Intelligent control system for RO water purifier

Abstract

The application discloses an intelligent control system of a RO water purifier, comprising: a sensing component detecting real-time working parameters of the water purifier; a control module calculating TDS pollution multiple, water quality environmental factors, dynamic time attenuation factors, dynamic thresholds, system health factors and flushing demand indexes according to the real-time working parameters of the water purifier; triggering a restorative flushing instruction when the TDS pollution multiple is greater than or equal to the dynamic threshold or the TDS pollution multiple is greater than a first threshold; triggering a maintenance flushing instruction when the TDS pollution multiple is less than the dynamic threshold and the flushing demand index is equal to or greater than a second threshold; the TDS pollution multiple represents the pollution degree of stale water on the pure water side of the RO membrane, the water quality environmental factors represent the influence of water temperature on the membrane flux and the pollution speed, the dynamic time attenuation factors represent the cumulative risk of the downtime to the stale water pollution, the dynamic threshold represents the triggering threshold changing with the total standby time, and the system health factors represent the health state of the physical pollution blocking degree of the RO membrane.

Description

Technical Field

[0001] This invention relates to the field of water treatment, and in particular to an intelligent control system for an RO water purifier. Background Technology

[0002] Currently, RO (reverse osmosis) water purifiers have become the mainstream product for household and similar water treatment equipment. To address the issue of "first cup water not meeting standards" caused by increased TDS values ​​in the RO membrane's purified water side after shutdown, the industry generally adopts "zero stagnant water" technology. Existing zero stagnant water technologies can be mainly divided into three categories: The first type is the timed / frequency flushing scheme. Regardless of water quality or actual operating conditions, this scheme automatically starts flushing at a fixed time (e.g., 24 hours) after shutdown. This "one-size-fits-all" approach lacks specificity and can easily lead to water waste when the raw water quality is good or during periods of frequent water use. On the other hand, it may result in insufficient flushing after the raw water quality deteriorates or after a long period of standby, leading to an unstable first-cup water compliance rate.

[0003] The second type is trigger-based flushing schemes based on a single parameter. For example, by monitoring the TDS value of pure water, flushing is initiated when it exceeds a fixed threshold (such as 100 ppm); or, as in Gree's patent published in 2025 (CN202511100815.1), the flushing interval is dynamically adjusted based on the difference between water temperature and ambient temperature. Although this type of method is an improvement over timed schemes, it relies on a single signal for decision-making and cannot comprehensively respond to multi-dimensional variables such as raw water TDS fluctuations, membrane fouling status, and differences in user water usage habits. Its adaptability under complex operating conditions remains insufficient.

[0004] The third type is the pure water recirculation flushing scheme. This scheme recirculates stored pure water back to the RO membrane for dilution. Although it can effectively reduce the TDS of stagnant water, if the control strategy is not good (such as using the triggering logic of the first and second types mentioned above), it will still lead to ineffective recirculation, increased water consumption, and the inability to predict the health status of the membrane.

[0005] The aforementioned existing technologies generally suffer from the following common defects: 1. The decision-making dimension is too narrow and the adaptability is poor.

[0006] 2. Passive response, lacking predictive and preventative capabilities. 3. Neglecting system health management and lacking real-time, low-cost monitoring methods for the health status of RO membranes. 4. There is a significant conflict between user experience and energy efficiency. In order to ensure water quality, there is often excessive rinsing, or the rinsing effect is sacrificed in order to avoid disturbing users.

[0007] To address these issues, the industry typically employs methods such as adding sensors (e.g., simultaneously monitoring the TDS of influent and pure water to calculate desalination rate), combining conditional judgments (e.g., flushing only when both "downtime > X hours" and "pure water TDS > Y ppm" are met), and optimizing hardware design. However, these methods are mostly static thresholds or simple logical additions, failing to form a dynamically integrated intelligent decision-making model, resulting in bottlenecks in system optimization. Summary of the Invention

[0008] The summary of this invention introduces a series of simplified concepts, all of which are simplifications of existing technologies in the field, and will be further explained in detail in the detailed description section. This summary is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0009] The technical problem to be solved by the present invention is to provide an intelligent control system for RO water purifiers that can achieve zero stagnant water by actively triggering flushing in real time with adaptive operating conditions without significantly increasing hardware costs.

[0010] To solve the above-mentioned technical problems, the present invention provides an intelligent control system for an RO water purifier, comprising: A sensing component for detecting real-time operating parameters of the water purifier; for example, the sensing component includes an inlet water TDS sensor for detecting the TDS value of raw water, a pure water TDS sensor for detecting the TDS value of pure water, a water temperature sensor for detecting water temperature, a flow sensor for detecting flow rate, and a pump current detection unit for detecting diaphragm pump current. The control module calculates the TDS pollution ratio T, water quality environmental factor W, dynamic time decay factor H, dynamic threshold T_threshold(t), system health factor S, and flushing demand index RDI based on the real-time operating parameters of the T water purifier. When the TDS contamination ratio is greater than or equal to the dynamic threshold T_threshold(t) or the TDS contamination ratio is greater than the first threshold, a restorative flushing command is triggered. When the TDS contamination ratio is less than the dynamic threshold T_threshold(t) and the flushing demand index RDI is greater than or equal to the second threshold, a maintenance flushing command is triggered. Among them, TDS pollution ratio T is a real-time parameter characterizing the degree of pollution in the refrigerated water on the pure water side of the RO membrane, water quality environmental factor W is a correction coefficient characterizing the influence of water temperature on membrane flux and pollution rate, dynamic time decay factor H is a time dimension quantitative parameter characterizing the risk of refrigerated water pollution accumulation due to downtime, dynamic threshold T_threshold(t) is an adaptive trigger threshold characterizing the change with total standby time, and system health factor S is a health status quantitative parameter characterizing the degree of physical fouling of the RO membrane.

[0011] Preferably, the intelligent control system of the RO water purifier is further improved, and the real-time operating parameters of the water purifier include: raw water TDS value, pure water TDS value, water temperature, flow rate and diaphragm pump current.

[0012] Preferably, the intelligent control system of the RO water purifier is further improved, where the TDS contamination ratio T = pure water TDS / raw water TDS. The TDS contamination ratio T directly reflects the concentration of the current stagnant water relative to the raw water. It serves as the core judgment criterion for the "rigid defense line" in the dual-track decision-making process, triggering a restorative flush when the TDS contamination ratio is ≥ the dynamic threshold or > 2.0. The higher the TDS contamination ratio T, the more severe the ion diffusion across the membrane during shutdown, and the greater the risk of the first cup of water failing to meet standards.

[0013] Preferably, the intelligent control system of the RO water purifier is further improved, and the water quality environmental factor W is determined based on the water temperature. Further explanation: based on the water temperature sensor's detection value, it is determined through a preset mapping relationship (for example, a water temperature of 25℃ corresponds to W=1.0, and W is adjusted accordingly when the temperature changes). This compensates for the nonlinear effect of temperature on RO membrane performance (membrane flux decreases and fouling accumulation accelerates at low temperatures; the opposite is true at high temperatures). The higher the water temperature, the faster the ion diffusion rate, and the steeper the TDS rise curve of the stale water, requiring a corresponding increase in flushing sensitivity.

[0014] Preferably, the intelligent control system of the RO water purifier is further improved by calculating the dynamic time decay factor H based on the total standby time t_long and the time after rinsing t_short; H=1 / [1+exp(-k_dynamic×(t_short-t0_dynamic))], where t_short is the time since the last flush (the time since the last flush), and k_dynamic and t0_dynamic are parameters adjusted according to the water quality environmental factor W.

[0015] For example, k_dynamic is the curve slope parameter (adjusted with W), and t_t0_dynamic is the time offset parameter (adjusted with W); the parameters are dynamically adjusted with the water quality environmental factor W to adapt to diffusion conditions at different temperatures. A rapid increase in the dynamic time decay factor H value during the initial stage of shutdown reflects a rapid accumulation of pollution, while after a long period of shutdown, the dynamic time decay factor H approaches 1, indicating that pollution has reached dynamic equilibrium. The calculation parameters for the dynamic time decay factor H (k_dynamic and t0_dynamic adjusted with W) are used to correct the environmental factor weights in the RDI calculation, achieving a smooth weighting of time risk in the RDI model.

[0016] Preferably, the intelligent control system of the RO water purifier is further improved, with a dynamic threshold T_threshold(t) = T_base + ΔT / (1 + exp(-k × (t_long - t0))), where T_base is the base threshold, ΔT is the threshold adjustment amount (a specified value, e.g., 1.0), k can be a curve slope parameter, a specified value, e.g., 0.15, t0 can be a time offset parameter, a specified value, e.g., 12 hours, t_long is the total standby time (time since the last water use), and T_base is the base threshold (a specified value, e.g., 1.5). The trigger threshold gradually decreases as the standby time increases, reflecting a safety strategy of "the longer the standby time, the lower the tolerance." Compared to a fixed threshold, this avoids excessive flushing during short-term shutdowns and insufficient flushing during long-term standbys. It forms an "OR" logical relationship with the RDI threshold, ensuring that restorative flushing is triggered when any condition is met. Even if the TDS contamination rate does not seriously exceed the standard after a long-term shutdown, intervention is initiated in advance due to the increased potential risk. Preferably, the intelligent control system of the RO water purifier is further improved, and the system health factor S is determined by a specific current diagnostic model: Obtain the operating current I_pump and actual flow rate Q of the diaphragm pump, and calculate the specific current I_pump / Q; The specific current I_pump / Q is compared with the reference specific current, and the system health factor S is determined based on the deviation. For example, a deviation of 0% corresponds to S=1.0, and a deviation of 30-40% corresponds to S=0.7.

[0017] In the RDI calculation, the gain effect of membrane health deterioration on flushing requirements is represented in the form of (1-S), enabling online monitoring of membrane condition without increasing additional hardware costs. This provides data for adaptive adjustment of flushing strategies and lifespan early warning. A lower system health factor S value indicates more severe membrane fouling, requiring more frequent flushing and maintenance under the same operating conditions. The RDI is correspondingly increased to prevent accelerated fouling. Preferably, the intelligent control system of the RO water purifier is further improved, and the flushing demand index RDI = α_norm×T + β_norm×H + γ_norm×W + δ_norm×(1-S); Where α_norm, β_norm, γ_norm, and δ_norm are normalized weight coefficients.

[0018] The flushing demand index (RDI) is calculated by integrating the TDS pollution ratio T (characterizing the real-time pollution level), water quality environmental factor W (characterizing the adjustment of environmental correction with water temperature mapping), dynamic time decay factor H (characterizing the cumulative risk over time), and system health factor S (characterizing the membrane health status based on specific current diagnostic updates). The above five factors are dynamically weighted and fused to form a comprehensive risk indicator, the Flushing Demand Index (RDI), which, together with the dynamic threshold T_threshold(t), constitutes the core of the dual-track intelligent decision-making system.

[0019] Preferably, the intelligent control system of the RO water purifier is further improved, and the control module also includes a user habit learning unit, which records the user's historical water usage time data, predicts future low water usage periods as a safety window based on the historical water usage time data, and actively triggers maintenance flushing within the safety window.

[0020] Preferably, in a further improvement to the RO water purifier intelligent control system, the control module is further configured as follows: The total standby time t_long is monitored. When the total standby time t_long exceeds the preset ultra-long standby threshold, a flushing action is forcibly triggered.

[0021] Preferably, the intelligent control system of the RO water purifier is further improved, wherein the control module is also configured to dynamically adjust the flushing duration and flushing intensity according to the flushing demand index (RDI) value using a linear interpolation method.

[0022] Preferably, the intelligent control system of the RO water purifier is further improved, wherein the control module is also configured to: trigger the corresponding low temperature protection or high temperature protection mechanism when the water temperature is lower than the first temperature threshold or higher than the second temperature threshold, and suspend or adjust the flushing strategy.

[0023] Preferably, the intelligent control system of the RO water purifier is further improved, wherein the restorative flushing includes a high-flow-rate flushing mode or a pulse flushing mode, and the maintenance flushing includes a pure water recirculation flushing mode.

[0024] Preferably, in a further improvement to the RO water purifier intelligent control system, the control module is further configured as follows: Monitor the operating status of the influent TDS sensor and the pure water TDS sensor; When a sensor failure is detected, the system switches to a degraded operation mode, triggering flushing based on the remaining valid sensors and a fixed time interval.

[0025] The working principle of this invention is as follows: The system acquires the TDS values ​​of raw water and pure water in real time through influent TDS sensors and pure water TDS sensors, and calculates the TDS fouling ratio T = pure water TDS / raw water TDS, serving as a direct indicator of the degree of pollution in the stagnant water. A water temperature sensor detects water temperature to determine the water quality environmental factor W, reflecting the impact of temperature on membrane flux and fouling rate. A flow sensor and a pump current detection unit detect flow rate and diaphragm pump operating current, respectively, providing a data foundation for health diagnosis.

[0026] The control module calculates the flushing demand index RDI based on a multi-parameter dynamic weighted decision model, integrating risk factors in four dimensions: TDS pollution multiple T: reflecting the direct risk of current stale water pollution; Dynamic time decay factor H: calculated by the function H = 1 / [1 + exp(-k_dynamic×(t_short - t0_dynamic))], reflecting the risk of pollution accumulation over time, with the parameter dynamically adjusted according to the water quality environment factor W; the water quality environment factor W is mapped based on water temperature, reflecting the impact of the environment on the pollution rate; the system health factor S reflects the degree of membrane physical fouling, and the lower the S value, the worse the membrane health condition and the higher the flushing demand.

[0027] The RDI calculation formula is: RDI = α_norm×T + β_norm×H + γ_norm×W + δ_norm×(1 - S), achieving dynamic weighted integration of multi-dimensional risks through normalized weight coefficients.

[0028] Based on the above scheme, the present invention realizes a dual-track parallel decision-making architecture: 1. Rigid defense line (dynamic threshold T_threshold(t)): The dynamic threshold T_threshold(t) = T_base + ΔT / (1 + exp(-k×(t_long - t0))) is calculated based on the total standby time t_long, and the trigger threshold gradually decreases as the standby time extends. When T ≥ T_threshold(t) or T > 2.0, it indicates that the pollution has reached the level that requires immediate repair, triggering a repair flushing (high flow rate / pulse mode).

[0029] 2. Flexible warning line (RDI threshold): When T < T_threshold(t) but RDI ≥ 1.6, it indicates that the comprehensive risk has reached the preventive maintenance threshold, triggering a maintenance flushing (reflux flushing) to perform low-cost intervention before the pollution deteriorates.

[0030] The present invention uses a diaphragm pump as a health sensor. By monitoring the change in specific current (I_pump / Q, that is, the ratio of pump current to actual flow rate), early diagnosis of membrane physical fouling is achieved. When the membrane is fouled, the pump load increases while the flow rate decreases, resulting in a significant increase in specific current. Based on this, the system health factor S is determined, realizing health management without additional hardware costs.

[0031] This invention employs a hierarchical timing model: the total standby time t_long records the total duration since the last use, and the flushing time t_short records the duration since the last flush. After each action, the S value is updated and the corresponding timer is reset to ensure strict synchronization between the algorithm logic and the physical process. Simultaneously, a user habit learning unit records historical water usage data and predicts low-water periods as a safety window, proactively triggering maintenance flushing during these periods to achieve "unobtrusive" maintenance.

[0032] Based on the above working principle, the present invention can achieve at least the following technical effects: 1. Existing technologies often rely on a single signal (time, TDS, or temperature) for decision-making, which cannot comprehensively respond to multidimensional variables. In complex scenarios such as increased membrane fouling, sudden changes in raw water quality, or long-term standby, the first cup water compliance rate is unstable.

[0033] This invention constructs a multi-parameter dynamic weighted decision model based on the Flushing Demand Index (RDI), integrating TDS pollution ratio, dynamic time decay factor, water quality environmental factors, and system health factors for decision-making. From a technical perspective, the RDI model simulates the nonlinear cumulative effect of time factors through functions, adapts to different water quality environments through dynamic weights, and incorporates membrane state feedback through health factors, thus forming a comprehensive response capability to complex operating conditions. In contrast, existing technologies using single parameters or simple combinations cannot capture the nonlinear coupling relationships between parameters, nor can they adaptively adjust strategies based on membrane aging levels, making it difficult to guarantee stable compliance under complex operating conditions.

[0034] 2. Existing solutions mostly take action only after pollution has occurred (TDS has exceeded the standard), which is a "post-event remedy" and cannot prevent pollution at low cost in the early stages of its spread, resulting in the need for longer and larger volumes of water to flush and repair it later.

[0035] This invention employs a dual-track intelligent decision-making architecture, triggering maintenance backflow flushing in advance through a flexible RDI (Reactive Water Discharge) early warning line, enabling low-cost intervention at the initial stage of contamination. From a technical perspective, maintenance flushing utilizes a pure water backflow mode, diluting the contamination with existing pure water in the system, resulting in significantly lower water consumption compared to the high-flow-rate / pulse mode of remedial flushing. Meanwhile, the rigid defense line of the dynamic threshold T_threshold(t) ensures timely and forceful remediation during the accelerated contamination phase. This "prevention-first, remediation-second" strategy avoids the excessive flushing caused by "minor issues escalating into major problems" in existing technologies. Existing technologies lack this risk stratification and predictive capability, resorting only to uniformly employing high-intensity flushing after TDS exceedances, leading to water waste.

[0036] 3. Existing solutions generally lack real-time, low-cost monitoring methods for the health status of RO membranes, and cannot achieve adaptive adjustment and lifespan early warning based on membrane performance degradation.

[0037] This invention reuses a diaphragm pump as a health sensor, enabling early diagnosis of membrane physical fouling by monitoring changes in specific current (I_pump / Q). From a technical perspective, the diaphragm pump, as an inherent actuator in the RO system, has an operating current positively correlated with its load, which is affected by membrane resistance; simultaneously, flow rate reflects membrane flux capacity. Specific current eliminates interference factors such as water pressure fluctuations and exhibits high sensitivity to membrane fouling. This actuator reuse diagnostic technology achieves health monitoring without additional sensors, whereas existing technologies typically require differential pressure sensors or additional flow meters to achieve similar functionality, resulting in higher costs. Based on early diagnostic results, the system can adjust its flushing strategy promptly, preventing the membrane from operating in a degraded state for extended periods, thereby extending the cleaning cycle.

[0038] 4. Existing technologies often tend to over-rinse (consuming water and electricity and generating noise) to ensure water quality, or sacrifice rinsing effect to avoid disturbing users, resulting in a contradiction between user experience and energy efficiency.

[0039] This invention uses a user habit learning model to predict "safe windows," enabling intelligent planning of maintenance tasks. From a technical perspective, the system records users' historical water usage times and uses time series analysis to predict future water usage low points, scheduling maintenance flushing during those periods. This predictive maintenance avoids waiting delays caused by flushing during peak water usage times and reduces flushing noise disturbance to users, achieving "seamless" maintenance. Existing technologies typically use fixed-time flushing or manual user triggering, which cannot adaptively adjust to individual usage habits, either affecting user experience or compromising water quality. Attached Figure Description

[0040] The accompanying drawings are intended to illustrate the general characteristics of the methods, structures, and / or materials used in specific exemplary embodiments of the invention, supplementing the description in the specification. However, the drawings are schematic diagrams not drawn to scale and may not accurately reflect the precise structural or performance characteristics of any of the given embodiments. The drawings should not be construed as limiting or restricting the range of numerical values ​​or properties covered by exemplary embodiments of the invention. The invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0041] Figure 1 This is a schematic diagram of the logic control of the present invention.

[0042] Figure 2 This is a flowchart of the intelligent decision-making (dual-track) algorithm of this invention.

[0043] Figure 3 This is a flowchart of the maintenance flushing (backflow flushing) process.

[0044] Figure 4It is a flowchart of the signal flow and functions of the hardware system. Detailed Implementation

[0045] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can fully understand other advantages and technical effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through different specific embodiments, and various details in this specification can also be applied based on different viewpoints, with various modifications or changes made without departing from the overall design concept of the invention. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. The following exemplary embodiments of the present invention can be implemented in many different forms and should not be construed as being limited to the specific embodiments set forth herein. It should be understood that these embodiments are provided so that the disclosure of the present invention is thorough and complete, and that the technical solutions of these exemplary embodiments are fully conveyed to those skilled in the art. It should be understood that when an element is referred to as "connected" or "combined" to another element, the element can be directly connected or combined to the other element, or there may be intermediate elements. The difference is that when an element is referred to as "directly connected" or "directly combined" to another element, there are no intermediate elements. Throughout the drawings, the same reference numerals always denote the same elements. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0046] First embodiment; This invention provides an intelligent control system for an RO water purifier, comprising: Sensing components are used to detect the real-time operating parameters of the water purifier; The control module calculates the TDS pollution ratio T, water quality environmental factor W, dynamic time decay factor H, dynamic threshold T_threshold(t), system health factor S, and flushing demand index RDI based on the real-time operating parameters of the T water purifier. When the TDS contamination ratio is greater than or equal to the dynamic threshold T_threshold(t) or the TDS contamination ratio is greater than the first threshold, a restorative flushing command is triggered. When the TDS contamination ratio is less than the dynamic threshold T_threshold(t) and the flushing demand index RDI is greater than or equal to the second threshold, a maintenance flushing command is triggered. Among them, TDS pollution ratio T is a real-time parameter characterizing the degree of pollution in the refrigerated water on the pure water side of the RO membrane, water quality environmental factor W is a correction coefficient characterizing the influence of water temperature on membrane flux and pollution rate, dynamic time decay factor H is a time dimension quantitative parameter characterizing the risk of refrigerated water pollution accumulation due to downtime, dynamic threshold T_threshold(t) is an adaptive trigger threshold characterizing the change with total standby time, and system health factor S is a health status quantitative parameter characterizing the degree of physical fouling of the RO membrane.

[0047] Based on the main design concept of the first embodiment described above, subsequent embodiments of the present invention are provided with hypothetical parameters to further illustrate the specific implementation of the present invention.

[0048] Taking an 800G flow rate RO water purifier as an example, the system hardware configuration includes: inlet water TDS sensor, pure water TDS sensor, water temperature sensor, flow sensor, pump current detection unit, diaphragm pump, inlet valve, pure water valve, and wastewater valve. The above are the standard hardware of the water purifier, and no additional hardware is added.

[0049] Hypothetical parameter settings: RDI calculation weights: α_norm=0.35, β_norm=0.25, γ_norm=0.20, δ_norm=0.20; Dynamic threshold parameters: T_base=1.5, ΔT=1.0, k=0.15, t0=12 hours; Dynamic time decay parameters: k_dynamic=0.3, t0_dynamic=4 hours (adjusted according to W from 3 to 6 hours). RDI trigger threshold: 1.6; Ultra-long standby time: 36 hours; The raw water TDS was stable at 515 ppm, and the pure water TDS was 37 ppm when the system was running stably. The user shut down the system after the last water usage at 8:00 AM.

[0050] Second embodiment; The intelligent control under standard operating conditions is illustrated by the following three operating conditions; First working condition: The state at t=6 hours (14:00); The measured TDS of pure water was 78 ppm, and the calculated T = 78 / 515 = 1.51. With a water temperature of 25℃, W = 1.0 is obtained. t_long = 6 hours, t_short = 6 hours; Assuming the membrane is in good health, S = 0.9; Calculate the dynamic threshold: T_threshold(6) = 1.5 + 1.0 / (1 + exp(-0.15×(6 - 12))) ≈ 1.93; Calculate the H factor: H = 1 / [1 + exp(-0.3×(6 - 4))] ≈ 0.88; Calculate RDI = 0.35×1.51 + 0.25×0.88 + 0.20×1.0 + 0.20×(1 - 0.9) ≈ 0.53 + 0.22 + 0.20 + 0.02 = 0.97; Decision result: T = 1.51 < T_threshold(6) ≈ 1.93 and T < 2.0, RDI = 0.97 < 1.6, no flushing is triggered.

[0051] The second working condition: The state at t = 12 hours (20:00); The measured TDS of pure water has risen to 92 ppm, T = 92 / 515 = 1.79; The water temperature is 24°C, W = 1.0; t_long = 12 hours, t_short = 12 hours; Calculate the dynamic threshold: T_threshold(12) = 1.5 + 1.0 / (1 + exp(-0.15×(12 - 12))) = 2.0; Calculate the H factor: H = 1 / [1 + exp(-0.3×(12 - 4))] ≈ 0.98; Calculate RDI = 0.35×1.79 + 0.25×0.98 + 0.20×1.0 + 0.20×0.1 ≈ 0.63 + 0.25 + 0.20 + 0.02 = 1.10; Decision result: T = 1.79 < T_threshold(12) = 2.0 and T < 2.0, RDI = 1.10 < 1.6, still no flushing is triggered, but the RDI is already close to the warning line.

[0052] The third working condition: The state at t = 18 hours (2:00 the next day): The measured TDS of pure water has risen to 105 ppm, T = 105 / 515 = 2.04; The water temperature is 23°C, W = 1.0; t_long = 18 hours, t_short = 18 hours; Calculate the dynamic threshold: T_threshold(18) = 1.5 + 1.0 / (1 + exp(-0.15×(s18 - 12))) ≈ 2.15; Calculate the H factor: H ≈ 0.998; Calculate RDI = 0.35 × 2.04 + 0.25 × 0.998 + 0.20 × 1.0 + 0.20 × 0.1 ≈ 0.71 + 0.25 + 0.20 + 0.02 = 1.18; Decision result: T=2.04>T_threshold(18)≈2.15? No, T=2.04<2.15, but T>2.0, according to the condition "or T>2.0", a corrective flush is triggered.

[0053] The system initiates a restorative pulse flushing mode: the diaphragm pump runs at its rated speed for 10 seconds, stops for 5 seconds, and repeats this cycle 3 times. Simultaneously, the wastewater valve is opened for forceful replacement. After flushing, the pure water TDS drops to 42 ppm, t_short=0 is reset, and the S value is updated (based on specific current monitoring).

[0054] Third embodiment; Early stage of membrane fouling: Assume the system has been running for 6 months and the membrane is gradually fouling.

[0055] The system recorded that under standard operating conditions (water temperature 25℃, inlet water pressure 0.3MPa) with a diaphragm pump rated flow rate of 2.1L / min, the operating current was 2.2A, and the reference specific current was approximately 1.05 A·min / L when the membrane was in its new state. Under the same operating conditions, when the flow rate drops to 1.8 L / min and the current rises to 2.5 A, the current specific current is approximately 2.5 / 1.8 ≈ 1.39 A·min / L. Specific current deviation rate = (1.39 - 1.05) / 1.05 ≈ 32% According to the preset mapping relationship, a deviation rate of 30-40% corresponds to S=0.7 (mild clogging). Based on this, the system reduces the S value to 0.7, and in the subsequent RDI calculation, the δ_norm×(1-S) term is increased to improve the flushing frequency and avoid aggravating fouling.

[0056] Fourth embodiment; This invention learns from user habits under specific working conditions; The system continuously recorded user water usage data for 30 days and found that users' weekday water usage patterns were: 7:00-8:00 AM, 6:00-7:00 PM, and 9:00-10:00 PM, with the lowest water usage period being 2:00-5:00 AM.

[0057] The system predicts a safe flush window from 3:00 to 4:00 every Monday to Friday. When the RDI value reaches 1.4 during the day (slightly below the 1.6 threshold), the system does not flush immediately, but instead delays until 3:00 the next day to proactively trigger a maintenance flush, achieving seamless maintenance.

[0058] Furthermore, assume that the pure water TDS sensor fails and the signal remains constant.

[0059] The system monitors that the pure water TDS value has not changed for 2 consecutive hours (it should normally rise slowly over time), and determines that the sensor has failed.

[0060] Switch to the degraded operation mode, ignore the T and RDI calculations, and trigger at a fixed time interval: trigger a maintenance flush every 12 hours to ensure basic water quality safety and prompt the user of the sensor failure through the display panel.

[0061] Furthermore, for the extreme temperature protection condition; In winter, when the water temperature drops to 4°C and the detected value of the water temperature sensor < W_low (assume 5°C), the system triggers low-temperature protection and suspends all flushing operations (to avoid damage caused by a sudden drop in membrane flux at low temperatures). If an emergency flush is required when T > 2.0, first start the preheating program and then execute it after the water temperature rises above 8°C. Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will also be understood that terms such as those defined in a general dictionary should be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and should not be interpreted in an ideal or overly formal sense unless expressly defined herein.

[0062] The present invention has been described in detail above through specific embodiments and examples, but these do not constitute a limitation to the present invention. Without departing from the principle of the present invention, those skilled in the art can also make many modifications and improvements, which should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent control system for an RO water purifier, characterized in that, include: Sensing components are used to detect the real-time operating parameters of the water purifier; The control module calculates the TDS pollution ratio, water quality environmental factor W, dynamic time decay factor H, dynamic threshold T_threshold(t), system health factor S, and flushing demand index RDI based on the real-time operating parameters of the water purifier. When the TDS contamination ratio is greater than or equal to the dynamic threshold T_threshold(t) or the TDS contamination ratio is greater than the first threshold, a restorative flushing command is triggered. When the TDS contamination ratio is less than the dynamic threshold T_threshold(t) and the flushing demand index RDI is greater than or equal to the second threshold, a maintenance flushing command is triggered. Among them, TDS pollution ratio T is a real-time parameter characterizing the degree of pollution in the reflux membrane pure water side; water quality environmental factor W is a correction coefficient characterizing the influence of water temperature on membrane flux and pollution rate; dynamic time decay factor H is a time dimension quantitative parameter characterizing the risk of reflux pollution accumulation due to downtime; dynamic threshold T_threshold(t) is an adaptive trigger threshold characterizing the change with total standby time; and system health factor S is a health status quantitative parameter characterizing the degree of physical fouling of the RO membrane.

2. The intelligent control system for an RO water purifier as described in claim 1, characterized in that: The real-time operating parameters of the water purifier include: raw water TDS value, purified water TDS value, water temperature, flow rate, and diaphragm pump current.

3. The intelligent control system for an RO water purifier as described in claim 2, characterized in that: TDS contamination ratio T = TDS of pure water / TDS of raw water.

4. The intelligent control system for an RO water purifier as described in claim 2, characterized in that: The water quality environmental factor W is determined based on water temperature.

5. The intelligent control system for an RO water purifier as described in claim 2, characterized in that: The dynamic time decay factor H is calculated based on the total standby time t_long and the time after flushing t_short; H=1 / [1+exp(-k_dynamic×(t_short-t0_dynamic))], where t_short is the time after rinsing, and k_dynamic and t0_dynamic are parameters adjusted according to the water quality environmental factor W.

6. The intelligent control system for an RO water purifier as described in claim 2, characterized in that: The dynamic threshold T_threshold(t) = T_base + ΔT / (1 + exp(-k × (t_long - t0))), where T_base is the base threshold, ΔT is the threshold adjustment amount, and k and t0 are preset parameters.

7. The intelligent control system for an RO water purifier as described in claim 2, characterized in that: The system health factor S was determined using a specific current diagnostic model: Obtain the operating current I_pump and actual flow rate Q of the diaphragm pump, and calculate the specific current I_pump / Q; The specific current I_pump / Q is compared with the reference specific current, and the system health factor S is determined based on the deviation.

8. The intelligent control system for an RO water purifier as described in claim 2, characterized in that: RDI (Relieving Demand Index) = α_norm×T + β_norm×H + γ_norm×W + δ_norm×(1-S); Where α_norm, β_norm, γ_norm, and δ_norm are normalized weight coefficients.

9. The intelligent control system for an RO water purifier as described in claim 1, characterized in that: The control module also includes a user habit learning unit, which records the user's historical water usage time data, predicts future low water usage periods as a safety window based on the historical water usage time data, and actively triggers maintenance flushing within the safety window.

10. The intelligent control system for an RO water purifier as described in claim 1, characterized in that: The control module is also configured to: The total standby time t_long is monitored. When the total standby time t_long exceeds the preset ultra-long standby threshold, a flushing action is forcibly triggered.

11. The intelligent control system for an RO water purifier as described in claim 8, characterized in that: The control module is also configured to dynamically adjust the flushing duration and flushing intensity based on the flushing demand index (RDI) value using a linear interpolation method.

Images