Automatic backwash control method and system for liquid inlet of filtration station

Abstract

The present invention provides an automatic backwash control method and system for liquid inlet in a filter station, which relates to the technical field of backwash control, including: interactively obtaining liquid characteristic parameters and filtration requirement parameters of the liquid to be filtered; performing filter medium matching, obtaining filter medium selection, and then configuring the filter element of the filter station to obtain the target filter element; obtaining target structural characteristics, initializing filtration conditions, and outputting initial filtration control constraints; using the initial filtration control constraints as optimization conditions, performing liquid inlet speed optimization, and locating the liquid inlet control speed; performing blockage trend analysis, performing backwash control optimization, and obtaining backwash control parameters; and using the backwash control parameters to perform intermittent automatic backwashing. The present invention solves the technical problem that the backwash control of the prior art is usually performed at a timed or preset cycle, and backwashing is often performed when the filter element is not completely blocked or is already severely blocked, resulting in resource waste or affecting the filtration effect.

Description

Technical Field

[0001] The present invention relates to the technical field of backwash control, and in particular to an automatic backwash control method and system for liquid inlet in a filter station. Background Art

[0002] During operation, the filter elements in a filtration station are prone to clogging due to the continuous accumulation of impurities. Existing backwash systems mostly use timed or preset cycles for backwashing. Because the backwash cycle is preset, premature backwashing, when the filter element is not completely clogged or the optimal backwashing time has not been reached, will result in a waste of resources. Conversely, if backwashing is delayed, the filter element will already be severely clogged, further affecting the filtration effect. Furthermore, the backwash control of traditional filtration systems is mostly based on fixed parameters such as liquid inlet speed, pressure, or cycle. This single control strategy cannot be dynamically adjusted based on the actual impurity content, filter element clogging, and filtration accuracy requirements, resulting in the inability to efficiently complete the filtration task within the specified time. Summary of the Invention

[0003] This application provides an automatic backwash control method and system for liquid inlet of a filtration station, aiming to solve the technical problem that the backwash control in the prior art is usually performed at a timed or preset cycle, and backwashing is often performed when the filter element is not completely clogged or is already severely clogged, resulting in waste of resources or affecting the filtration effect.

[0004] The first aspect disclosed in the present application provides an automatic backwash control method for liquid inlet of a filtration station, the method comprising: interactively obtaining liquid characteristic parameters and filtration requirement parameters of a liquid to be filtered, wherein the liquid characteristic parameters include impurity component information and filtration volume information, and the filtration requirement parameters include filtration time constraints and filtration accuracy constraints; matching filter media according to the impurity component information and filtration accuracy constraints, obtaining a filter medium selection, and then configuring the filter element of the filtration station based on the filter medium selection to obtain a target filter element; interactively obtaining target structural characteristics of the target filter element, and configuring the filter element according to the target structural characteristics and the filter medium selection. The selection is performed to initialize the filtering conditions and output the initial filtering control constraints, wherein the initial filtering control constraints include a filtering pressure difference threshold and a maximum allowable blockage rate; the initial filtering control constraints are used as optimization conditions, and the liquid inlet speed optimization is performed according to the filtering volume information and the filtering time constraint to locate the liquid inlet control speed; the blockage trend of the target filter element is analyzed according to the liquid inlet control speed, and the backwash control optimization is performed based on the analysis results to obtain the backwash control parameters; during the liquid inlet filtration process of the liquid to be filtered at the filtering station at the liquid inlet control speed, the backwash control parameters are used to perform intermittent automatic backwashing of the target filter element.

[0005] The second aspect disclosed in the present application provides an automatic backwash control system for liquid inlet of a filtration station, the system being used for the above-mentioned automatic backwash control method for liquid inlet of a filtration station, the system comprising: a liquid parameter acquisition module, the liquid parameter acquisition module being used to interactively obtain liquid characteristic parameters and filtration requirement parameters of a liquid to be filtered, wherein the liquid characteristic parameters include impurity component information and filtration volume information, and the filtration requirement parameters include filtration time constraints and filtration accuracy constraints; a filter element configuration module, the filter element configuration module being used to match filter media according to the impurity component information and filtration accuracy constraints, and after obtaining the filter medium selection, obtain the target filter element by configuring the filter element of the filtration station based on the filter medium selection; a condition initialization module, the condition initialization module being used to interactively obtain the target structural characteristics of the target filter element, and The filtering conditions are initialized according to the target structural characteristics and the filter medium selection, and the initial filtering control constraints are output, wherein the initial filtering control constraints include the filtering pressure difference threshold and the maximum allowable blockage rate; a liquid inlet speed optimization module, the liquid inlet speed optimization module is used to use the initial filtering control constraints as optimization conditions, perform liquid inlet speed optimization according to the filtering volume information and the filtering time constraint, and locate the liquid inlet control speed; a control optimization module, the control optimization module is used to analyze the blockage trend of the target filter element according to the liquid inlet control speed, and perform backwash control optimization based on the analysis results to obtain backwash control parameters; an automatic backwash module, the automatic backwash module is used to use the backwash control parameters to perform intermittent automatic backwashing of the target filter element during the liquid inlet filtration process of the liquid to be filtered at the liquid inlet control speed at the filtration station.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] Interactively obtain the liquid characteristic parameters and filtration requirement parameters of the liquid to be filtered, among which the liquid characteristic parameters include impurity component information and filtration volume information, and the filtration requirement parameters include filtration time constraints and filtration accuracy constraints. These data provide an important basis for subsequent filtration operations and effectively ensure the filtration quality; match the filter media according to the impurity component information and filtration accuracy constraints, select appropriate filter media and configure filter elements, and ensure that the system can intercept impurities of different particle sizes through precise medium selection and filter element configuration. The matching of multi-layer filter media ensures effective interception of particles from large to small, improving the accuracy of filtration. At the same time, different filter layer structures can be designed according to different impurity components to flexibly respond to complex filtration requirements; according to the structural characteristics of the target filter element and the selection of filter media, initialize the filtration conditions, output the filtration pressure difference threshold and the maximum allowable blockage rate. These control constraints can ensure that the system is maintained within the service life of the filter element. Maintain its efficient operation; optimize the liquid inlet speed by filtering volume information and filtering time constraints, so that the filter station can automatically adjust the liquid inlet speed according to the needs of the task, ensuring that the task is completed efficiently within the specified time, avoiding time waste and unnecessary energy consumption. At the same time, the optimized speed helps to reduce the fluctuation of pressure difference and the clogging speed of the filter element; analyze the clogging trend of the filter element through the liquid inlet speed, and optimize the backwash control parameters. This step ensures that backwashing is carried out at the best time by real-time monitoring of the clogging situation and pressure difference changes, while reducing unnecessary resource consumption and improving the overall energy efficiency of the system; finally, intermittent automatic backwashing of the filter station is achieved through the backwash control parameters, and automatic cleaning of the filter element without affecting the filtration efficiency, ensuring the stability and continuity of the filter station during long-term operation. Since the backwash process is automated, the need for human intervention is reduced, the risk of operating errors is reduced, and the reliability of the system is improved.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of the automatic backwash control method for liquid inlet of a filtration station provided in an embodiment of the present application.

[0010] Figure 2 Schematic diagram of the structure of the automatic backwash control system for liquid inlet of the filtration station provided in an embodiment of the present application.

[0011] Description of the reference numerals: liquid parameter acquisition module 10 , filter element configuration module 20 , condition initialization module 30 , liquid inlet speed optimization module 40 , control optimization module 50 , automatic backwashing module 60 . DETAILED DESCRIPTION

[0012] The embodiments of the present application provide an automatic backwash control method for liquid inlet of a filtration station, thereby solving the technical problem that the backwash control in the prior art is usually performed at a timed or preset cycle, and backwashing is often performed when the filter element is not completely clogged or is already severely clogged, resulting in waste of resources or affecting the filtration effect.

[0013] After introducing the basic principles of this application, various non-limiting embodiments of this application will be specifically described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0014] like Figure 1 As shown, an embodiment of the present application provides a method for controlling an automatic backwash of an inlet liquid for a filtration station, the method comprising:

[0015] Interactively obtain liquid characteristic parameters and filtration requirement parameters of the liquid to be filtered, wherein the liquid characteristic parameters include impurity component information and filtration volume information, and the filtration requirement parameters include filtration time constraints and filtration accuracy constraints.

[0016] Parameter information is obtained from multiple sources, such as users, sensors, and process monitoring systems. Among them, liquid characteristic parameters are about the physical and chemical properties of the liquid to be filtered, including impurity component information and filtration volume information. Impurity component information refers to the type, particle size, form and concentration of impurities contained in the liquid to be filtered. Different types of impurities have a direct impact on the selection of filter media and filtration process design. It can be obtained through laboratory analysis or online sensor equipment detection, such as using a laser particle size analyzer to measure particle size distribution; filtration volume information refers to the total amount of liquid to be filtered, which can be obtained through a liquid flow meter or other fluid monitoring equipment.

[0017] The filtration requirement parameters define the performance standards of the entire filtration process and are determined by the specific needs of the filtration task, including filtration time constraints and filtration accuracy constraints. The filtration time constraint is the requirement that the filtration task must be completed within a specified time. It defines how long the filtration station must take to complete the required filtration task. It is set by the user or process engineer based on actual production needs; the filtration accuracy constraint is the minimum particle size or minimum particle concentration that the system can effectively filter impurities. It is also set by the user or process engineer based on actual production needs.

[0018] The filter medium is matched according to the impurity component information and the filtration accuracy constraint. After the filter medium selection is obtained, the filter element of the filter station is configured based on the filter medium selection to obtain the target filter element.

[0019] Filter media matching involves selecting the appropriate filter material and structure based on the liquid's impurity composition and the required filtration accuracy. Specifically, different types of impurities, such as silt, suspended solids, grease, and organic matter, require different filter materials. For example, grease-based impurities require a hydrophobic medium, while suspended solid particles require a hydrophilic medium. Filtration accuracy represents the minimum particle size or concentration of impurities to be removed. Based on the filtration accuracy constraints, the pore size or layer configuration of the filter media can be determined. For example, if a filtration accuracy of 10 microns is required, the selected filter media must be able to remove particles 10 microns and larger. By analyzing the impurity type and filtration particle size, the appropriate filter media is selected, including the media material, pore size, and filter layer structure. After the filter media is selected, it is assembled. The multi-layer filter elements can be arranged in descending order of particle size to gradually filter different impurities in the liquid.

[0020] After media selection is complete, the filter elements of the filtration station are configured. Filter elements include filter cartridges, filter bags, and filter screens. Filter element configuration includes the size, quantity, and arrangement of the filter elements. Specifically, appropriate filter element dimensions, including length and diameter, are selected based on the design specifications of the filtration station. These dimensions affect the filtration area, thereby affecting filtration efficiency and service life. The number of filter elements is calculated based on the filtration volume and filtration time requirements to ensure sufficient processing capacity. For example, if the filtration task requires processing a large amount of liquid, multiple groups of filter elements will be required to operate in parallel. Through the configuration process, the target filter elements are obtained that match the impurity composition and filtration accuracy requirements, ensuring that the filtration station can operate efficiently while meeting the accuracy requirements and maintaining filtration performance through subsequent backwashing.

[0021] Furthermore, the filter medium is matched according to the impurity component information and the filtration accuracy constraint to obtain the filter medium selection, and the method includes:

[0022] Based on the impurity type, the impurity component information is disassembled to obtain multiple impurity particle size distribution characteristics of multiple impurity types; the multiple impurity particle size distribution characteristics are updated according to the filtration accuracy constraint to obtain multiple filtration particle size distribution characteristics; the multiple filtration particle size distribution characteristics are integrated to obtain a global particle size distribution characteristic; based on the global particle size distribution characteristic, multi-stage filter media matching is performed to obtain a multi-layer filter element, wherein the multi-layer filter element has multiple filtration scales, filter layer thicknesses and filter layer material identifications; based on the multiple filtration scales, multi-layer filter elements are serially assembled to obtain the filter medium selection.

[0023] Impurity component information includes various impurity types in the liquid to be filtered, such as solid particles, suspended matter, organic matter, colloids, etc. Different impurity types have different physical and chemical properties, and these impurities have different effects on the filter media during the filtration process. By analyzing the impurity component information, the impurities in the liquid are broken down into categories. Common classification methods include classification based on physical form (such as particulate matter, colloids, etc.), chemical properties (organic matter, inorganic matter, etc.), or size (micron-level, nano-level). The particle size range of each impurity determines its ability to pass through different porous media. The particle size distribution characteristics of different impurity types can be obtained through experimental analysis or online monitoring equipment. Solid particles may have larger particle sizes, such as above 10 microns, and are easily captured by primary filter media. Colloidal substances have smaller particle sizes, typically between 0.1 and 1 micron, and require finer filter media. Organic matter and dissolved substances are usually extremely small, even at the nanometer level, and require special treatment or deep filtration.

[0024] Not all impurities with extremely small particle sizes need to be completely removed. For example, in some applications, some very small particles are allowed to exist, so the filtration accuracy can be appropriately relaxed. According to the filtration accuracy constraint, the impurity particle size distribution characteristics are updated, that is, those extremely low particle size impurities that do not need to be removed are ignored, and the overall particle size distribution is adjusted to meet the filtration requirements. For example, assuming the filtration accuracy requirement is 5 microns, then impurities below 5 microns will not be filtered even if they exist, and only impurities of 5 microns and above need to be removed. In this way, the design of the filter medium is ensured to meet the actual needs of the filtration task.

[0025] By superimposing or statistically processing the particle size distribution characteristics of each impurity type, a comprehensive global particle size distribution characteristic is formed. This global particle size distribution characteristic represents the overall distribution of impurity particles in the liquid to be filtered within all particle size ranges, providing a basis for subsequent filter media selection and design.

[0026] In order to handle impurities of different particle size ranges, it is necessary to design a multi-layer filtration structure. Each layer of filter medium is responsible for filtering impurities within a specific particle size range. The multi-layer filter element has multiple filtration scales, filter layer thicknesses, and filter layer material identifiers. Among them, the filtration scale refers to the size range of particles that can be intercepted by each layer of filter medium; the filter layer thickness refers to the thickness of each layer of filter material, which affects the depth and durability of the filtration; the filter layer material identifier is based on the physical properties of different materials, such as corrosion resistance and mechanical strength, to select appropriate materials for multi-layer design, such as metal mesh, fiber filter layer, ceramic material, etc. For example, the coarse filter layer is used to capture larger particles, such as 10 microns and above, reducing the burden on subsequent filter layers; the intermediate filter layer is used to capture medium-sized particles, such as 1-10 microns; and the fine filter layer is used to remove smaller particles, such as 0.1-1 microns.

[0027] Multiple filter media are arranged layer by layer according to particle size to form a filtration structure from coarse to fine. The precision of each layer of filter elements is gradually improved to ensure that impurities are intercepted step by step. Specifically, the outermost layer is the coarse filter layer, which captures larger particles. The filtration precision increases as you go deeper into the inner layer until the finest filter layer. The final filter media selection ensures that the system can effectively remove impurities, while extending the life of the filter elements and reducing frequent maintenance and backwashing.

[0028] The target structural characteristics of the target filter element are interactively obtained, and the filter conditions are initialized according to the target structural characteristics and the filter medium selection, and the initial filter control constraints are output, wherein the initial filter control constraints include a filter pressure difference threshold and a maximum allowable blockage rate.

[0029] The structural characteristics of the target filter element refer to the physical and geometric properties of the filter element. These characteristics will affect key performance indicators such as filtration efficiency, pressure difference, and clogging tendency. The target structural characteristics include the geometric dimensions of the filter element, such as length, diameter, thickness, and material porosity. These characteristics determine the flow path and area of the liquid when passing through the filter element.

[0030] Initialize the filtering conditions according to the target structural characteristics and filter medium selection, and output the filter pressure difference threshold and the maximum allowable blockage rate. Specifically, the filter pressure difference threshold is the maximum allowable difference in liquid pressure before and after the filter element. It is an indicator to measure whether the filter element is close to blockage. The pressure difference can be calculated through fluid mechanics simulation, combined with the standard liquid inlet speed and the resistance coefficient of the filter element; the maximum allowable blockage rate is the maximum impurity coverage or blockage ratio that the filter element can withstand. When the surface blockage of the element exceeds this ratio, the filtration efficiency is significantly reduced, or the liquid cannot pass smoothly. The maximum allowable blockage rate can be set according to the material properties of the filter element, the impurity particle size distribution and the fluid dynamics simulation. It should be understood that when the blockage rate is the largest, that is, when the pressure difference is the largest, that is, when backwashing is required.

[0031] Furthermore, target structural characteristics of the target filter element are interactively obtained, and filtering conditions are initialized according to the target structural characteristics and the filter medium selection, and initial filtering control constraints are output. The method includes:

[0032] Interactively obtain multiple element material information of the multi-layer filter element; calculate the filter area according to the target structural characteristics to obtain the effective filter area; perform network data call based on the multiple element material information and the effective filter area to obtain multiple filter simulation models, and then obtain the filter element model by fusing the multiple filter simulation models; after performing local data call on the filter station to obtain the standard liquid inlet speed, use the standard liquid inlet speed to perform fluid mechanics simulation of the filter element model, output the structural pressure difference threshold, use the standard liquid inlet speed to perform fluid mechanics simulation of the multiple filter simulation models, and output multiple single pressure difference thresholds; perform intersection solution on the structural pressure difference threshold and multiple single pressure difference thresholds to obtain the filtration pressure difference threshold; perform fluid mechanics simulation of the filter element model with the maximum value of the filtration pressure difference threshold as a constraint, and obtain the maximum allowable blockage rate in the filter element model call based on the simulation results.

[0033] The material of the multi-layer filter element determines the performance of the filter medium, such as corrosion resistance, mechanical strength, high temperature resistance, hydrophilicity or hydrophobicity, etc. These characteristics directly affect the performance and life of the filter element in different working environments. By interacting with suppliers, designers or material databases, specific material information of the filter element can be obtained. Each layer of the filter element may use different materials, depending on the requirements of the filter medium and the working environment. The material type may be metal, ceramic, fiber, polymer, etc.

[0034] The effective filtration area is the surface area of the filter element actually used for liquid filtration and is a key factor affecting filtration efficiency. The target structural characteristics include the geometric dimensions of the filter element, such as length, diameter, thickness, and material porosity. Based on the target structural characteristics of the filter element, the effective filtration area is obtained through geometric calculation or simulation tools. The larger the effective filtration area, the faster the liquid flows through the filter element, which helps to improve the filtration effect and reduce the pressure difference and blockage rate.

[0035] Based on the filter element material information and effective filtration area, online material databases or simulation tools are used to retrieve filtration simulation models specific to these materials. These models simulate the filter element's performance under various conditions, such as impurity retention capacity, pressure differential variation, and clogging rate. By accessing this data, multiple filtration simulation models are generated, covering performance across different materials, filtration areas, and operating conditions. These different filtration simulation models are then integrated to form a comprehensive filter element model. This model provides comprehensive predictions of filtration performance, including filtration efficiency, pressure differential variation, and clogging trends, providing a reference for optimizing and controlling the filtration system. The standard inlet velocity is the default inlet velocity set by the system. This velocity represents the rate at which fluid flows into the filter element and is typically determined based on the filter station's design and historical data. Within the filter element model, a fluid dynamics simulation using this standard inlet velocity simulates the flow path and velocity distribution of the fluid through the filter element, predicting the pressure differential generated by the fluid passing through the element. The simulation results output a structural pressure differential threshold, representing the maximum pressure differential that the filter element can withstand across its entire structure. Exceeding this pressure differential threshold can lead to damage or a significant decrease in efficiency. For multiple filtration simulation models, fluid mechanics simulation is performed using standard liquid inlet speeds. Each model represents a filter layer with different materials, pore sizes, and filtration scales. Each simulation model outputs a corresponding single-unit pressure difference threshold, which represents the maximum pressure difference that the filter element in this layer can withstand at the standard liquid inlet speed.

[0036] By comparing the structural pressure difference threshold and multiple individual pressure difference thresholds, their common limit value is found as the filtration pressure difference threshold. The filtration pressure difference threshold is the maximum pressure difference that the system can withstand in actual operation. If this threshold is exceeded, a part of the system may fail or the filtration performance may be seriously degraded.

[0037] Using the maximum value of the filter differential pressure threshold as a constraint, further fluid dynamics simulations were performed to predict how the differential pressure changes as the filter element gradually clogs, as well as the changes in the filter element's blockage rate over different time periods. The blockage rate refers to the proportion of the effective filtration area of the filter element reduced due to impurity accumulation. As impurities accumulate on the filter element, the flow path narrows, causing the pressure differential to increase. The blockage rate is equal to the difference between the initial filtration area and the effective filtration area divided by the initial filtration area. When the blockage rate reaches its maximum value, the filter element's differential pressure reaches the filter differential pressure threshold, marking the point at which the system needs to be backwashed. At this point, the filter element can no longer effectively filter any more liquid, and backwashing must be performed to remove sediment to restore filtration performance. Through fluid dynamics simulations, it is possible to predict the pressure changes of the filter element under different blockage rates and ultimately determine the maximum allowable blockage rate. This value corresponds to the degree of blockage when the filter element reaches its pressure differential limit, reflecting the maximum amount of impurity accumulation that the filter element can withstand without affecting filtration efficiency. It should be understood that when the blockage rate is maximum, the pressure differential is maximum, which is also when backwashing is necessary.

[0038] The initial filtration control constraint is used as an optimization condition, and the liquid inlet speed optimization is performed according to the filtration volume information and the filtration time constraint to determine the liquid inlet control speed.

[0039] The set filtration pressure difference threshold and maximum allowable blockage rate are used as optimization conditions for the liquid inlet process, providing restrictions and references for the subsequent liquid inlet speed optimization. The liquid inlet speed optimization is performed according to the filtration volume information and filtration time constraints. The purpose is to find a suitable liquid inlet speed to maximize the filtration efficiency and minimize the clogging risk while meeting the filtration volume and filtration time constraints. Specifically, 1 / K of the standard liquid inlet speed is used as the speed change scale, and the liquid inlet speed is gradually adjusted to test the impact of different speeds on the filtration performance. The filtration efficiency is predicted by the model, and combined with the filtration volume information, the filtration time corresponding to each liquid inlet speed is calculated to ensure that the filtration task can be completed within the specified time. By continuously adjusting the liquid inlet speed and conducting simulation analysis, the appropriate liquid inlet control speed is finally determined.

[0040] A clogging trend analysis of the target filter element is performed according to the liquid inlet control speed, and a backwash control optimization is performed based on the analysis result to obtain backwash control parameters.

[0041] After determining the liquid inlet control speed, the clogging trend of the target filter element is monitored in real time. For example, the pressure difference before and after the filter element is monitored to predict the clogging trend of the filter element. When the pressure difference increases to a certain threshold, it means that the filter element is being clogged. Combined with the structural characteristics of the filter element and real-time monitoring data, the clogging rate of the filter element is calculated. The higher the clogging rate, the more obvious the decline in filtration performance.

[0042] By comparing the blockage rate and the pressure differential time limit, the backwash cycle—that is, how often backwash should be initiated—is determined. Generally, backwashing needs to be initiated when the blockage rate or pressure differential approaches the maximum allowable value. A fitness evaluation function, which considers energy consumption, life loss, and water consumption, is used to optimize backwash parameters based on historical backwash records and simulation data. Backwash control parameters include backwash water flow rate, backwash water duration, backwash gas flow rate, backwash gas duration, and comprehensive flushing duration.

[0043] During the process of the filtration station performing the inlet filtration of the liquid to be filtered at the inlet control speed, the backwashing control parameters are used to perform intermittent automatic backwashing of the target filter element.

[0044] During normal operation of the filtration station, the liquid to be filtered is controlled to enter the filtration system at a predetermined liquid inlet control rate. At this time, the filter elements perform conventional filtration operations, gradually removing impurities from the liquid. To prevent clogging of the filter elements, backwashing is performed intermittently. Specifically, backwashing is automatically initiated according to the backwash cycle. During backwashing, impurities on the surface of the filter element are first cleaned by reverse water flow, followed by gas flushing to enhance the cleaning effect. Backwashing is performed intermittently and does not run in parallel with the filtration process to ensure the overall efficiency of the filtration station. After backwashing is completed, the permeability of the filter element is restored, and the filtration operation continues at the set liquid inlet rate. This ensures that the filter station can efficiently complete the filtration task while maintaining the performance of the filter element through an optimized backwashing process, thereby reducing the operating costs of the system.

[0045] Furthermore, the initial filtration control constraint is used as an optimization condition, and the liquid inlet speed optimization is performed according to the filtration volume information and the filtration time constraint to locate the liquid inlet control speed. The method includes:

[0046] A liquid inlet correlation prediction model is pre-constructed; 1 / K of the standard liquid inlet speed is used as a speed change scale to update the data of the standard liquid inlet speed to obtain a first standby liquid inlet speed; the first standby liquid inlet speed is input into the liquid inlet correlation prediction model to obtain a first blockage rate time limit, a first filtration pressure difference time limit and a first predicted filtration efficiency; the filtration volume information and the first predicted filtration efficiency are used to calculate a first predicted filtration time, and if the first predicted filtration time meets the filtration time constraint, the first standby liquid inlet speed is retained, and the first difference between the first blockage rate time limit and the first filtration pressure difference time limit is used as the first control reliability coefficient of the first standby liquid inlet speed; and so on, by continuously updating the standard liquid inlet speed and using the liquid inlet correlation prediction model and the filtration time constraint to evaluate the update results, multiple standby liquid inlet speeds and multiple control reliability coefficients that meet the preset update frequency are obtained; the multiple control reliability coefficients are serialized, and the liquid inlet control speed is located from the multiple standby liquid inlet speeds based on the sorting results.

[0047] The liquid inlet correlation prediction model is built based on a back-propagation neural network. Its purpose is to predict the clogging trend, filtration pressure difference and filtration efficiency of the filter element at different liquid inlet rates through training and learning of historical data. This model is used to evaluate the performance of the system at various liquid inlet rates and help select the optimal liquid inlet rate.

[0048] The standard liquid inlet speed is the initial set liquid inlet speed based on the system design and filtration task. It can be set based on design specifications, historical data, or the requirements of the filtration task. The speed change scale is a reference value for adjustment based on the standard liquid inlet speed. Specifically, 1 / K of the standard liquid inlet speed is used as the adjustment basis to increase or decrease the speed. K is an integer representing the degree of fine-grained adjustment. If K is small, such as 2, the adjustment range is large and the change in liquid inlet speed is more extreme. If K is large, such as 10, the adjustment range is small and the change in liquid inlet speed is more subtle. Adjust the standard liquid inlet speed according to the determined speed change scale to obtain the first backup liquid inlet speed.

[0049] The obtained first backup liquid inlet speed is input into the constructed liquid inlet association prediction model. The model analyzes the input speed according to the patterns and features learned during the training process, and outputs the corresponding first blockage rate time limit, first filtration pressure difference time limit and first predicted filtration efficiency, wherein the first blockage rate time limit is the length of time for the filter element to reach the maximum allowable blockage rate at the liquid inlet speed. The length of this time limit determines the time the filter element can work continuously and also affects the backwash cycle; the first filtration pressure difference time limit is the length of time for the filter element to reach the maximum pressure difference threshold at the liquid inlet speed, which indicates the trend of pressure loss of the filter element over time; the first predicted filtration efficiency indicates the volume of liquid that the filtration system can process per unit time at the first backup liquid inlet speed.

[0050] The filtration time is calculated using the filtration volume information (i.e., the total volume of the liquid to be filtered) and the first predicted filtration efficiency (the volume of liquid that the filter element can process per unit time). That is, the filtration volume is divided by the first predicted filtration efficiency to obtain the first predicted filtration time. The predicted filtration time is a measurement indicator to ensure that the filtration task can be completed within the specified time. If the first predicted filtration time meets, that is, is less than or equal to, the time constraint, the current first backup liquid inlet speed can be retained; otherwise, it means that the current liquid inlet speed is inappropriate and needs to be readjusted.

[0051] While retaining the first backup liquid inlet speed, the first difference between the first blockage rate time limit and the first filtration pressure difference time limit is calculated. This difference reflects the time gap between the filter element reaching the blockage rate and pressure difference thresholds. The smaller the difference, the closer the system is to the ideal state. The first difference is used as the first control reliability coefficient of the speed. The smaller the control reliability coefficient, the better the liquid inlet speed and the more stable the system operation.

[0052] On the basis of the first backup liquid inlet speed, continue to adjust the liquid inlet speed, fine-tune the standard liquid inlet speed each time, and gradually increase or decrease the liquid inlet speed. After each speed adjustment, input the new backup liquid inlet speed into the liquid inlet association prediction model, repeat the previous process, obtain the blockage rate time limit, filtration pressure difference time limit, and predicted filtration efficiency, and calculate its predicted filtration time to determine whether the filtration time constraint is met. If not, continue to adjust the speed. If satisfied, retain the speed and calculate the corresponding control reliability coefficient until the preset update frequency is met. The preset update frequency is set according to actual needs, and finally multiple backup liquid inlet speeds that meet the filtration time constraint are obtained. For each backup liquid inlet speed, the corresponding control reliability coefficient is calculated.

[0053] All the obtained control reliability coefficients are arranged in ascending order. The smaller the control reliability coefficient, the better the performance of the filtration system at this speed. Therefore, the alternative liquid inlet speed with a smaller control reliability coefficient will be given priority. According to the sorting results, the selection starts from the speed with the smallest control reliability coefficient, and the liquid inlet speed corresponding to the smallest control reliability coefficient is positioned as the final liquid inlet control speed.

[0054] Furthermore, a liquid inflow correlation prediction model is pre-built, and the method includes:

[0055] The filter medium selection and impurity component information are used as historical data call constraints to obtain historical liquid inlet related data, wherein the historical liquid inlet related data includes multiple sample liquid inlet speeds, multiple sample filtration efficiencies, multiple blockage rate change speeds and multiple filtration pressure difference change speeds; multiple filtration pressure difference change time limits are calculated based on the filtration pressure difference threshold and multiple filtration pressure difference change speeds; multiple blockage rate change time limits are calculated based on the maximum allowable blockage rate and multiple blockage rate change speeds; the multiple sample liquid inlet speeds, multiple sample filtration efficiencies, multiple filtration pressure difference time limits and multiple blockage rate change time limits are used as training constructions to train the liquid inlet related prediction model constructed based on the back propagation neural network.

[0056] Using filter media selection and impurity composition information as constraints, the system then calls upon historical inflow data related to the filter media. This data can come from previous filtration run records, laboratory test results, or simulation data. The sample inflow rate is the inflow rate used in historical runs (each rate corresponds to a filtration process), selected for each specific situation. The sample filtration efficiency is the volume of liquid processed per unit time by the filter element at different inflow rates, representing the performance of the filtration system. The blockage rate represents the rate of increase in the blockage rate of the filter element at each sample inflow rate, reflecting the rate at which impurities accumulate on or within the filter element at a given inflow rate. The filter pressure differential change rate represents the rate at which the pressure differential across the filter element changes over time at each inflow rate. An increase in the pressure differential indicates that the filter element is gradually clogged, hindering liquid flow. The filter pressure differential change time limit is the maximum time allowed for the system to reach the filter pressure threshold at the current pressure differential change rate. This time limit is calculated by calculating the difference between the filter pressure threshold and the current pressure differential and dividing this difference by the filter pressure differential change rate.

[0057] The congestion rate change time limit represents the time required to reach the maximum allowable congestion rate from the current congestion rate at the current congestion rate change speed. The congestion rate change time limit is obtained by calculating the difference between the maximum allowable congestion rate and the current congestion rate, and then dividing the difference by the congestion rate change speed.

[0058] The obtained sample data, including liquid inlet speed, filtration efficiency, pressure difference time limit, and blockage rate change time limit, are used as training data for the model. These data are used to establish the association between liquid inlet speed and system performance (blockage rate, pressure difference, filtration efficiency). The back propagation neural network is a common multi-layer neural network, which is trained using the error back propagation algorithm. The network inputs historical data and adjusts the weight parameters after multiple iterations and learning to make the model's prediction results as consistent as possible with the actual situation. The specific training process is as follows: the sample liquid inlet speed, filtration efficiency, blockage rate time limit, and pressure difference time limit are input into the neural network. After nonlinear mapping of the hidden layer, the predicted value is output. The difference between the predicted value output by the model and the actual historical data is compared to calculate the error. According to the error, the gradient descent algorithm is used to adjust the weight parameters of the neural network to gradually reduce the error. The forward propagation and back propagation processes are repeated until the model error converges to the preset threshold range to obtain the liquid inlet correlation prediction model. The trained liquid inlet correlation prediction model can predict the blockage rate time limit, filtration pressure difference time limit, and filtration efficiency according to the input liquid inlet speed.

[0059] Furthermore, a clogging trend analysis of the target filter element is performed according to the liquid inlet control speed, and backwash control optimization is performed based on the analysis result to obtain backwash control parameters. The method includes:

[0060] Direction data of the liquid inlet control speed is called to obtain a control blockage rate time limit and a control filtration pressure difference time limit; the smaller value is called by comparing the control blockage rate time limit and the control filtration pressure difference time limit as the backwash period; a fitness weight configuration is predefined, and a fitness evaluation function is constructed based on the fitness weight configuration, wherein the fitness weight configuration includes energy consumption weight, life loss weight and water consumption weight; the initial filtration control constraint is used as a data call constraint to filter and call historical backwash records to obtain multiple sample backwash records, wherein each sample backwash record in the multiple sample backwash records includes a sample control parameter and a sample flushing consumption; the fitness evaluation function is used to evaluate the fitness of the multiple sample backwash records, and the initial control parameters are located based on the evaluation results, wherein the initial control parameters are composed of backwash water flow rate, backwash water flushing time, backwash gas flow rate, backwash gas flushing time and comprehensive flushing time; the backwash period is added to the initial control parameters to obtain the backwash control parameters.

[0061] For the liquid inlet control speed, the system's operation records at the current liquid inlet speed are called through historical data, simulation models or real-time monitoring data to obtain two time limit data: the control blockage rate time limit and the control filtration pressure difference time limit. Among them, the control blockage rate time limit indicates when the filter element reaches the set blockage rate threshold as the blockage rate gradually increases; the control filtration pressure difference time limit indicates when the pressure difference before and after the filter element gradually increases as the filtration process progresses, and reaches the maximum allowable pressure difference.

[0062] Compare the time limit for controlling the blockage rate and the time limit for controlling the filtration pressure difference, and select the smaller value of the two time limits as the backwash cycle. Because no matter whether the blockage rate exceeds the threshold or the pressure difference exceeds the limit, the filter element can no longer continue to work efficiently. Therefore, it is necessary to start backwashing when the smaller time limit is reached to prevent a serious decline in filtration performance.

[0063] To optimize the backwash process, multiple influencing factors need to be comprehensively considered and each factor assigned a weight. Specifically, energy consumption includes the electricity or other energy consumed during the backwash process. The lower the energy consumption, the lower the system's operating costs. Therefore, energy consumption is an important weight. The backwash process causes a certain amount of wear and tear on the filter elements, affecting their service life. To extend the service life of the elements, life loss is incorporated into the fitness evaluation. The backwash process consumes a certain amount of water, and water consumption is a key consideration. The size of these three weights is predefined by the user or system engineer based on the needs of the application scenario. For example, in scenarios where energy conservation is a priority, the energy consumption weight can be set higher, while in scenarios where equipment maintenance costs are high, the weight of life loss may be higher.

[0064] Based on these weights, a fitness evaluation function is constructed to assess the comprehensive effectiveness of different backwash parameter configurations. The goal of fitness evaluation is to find the optimal balance between energy consumption, life loss, and water consumption, ensuring that backwashing effectively removes impurities while minimizing resource consumption and equipment wear. The output of the fitness function is a numerical value. A larger value indicates a better balance between energy consumption, life loss, and water consumption, and a more optimal backwash process.

[0065] Taking the initial filtration control constraint as the screening condition, backwash records similar to the current filtration task and filter element are screened out from the historical operation to obtain multiple sample backwash records. Each record can effectively eliminate the congestion condition described by the initial filtration control constraint. Each sample backwash record includes sample control parameters and sample flushing consumption. Among them, the sample control parameters record the specific parameters of the historical backwash operation, including backwash water flow rate, air flow rate, flushing time, etc. The sample flushing consumption represents the resources consumed during the backwash process, including water consumption, energy consumption, and wear on the filter element.

[0066] The constructed fitness evaluation function is used to evaluate multiple sample backwash records. The fitness evaluation function calculates the fitness value of each sample based on its energy consumption, life loss and water consumption indicators to represent its comprehensive performance. The larger the fitness value, the better the backwash scheme is in terms of the balance between energy consumption, life loss and water consumption. According to the fitness evaluation results, the sample backwash record with the largest fitness is selected, and its corresponding control parameters are extracted as the initial control parameters. The initial control parameters are composed of backwash water flow rate, backwash water flushing time, backwash air flow rate, backwash air flushing time and comprehensive flushing time.

[0067] The backwash water flow rate is the water flow rate used to flush the filter element, which usually affects the cleaning effect and water consumption; the backwash water flushing time is the duration of the water flow during the backwash process, which determines the length of the cleaning process; the backwash air flow rate is the air flow rate used for auxiliary flushing, which is usually used to accelerate the shedding of impurities; the backwash air flushing time is the duration of the air flow, which cooperates with the water flow flushing; the comprehensive flushing is the time it takes for the air flow and water flow to flush the filter element synchronously using the water flow rate and air flow rate.

[0068] After combining the initial control parameters with the backwash cycle, the final backwash control parameters are generated to guide the backwash process.

[0069] Furthermore, the sample control parameters are composed of sample water flow rate, sample water flushing time, sample gas flow rate, sample gas flushing time, and sample comprehensive flushing time.

[0070] The sample water flow rate is the water flow rate used to flush the filter element, which usually affects the cleaning effect and water consumption; the sample water flushing time is the duration of the water flow during the backwash process, which determines the length of the cleaning process; the sample gas flow rate is the gas flow rate used for auxiliary flushing, which is usually used to accelerate the removal of impurities; the sample gas flushing time is the duration of the gas flow, which cooperates with the water flushing; the sample comprehensive flushing is the time it takes for the air flow and water flow to flush the filter element simultaneously using the sample water flow rate and the sample gas flow rate.

[0071] Furthermore, the sample flushing consumption is composed of sample backwashing energy consumption, sample element life loss and sample water consumption.

[0072] During the backwash operation, certain resources will be consumed, including energy consumption, loss of filter element life, and water resource consumption. Among them, the sample backwash energy consumption is the electrical energy or other forms of energy consumed during the backwash process. The amount of energy consumption directly affects the economy of backwashing; the sample element life loss is the wear and tear of the filter element caused by repeated flushing during each backwash process, which shortens its service life. The lower the life shortening rate of the filter element, the higher the adaptability; the sample water consumption is the amount of water consumed during the backwash process. Reducing water consumption is an important goal of optimizing the backwash operation.

[0073] In summary, the automatic backwash control method for the inlet liquid of the filtration station provided in the embodiment of the present application has the following technical effects:

[0074] Interactively obtain the liquid characteristic parameters and filtration requirement parameters of the liquid to be filtered, among which the liquid characteristic parameters include impurity component information and filtration volume information, and the filtration requirement parameters include filtration time constraints and filtration accuracy constraints. These data provide an important basis for subsequent filtration operations and effectively ensure the filtration quality; match the filter media according to the impurity component information and filtration accuracy constraints, select appropriate filter media and configure filter elements, and ensure that the system can intercept impurities of different particle sizes through precise medium selection and filter element configuration. The matching of multi-layer filter media ensures effective interception of particles from large to small, improving the accuracy of filtration. At the same time, different filter layer structures can be designed according to different impurity components to flexibly respond to complex filtration requirements; according to the structural characteristics of the target filter element and the selection of filter media, initialize the filtration conditions, output the filtration pressure difference threshold and the maximum allowable blockage rate. These control constraints can ensure that the system is maintained within the service life of the filter element. Maintain its efficient operation; optimize the liquid inlet speed by filtering volume information and filtering time constraints, so that the filter station can automatically adjust the liquid inlet speed according to the needs of the task, ensuring that the task is completed efficiently within the specified time, avoiding time waste and unnecessary energy consumption. At the same time, the optimized speed helps to reduce the fluctuation of pressure difference and the clogging speed of the filter element; analyze the clogging trend of the filter element through the liquid inlet speed, and optimize the backwash control parameters. This step ensures that backwashing is carried out at the best time by real-time monitoring of the clogging situation and pressure difference changes, while reducing unnecessary resource consumption and improving the overall energy efficiency of the system; finally, intermittent automatic backwashing of the filter station is achieved through the backwash control parameters, and automatic cleaning of the filter element without affecting the filtration efficiency, ensuring the stability and continuity of the filter station during long-term operation. Since the backwash process is automated, the need for human intervention is reduced, the risk of operating errors is reduced, and the reliability of the system is improved.

[0075] Based on the same inventive concept as the automatic backwash control method for the filter station in the above embodiment, Figure 2 As shown, an embodiment of the present application provides an automatic backwash control system for a filtration station, the system comprising:

[0076] A liquid parameter acquisition module 10 is used to interactively obtain liquid characteristic parameters and filtration requirement parameters of the liquid to be filtered, wherein the liquid characteristic parameters include impurity component information and filtration volume information, and the filtration requirement parameters include filtration time constraints and filtration accuracy constraints; a filter element configuration module 20 is used to match the filter medium according to the impurity component information and filtration accuracy constraints, and after obtaining the filter medium selection, the filter element configuration of the filter station is performed based on the filter medium selection to obtain the target filter element; a condition initialization module 30 is used to interactively obtain the target structural characteristics of the target filter element, and initialize the filtration conditions according to the target structural characteristics and the filter medium selection, and output the initial filter Control constraints, wherein the initial filtration control constraints include a filtration pressure difference threshold and a maximum allowable blockage rate; a liquid inlet speed optimization module 40, the liquid inlet speed optimization module 40 is used to use the initial filtration control constraints as optimization conditions, perform liquid inlet speed optimization according to the filtration volume information and filtration time constraints, and locate the liquid inlet control speed; a control optimization module 50, the control optimization module 50 is used to perform a blockage trend analysis of the target filter element according to the liquid inlet control speed, and perform backwash control optimization based on the analysis results to obtain backwash control parameters; an automatic backwash module 60, the automatic backwash module 60 is used to use the backwash control parameters to perform intermittent automatic backwashing of the target filter element during the liquid inlet filtration process of the liquid to be filtered at the liquid inlet control speed at the filtration station.

[0077] Furthermore, the system further includes a filter medium selection acquisition module to perform the following operation steps:

[0078] Based on the impurity type, the impurity component information is disassembled to obtain multiple impurity particle size distribution characteristics of multiple impurity types; the multiple impurity particle size distribution characteristics are updated according to the filtration accuracy constraint to obtain multiple filtration particle size distribution characteristics; the multiple filtration particle size distribution characteristics are integrated to obtain a global particle size distribution characteristic; based on the global particle size distribution characteristic, multi-stage filter media matching is performed to obtain a multi-layer filter element, wherein the multi-layer filter element has multiple filtration scales, filter layer thicknesses and filter layer material identifications; based on the multiple filtration scales, multi-layer filter elements are serially assembled to obtain the filter medium selection.

[0079] Furthermore, the system further includes a maximum allowable congestion rate acquisition module to perform the following operation steps:

[0080] Interactively obtain multiple element material information of the multi-layer filter element; calculate the filter area according to the target structural characteristics to obtain the effective filter area; perform network data call based on the multiple element material information and the effective filter area to obtain multiple filter simulation models, and then obtain the filter element model by fusing the multiple filter simulation models; after performing local data call on the filter station to obtain the standard liquid inlet speed, use the standard liquid inlet speed to perform fluid mechanics simulation of the filter element model, output the structural pressure difference threshold, use the standard liquid inlet speed to perform fluid mechanics simulation of the multiple filter simulation models, and output multiple single pressure difference thresholds; perform intersection solution on the structural pressure difference threshold and multiple single pressure difference thresholds to obtain the filtration pressure difference threshold; perform fluid mechanics simulation of the filter element model with the maximum value of the filtration pressure difference threshold as a constraint, and obtain the maximum allowable blockage rate in the filter element model call based on the simulation results.

[0081] Furthermore, the system further includes a liquid inlet control speed positioning module to perform the following operation steps:

[0082] A liquid inlet correlation prediction model is pre-constructed; 1 / K of the standard liquid inlet speed is used as a speed change scale to update the data of the standard liquid inlet speed to obtain a first standby liquid inlet speed; the first standby liquid inlet speed is input into the liquid inlet correlation prediction model to obtain a first blockage rate time limit, a first filtration pressure difference time limit and a first predicted filtration efficiency; the filtration volume information and the first predicted filtration efficiency are used to calculate a first predicted filtration time, and if the first predicted filtration time meets the filtration time constraint, the first standby liquid inlet speed is retained, and the first difference between the first blockage rate time limit and the first filtration pressure difference time limit is used as the first control reliability coefficient of the first standby liquid inlet speed; and so on, by continuously updating the standard liquid inlet speed and using the liquid inlet correlation prediction model and the filtration time constraint to evaluate the update results, multiple standby liquid inlet speeds and multiple control reliability coefficients that meet the preset update frequency are obtained; the multiple control reliability coefficients are serialized, and the liquid inlet control speed is located from the multiple standby liquid inlet speeds based on the sorting results.

[0083] Furthermore, the system also includes a liquid inlet correlation prediction model building module to perform the following operation steps:

[0084] The filter medium selection and impurity component information are used as historical data call constraints to obtain historical liquid inlet related data, wherein the historical liquid inlet related data includes multiple sample liquid inlet speeds, multiple sample filtration efficiencies, multiple blockage rate change speeds and multiple filtration pressure difference change speeds; multiple filtration pressure difference change time limits are calculated based on the filtration pressure difference threshold and multiple filtration pressure difference change speeds; multiple blockage rate change time limits are calculated based on the maximum allowable blockage rate and multiple blockage rate change speeds; the multiple sample liquid inlet speeds, multiple sample filtration efficiencies, multiple filtration pressure difference time limits and multiple blockage rate change time limits are used as training constructions to train the liquid inlet related prediction model constructed based on the back propagation neural network.

[0085] Furthermore, the system further includes a backwash control parameter acquisition module to perform the following operation steps:

[0086] Direction data of the liquid inlet control speed is called to obtain a control blockage rate time limit and a control filtration pressure difference time limit; the smaller value is called by comparing the control blockage rate time limit and the control filtration pressure difference time limit as the backwash period; a fitness weight configuration is predefined, and a fitness evaluation function is constructed based on the fitness weight configuration, wherein the fitness weight configuration includes energy consumption weight, life loss weight and water consumption weight; the initial filtration control constraint is used as a data call constraint to filter and call historical backwash records to obtain multiple sample backwash records, wherein each sample backwash record in the multiple sample backwash records includes a sample control parameter and a sample flushing consumption; the fitness evaluation function is used to evaluate the fitness of the multiple sample backwash records, and the initial control parameters are located based on the evaluation results, wherein the initial control parameters are composed of backwash water flow rate, backwash water flushing time, backwash gas flow rate, backwash gas flushing time and comprehensive flushing time; the backwash period is added to the initial control parameters to obtain the backwash control parameters.

[0087] Furthermore, the sample control parameters are composed of sample water flow rate, sample water flushing time, sample gas flow rate, sample gas flushing time, and sample comprehensive flushing time.

[0088] Furthermore, the sample flushing consumption is composed of sample backwashing energy consumption, sample element life loss and sample water consumption.

[0089] Through the above detailed description of the automatic backwash control method for the liquid inlet of the filter station in this specification, those skilled in the art can clearly understand the automatic backwash control system for the liquid inlet of the filter station in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part. The above description of the disclosed embodiments enables professionals in this field to implement or use the present application. Various modifications to these embodiments will be obvious to professionals in this field, and the general principles defined in this article can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, the present application will not be limited to the embodiments shown in this article, but will conform to the widest range consistent with the principles and novel features disclosed in this article.

Claims

1. A method for controlling the automatic backwashing of liquid inlet in a filtration station, characterized in that: The method comprises: Interactively obtaining liquid characteristic parameters and filtration requirement parameters of the liquid to be filtered, wherein the liquid characteristic parameters include impurity component information and filtration volume information, and the filtration requirement parameters include filtration time constraints and filtration accuracy constraints; Matching filter media according to the impurity component information and the filtration accuracy constraint, obtaining a filter medium selection, and configuring filter elements of the filtration station based on the filter medium selection to obtain a target filter element; Interactively obtaining target structural characteristics of the target filter element, initializing filtering conditions based on the target structural characteristics and filter medium selection, and outputting initial filtering control constraints, wherein the initial filtering control constraints include a filtering pressure difference threshold and a maximum allowable blockage rate; Taking the initial filtration control constraint as an optimization condition, performing liquid inlet speed optimization according to the filtration volume information and the filtration time constraint, and determining the liquid inlet control speed; performing a clogging trend analysis of the target filter element according to the liquid inlet control speed, and performing backwash control optimization based on the analysis result to obtain backwash control parameters; During the process of the filtration station filtering the liquid to be filtered at the liquid inlet control speed, the backwash control parameter is used to perform intermittent automatic backwashing of the target filter element; The method uses the initial filtration control constraint as an optimization condition, performs liquid inlet speed optimization according to the filtration volume information and the filtration time constraint, and locates the liquid inlet control speed. Pre-built liquid inflow correlation prediction model; The data of the standard liquid inlet speed is updated by using 1 / K of the standard liquid inlet speed as a speed change scale to obtain a first standby liquid inlet speed, wherein K represents the degree of subdivision of the adjustment range; Inputting the first standby liquid inlet speed into a liquid inlet correlation prediction model to obtain a first blockage rate time limit, a first filtration pressure difference time limit, and a first predicted filtration efficiency; A first predicted filtration time is calculated using the filtration volume information and the first predicted filtration efficiency. If the first predicted filtration time satisfies the filtration time constraint, the first standby liquid inlet speed is retained, and a first difference between the first blockage rate time limit and the first filtration pressure difference time limit is used as a first control reliability coefficient of the first standby liquid inlet speed. Similarly, by continuously updating the standard liquid inlet speed and using the liquid inlet correlation prediction model and the filtering time constraint to evaluate the update results, multiple backup liquid inlet speeds and multiple control reliability coefficients that meet the preset update frequency are obtained; Sequencing the plurality of control reliability coefficients, and locating the liquid inlet control speed from the plurality of backup liquid inlet speeds based on the sequencing result; Performing a clogging trend analysis of the target filter element according to the liquid inlet control speed, and performing backwash control optimization based on the analysis result to obtain backwash control parameters, the method comprising: Direction data of the liquid inlet control speed is called to obtain a time limit for controlling a blockage rate and a time limit for controlling a filtration pressure difference; By comparing the control blockage rate time limit and the control filtration pressure difference time limit, a smaller value is called as the backwash cycle; Predefine a fitness weight configuration, and construct a fitness evaluation function based on the fitness weight configuration, wherein the fitness weight configuration includes an energy consumption weight, a life loss weight, and a water consumption weight; Using the initial filter control constraint as a data call constraint to filter and call historical backwash records, a plurality of sample backwash records are obtained, wherein each of the plurality of sample backwash records includes a sample control parameter and a sample flushing consumption; Performing fitness evaluation on the plurality of sample backwash records using the fitness evaluation function, and locating initial control parameters based on the evaluation results, wherein the initial control parameters are composed of a backwash water flow rate, a backwash water flushing time, a backwash gas flow rate, a backwash gas flushing time, and a comprehensive flushing time; The backwash period is added to the initial control parameters to obtain the backwash control parameters.

2. The automatic backwash control method for a filter station according to claim 1, characterized in that: Matching filter media according to the impurity component information and the filtration accuracy constraint to obtain filter media selection, the method comprising: Decomposing the impurity component information based on the impurity type to obtain multiple impurity particle size distribution characteristics of multiple impurity types; updating the plurality of impurity particle size distribution characteristics according to the filtration accuracy constraint to obtain a plurality of filtration particle size distribution characteristics; fusing the plurality of filtered particle size distribution features to obtain a global particle size distribution feature; Performing multi-stage filter media matching based on the global particle size distribution characteristics to obtain a multi-layer filter element, wherein the multi-layer filter element has multiple filter scales, filter layer thicknesses, and filter layer material identifiers; The filter medium selection is obtained by serially assembling multi-layer filter elements based on the multiple filter dimensions.

3. The automatic backwash control method for a filter station according to claim 2, characterized in that: Interactively obtaining target structural features of the target filter element, initializing filtering conditions based on the target structural features and filter medium selection, and outputting initial filtering control constraints, the method includes: interactively obtaining multiple element material information of the multi-layer filter element; Calculating the filtration area according to the target structural characteristics to obtain an effective filtration area; After obtaining multiple filtration simulation models through network data call based on the multiple element material information and effective filtration areas, a filter element model is obtained by fusing the multiple filtration simulation models; After local data of the filtration station is called to obtain the standard liquid inlet speed, a fluid mechanics simulation of the filter element model is performed using the standard liquid inlet speed to output a structural pressure difference threshold value, and a fluid mechanics simulation of the multiple filtration simulation models is performed using the standard liquid inlet speed to output multiple single-unit pressure difference threshold values; Solving the intersection of the structural pressure difference threshold and multiple monomer pressure difference thresholds to obtain the filtering pressure difference threshold; Taking the maximum value of the filter pressure difference threshold as a constraint, a fluid mechanics simulation of the filter element model is performed, and based on the simulation result, the maximum allowable blockage rate is obtained by calling the filter element model.

4. The automatic backwash control method for a filter station according to claim 1, characterized in that: Pre-building a liquid inlet correlation prediction model, the method comprising: Using the filter medium selection and impurity component information as historical data call constraints, historical liquid inlet associated data is called to obtain, wherein the historical liquid inlet associated data includes multiple sample liquid inlet speeds, multiple sample filtration efficiencies, multiple blockage rate change speeds, and multiple filter pressure difference change speeds; Calculating and obtaining multiple filter pressure difference change time limits according to the filter pressure difference threshold and multiple filter pressure difference change speeds; Calculating and obtaining multiple congestion rate change time limits according to the maximum allowable congestion rate and multiple congestion rate change speeds; The multiple sample liquid inlet speeds, multiple sample filtration efficiencies, multiple filtration pressure difference time limits and multiple blockage rate change time limits are used as training structures to train the liquid inlet association prediction model constructed based on the back propagation neural network.

5. The automatic backwash control method for a filter station according to claim 1, characterized in that: The sample control parameters are composed of sample water flow rate, sample water flushing time, sample gas flow rate, sample gas flushing time, and sample comprehensive flushing time.

6. The automatic backwash control method for a filter station according to claim 5, characterized in that: The sample flushing consumption is composed of sample backwashing energy consumption, sample element life loss and sample water consumption.

7. The automatic backwash control system for liquid inlet of the filtration station is characterized by: A system for implementing the automatic backwash control method for a filter station according to any one of claims 1 to 6, comprising: a liquid parameter acquisition module, the liquid parameter acquisition module being used to interactively obtain liquid characteristic parameters and filtration requirement parameters of the liquid to be filtered, wherein the liquid characteristic parameters include impurity component information and filtration volume information, and the filtration requirement parameters include filtration time constraints and filtration accuracy constraints; a filter element configuration module, the filter element configuration module being configured to match filter media according to the impurity component information and the filtration accuracy constraint, and after obtaining the filter medium selection, configure the filter elements of the filter station based on the filter medium selection to obtain a target filter element; a condition initialization module, the condition initialization module being used to interactively obtain target structural characteristics of the target filter element, initialize filter conditions based on the target structural characteristics and filter medium selection, and output initial filter control constraints, wherein the initial filter control constraints include a filter pressure difference threshold and a maximum allowable blockage rate; a liquid inlet speed optimization module, the liquid inlet speed optimization module being configured to use the initial filtration control constraint as an optimization condition, perform liquid inlet speed optimization according to the filtration volume information and the filtration time constraint, and determine the liquid inlet control speed; a control optimization module, the control optimization module being used to analyze the clogging trend of the target filter element according to the liquid inlet control speed, and to perform backwash control optimization based on the analysis result to obtain backwash control parameters; An automatic backwashing module is used to use the backwashing control parameters to perform intermittent automatic backwashing of the target filter element during the liquid inlet filtration process of the liquid to be filtered at the liquid inlet control speed in the filtration station.

Images