update and optimize the filtration optimization parameters based on the state parameters while balancing the flux and the filtration accuracy, to obtain updated and optimized filtration parameters; The intelligent control module is used to optimize the updated and optimized filtering parameters in combination with the historical data of the clean fluid to obtain the final filtering parameters, and perform filtering adjustments based on the final filtering parameters.

[0013] In one embodiment, the real-time monitoring module monitors the fluid to be filtered in real time to obtain monitoring data, converts the monitoring data into a continuous electronic signal and outputs it as a real-time data stream, and uses a pre-configured sensor to monitor the fluid to be filtered in real time to obtain monitoring data; wherein the monitoring data includes particle concentration, particle size distribution and chemical composition; the monitoring data is amplified by a signal amplification circuit and then converted into analog to digital to obtain a continuous electronic signal as a real-time data stream.

[0014] In one embodiment, the filtering optimization parameters include filtering pore size, filtering pressure and filtering flow rate; and, when the intelligent analysis module uses a dynamic interactive comprehensive analysis algorithm to analyze the real-time data stream, obtains analysis results, and generates filtering optimization parameters based on the analysis results, the multi-dimensional characteristics of the real-time data stream are converted into a feature distribution function through dynamic feature distribution modeling; based on the feature distribution function, a dynamic interactive mapping function is constructed, and a comprehensive evolution analysis is performed on the dynamic interactive mapping function to generate a time evolution quantity of the feature; based on the time evolution quantity of the feature, a recursive optimization function is constructed, and the filtering optimization parameters are generated in real time according to the recursive optimization function.

[0015] In one embodiment, the state parameters include: the residual concentration of particulate matter in the clean fluid, the fluid flow rate and the pressure difference across the filter; and the balance control module updates and optimizes the filtration optimization parameters based on the state parameters while balancing the flux and the filtration accuracy. When the updated and optimized filtration parameters are obtained, the residual concentration of particulate matter in the clean fluid is compared with a pre-configured target concentration. If the comparison result is that the residual concentration of particulate matter in the clean fluid is higher than the target concentration, the filtration aperture is reduced; otherwise, the filtration aperture is maintained or increased; based on the adjusted filtration aperture, the filtration area of ​​the fluid is determined, and the fluid flow rate is adjusted according to the filtration area; and the filtration pressure is adjusted according to the pressure difference across the filter and a predetermined pressure difference adjustment coefficient.

[0016] In one embodiment, the intelligent control module optimizes the updated and optimized filtering parameters in combination with the historical data of the cleaning fluid to obtain the final filtering parameters, and uses a time series algorithm to perform trend analysis on the historical data of the cleaning fluid to obtain trend optimization sequence values; and optimizes the updated and optimized filtering parameters based on the trend optimization sequence values ​​to obtain the final filtering parameters.

[0017] According to a third aspect of an embodiment of the present invention, a computer device is provided.

[0018] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0019] According to a fourth aspect of embodiments of the present invention, a computer-readable storage medium is provided.

[0020] In one embodiment, the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0021] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: 1. Through the dynamic interactive comprehensive analysis algorithm, combined with real-time monitoring data (particle concentration, particle size distribution, chemical composition, etc.), dynamic characteristic distribution function and dynamic interactive mapping function are constructed to capture the complex change law of fluid characteristics, ensure the accurate optimization of filtration parameters, reduce unnecessary adjustments and redundant processing, generate optimized parameters through efficient calculation, and improve the operation efficiency of the system.

[0022] 2. Through the dynamic balance optimization of flow rate and pressure, high-throughput fluid processing is achieved while ensuring high precision, adapting to large-scale filtration needs on an industrial scale.

[0023] 3. Using recursive optimization functions and time series analysis algorithms, on the basis of adjusting the filtering parameters, trend optimization values ​​are generated through trend analysis of historical data, the filtering parameters are further optimized, and an intelligent optimization closed loop is constructed.

[0024] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0026] Figure 1 is a flow chart of a high-precision intelligent large-flux filtering method based on real-time monitoring according to an exemplary embodiment; Figure 2 is a structural schematic diagram of a high-precision intelligent large-flux filtration system based on real-time monitoring according to an exemplary embodiment; Figure 3 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0027] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0028] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0029] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0030] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0031] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0032] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0033] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0034] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0035] Figure 1An embodiment of a high-precision intelligent large-flux filtering method based on real-time monitoring of the present invention is shown.

[0036] In this optional embodiment, the high-precision intelligent high-flux filtering method based on real-time monitoring includes: Step S101, real-time monitoring of the fluid to be filtered is performed to obtain monitoring data, and the monitoring data is converted into a continuous electronic signal and output as a real-time data stream; Step S103, analyzing the real-time data stream using a dynamic interactive comprehensive analysis algorithm to obtain analysis results, and generating filtering optimization parameters based on the analysis results; Step S105, preliminarily separating the particles in the fluid based on the filtration optimization parameters to obtain a clean fluid and separated particles, and monitoring the obtained clean fluid in real time to obtain state parameters of the clean fluid; Step S107, based on the state parameters, the filtration optimization parameters are updated and optimized under the condition of balancing flux and filtration accuracy to obtain updated and optimized filtration parameters; and the updated and optimized filtration parameters are optimized in combination with historical data of the clean fluid to obtain final filtration parameters, and filtration adjustment is performed based on the final filtration parameters.

[0037] Figure 2 An embodiment of a high-precision intelligent large-flux filtering system based on real-time monitoring of the present invention is shown.

[0038] In this optional embodiment, the high-precision intelligent high-flux filtering system based on real-time monitoring includes: A real-time monitoring module 201 is used to monitor the fluid to be filtered in real time, obtain monitoring data, and convert the monitoring data into a continuous electronic signal and output it as a real-time data stream; The intelligent analysis module 203 is used to analyze the real-time data stream using a dynamic interactive comprehensive analysis algorithm to obtain analysis results, and generate filtering optimization parameters based on the analysis results; The adaptive filtering module 205 is used to perform preliminary separation of particles in the fluid based on the filtering optimization parameters to obtain clean fluid and separated particles, and to monitor the obtained clean fluid in real time to obtain state parameters of the clean fluid; A balance control module 207 is used to update and optimize the filtration optimization parameters based on the state parameters while balancing the flux and the filtration accuracy to obtain updated and optimized filtration parameters; The intelligent control module 209 is used to optimize the updated and optimized filtering parameters in combination with the historical data of the clean fluid to obtain the final filtering parameters, and perform filtering adjustments based on the final filtering parameters.

[0039] In specific applications, when the fluid to be filtered is monitored in real time to obtain monitoring data, and the monitoring data is converted into a continuous electronic signal and output as a real-time data stream, a pre-configured sensor is used to monitor the fluid to be filtered in real time to obtain monitoring data; the monitoring data is amplified by a signal amplification circuit and then converted into analog to digital to obtain a continuous electronic signal as a real-time data stream.

[0040] The sensors include: laser particle counters, optical sensors of spectrometers, and electrochemical sensors; the monitoring data include particle concentration, particle size distribution, and chemical composition; In addition, in the above embodiment, the filtering optimization parameters include filtering aperture, filtering pressure and filtering flow rate; when the real-time data stream is analyzed by using a dynamic interactive comprehensive analysis algorithm to obtain analysis results, and filtering optimization parameters are generated based on the analysis results, the multi-dimensional characteristics of the real-time data stream can be converted into a feature distribution function through dynamic feature distribution modeling; based on the feature distribution function, a dynamic interactive mapping function is constructed, and a comprehensive evolution analysis is performed on the dynamic interactive mapping function to generate a time evolution quantity of the feature; based on the time evolution quantity of the feature, a recursive optimization function is constructed, and the filtering optimization parameters are generated in real time according to the recursive optimization function.

[0041] Specifically, the dynamic interactive comprehensive analysis algorithm aims to achieve comprehensive optimization of high-precision filtering parameters through dynamic modeling of real-time data and multi-dimensional feature interaction, combined with sensitivity analysis of optimization functions and dynamic parameter update mechanism. The specific implementation process is as follows: First, based on real-time data flow ,in Represents the concentration of particulate matter; it is a time function of the pollutant concentration; It represents the particle size distribution, which is the time distribution of particle diameter; A vector representing chemical composition, each For time On Through dynamic feature distribution modeling, the multi-dimensional characteristics of real-time data streams are transformed into feature distribution functions. The formula is: ; in, is the characteristic distribution function, describing the fluid in time Dynamic changes in the combined effects of particle concentration, size distribution and chemical properties within the range; Represents time, which is a continuous variable used to describe the range of time changes; is the time weight factor, used to adjust the time point Contribution to the overall feature distribution, value range ; is a discrete time sampling point, in continuous time a finite set of time segments selected from is the particle concentration, describing the time The concentration of particles in the fluid at is the particle size distribution, describing the time The average particle size of particles in the fluid; is the mean of the particle size distribution, reflecting the entire time range The center value of the particle size distribution of the internal fluid; is the standard deviation of the particle size distribution, which indicates the degree of dispersion of the particle size distribution of the fluid; It is chemical properties that describe the particle's Time Chemical properties, such as metal ion concentration, dissolved organic matter content, etc. is the total time range, which represents the time range for modeling fluid properties; is the total number of discrete time points, indicating The number of samples or discrete time points within the time range; It is the total number of chemical property dimensions, indicating the number of chemical property types of particles.

[0042] Based on the characteristic distribution function , build dynamic interactive mapping function , used to capture the deep association and temporal correlation between features. The formula is: ; in, is a dynamic interaction mapping function and a feature distribution function The results after nonlinear and time-periodic mapping reflect the complex interactions and time-evolution relationships of different features; is the mapping weight factor, indicating a specific power and time period The degree of impact on the overall mapping results; is the mapping bias, which indicates the basic offset of the mapping result and is used to adjust non-zero characteristics or eliminate errors; is the characteristic distribution function of Power, which indicates a nonlinear expansion of the feature distribution; It is a time period function, reflecting the periodic changes of characteristic distribution over time; is the integration variable; Is the maximum value of the polynomial power, representing the characteristic distribution function The highest order of nonlinear expansion is performed; Is the maximum value of the time period number, indicating the time period function Resolution control.

[0043] After completing the dynamic interaction mapping, the dynamic interaction mapping function Perform comprehensive evolution analysis to generate time evolution quantities of features The formula is: ; in, It's time The time evolution of the features on represents the comprehensive dynamic change trend of the feature interaction at the current moment; is a dynamic interactive mapping function About Time The rate of change of indicates the immediate change trend of feature interaction in the time dimension; is the cumulative weight factor, which is used to adjust the influence of the historical time accumulation item; It is the time interval The cumulative amount of the square value of the internal dynamic interaction mapping function represents the cumulative intensity of the interaction feature in the historical time dimension; is the exponential adjustment factor, which is used to control the amplitude of the exponential suppression term; is the exponential decay term of the dynamic interaction feature, representing the dynamic interaction mapping function Nonlinear suppression of evolution trends; is an exponential decay adjustment parameter, representing the dynamic interaction mapping function Scope of influence.

[0044] Feature-based time evolution , construct a recursive optimization function , used to generate optimization parameters in real time. The recursive optimization formula is: ; in, It is a recursive optimization function, which represents the dynamic optimization result of the filtration parameters. Its value is used to guide the generation of filtration aperture, filtration pressure and flow rate; is the weight in the recursive optimization function, indicating the The influence weight of layer recursion on the optimization results; It is the adjustment factor of recursive optimization, which controls the time evolution of the feature In the The degree of influence on the optimization results in layer recursion; is the identifier of the recursive layer, which is used to indicate that the current calculation in the recursive optimization function is the first Contribution of layer recursion; is the total number of layers of the recursive optimization function, indicating the complexity of the recursive optimization; is a regularization factor, which is used to prevent overfitting during the optimization process and ensure the robustness of the optimization results; It is the time interval The cumulative value of the square of the time evolution of the internal features.

[0045] Recursive optimization function based on filtering parameters , generate filtration optimization parameters, including filter pore size , Filtration pressure and filtration flow rate The specific formula is: Filter aperture: ; in, is the filtration pore size, which is the actual working pore size of the filter under current conditions; is the minimum permissible pore size of the filter; is a recursive optimization function Standard deviation of particle size distribution; Sensitivity; is the sensitivity adjustment factor used to balance the partial derivative Impact on filter pore size adjustment.

[0046] Filtration pressure: ; in, is the filtration pressure, used to drive the fluid for filtration; is the dynamic viscosity of the fluid, describing the friction inside the fluid, obtained through a correlation function with the chemical composition and concentration distribution of the particles, which is obtained empirically; is the effective filtration area during filtration, obtained by a function related to the particle size distribution and concentration distribution of the particles, the function being obtained empirically; is the weight factor, describing the effective filtration area during filtration Sensitivity of changes in the optimized pressure; is the effective filtering area of ​​the recursive optimization function during filtering The partial derivative of , which is composed of the partial derivatives of the concentration distribution and the particle size distribution, represents the sensitivity of the optimization state to the change of the filtration area; is a weighting factor describing the dynamic viscosity of the fluid Sensitivity of changes in the optimized pressure; is the recursive optimization function for the dynamic viscosity of the fluid The partial derivative of , which consists of the partial derivatives with respect to the concentration distribution and the chemical composition, represents the sensitivity of the optimization state to the change of fluid viscosity.

[0047] Filtration flow rate: ; in, is the filtration flow rate; is the target fluid flow rate, which indicates the maximum volume flow rate of the fluid that the filtration system needs to handle; is the density of the fluid, describing the ratio of the fluid's mass to its volume; is the adjustment coefficient of the partial derivative of flow velocity sensitivity to density; is the adjustment coefficient of the partial derivative of flow rate sensitivity to viscosity; is the recursive optimization function for the fluid density The partial derivative of .

[0048] When the particles in the fluid are initially separated based on the filtration optimization parameters to obtain clean fluid and separated particles, the filtration module can be selected according to the required filtration parameters, such as filtration devices customized or directly purchased from Mott, Micronics Engineering Filtration Group, Jiangsu Unite, etc. for filtration treatment.

[0049] In addition, in the above embodiment, the state parameters include: the residual concentration of particulate matter in the cleaning fluid, the fluid flow rate and the pressure difference across the filter; in addition, the state parameters can also be compared with the target state preset according to the specific scenario using the empirical method. If the preset target state is met, there is no need for update optimization and subsequent optimization of the filtering parameters using historical data.

[0050] When the filtration optimization parameters are updated and optimized based on the state parameters while balancing the flux and the filtration accuracy to obtain the updated and optimized filtration parameters, the residual concentration of particulate matter in the clean fluid is compared with the pre-configured target concentration. When the comparison result shows that the residual concentration of particulate matter in the clean fluid is higher than the target concentration, the filtration aperture is reduced; otherwise, the filtration aperture is maintained or increased; based on the adjusted filtration aperture, the filtration area of ​​the fluid is determined, and the fluid flow rate is adjusted according to the filtration area; and the filtration pressure is adjusted according to the pressure difference at both ends of the filter and the predetermined pressure difference adjustment coefficient.

[0051] Specifically, based on the state parameters including the residual concentration of particles in the clean fluid , Pressure difference between the two ends of the filter , and the fluid flow rate ; By comparing the residual concentration of particulate matter With target concentration , to determine whether the filtration accuracy meets the requirements and to evaluate the filtration effect of the clean fluid. The derivation logic is as follows: If the particle concentration is higher than the target value, it means that the current filter aperture is too large and needs to be reduced; otherwise, the aperture is maintained or appropriately widened. The update formula for the filter aperture is: ; in, It is the updated and optimized filter aperture, which indicates the pore size of the filter medium and is used to control the particle retention capacity when the fluid passes through the filter; It is the aperture adjustment coefficient, which is used to control the sensitivity of concentration deviation to filter aperture adjustment. It is determined according to the specific scenario and has a value range of .

[0052] Adjust flow rate according to filter area , while ensuring that the filtration flux meets the target requirements. The logic of flow rate adjustment is based on the flow formula: ; in, It is the updated and optimized filtration flow rate, which means the running speed of the fluid during filtration after the new round of parameter adjustment; is the flux adjustment coefficient, which controls the sensitivity of the filtration flux deviation to the flow rate adjustment. It is determined by empirical method and has a value range of ; is the target filtration flux, which indicates the filtration flow value that is expected to be achieved during system operation; is the current filtration flux, which indicates the actual volume flow of fluid passing through the filter monitored in real time; It is the effective filtering area of ​​the filter, which indicates the current working area during filtering; is the adjustment coefficient of particle concentration adjustment, which controls the sensitivity of particle concentration deviation to flow rate adjustment. It is determined by empirical method and has a value range of .

[0053] The filter pressure is further adjusted in real time to balance the filter resistance and fluid flux. The logic of pressure adjustment is based on the current pressure difference between the two ends of the filter. If the pressure difference is too large, the filter will be clogged; if the pressure difference is too small, the filtration efficiency may be insufficient. The pressure adjustment formula is: ; in, is the updated and optimized filtration pressure, which is the pressure that should be reached during filtration after this optimization adjustment; It is the pressure difference adjustment coefficient, which is used to determine the influence of the current pressure difference on the filter pressure adjustment. It is determined according to the specific scenario and the value range is ; is the flux adjustment coefficient, which is used to determine the contribution weight of the filtration flux deviation to the pressure adjustment. It is determined by empirical method and has a value range of .

[0054] When the updated and optimized filtration parameters are obtained, the particulate matter in the fluid can be secondary separated based on the updated and optimized filtration parameters to obtain the optimized clean fluid, and the monitoring parameters of the obtained clean fluid can be stored and analyzed to form historical data, including historical data records and trend analysis.

[0055] When optimizing the updated and optimized filtering parameters in combination with the historical data of the clean fluid to obtain the final filtering parameters, the time series algorithm can be used to perform trend analysis on the historical data of the clean fluid to obtain the trend optimization sequence value; and based on the trend optimization sequence value, the updated and optimized filtering parameters are optimized to obtain the final filtering parameters.

[0056] Specifically, the trend analysis of the historical data of the cleaning fluid is performed using the time series algorithm, and the trend optimization sequence value obtained is ; Then the updated and optimized filtering parameters are optimized based on the trend optimization sequence value, and the final filtering parameters are:

[0057] ; ; ; in, , , is the final filtering parameter; is the trend optimization value of aperture change; is the trend optimization value of flow velocity change; is the trend optimization value of pressure change; is the scaling factor for aperture adjustment, determined empirically; is the proportional factor for flow rate adjustment, determined empirically; is the proportional factor for pressure adjustment, determined empirically.

[0058] In addition, in the process of using the final filtering parameters to adjust the filtering, the final state parameters at this time are obtained, and the final state parameters are compared with the target state preset according to the specific scenario using the empirical method. If both meet the preset target state, there is no need to update and optimize; if the preset target state is not met, further processing is performed according to the updating and optimization process of the filtering parameters until the preset target state is met.

[0059] Figure 3An embodiment of a computer device of the present invention is shown. The computer device may be a server, and the computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0060] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0061] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0062] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0063] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0064] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A high-precision intelligent high-throughput filtering method based on real-time monitoring, characterized in that: include: Performing real-time monitoring on the fluid to be filtered to obtain monitoring data, and converting the monitoring data into a continuous electronic signal and outputting it as a real-time data stream; Analyzing the real-time data stream using a dynamic interactive comprehensive analysis algorithm to obtain analysis results, and generating filtering optimization parameters based on the analysis results; Preliminarily separating the particles in the fluid based on the filtration optimization parameters to obtain a clean fluid and separated particles, and monitoring the obtained clean fluid in real time to obtain the state parameters of the clean fluid; Based on the state parameters, the filtration optimization parameters are updated and optimized while balancing the flux and the filtration accuracy to obtain updated and optimized filtration parameters; and the updated and optimized filtration parameters are optimized in combination with the historical data of the clean fluid to obtain the final filtration parameters, and the filtration adjustment is performed based on the final filtration parameters.

2. The high-precision intelligent high-flux filtering method based on real-time monitoring according to claim 1 is characterized in that: Performing real-time monitoring on the fluid to be filtered, obtaining monitoring data, and converting the monitoring data into a continuous electronic signal and outputting it as a real-time data stream includes: Using pre-configured sensors to monitor the fluid to be filtered in real time to obtain monitoring data; wherein the monitoring data includes particle concentration, particle size distribution and chemical composition; The monitoring data is amplified by a signal amplification circuit and then converted into analog-to-digital form to obtain a continuous electronic signal as a real-time data stream.

3. The high-precision intelligent high-flux filtering method based on real-time monitoring according to claim 1 is characterized in that: The filtration optimization parameters include filtration pore size, filtration pressure and filtration flow rate; Furthermore, the real-time data stream is analyzed using a dynamic interactive comprehensive analysis algorithm to obtain analysis results, and filtering optimization parameters are generated based on the analysis results, including: Through dynamic feature distribution modeling, the multi-dimensional characteristics of real-time data streams are converted into feature distribution functions; Based on the feature distribution function, a dynamic interaction mapping function is constructed, and a comprehensive evolution analysis is performed on the dynamic interaction mapping function to generate the time evolution quantity of the feature; Based on the time evolution of the feature, a recursive optimization function is constructed, and filtering optimization parameters are generated in real time according to the recursive optimization function.

4. The high-precision intelligent high-flux filtering method based on real-time monitoring according to claim 1 is characterized in that: The state parameters include: residual concentration of particles in the clean fluid, fluid flow rate, and pressure difference across the filter; Furthermore, based on the state parameters, the filtration optimization parameters are updated and optimized under the condition of balancing the flux and the filtration accuracy, and the updated and optimized filtration parameters include: Compare the residual concentration of particles in the clean fluid with a pre-configured target concentration, and if the comparison result shows that the residual concentration of particles in the clean fluid is higher than the target concentration, reduce the filter aperture; otherwise, maintain or increase the filter aperture; Based on the adjusted filter aperture, the filter area of ​​the fluid is determined, and the fluid flow rate is adjusted according to the filter area; the filter pressure is adjusted according to the pressure difference at both ends of the filter and the predetermined pressure difference adjustment coefficient.

5. The high-precision intelligent high-flux filtering method based on real-time monitoring according to claim 1 is characterized in that: The updated and optimized filtration parameters are optimized in combination with the historical data of the clean fluid, and the final filtration parameters include: A time series algorithm is used to perform trend analysis on historical data of the cleaning fluid to obtain a trend optimization sequence value; and based on the trend optimization sequence value, the updated and optimized filtering parameters are optimized to obtain the final filtering parameters.

6. A high-precision intelligent high-flux filtration system based on real-time monitoring, characterized in that: include: A real-time monitoring module, used to monitor the fluid to be filtered in real time, obtain monitoring data, and convert the monitoring data into a continuous electronic signal and output it as a real-time data stream; An intelligent analysis module, used to analyze the real-time data stream using a dynamic interactive comprehensive analysis algorithm, obtain analysis results, and generate filtering optimization parameters based on the analysis results; An adaptive filtering module is used to perform preliminary separation of particles in the fluid based on the filtering optimization parameters to obtain clean fluid and separated particles, and to perform real-time monitoring of the obtained clean fluid to obtain state parameters of the clean fluid; A balance control module, used to update and optimize the filtration optimization parameters based on the state parameters while balancing the flux and the filtration accuracy, to obtain updated and optimized filtration parameters; The intelligent control module is used to optimize the updated and optimized filtering parameters in combination with the historical data of the clean fluid to obtain the final filtering parameters, and perform filtering adjustments based on the final filtering parameters.

7. The high-precision intelligent high-flux filtration system based on real-time monitoring according to claim 6 is characterized in that: The real-time monitoring module monitors the fluid to be filtered in real time to obtain monitoring data, converts the monitoring data into a continuous electronic signal and outputs it as a real-time data stream, and uses a pre-configured sensor to monitor the fluid to be filtered in real time to obtain monitoring data; wherein the monitoring data includes particle concentration, particle size distribution and chemical composition; the monitoring data is amplified by a signal amplification circuit and then analog-to-digital conversion is performed to obtain a continuous electronic signal as a real-time data stream.

8. The high-precision intelligent high-flux filtration system based on real-time monitoring according to claim 6, characterized in that: The filtration optimization parameters include filtration pore size, filtration pressure and filtration flow rate; Furthermore, when the intelligent analysis module analyzes the real-time data stream using a dynamic interactive comprehensive analysis algorithm to obtain analysis results and generates filtering optimization parameters based on the analysis results, the multi-dimensional characteristics of the real-time data stream are converted into a feature distribution function through dynamic feature distribution modeling; Based on the feature distribution function, a dynamic interaction mapping function is constructed, and a comprehensive evolution analysis is performed on the dynamic interaction mapping function to generate the time evolution quantity of the feature; Based on the time evolution of the feature, a recursive optimization function is constructed, and filtering optimization parameters are generated in real time according to the recursive optimization function.

9. The high-precision intelligent high-flux filtration system based on real-time monitoring according to claim 6, characterized in that: The state parameters include: residual concentration of particles in the clean fluid, fluid flow rate, and pressure difference across the filter; Furthermore, the balance control module updates and optimizes the filtration optimization parameters based on the state parameters while balancing the flux and the filtration accuracy. When the updated and optimized filtration parameters are obtained, the residual concentration of particulate matter in the clean fluid is compared with a pre-configured target concentration. When the comparison result shows that the residual concentration of particulate matter in the clean fluid is higher than the target concentration, the filtration aperture is reduced; otherwise, the filtration aperture is maintained or increased; based on the adjusted filtration aperture, the filtration area of ​​the fluid is determined, and the fluid flow rate is adjusted according to the filtration area; and the filtration pressure is adjusted according to the pressure difference at both ends of the filter and a predetermined pressure difference adjustment coefficient.

10. The high-precision intelligent high-flux filtration system based on real-time monitoring according to claim 6, characterized in that: The intelligent control module optimizes the updated and optimized filtering parameters in combination with the historical data of the clean fluid to obtain the final filtering parameters, and uses a time series algorithm to perform trend analysis on the historical data of the clean fluid to obtain a trend optimization sequence value; The updated and optimized filtering parameters are optimized based on the trend optimization sequence values ​​to obtain the final filtering parameters.

Images