Multi-stage filtration water purifier control method based on artificial intelligence

Abstract

The invention relates to the technical field of water purification, and discloses a multi-stage filtration water purifier control method based on artificial intelligence, which comprises the following steps: step 1, by configuring a water quality sensor and an operation state sensor, collecting parameters of inflow water quality, including soluble solid concentration, water pH value, suspended particulate matter concentration and heavy metal concentration, the water flow velocity is obtained through the flow sensor, the water flow pressure in the filter is monitored through the pressure sensor, the service life and the blockage condition of a filter element are evaluated through the filter element state monitoring module, collected data are subjected to normalization processing, and input parameters of physical modeling are formed. By establishing a physical model based on water flow dynamics and pollutant diffusion and combining water quality data and flow velocity pressure data collected in real time, the running state of each filtering module is dynamically adjusted, the filtering process is dynamically optimized according to the water quality change, and the effects of improving the filtering efficiency and remarkably improving the pollutant removal rate are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of water purification, and in particular to a multi-stage filtering water purifier control method based on artificial intelligence. Background Art

[0002] As people's requirements for drinking water quality increase, multi-stage filtration water purifiers are widely used in households and industries. Water purifiers usually use a combination of modules such as particle filtration, activated carbon filtration, reverse osmosis filtration, and ultraviolet sterilization to meet the needs of water purification in different scenarios. However, existing multi-stage filtration water purifiers still face the following technical problems and limitations during operation:

[0003] The filter modules of existing water purifiers usually operate in a fixed mode. Regardless of the degree of water pollution, the activation order and operating parameters of the filter modules remain unchanged, which can easily lead to inefficiency and waste of resources in the filtration process. Especially when the water quality changes, the filtration process cannot be dynamically optimized according to actual needs, and efficient pollutant removal cannot be achieved.

[0004] There are significant differences in the characteristics of different filtration modules. For example, particle filtration modules are suitable for removing suspended particles, activated carbon filtration modules are suitable for adsorbing organic pollutants and odors, and reverse osmosis filtration modules are suitable for removing heavy metal ions and dissolved solids. However, the existing technology fails to make full use of characteristic parameters to optimize the activation sequence and operation time of the modules, resulting in the system being unable to adapt to changing water quality conditions and having poor flexibility and adaptability.

[0005] Existing water purifiers are unable to accurately calculate the relationship between filtration efficiency and power consumption. The pressure and flow rate of the water pump are usually set within a fixed range, and cannot be dynamically adjusted according to actual water quality and operating requirements, which in turn wastes energy, increases equipment operating costs, and fails to meet users' needs for energy saving and high efficiency.

[0006] The filter element is an important component of the water purifier, and its lifespan directly affects the operating efficiency and water quality safety of the water purification system. However, the replacement cycle of the filter element in the prior art is usually based on a simple time and flow calculation, which fails to take into account the changes in water quality and actual usage, and easily leads to untimely or premature replacement of the filter element, increasing maintenance costs and affecting the water purification effect.

[0007] Therefore, those skilled in the art provide a multi-stage filtering water purifier control method based on artificial intelligence to solve the above-mentioned problems. Summary of the invention

[0008] In view of the deficiencies in the prior art, the present invention provides a multi-stage filtering water purifier control method based on artificial intelligence to solve the problems raised in the above background technology.

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: A multi-stage filtering water purifier control method based on artificial intelligence, comprising:

[0010] Step 1: By configuring water quality sensors and operating status sensors, the parameters of the inlet water quality, including dissolved solid concentration, water pH, suspended particle concentration and heavy metal concentration, the water flow rate is obtained through the flow sensor, the water flow pressure inside the filter is monitored through the pressure sensor, and the filter element life and clogging are evaluated through the filter element status monitoring module. The collected data are normalized to form the input parameters of physical modeling;

[0011] Step 2: Based on the flow rate and pressure data collected in step 1, the water flow dynamics equation is used to describe the velocity and pressure distribution of the water flow inside the filter. By defining the fluid density, dynamic viscosity and water flow resistance, a dynamic behavior model of the water flow is constructed to characterize the movement characteristics of the water flow in different filter modules, combined with the change characteristics of pressure and flow rate;

[0012] Step 3: Based on the water quality data collected in step 1 and the water flow dynamics model generated in step 2, the pollutant diffusion equation is used to describe the migration process of pollutants in the filter. By setting the pollutant concentration, diffusion coefficient and pollutant removal rate parameters, a pollutant diffusion behavior model is constructed; according to the characteristics of different filtration modules, the pollutant removal rate and efficiency of the module are defined to provide data support for calculating the filtration efficiency and module performance;

[0013] Step 4: Combine the water flow dynamics model in step 2 and the pollutant diffusion model in step 3 to establish a comprehensive model of filtration efficiency and power consumption. Calculate the changes in pollutant concentrations of inlet and outlet water through the filtration efficiency model, define the pollutant removal capacity of the filter, associate the water flow rate, pressure and pump energy efficiency through the power consumption model, calculate the energy consumption characteristics of the filtration module, and form a mathematical relationship between filtration efficiency and power consumption.

[0014] Step 5: Based on the relationship between filtration efficiency and power consumption established in step 4, combined with the characteristics of the particle filtration module, activated carbon filtration module, reverse osmosis filtration module and ultraviolet disinfection module, formulate control rules for each module, and associate filtration efficiency with module operating parameters by analyzing the pressure requirements, flow rate conditions and pollutant removal capabilities of different modules to build a control strategy framework for different water quality conditions;

[0015] Step 6. According to the control strategy formulated in step 5, dynamically adjust the operating status of the filter module, optimize the filtration efficiency and power consumption by adjusting the module's enable, disable, pressure and flow rate parameters in real time, and feed the adjusted operating status back to the physical model through the comprehensive model of step 4 to update the relationship between filtration efficiency and power consumption, continuously monitor the filter element life, adjust the filtration mode and prompt filter element replacement according to the operating status of the filter element, and complete the closed-loop control of the filtration system.

[0016] Preferably, the hydrodynamic equation in step 2 is the following formula:

[0017]

[0018] Among them, v represents the water flow velocity vector, p represents the water flow pressure, ρ represents the fluid density, μ represents the dynamic viscosity of water, and f represents the water flow resistance generated by the filtration module.

[0019] Preferably, the pollutant diffusion equation described in step 3 is:

[0020]

[0021] Where C represents the pollutant concentration, D represents the diffusion coefficient,

[0022] RC=k filter C represents the pollutant removal rate, k filter is the removal coefficient of the filter module.

[0023] Preferably, the removal efficiency coefficient k in step 3 is filter According to the characteristics of the filter module, including:

[0024] The removal efficiency coefficient of the particle filter module is k filter1 =0.2~0.5;

[0025] The removal efficiency coefficient of the activated carbon filter module is k filter2 =0.6~1.0;

[0026] The removal efficiency coefficient of the reverse osmosis filtration module is k filter3 =1.5~2.5.

[0027] Preferably, the model for calculating the filtration efficiency in step 4 is defined as follows:

[0028]

[0029] Among them, C in Indicates the influent pollutant concentration, C out Indicates the concentration of pollutants in water.

[0030] V represents the volume of the filter,

[0031] E represents the filtration efficiency, which ranges from 0 to 1.

[0032] Preferably, the power consumption model in step 4 is defined as:

[0033] P = η·Q·p,

[0034] Where P represents the energy consumption of the filter module,

[0035] η represents the pump efficiency, which is dimensionless and ranges from 0 to 1;

[0036] Q=v·A represents the water flow rate, v represents the water flow velocity, A represents the cross-sectional area of ​​the filter, and p represents the water flow pressure.

[0037] Preferably, the control strategy in step 5 is formulated based on a comprehensive trade-off between filtration efficiency and power consumption, and preferentially enables the filtration module with the highest pollutant removal rate according to the current pollutant concentration, flow rate and pressure, and dynamically allocates the operating time and operating parameters of each module.

[0038] Preferably, the dynamic control in step 6 includes real-time monitoring of the filter element life, and the filter element life is calculated by the following formula:

[0039]

[0040] Among them, L represents the remaining life of the filter element, L 0 represents the initial life of the filter element, Q represents the water flow rate, C in Indicates the influent pollutant concentration, C out Indicates the concentration of water pollutants.

[0041] Preferably, when the calculated result of the filter element life is lower than a preset threshold, an alarm is triggered through the monitoring module, and at the same time, an appropriate filter element replacement plan is recommended in combination with the pollutant removal efficiency and energy consumption analysis;

[0042] During operation, the control strategy periodically retrains the model based on the collected historical operation data and real-time water quality data to dynamically optimize the activation conditions and operation parameters of the filtration module.

[0043] Preferably, the control strategy is based on the monitoring of the filter life, combined with the real-time water quality changes and pollutant removal efficiency, and dynamically adjusts the water flow rate and pressure. When the filter blockage degree reaches a certain threshold, the water flow pressure p is optimized by the following formula: opt and flow rate v opt :

[0044]

[0045] Among them, p optis the optimized water flow pressure, v opt is the optimized water flow velocity, C in Indicates the influent pollutant concentration, C out Indicates the concentration of pollutants in the water, k p , k v is the adjustment coefficient related to the characteristics of the filter module, c p 、c v is the compensation constant for pressure and flow rate.

[0046] The present invention provides a multi-stage filtering water purifier control method based on artificial intelligence. It has the following beneficial effects:

[0047] 1. The present invention establishes a physical model based on water flow dynamics and pollutant diffusion, combines real-time collected water quality data and flow rate and pressure data, dynamically adjusts the operating status of each filtration module, and dynamically optimizes the filtration process according to water quality changes, thereby achieving the effect of improving filtration efficiency and significantly improving pollutant removal rate.

[0048] 2. The present invention optimizes the activation sequence and operation time of the filter modules by combining the characteristic parameters of different filter modules, realizes adaptive adjustment to different water quality conditions, and obtains higher flexibility and adaptability of the water purification system.

[0049] 3. The present invention constructs a comprehensive mathematical model of filtration efficiency and power consumption, relates the water flow rate, pressure and energy consumption characteristics of the filtration module, dynamically regulates the operating pressure and flow rate of the water pump, and achieves the operating state of maintaining high-efficiency filtration under the lowest power consumption, thereby achieving the effect of reducing the overall energy consumption of the filtration system.

[0050] 4. The present invention realizes balanced distribution of filter element load by monitoring the filter element life in real time and dynamically calculating the remaining use time, and optimizes and adjusts the filtration mode in combination with the activation status of the filter module, thereby achieving the effect of extending the service life of the filter element and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0052] In order to make the technical personnel in the technical field understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in combination with the drawings in the embodiment of the present invention. Obviously, the described embodiment is a partial embodiment of the present invention, not a complete embodiment. Based on the embodiment of the present invention, other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present invention.

[0053] The present invention is described in detail below in conjunction with the accompanying drawings:

[0054] Example:

[0055] Please see attached Figure 1 The embodiment of the present invention provides a multi-stage filtering water purifier control method based on artificial intelligence, comprising:

[0056] Step 1: By configuring water quality sensors and operating status sensors, the parameters of the inlet water quality, including dissolved solid concentration, water pH, suspended particle concentration and heavy metal concentration, the water flow rate is obtained through the flow sensor, the water flow pressure inside the filter is monitored through the pressure sensor, and the filter element life and clogging are evaluated through the filter element status monitoring module. The collected data are normalized to form the input parameters of physical modeling;

[0057] Step 2: Based on the flow rate and pressure data collected in step 1, the water flow dynamics equation is used to describe the velocity and pressure distribution of the water flow inside the filter. By defining the fluid density, dynamic viscosity and water flow resistance, a dynamic behavior model of the water flow is constructed to characterize the movement characteristics of the water flow in different filter modules, combined with the change characteristics of pressure and flow rate;

[0058] Step 3: Based on the water quality data collected in step 1 and the water flow dynamics model generated in step 2, the pollutant diffusion equation is used to describe the migration process of pollutants in the filter. By setting the pollutant concentration, diffusion coefficient and pollutant removal rate parameters, a pollutant diffusion behavior model is constructed; according to the characteristics of different filtration modules, the pollutant removal rate and efficiency of the module are defined to provide data support for calculating the filtration efficiency and module performance;

[0059] Step 4: Combine the water flow dynamics model in step 2 and the pollutant diffusion model in step 3 to establish a comprehensive model of filtration efficiency and power consumption. Calculate the changes in pollutant concentrations of inlet and outlet water through the filtration efficiency model, define the pollutant removal capacity of the filter, associate the water flow rate, pressure and pump energy efficiency through the power consumption model, calculate the energy consumption characteristics of the filtration module, and form a mathematical relationship between filtration efficiency and power consumption.

[0060] Step 5: Based on the relationship between filtration efficiency and power consumption established in step 4, combined with the characteristics of the particle filtration module, activated carbon filtration module, reverse osmosis filtration module and ultraviolet disinfection module, formulate control rules for each module, and associate filtration efficiency with module operating parameters by analyzing the pressure requirements, flow rate conditions and pollutant removal capabilities of different modules to build a control strategy framework for different water quality conditions;

[0061] Step 6. According to the control strategy formulated in step 5, dynamically adjust the operating status of the filter module, optimize the filtration efficiency and power consumption by adjusting the module's enable, disable, pressure and flow rate parameters in real time, and feed the adjusted operating status back to the physical model through the comprehensive model of step 4 to update the relationship between filtration efficiency and power consumption, continuously monitor the filter element life, adjust the filtration mode and prompt filter element replacement according to the operating status of the filter element, and complete the closed-loop control of the filtration system.

[0062] Benefits of step 1: By configuring water quality sensors and operating status sensors, multi-dimensional data including dissolved solid concentration, water pH, suspended particle concentration, heavy metal concentration, water flow rate, pressure and filter life can be collected in real time, providing accurate input parameters for subsequent physical modeling and control strategies, solving the limitation of traditional water purifiers that rely on a single water quality parameter to evaluate water quality, achieving comprehensive perception of complex water quality changes, and improving the comprehensiveness and accuracy of system data collection;

[0063] Benefits of step 2: By using the hydrodynamic equation to establish the water flow velocity and pressure distribution model, combined with the definition of fluid density, dynamic viscosity and water flow resistance, the characteristics of the water flow inside the filter are dynamically described, effectively solving the problem of complex water flow behavior and uneven distribution during the filtration process, ensuring an accurate description of the flow state of the water flow in different filter modules, and providing a basis for subsequent pollutant diffusion modeling and filtration efficiency calculation;

[0064] Benefits of step 3: By using the pollutant diffusion equation and combining it with the water flow dynamics model, a pollutant migration behavior model in the filter is established, and the pollutant concentration, diffusion coefficient and pollutant removal rate parameters are set. This can accurately describe the diffusion, migration and removal characteristics of pollutants in the water flow, solve the problem that traditional water purifiers cannot accurately evaluate the pollutant removal efficiency, and provide data support for optimizing filtration performance;

[0065] Benefits of step 4: By integrating the water flow dynamics model and the pollutant diffusion model, a mathematical relationship between filtration efficiency and power consumption is established, the change in pollutant concentration of inlet and outlet water is calculated, the pollutant removal capacity of the filter is defined, the water flow rate, pressure and pump energy efficiency are related, and the energy consumption characteristics are calculated, so that the system can consider both filtration efficiency and energy consumption optimization at the same time, solving the problem of excessive focus on filtration efficiency and neglect of energy consumption in the existing technology, and realizing the comprehensive performance optimization of the water purification system;

[0066] Benefits of step 5: Based on the relationship between filtration efficiency and power consumption, as well as the characteristics of the particle filtration module, activated carbon filtration module, reverse osmosis filtration module and ultraviolet disinfection module, the module control rules are formulated and a control strategy framework for different water quality conditions is constructed. By optimizing the module activation sequence and operating parameters, the problem of the single and fixed activation strategy of the traditional water purifier filtration module is solved, the system's adaptability to variable water quality is improved, and flexible and efficient module management is achieved;

[0067] Benefits of step 6: By dynamically adjusting the operating status of the filter module in real time, controlling the pressure, flow rate and module enable / disable status, and feeding back the adjusted operating status to the comprehensive model, the filtration efficiency and power consumption are continuously optimized. At the same time, the filter element life is dynamically monitored, and the user is prompted to replace and adjust the filtration mode according to the filter element operating status, to achieve closed-loop control of the water purification system, solve the problem that traditional water purifiers lack dynamic optimization capabilities and intelligent maintenance functions, and significantly improve the system's operating stability, efficiency and maintenance convenience.

[0068] The hydrodynamic equation in step 2 is the following formula:

[0069]

[0070] Among them, v represents the water flow velocity vector, p represents the water flow pressure, ρ represents the fluid density, μ represents the dynamic viscosity of water, and f represents the water flow resistance generated by the filtration module.

[0071] The distribution model of water flow velocity and pressure inside the filter is established through equations, which can fully and accurately reflect the flow characteristics of water flow in the filter, including the magnitude and direction of the flow velocity and the pressure gradient of the water flow, and can provide an accurate fluid basis for subsequent pollutant diffusion modeling;

[0072] Considering the fluid density, dynamic viscosity and the resistance of the filter module to the water flow, it can effectively deal with the complex fluid behavior under different flow rates, pressures and filter module conditions. Compared with static modeling, it has higher applicability and accuracy under dynamic fluid conditions;

[0073] By analyzing the pressure distribution and flow velocity field inside the filter, the water flow distribution in the filter module can be optimized to avoid efficiency loss caused by too fast or too slow water flow;

[0074] By introducing the resistance term of the filtration module into the equation, the fluid characteristics of different modules can be independently analyzed and modeled, supporting the coordinated design and optimization of multiple modules such as particle filtration, activated carbon filtration, and reverse osmosis filtration.

[0075] The pollutant diffusion equation described in step 3 is:

[0076]

[0077] Where C represents the pollutant concentration, D represents the diffusion coefficient,

[0078] RC=k filter C represents the pollutant removal rate, k filter is the removal coefficient of the filter module.

[0079] The removal efficiency coefficient k in step 3 filter According to the characteristics of the filter module, including:

[0080] The removal efficiency coefficient of the particle filter module is k filter1 =0.2~0.5;

[0081] The removal efficiency coefficient of the activated carbon filter module is k filter2 =0.6~1.0;

[0082] The removal efficiency coefficient of the reverse osmosis filtration module is k filter3 =1.5~2.5.

[0083] The model for calculating the filtration efficiency in step 4 is defined as follows:

[0084]

[0085] Among them, C in Indicates the influent pollutant concentration, C out Indicates the concentration of pollutants in water.

[0086] V represents the volume of the filter,

[0087] E represents the filtration efficiency, and its value ranges from 0 to 1.

[0088] Application of the pollutant diffusion equation provides a tool for accurate modeling and efficient management of the pollutant removal process in filters, with significant benefits:

[0089] Accurately describe the migration process of pollutants to ensure the scientific nature of filtration efficiency;

[0090] Reflect the characteristic differences of the filtering modules and support modular optimization design;

[0091] Supports filtration capacity analysis of multiple pollutants and adapts to complex water quality conditions;

[0092] Dynamically optimize pollutant removal efficiency and improve the overall performance of the filtration system;

[0093] Improve the adaptability of the filtration module to maintain efficient operation when water quality fluctuates;

[0094] Supports real-time monitoring of pollutant removal rate and provides data support for operation optimization.

[0095] Through the above benefits, the pollutant diffusion equation lays a theoretical foundation for the intelligent and dynamic optimization control of the water purification system, significantly improving the efficiency, adaptability and operational stability of the system.

[0096] The power consumption model in step 4 is defined as:

[0097] P = η·Q·p,

[0098] Where P represents the energy consumption of the filter module,

[0099] η represents the pump efficiency, which is dimensionless and ranges from 0 to 1;

[0100] Q=v·A represents the water flow rate, v represents the water flow velocity, A represents the cross-sectional area of ​​the filter, and p represents the water flow pressure.

[0101] The filtration efficiency model quantifies the filter's ability to remove pollutants by calculating the ratio of inlet and outlet pollutant concentrations, avoiding the subjective evaluation of filtration effects in traditional water purification technology, making the evaluation of filtration performance more scientific and accurate, and clearly reflecting the working status of the filter under different water quality conditions.

[0102] The range of filtration efficiency is clearly defined as 0 to 1. Values ​​closer to 1 indicate higher pollutant removal rates, while values ​​closer to 0 indicate filter failure and poor performance. Intuitive quantitative indicators can quickly reflect filter operating results and facilitate maintenance and optimization.

[0103] The introduction of the filter volume parameter combines the filtration efficiency with the actual working area of ​​the filter, making the calculation results more accurate, especially suitable for the performance evaluation of multi-module filters. The model can adaptively adjust the filter modules of different volumes, reflecting the flexibility of the system.

[0104] By real-time monitoring of the pollutant concentrations in the inlet and outlet water, the filtration efficiency can be dynamically calculated, thereby achieving real-time evaluation of the filter performance, providing key data support for subsequent system optimization and dynamic adjustment, and solving the problem of lagging efficiency evaluation in traditional systems.

[0105] In summary, the application of the filtration efficiency model has significant benefits:

[0106] Accurately quantify filtration performance and achieve scientific evaluation;

[0107] Intuitively measure the filtering effect and quickly judge the performance status;

[0108] Adapt to various water quality scenarios and improve system flexibility;

[0109] Combined with the filter volume, the analysis accuracy is improved;

[0110] Support real-time monitoring and optimization, and provide a basis for dynamic regulation;

[0111] Assist in identifying the operating status and avoid performance loss;

[0112] Supports module performance comparison and optimizes module operation strategies.

[0113] Through the scientific modeling and application of the filtration efficiency model, the present invention can comprehensively quantify the filter performance and dynamically adapt to different water quality conditions. At the same time, it supports the real-time optimization and intelligent regulation of the system operation, further improving the efficiency and reliability of the water purification system.

[0114] The control strategy in step 5 is formulated based on a comprehensive trade-off between filtration efficiency and power consumption. The filtration module with the highest pollutant removal rate is preferentially enabled according to the current pollutant concentration, flow rate and pressure, and the operating time and operating parameters of each module are dynamically allocated.

[0115] The dynamic control in step 6 includes real-time monitoring of the filter life, which is calculated by the following formula:

[0116]

[0117] Among them, L represents the remaining life of the filter element, L 0 represents the initial life of the filter element, Q represents the water flow rate, C in Indicates the influent pollutant concentration, C out Indicates the concentration of water pollutants.

[0118] By combining the control strategy formulation in step 5 and the dynamic regulation in step 6, the present invention reduces system energy consumption while ensuring efficient filtration, significantly improving the service life of the filter element and the intelligent maintenance level. The control strategy can dynamically adapt to different water qualities and operating conditions to ensure the efficient operation of the filtration module. The filter element life monitoring and maintenance mechanism realizes intelligent maintenance reminders and reduces manual intervention and maintenance costs. Overall, it has significant technical advantages in improving filtration efficiency, reducing operating costs and enhancing system adaptability, providing support for intelligent multi-stage filtration water purifiers.

[0119] When the calculated result of the filter life is lower than the preset threshold, the monitoring module triggers an alarm prompt. At the same time, combined with the pollutant removal efficiency and energy consumption analysis, an appropriate filter replacement plan is recommended;

[0120] During the operation of the control strategy, the model is regularly retrained based on the collected historical operation data and real-time water quality data to dynamically optimize the activation conditions and operating parameters of the filtration module.

[0121] The control strategy is based on the filter life monitoring, combined with the real-time water quality changes and pollutant removal efficiency, by dynamically adjusting the water flow rate and pressure. When the filter blockage degree reaches a certain threshold, the water flow pressure p is optimized by the following formula: opt and flow rate vopt :

[0122]

[0123] Among them, p opt is the optimized water flow pressure, v opt is the optimized water flow velocity, C in represents the influent pollutant concentration, C out represents the effluent pollutant concentration, k p , k v are adjustment coefficients related to the characteristics of the filtration module, c p , c v are compensation constants for pressure and flow rate.

[0124] The present invention significantly improves the intelligent level and operation efficiency of the water purifier by monitoring the filter element life and giving alarm prompts, dynamically optimizing the control strategy, and real-time adjusting the water flow velocity and pressure.

[0125] The monitoring of the filter element life and the alarm prompt can achieve accurate replacement of the filter element, ensure water quality safety, and at the same time, reduce resource waste and maintenance costs;

[0126] The dynamically optimized control strategy improves the adaptive ability and filtration efficiency of the system by combining historical data and real-time water quality data;

[0127] The dynamic adjustment of the water flow velocity and pressure enables the system to maintain efficient filtration under different water quality conditions, extend the filter element life and reduce energy consumption.

[0128] Overall, the system operation efficiency, energy utilization rate, and filter element management comprehensively improve the performance of the water purifier, can adapt to complex water quality environments, and achieve the comprehensive effects of energy conservation, high efficiency, and intelligence.

[0129] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-stage filtering water purifier control method based on artificial intelligence, characterized in that: include: Step 1: By configuring water quality sensors and operating status sensors, the parameters of the inlet water quality, including dissolved solid concentration, water pH, suspended particle concentration and heavy metal concentration, the water flow rate is obtained through the flow sensor, the water flow pressure inside the filter is monitored through the pressure sensor, and the filter element life and clogging are evaluated through the filter element status monitoring module. The collected data are normalized to form the input parameters of physical modeling; Step 2: Based on the flow rate and pressure data collected in step 1, the water flow dynamics equation is used to describe the velocity and pressure distribution of the water flow inside the filter. By defining the fluid density, dynamic viscosity and water flow resistance, a dynamic behavior model of the water flow is constructed to characterize the movement characteristics of the water flow in different filter modules, combined with the change characteristics of pressure and flow rate; Step 3: Based on the water quality data collected in step 1 and the water flow dynamics model generated in step 2, the pollutant diffusion equation is used to describe the migration process of pollutants in the filter. By setting the pollutant concentration, diffusion coefficient and pollutant removal rate parameters, a pollutant diffusion behavior model is constructed; according to the characteristics of different filtration modules, the pollutant removal rate and efficiency of the module are defined to provide data support for calculating the filtration efficiency and module performance; Step 4: Combine the water flow dynamics model in step 2 and the pollutant diffusion model in step 3 to establish a comprehensive model of filtration efficiency and power consumption. Calculate the changes in pollutant concentrations of inlet and outlet water through the filtration efficiency model, define the pollutant removal capacity of the filter, associate the water flow rate, pressure and pump energy efficiency through the power consumption model, calculate the energy consumption characteristics of the filtration module, and form a mathematical relationship between filtration efficiency and power consumption. Step 5: Based on the relationship between filtration efficiency and power consumption established in step 4, combined with the characteristics of the particle filtration module, activated carbon filtration module, reverse osmosis filtration module and ultraviolet disinfection module, formulate control rules for each module, and associate filtration efficiency with module operating parameters by analyzing the pressure requirements, flow rate conditions and pollutant removal capabilities of different modules to build a control strategy framework for different water quality conditions; Step 6. According to the control strategy formulated in step 5, dynamically adjust the operating status of the filter module, optimize the filtration efficiency and power consumption by adjusting the module's enable, disable, pressure and flow rate parameters in real time, and feed the adjusted operating status back to the physical model through the comprehensive model of step 4 to update the relationship between filtration efficiency and power consumption, continuously monitor the filter element life, adjust the filtration mode and prompt filter element replacement according to the operating status of the filter element, and complete the closed-loop control of the filtration system.

2. The artificial intelligence-based multi-stage filtering water purifier control method according to claim 1 is characterized in that: The hydrodynamic equation in step 2 is the following formula: Among them, v represents the water flow velocity vector, p represents the water flow pressure, ρ represents the fluid density, μ represents the dynamic viscosity of water, and f represents the water flow resistance generated by the filtration module.

3. The artificial intelligence-based multi-stage filtering water purifier control method according to claim 2 is characterized in that: The pollutant diffusion equation described in step 3 is: Where C represents the pollutant concentration, D represents the diffusion coefficient, R(C)=k filter C represents the pollutant removal rate, k filter is the removal coefficient of the filter module.

4. The artificial intelligence-based multi-stage filtering water purifier control method according to claim 3 is characterized in that: The removal efficiency coefficient k in step 3 filter According to the characteristics of the filter module, including: The removal efficiency coefficient of the particle filter module is k filter1 =0.2~0.5; The removal efficiency coefficient of the activated carbon filter module is k filter2 =0.6~1.0; The removal efficiency coefficient of the reverse osmosis filtration module is k filter3 =1.5~2.

5.

5. The artificial intelligence-based multi-stage filtering water purifier control method according to claim 4 is characterized in that: The model for calculating the filtration efficiency in step 4 is defined as follows: Among them, C in Indicates the influent pollutant concentration, C out Indicates the concentration of pollutants in water. V represents the volume of the filter, E represents the filtration efficiency, and its value ranges from 0 to 1.

6. The artificial intelligence-based multi-stage filtering water purifier control method according to claim 5 is characterized in that: The power consumption model in step 4 is defined as: P = η·Q·p, Where P represents the energy consumption of the filter module, η represents the pump efficiency, which is dimensionless and ranges from 0 to 1; Q=v·A represents the water flow rate, v represents the water flow velocity, A represents the cross-sectional area of ​​the filter, and p represents the water flow pressure.

7. The artificial intelligence-based multi-stage filtering water purifier control method according to claim 6 is characterized in that: The control strategy in step 5 is formulated based on a comprehensive trade-off between filtration efficiency and power consumption, and preferentially enables the filtration module with the highest pollutant removal rate according to the current pollutant concentration, flow rate and pressure, and dynamically allocates the operating time and operating parameters of each module.

8. The artificial intelligence-based multi-stage filtering water purifier control method according to claim 7, characterized in that: The dynamic control in step 6 includes real-time monitoring of the filter element life, and the filter element life is calculated by the following formula: Among them, L represents the remaining life of the filter element, L0 represents the initial life of the filter element, Q represents the water flow rate, C in Indicates the influent pollutant concentration, C out Indicates the concentration of water pollutants.

9. The artificial intelligence-based multi-stage filtering water purifier control method according to claim 8, characterized in that: When the calculated result of the filter element life is lower than the preset threshold, the monitoring module triggers an alarm prompt. At the same time, combined with the pollutant removal efficiency and energy consumption analysis, an appropriate filter element replacement plan is recommended; During operation, the control strategy periodically retrains the model based on the collected historical operation data and real-time water quality data to dynamically optimize the activation conditions and operation parameters of the filtration module.

10. The artificial intelligence-based multi-stage filtering water purifier control method according to claim 9, characterized in that: The control strategy is based on the filter life monitoring, combined with the real-time water quality changes and pollutant removal efficiency, and dynamically adjusts the water flow rate and pressure. When the filter blockage degree reaches a certain threshold, the water flow pressure p is optimized by the following formula opt and flow rate v opt : Among them, p opt is the optimized water flow pressure, v opt is the optimized water flow velocity, C in Indicates the influent pollutant concentration, C out Indicates the concentration of pollutants in the water, k p , k v is the adjustment coefficient related to the characteristics of the filter module, c p 、c v is the compensation constant for pressure and flow rate.

Images