Filter element loss state evaluation method and system, intelligent electric appliance and storage medium

Abstract

The invention provides a filter element loss state evaluation method and system, an intelligent electric appliance and a storage medium. The loss state evaluation method comprises the following steps: collecting state data in an operation process of a filter element, wherein the state data comprises fluid dynamic parameters, water quality chemical parameters and physical state parameters; respectively calculating an emergency risk item, a progressive loss item and a physical anomaly item based on the state data; superposing the sudden risk item, the progressive loss item and the physical anomaly item to generate a composite loss index; and triggering a hierarchical response mechanism according to the composite loss index. According to the method, accurate prediction capability is realized through multi-parameter collaborative analysis; a sudden risk item captures coupling association of flow and water quality sudden change, so that the misjudgment risk is remarkably reduced; the progressive loss item dynamically adapts to regional water quality characteristics, and unnecessary replacement is reduced; real-time response efficiency: a physical abnormal item identifies the damage characteristics of the filter screen, and second-level fault blocking is realized; resource optimization value: a graded response mechanism synchronously prolongs the service life of the filter element and ensures the safety of water quality.

Description

Technical Field

[0001] This disclosure relates to the field of smart appliances, and more particularly to a method, system, smart appliance, and storage medium for evaluating the wear status of a filter element. Background Technology

[0002] With the improvement of people's living standards and the promotion and popularization of technologies such as the Internet, big data, artificial intelligence, and voice interaction, more and more traditional lifestyles are gradually changing, and the use of home appliances is gradually moving towards intelligence. While bringing more convenience to users, the functions of various home appliances are also becoming more diversified. Currently, the life management of water purification equipment filters mainly relies on two technical paths: fixed cycle replacement strategy: replacing the filter based on a preset time or fixed water flow, without considering water quality fluctuations and differences in usage frequency; single sensor threshold alarm: triggering commands through a single parameter such as flow rate or TDS, unable to identify the synergistic effect of multiple parameters. These methods have significant drawbacks: sudden water quality events (such as raw water pollution) are difficult to capture in a timely manner; the deterioration of the filter's microstructure (such as membrane pore cracks) cannot be quantitatively assessed; and maintenance decisions rely on manual disassembly, resulting in a serious delay in response. Summary of the Invention

[0003] The technical problem to be solved by this disclosure is to overcome the shortcomings of the prior art, which does not establish a multi-parameter dynamic coupling evaluation system for filter element loss and cannot effectively solve the problems of prediction distortion and response lag. This disclosure provides a method, system, smart appliance and storage medium for evaluating the loss status of filter elements.

[0004] This disclosure solves the above-mentioned technical problems through the following technical solution:

[0005] This disclosure provides a method for evaluating the wear status of a filter element, the method comprising:

[0006] Collect status data during the operation of the filter element, including fluid dynamics parameters, water quality chemical parameters, and physical state parameters;

[0007] Based on the aforementioned state data, the sudden risk item, the gradual loss item, and the physical anomaly item are calculated respectively.

[0008] The sudden risk item, the gradual loss item, and the physical anomaly item are superimposed to generate a composite loss index;

[0009] The graded response mechanism is triggered based on the composite loss index.

[0010] Optionally, the fluid dynamics parameters include flow fluctuation characteristic parameters; the water quality chemical parameters include TDS change acceleration parameters; the calculation of sudden risk terms, gradual loss terms, and physical anomaly terms based on the state data includes:

[0011] Calculate the flow fluctuation coefficient based on the aforementioned flow fluctuation characteristic parameters;

[0012] Calculate the water quality deterioration acceleration based on the TDS change acceleration parameters;

[0013] The sudden risk item is generated by multiplying the flow fluctuation coefficient with the water quality deterioration acceleration.

[0014] Optionally, the water quality chemical parameters include TDS concentration and pH value; the calculation of sudden risk items, gradual loss items, and physical anomaly items based on the state data includes:

[0015] Based on the TDS concentration parameter and the corresponding first dynamic weighting coefficient, a first fusion term is formed;

[0016] A second fusion term is formed based on the pH value parameter and the corresponding second dynamic weighting coefficient;

[0017] The first fusion term and the second fusion term are linearly fused to generate an asymptotic loss term.

[0018] Optionally, the fluid dynamics parameters include real-time flow parameters; the physical state parameters include turbidity parameters; and the calculation of the sudden risk term, the gradual loss term, and the physical anomaly term based on the state data includes:

[0019] Synchronize the real-time flow rate with the turbidity parameter;

[0020] Calculate the correlation characteristic between the real-time flow rate and the turbidity parameter, wherein the correlation characteristic is used to characterize the consistency of the changing trends of the real-time flow rate and the turbidity parameter;

[0021] Physical anomaly values ​​are generated based on the associated feature values.

[0022] Optionally, the step of superimposing the sudden risk item, the gradual loss item, and the physical anomaly item to generate a composite loss index includes:

[0023] Obtain the weight combination corresponding to the sudden risk item, the gradual loss item, and the physical anomaly item; the weight combination is updated based on a genetic algorithm;

[0024] The composite loss index is calculated based on the sudden risk item, the gradual loss item, the physical anomaly item, and the weight combination.

[0025] Optionally, triggering the graded response mechanism based on the composite loss index includes:

[0026] In response to the composite loss index indicating mild loss, a remaining life prediction and preventative maintenance plan are generated.

[0027] When the composite loss index indicates moderate damage, non-destructive testing is activated to identify micro-defects.

[0028] In response to the composite loss index indicating severe failure, equipment shutdown and physical damage quantification analysis are performed.

[0029] This disclosure provides a filter element wear status evaluation system, the wear status evaluation system comprising:

[0030] The data acquisition module is used to collect status data during the operation of the filter element. The status data includes fluid dynamics parameters, water quality chemical parameters, and physical state parameters.

[0031] The evaluation module is used to calculate the sudden risk item, the gradual loss item, and the physical anomaly item based on the state data.

[0032] The evaluation module is also used to superimpose the sudden risk item, the gradual loss item, and the physical anomaly item to generate a composite loss index.

[0033] The response module is used to trigger a graded response mechanism based on the composite loss index.

[0034] Optionally, the fluid dynamics parameters include flow rate fluctuation characteristic parameters; the water quality chemical parameters include TDS change acceleration parameters; the evaluation module is specifically used for:

[0035] Calculate the flow fluctuation coefficient based on the aforementioned flow fluctuation characteristic parameters;

[0036] Calculate the water quality deterioration acceleration based on the TDS change acceleration parameters;

[0037] The sudden risk item is generated by multiplying the flow fluctuation coefficient with the water quality deterioration acceleration.

[0038] Optionally, the water quality chemical parameters include TDS concentration and pH value; the evaluation module is specifically used for:

[0039] Based on the TDS concentration parameter and the corresponding first dynamic weighting coefficient, a first fusion term is formed;

[0040] A second fusion term is formed based on the pH value parameter and the corresponding second dynamic weighting coefficient;

[0041] The first fusion term and the second fusion term are linearly fused to generate an asymptotic loss term.

[0042] Optionally, the fluid dynamics parameters include real-time flow parameters; the physical state parameters include turbidity parameters; the evaluation module is specifically used for:

[0043] Synchronize the real-time flow rate with the turbidity parameter;

[0044] Calculate the correlation characteristic between the real-time flow rate and the turbidity parameter, wherein the correlation characteristic is used to characterize the consistency of the changing trends of the real-time flow rate and the turbidity parameter;

[0045] Physical anomaly values ​​are generated based on the associated feature values.

[0046] Optionally, the evaluation module is specifically used for:

[0047] Obtain the weight combination corresponding to the sudden risk item, the gradual loss item, and the physical anomaly item; the weight combination is updated based on a genetic algorithm;

[0048] The composite loss index is calculated based on the sudden risk item, the gradual loss item, the physical anomaly item, and the weight combination.

[0049] Optionally, the response module is specifically used for:

[0050] In response to the composite loss index indicating mild loss, a remaining life prediction and preventative maintenance plan are generated.

[0051] When the composite loss index indicates moderate damage, non-destructive testing is activated to identify micro-defects.

[0052] In response to the composite loss index indicating severe failure, equipment shutdown and physical damage quantification analysis are performed.

[0053] This disclosure provides a smart appliance, including a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein the processor executes the computer program to implement the filter element wear status evaluation method described in any of the above claims.

[0054] This disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the filter element wear status evaluation method described in any of the preceding claims.

[0055] This disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the filter element wear status evaluation method described in any of the above claims.

[0056] Based on common knowledge in the field, the above-mentioned preferred conditions can be combined arbitrarily to obtain various preferred embodiments of this disclosure.

[0057] The positive and progressive effects of this invention are as follows: the invention achieves accurate prediction capability through multi-parameter collaborative analysis: the sudden risk item captures the coupling correlation between flow rate and water quality changes, significantly reducing the risk of misjudgment; the progressive loss item dynamically adapts to regional water quality characteristics, reducing unnecessary replacement; real-time response efficiency: the physical anomaly item identifies filter damage characteristics, achieving second-level fault blocking; resource optimization value: the graded response mechanism simultaneously extends the service life of the filter element and ensures water quality safety. Attached Figure Description

[0058] Figure 1 A flowchart illustrating a method for evaluating the wear status of a filter element, provided as an exemplary embodiment of this disclosure;

[0059] Figure 2 A flowchart of step 103 provided for an exemplary embodiment of this disclosure;

[0060] Figure 3 A schematic diagram of a filter element wear status evaluation system provided for an exemplary embodiment of this disclosure;

[0061] Figure 4 This is a schematic diagram of the structure of a smart appliance provided as an exemplary embodiment of the present disclosure. Detailed Implementation

[0062] The present disclosure is further illustrated below by way of embodiments, but the present disclosure is not limited to the scope of the embodiments described herein.

[0063] The prefixes such as "first" and "second" used in this disclosure are merely for distinguishing different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in this disclosure does not constitute a limitation on the described objects. The description of the described objects is given in the context of the embodiments, and the use of such prefixes should not constitute unnecessary restrictions. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0064] In this embodiment of the disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good morals.

[0065] Example 1

[0066] Figure 1 A flowchart illustrating a method for evaluating the wear status of a filter element, provided as an exemplary embodiment of this disclosure.

[0067] This disclosure provides a method for evaluating the wear status of a filter element, the method comprising:

[0068] Step 101: Collect status data during the operation of the filter element. The status data includes fluid dynamics parameters, water quality chemical parameters, and physical state parameters.

[0069] Step 101 aims to acquire multi-dimensional status data of the filter element in real time through a sensor system, providing a data foundation for subsequent loss status evaluation. The status data includes the following three types of parameters, each reflecting the filter element's working status from different physical perspectives:

[0070] 1. Fluid dynamic parameters

[0071] Technical function: Characterizes the dynamic characteristics of water flowing through the filter element, reflecting the degree of filter element clogging, fluid stability and pressure changes.

[0072] Example of specific parameters:

[0073] Example 1-1. Flow fluctuation characteristic parameters: Instantaneous flow values ​​are obtained through high-frequency sampling (e.g., once per second) and used to calculate statistical characteristics such as flow standard deviation and rate of change.

[0074] Example 1-2. Real-time flow parameters: The volume of liquid flowing through the filter element per unit time (unit: L / min), reflecting the degree of filter element flux attenuation.

[0075] Example 1-3. Pressure difference parameter: The pressure difference between the inlet and outlet of the filter element (unit: kPa), which is directly related to the filter element's clogging resistance.

[0076] 2. Water quality chemical parameters

[0077] Technical function: to quantify changes in dissolved substances and chemical properties in water, and to monitor the decline in the adsorption capacity of filter elements and the corrosion status of materials.

[0078] Example of specific parameters:

[0079] Example 2-1. Acceleration parameter of TDS (Total Dissolved Solids) change: Second time derivative of TDS concentration (unit: ppm / s) 2 ), to capture sudden water quality events (such as outbreaks of raw water pollution).

[0080] Example 2-2. TDS concentration parameter: Total dissolved inorganic salts in water (unit: ppm), reflecting the degradation of the filter element's desalination performance.

[0081] Example 2-3. pH value parameter: water body acidity and alkalinity index (dimensionless), monitoring filter media corrosion caused by deviation from neutrality (pH=7).

[0082] 3. Physical state parameters

[0083] Technical function: To monitor the structural integrity of the filter element and the physical properties of pollutants, and to identify mechanical damage or abnormal blockage.

[0084] Example of specific parameters:

[0085] Example 3-1. Turbidity parameter: content of suspended particulate matter in water (unit: NTU). An abnormally high level may indicate filter damage.

[0086] Example 3-3. Temperature Parameter: Filter Cartridge Operating Ambient Temperature (Unit: This affects the aging rate of materials and the reproduction of microorganisms.

[0087] Example 3-3. Vibration frequency parameters (applicable to rotary filter elements): The natural frequency of the filter element during operation (unit: Hz), and offset indicates structural deformation.

[0088] In step 101, it should be noted that:

[0089] 1. Data Relationship Design

[0090] The three types of parameters collected in step 101 have a clear technical division:

[0091] Fluid dynamics parameters → Filter cartridge physical clogging diagnosis (e.g., a sudden increase in pressure differential indicates clogging);

[0092] Water quality chemical parameters → Deterioration of filter element chemical performance (e.g., increased TDS indicates a decrease in desalination rate);

[0093] Physical state parameters → Filter element structural integrity monitoring (e.g., negative correlation between turbidity and flow rate indicates damage).

[0094] 2. Parameter Acquisition Technical Solution

[0095] Synchronization Guarantee: Unified clock source for multiple sensors ensures alignment of timing data (e.g., flow rate and turbidity are matched with millisecond-level timestamps).

[0096] Robust design: Apply medium filtering to the raw data to eliminate impulse noise, and update the baseline value by exponential weighted averaging.

[0097] Dynamic sampling strategy: High-frequency parameters (such as flow rate) are collected every second, and low-frequency parameters (such as pH) are collected every minute, balancing accuracy and energy consumption.

[0098] 3. Clear definitions to avoid ambiguity

[0099] The "TDS change acceleration" refers to the second derivative of TDS concentration with respect to time, which can optionally be calculated as follows:

[0100] Step 1: Record the TDS value every minute to construct the time series C(t);

[0101] Step 2: Fit the quadratic curve C(t) = k1t 2 +k2t+k3;

[0102] Step 3: Take the second derivative .

[0103] The "flow fluctuation characteristics" specifically refer to the statistical dispersion of flow data, which can be optionally calculated as follows:

[0104] (Window size = 30 seconds);

[0105] 4. Technical support

[0106] Step 101 addresses two major shortcomings of traditional solutions:

[0107] Limitations of a single parameter: For example, monitoring only the flow rate may overlook the hidden losses caused by water quality deterioration;

[0108] Static sampling is insufficient: fixed-frequency sampling cannot capture sudden pollution events (high-frequency sampling is dynamically triggered by TDS change acceleration).

[0109] Step 102: Calculate the sudden risk item, the gradual loss item, and the physical anomaly item based on the state data;

[0110] Optionally, the fluid dynamics parameters include flow fluctuation characteristic parameters; the water quality chemical parameters include TDS change acceleration parameters; step 102, calculate the sudden risk term, the gradual loss term, and the physical anomaly term based on the state data, including: calculating the flow fluctuation coefficient based on the flow fluctuation characteristic parameters; calculating the water quality deterioration acceleration based on the TDS change acceleration parameters; performing a product operation on the flow fluctuation coefficient and the water quality deterioration acceleration to generate the sudden risk term.

[0111] This step, concerning sudden risk factors, is one of the core innovative aspects of the filter cartridge wear status evaluation method. It aims to capture the risk of sudden filter cartridge failure through specific parameter combinations. Its technical essence lies in the nonlinear coupling of fluid dynamics and the abrupt changes in water quality to quantify the instantaneous failure probability.

[0112] 1. Technical Objectives

[0113] To address the shortcomings of traditional solutions in failing to provide early warning of sudden failures (such as membrane rupture or raw water contamination), this approach captures abnormal fluctuations in water flow (indicating mechanical failure) and links them to accelerated water quality deterioration (indicating a pollution event). The combined effect of these two factors amplifies the risk signal.

[0114] 2. Basis for parameter selection

[0115] Flow fluctuation characteristic parameters reflect fluid instability caused by pump failure, pipeline blockage, etc. Using only the average flow rate will lose dynamic information.

[0116] TDS change acceleration parameter captures the acceleration (non-velocity) of changes in dissolved solids concentration, providing early warning of sudden pollution. However, the first derivative cannot distinguish between continuous pollution and sudden pollution.

[0117] 3. Detailed explanation of the calculation process

[0118] Step 1: Calculation of flow fluctuation coefficient

[0119] Physical meaning: It quantifies the degree of instability of water flow; the larger the value, the more turbulent the flow.

[0120] Calculation method: Collect traffic time-series data within a fixed time window (e.g., 30 seconds). ;

[0121] Calculate the ratio of the standard deviation to the mean of the flow rate within the window:

[0122] ;

[0123] in, For instantaneous flow, it captures dynamic changes in flow in real time, such as sudden changes in flow caused by pump start-up and shutdown or pipe blockage; The average flow rate serves as a baseline value, used to quantify the degree of deviation at each sampling point. This is the flow fluctuation coefficient.

[0124] Example explanation:

[0125] If the flow rate within a 30-second window is 10.2, 12.5, 8.7, 11.3 L / min (mean) ),but:

[0126] Standard deviation = 1.52 → ;

[0127] Step 2: Calculation of water quality deterioration acceleration

[0128] Physical meaning: Characterizes the acceleration of TDS concentration change; a positive value indicates that pollution is accelerating.

[0129] Calculation method: Collect TDS values ​​every minute and construct a time series C(t);

[0130] Fit a quadratic curve C(t) = k1t to five consecutive data points. 2 +k2t+k3;

[0131] Take the second derivative as the acceleration: (Unit: ppm / min²).

[0132] Example explanation:

[0133] If the TDS values ​​within 5 minutes are: 100, 120, 150, 190, 240 ppm → fitted curve C(t) = 8t 2 +10t+100 → ;

[0134] Step 3: Generate sudden risk items through product operation

[0135] Technical principle:

[0136] Product rather than weighted summation: Emphasizing the synergistic amplification effect of fluctuations and deterioration (e.g., when a pollution outbreak occurs during a flow fluctuation, the risk index increases).

[0137] Mathematical expression: (Unit: dimensionless × ppm / min) 2 );in, This is a sudden risk item. For flow fluctuation coefficient, The acceleration of TDS change;

[0138] Example scenario, such as when a certain filter element appears simultaneously:

[0139] Flow fluctuation coefficient (Due to water pump malfunction);

[0140] TDS change acceleration (Sudden pollution of raw water);

[0141] Then sudden risk items .

[0142] Regarding the technical advantages and parameter design of this step:

[0143] 1. The scientific basis of nonlinear coupling

[0144] when and When both increase, The growth rate is exponential (e.g., 0.3×20=6.0 > 0.3+20=20.3), which is more in line with the physical nature of sudden risks: fluid instability will accelerate the rate at which pollutants penetrate the filter element.

[0145] 2. Robustness Guarantee of Parameter Calculation

[0146] Traffic fluctuation coefficient: Calculated using a sliding window, the window size can be adjusted according to the application scenario (e.g., 30 seconds for home devices, 10 seconds for industrial devices).

[0147] TDS change acceleration: Before fitting, perform median filtering on the data to eliminate interference from single-point outliers (such as impulse noise).

[0148] 3. Flexibility in project implementation

[0149] Scalable parameters: If the system supports pressure monitoring, pressure fluctuations can be incorporated. calculate;

[0150] Alternative algorithms: In addition to quadratic curve fitting, numerical differentiation methods (such as the central difference method) can also be used to calculate the TDS change acceleration.

[0151] ;

[0152] Here, we provide an example (sudden failure warning scenario) illustrating an abnormal operation event of a reverse osmosis filter element:

[0153] 1. Background: A ruptured raw water pipe caused sewage to enter the system, and the water pump voltage was unstable.

[0154] 2. Parameter monitoring:

[0155] Flow rate data: 15.0, 17.2, 12.8, 18.5 L / min );

[0156] TDS data: 80 → 95 → 120 → 155 ppm ( )

[0157] 3. Calculation of sudden risk items:

[0158] ;

[0159] 4. System Response:

[0160] when When the preset threshold is reached, a level 2 alarm is triggered: a combined alarm of "raw water pollution + equipment failure" is pushed; it is recommended to immediately shut down the machine for maintenance.

[0161] Additionally, it should be noted that:

[0162] 1. Connection with subsequent steps

[0163] This step generates the emergency risk item. The input will be passed to step 103, along with the asymptotic loss term. Physical anomalies Together, they constitute the composite loss index. Its numerical range needs to match the other two (e.g., through coefficient normalization) to ensure the effectiveness of the superposition.

[0164] 2. Clear definitions to avoid ambiguity

[0165] "Flow fluctuation characteristic parameters" specifically refer to statistics describing flow instability (such as standard deviation / mean ratio, coefficient of variation), excluding the flow mean itself;

[0166] "TDS acceleration" refers only to the result of the second derivative calculation; the first derivative (rate of change) cannot be substituted.

[0167] 3. Technical Boundary Declaration

[0168] Product operation This is the preferred implementation of the scheme, but equivalent mathematical transformations (such as...) (This is still considered an equivalent alternative to the present technical solution.)

[0169] Optionally, the water quality chemical parameters include TDS concentration parameters and pH value parameters; Step 102: Calculate the sudden risk item, the gradual loss item, and the physical anomaly item based on the state data, including: forming a first fusion item based on the TDS concentration parameter and the corresponding first dynamic weight coefficient; forming a second fusion item based on the pH value parameter and the corresponding second dynamic weight coefficient; performing linear fusion of the first fusion item and the second fusion item to generate the gradual loss item.

[0170] This step, concerning the progressive loss term, is one of the core components of the filter cartridge wear status evaluation method, focusing on quantifying the progressive performance degradation of the filter cartridge. Its technical essence lies in: scientifically characterizing the long-term wear trend of the filter cartridge material by dynamically weighting and integrating key water quality chemical parameters.

[0171] 1. Technical Objectives

[0172] This addresses the assessment bias caused by traditional solutions neglecting differences in water quality characteristics (such as high hardness or acidic water sources), and achieves the following:

[0173] TDS concentration → Quantifies the attenuation of filter cartridge adsorption capacity;

[0174] pH value → Monitors acid and alkaline corrosion effects;

[0175] The dynamic weight allocation of the two is adapted to the regional water quality characteristics.

[0176] 2. Basis for parameter selection

[0177] TDS concentration parameter directly reflects the decay of the filter element's ability to remove dissolved solids. Monitoring based on conductivity sensors is low-cost and highly accurate.

[0178] The pH parameter, which captures the chemical corrosion of filter media caused by deviations from neutral (pH=7) (acidic corrosion of metal filter screens, alkaline hydrolysis of polymers), can be measured based on the glass electrode method and has been certified by ISO standards.

[0179] 3. Detailed explanation of the calculation process

[0180] Step 1: Generation of the first fusion term (TDS concentration term)

[0181] Physical meaning: Increased TDS concentration indicates a decrease in the desalination performance of the filter element, but its influence weight needs to be dynamically adjusted under different water quality environments.

[0182] Calculation method:

[0183] Get the current TDS concentration value (Unit: ppm);

[0184] Apply the first dynamic weighting coefficient a: ;

[0185] Among them, the dynamic weight 'a' has the following characteristics:

[0186] Value range (example): 0.2 ≤ a ≤ 0.7 (determined through optimization using historical data);

[0187] Adjustment logic: For water source areas with high TDS (such as groundwater), a higher value (a=0.6) is adopted to strengthen the weight of desalination performance.

[0188] Step 2: Generation of the second fusion term (pH value term)

[0189] Physical significance: When the pH value deviates from neutral, the filter media wears out faster, and a punitive weight needs to be applied.

[0190] Calculation method:

[0191] Get the current pH value (dimensionless);

[0192] Apply a second dynamic weighting coefficient b: ;Note: Quantitative deviation from neutrality

[0193] Among them, the dynamic weight b has the following characteristics:

[0194] Value range (example): -0.3 ≤ b ≤ -0.1 (negative values ​​indicate penalties);

[0195] Regulation logic: In areas with acidic water quality (pH<6.5), increase |b| (e.g., b=−0.25) to strengthen corrosion punishment.

[0196] Step 3: Linear fusion to generate asymptotic loss terms

[0197] Technical principle:

[0198] Additive fusion reflects the independent contributions of TDS and pH (non-productive relationship), which is consistent with the cumulative characteristics of asymptotic loss;

[0199] Mathematical expression: (Unit: ppm·weighting factor);

[0200] Example scenario:

[0201] Water quality in a certain area: TDS = 250 ppm, pH = 6.3;

[0202] Optimization weights: a = 0.5 (high TDS water source), b = −0.2 (acidic water);

[0203] calculate:

[0204] ;

[0205] Regarding the technical advantages and design details of this step:

[0206] 1. The Scientific Basis of Dynamic Weights

[0207] TDS weight a: positively correlated with water hardness (a increases by 0.1 for every 50 ppm increase in hardness);

[0208] pH weight b: negatively correlated with water corrosivity (for every 0.5 decrease in pH, |b| increases by 0.05).

[0209] 2. Robustness safeguards

[0210] Outlier handling: When pH < 4 or > 10, activate the backup sensor to verify the validity of the data;

[0211] Weight freezing mechanism: If the water quality is stable for 24 consecutive hours (fluctuation <5%), the weight is locked to prevent oscillation.

[0212] 3. Scalable Design

[0213] Auxiliary parameters can be introduced, such as adding a temperature compensation term c(T-25) to correct the high-temperature accelerated corrosion effect;

[0214] Alternative algorithm: If the system supports ORP (oxidation-reduction potential) monitoring, the pH term can be replaced with b⋅ORP.

[0215] Here, we provide an example (regional water quality adaptation) of a filter cartridge evaluation in an acidic groundwater area in southern China:

[0216] 1. Background: Water quality characteristics: TDS=320 ppm, pH=6.1, water temperature 25°C year-round. .

[0217] 2. Weight optimization:

[0218] Historical data training yielded: a=0.62 (high TDS requires reinforcement), b=-0.26 (strong acidity requires high penalty);

[0219] 3. Asymptotic loss calculation:

[0220] ;

[0221] Additionally, it should be noted that:

[0222] 1. Integration with the overall approach

[0223] This step generates With sudden risk items Physical anomalies In step 103, the weights are superimposed according to the system weights ( ):

[0224] ;

[0225] in The system-level weights for the asymptotic loss term (see step 103 optimization logic).

[0226] 2. Declaration of Terminology Consistency

[0227] "First dynamic weighting coefficient" refers to the weight 'a' of the TDS concentration term;

[0228] "Linear fusion" is defined as a weighted summation operation, excluding nonlinear transformations (such as multiplication and exponentiation).

[0229] 3. Clarification of technical boundaries

[0230] Dynamic weight optimization can employ intelligent algorithms such as genetic algorithms (GA) and particle swarm optimization (PSO), but the core innovation lies in: "achieving precise quantification of progressive loss through dynamic mapping of water quality characteristics and weight coefficients."

[0231] Optionally, the fluid dynamics parameters include real-time flow parameters; the physical state parameters include turbidity parameters; step 102, calculate the sudden risk term, the gradual loss term, and the physical anomaly term based on the state data, including: synchronizing real-time flow and turbidity parameters; calculating the correlation characteristic quantity between real-time flow and turbidity parameters, the correlation characteristic quantity being used to characterize the consistency of the changing trends of real-time flow and turbidity parameters; generating physical anomaly values ​​based on the correlation characteristic quantity.

[0232] This step, focusing on physical anomalies, is a crucial aspect of filter cartridge wear status evaluation methods. It concentrates on the real-time diagnosis of filter cartridge structural integrity failure risks through the synergistic analysis of fluid dynamics parameters and physical state parameters. The core technology lies in capturing the dynamic correlation between flow rate and turbidity, quantifying the instantaneous state of mechanical damage or abnormal clogging of the filter cartridge.

[0233] 1. Technical Objectives

[0234] To address the shortcomings of traditional solutions that cannot detect structural damage to the filter element (such as filter screen breakage or support frame deformation) in real time, the following method is used:

[0235] Real-time flow parameters → reflect instantaneous changes in fluid flux (e.g., a sudden drop indicates blockage, a sudden increase indicates damage);

[0236] Turbidity parameter → Monitors abnormal fluctuations in the concentration of suspended particulate matter in water (such as an abnormal increase indicating leakage of unfiltered liquid due to filter rupture);

[0237] Correlation features → Quantify the consistency of the changing trends of the two, and amplify the signal sensitivity of structural failures.

[0238] 2. Basis for parameter selection

[0239] Real-time flow parameters: directly characterize the instantaneous flow rate of fluid through the filter element (unit: L / min). A sudden drop in flow rate may be caused by blockage, while a sudden increase in flow rate may be caused by filter damage leading to a decrease in fluid resistance.

[0240] Turbidity parameter: unit NTU (Nephelometric Turbidity Unit). An abnormally high level indicates that unfiltered impurities have penetrated the filter element (such as membrane pore cracks leading to contaminant leakage).

[0241] Explanation of irreplaceability: Monitoring only flow rate may misinterpret normal fluctuations (such as pump start-up and shutdown), while monitoring only turbidity may overlook mechanical deformation without particle leakage (such as metal filter deformation). The combined use of both methods can accurately distinguish between blockage and damage.

[0242] 3. Detailed explanation of the calculation process

[0243] Step 1: Parameter Synchronization Mechanism

[0244] Technical necessity: Flow rate and turbidity need to be compared under the same time reference to avoid misjudgment caused by time sequence misalignment.

[0245] Synchronization method:

[0246] Timestamp alignment: Match data points from flow sensor and turbidity sensor with millisecond-level timestamps (e.g., data collected every 100ms).

[0247] Event-triggered sampling: When the rate of change in flow exceeds a threshold (e.g., ±10%), the turbidity sensor is triggered to synchronously sample at high frequencies (e.g., from 1Hz to 10Hz).

[0248] Step 2: Calculation of Correlation Features

[0249] Physical meaning: It represents the consistency between the trends of flow rate and turbidity. Under normal operating conditions, the two are usually negatively correlated (decreasing flow rate → increasing turbidity indicates blockage), while a positive correlation may occur when there is damage (increasing flow rate → increasing turbidity indicates leakage).

[0250] Calculation method:

[0251] Obtain the traffic sequence within a sliding time window (e.g., 30 seconds). and turbidity sequence ;

[0252] Calculate the ratio of covariance to standard deviation to generate the normalized correlation coefficient. :

[0253] (Dimensionless, range [-1, 1]);

[0254] Example:

[0255] Normal blockage: Flow rate decreases from 12 L / min to 8 L / min (change -33%), turbidity increases from 5 NTU to 8 NTU (change +60%) → (Strong negative correlation);

[0256] Filter damage: Flow rate increased from 10L / min to 15L / min (+50%), turbidity increased from 5 NTU to 20 NTU (+300%) → (Strong positive correlation).

[0257] Step 3: Generating Physical Outliers

[0258] Transformation logic: Mapping correlation coefficients to an anomaly scale:

[0259] ;

[0260] Design principle: The penalty weight for positive correlation (damage) is higher than that for negative correlation (blockage), because the risk of pollution spread caused by damage is more urgent.

[0261] Regarding the technical advantages and robust design of this step:

[0262] 1. Dynamic baseline value adaptation

[0263] Under normal operating conditions, the correlation coefficient exhibits baseline fluctuations (e.g., ±0.2). Misjudgments are eliminated through baseline correction using moving averages. Update method:

[0264] ;

[0265] Example: Household water flow fluctuates greatly during morning and evening peak hours; after baseline correction, only when... Only then was the exception triggered.

[0266] 2. Anti-interference mechanism

[0267] Pulse filtering: Apply medium-range filtering (window size 5 points) to transient noise (such as turbidity spikes caused by bubbles);

[0268] Delayed triggering: The abnormality is only confirmed when the abnormal state lasts for more than a set time (such as 10 seconds), thus avoiding instantaneous interference.

[0269] 3. Scalable Design

[0270] Pressure parameters can be introduced: If the system is equipped with a differential pressure sensor, the differential pressure-flow correlation can be incorporated. Calculations (e.g., sudden increase in differential pressure + sudden decrease in flow rate → confirm blockage);

[0271] Alternative Algorithm: To reduce computational load, the difference integration method can be used instead of covariance.

[0272] ;

[0273] Therefore, let's illustrate with examples (filter damage diagnosis scenario): a reverse osmosis filter element suddenly ruptures.

[0274] 1. Background: Due to mechanical fatigue, the filter element developed membrane pore cracks, allowing unfiltered raw water to seep into the purified water side.

[0275] 2. Parameter monitoring:

[0276] Flow rate data: 10.0 → 14.2 → 16.5 L / min (+65% within 30 seconds)

[0277] Turbidity data: 5 → 18 → 35 NTU (+600%)

[0278] 3. Correlation analysis:

[0279] Calculate the correlation coefficient → Physical anomalies ;

[0280] 4. System Response:

[0281] when When the preset threshold is reached, a three-level response is triggered:

[0282] Close the inlet solenoid valve (action within seconds);

[0283] Initiate optical scanning to locate the damaged area (such as crack coordinate markers).

[0284] Additionally, it should be noted that:

[0285] 1. Integration with the overall approach

[0286] This step generates In step 103, with the sudden risk item Asymptotic loss term Added by dynamic weights:

[0287] ;

[0288] in The system-level weights for physical anomaly items (see step 103, genetic algorithm optimization logic), are typically set as follows: (Structural failures require priority response).

[0289] 2. Declaration of Terminology Consistency

[0290] "Correlation characteristic" specifically refers to the normalized correlation coefficient between flow rate and turbidity. ;

[0291] "Synchronous" is strictly defined as timestamp alignment or event-triggered sampling, excluding asynchronous batch processing.

[0292] 3. Clarification of technical boundaries

[0293] The calculation of associated characteristic quantities needs to exclude nonlinear transformations (such as exponential weighting). The core innovation lies in: "real-time diagnosis of structural failures can be achieved by correlating the time-series trends of fluid dynamic parameters (flow rate) and physical state parameters (turbidity).

[0294] Step 103: Combine the sudden risk items, gradual loss items, and physical anomaly items to generate a composite loss index;

[0295] Step 103 is the core integration step in the filter element wear status evaluation method. Its technical essence lies in: scientifically integrating three types of heterogeneous wear items (sudden risk / gradual wear / physical anomaly) through a dynamically optimized weighting system to generate a comprehensive evaluation index that quantifies the filter element's health status. The following is a layered analysis of its technical logic and implementation details:

[0296] 1. Technical necessity

[0297] Overcoming the limitations of traditional methods that simply use weighted summation:

[0298] Differences in loss types: Sudden risk items (second-level failures) and gradual loss items (monthly decays) have different dimensions and timeliness;

[0299] Environmental adaptation requirements: The weight of water quality requirements in different regions is dynamically adjusted (e.g., the weight of sudden risk needs to be increased in highly polluted areas).

[0300] System-level coordination: Physical anomalies need to be linked with chemical / fluid parameters to amplify diagnostic signals.

[0301] 2. Weighting System Design Principles

[0302] Inter-item weights apply to the overall three types of loss items, with the optimization objective being to balance the priorities of sudden / gradual / physical anomalies.

[0303] The in-item weights apply to the internal parameters of a single item, and the optimization objective is the optimization already completed in step 102.

[0304] Optionally, see Figure 2 It can be seen that step 103, which involves superimposing the sudden risk item, the gradual loss item, and the physical anomaly item to generate a composite loss index, includes:

[0305] Step 1031: Obtain the weight combinations corresponding to the sudden risk item, the gradual loss item, and the physical anomaly item; the weight combinations are updated based on the genetic algorithm; the purpose of step 1031 is to obtain the weight combinations.

[0306] Physical meaning: Establishing the contribution ratio coefficients and weights for the three types of loss terms. Satisfies the normalization constraint: ;

[0307] Optimization mechanism:

[0308] Initialization: Randomly generate 100 sets of weight vectors (e.g., [0.3, 0.5, 0.2]);

[0309] Fitness assessment: The mean square error between the predicted value and the actual loss rate Y is used as the optimization objective.

[0310] ;

[0311] Genetic manipulation:

[0312] Selection: Retain the top 10% of elite individuals in terms of fitness;

[0313] Crossover: Perform an arithmetic crossover on the weight vector (child = parent mean);

[0314] Mutation: against Apply a Gaussian perturbation of ±0.05.

[0315] Triggering conditions:

[0316] Optimization is activated only when the water quality type changes (e.g., TDS mean change >20%) or when the filter cartridge is replaced.

[0317] Example: The initial weights of a coastal area are [0.4, 0.4, 0.2], and the optimized weights are [0.55, 0.3, 0.15] (α needs to be increased due to the risk of seawater intrusion).

[0318] Step 1032: Calculate the composite loss index based on the sudden risk item, the gradual loss item, the physical anomaly item, and the weight combination.

[0319] Step 1032: Calculation of Composite Indicators

[0320] Fusion formula:

[0321] ( (for optimized weights)

[0322] Normalization process:

[0323] Will Scale to the [0, 100] range;

[0324] Calculate the weighted sum The larger the value, the more severe the loss.

[0325] Calculation example:

[0326] enter: , ;

[0327] Weight: ;

[0328] Output: 0.5×3.2 + 0.3×45.6 + 0.2×12.3 = 1.6+13.68+2.46=17.74;

[0329] Regarding the technical advantages and robust design of this step:

[0330] 1. Balancing dynamic optimization and static execution

[0331] The optimization results are stored in the device's non-volatile memory, and the weights are read directly during daily operation (avoiding real-time calculation load).

[0332] When a parameter distribution offset is detected, a weight update is automatically triggered (e.g., KL divergence > 0.3).

[0333] 2. Scalable Design

[0334] Environmental compensation factors can be introduced:

[0335] ;

[0336] Alternative algorithm: If the genetic algorithm consumes too many resources, the gradient descent method can be used to fine-tune the weights online.

[0337] Here, we provide an example (industrial zone filter element weight optimization) of a reverse osmosis filter element scenario in a chemical plant:

[0338] 1. Background: High-chlorine wastewater leads to frequent sudden risks ( (The proportion increased)

[0339] 2. Weight optimization process:

[0340] Initial weights: [0.4, 0.4, 0.2] → Prediction error 22.3%;

[0341] After 50 generations of genetic algorithm iterations:

[0342] Elite individuals: [0.58, 0.28, 0.14];

[0343] Improved adaptability: Error reduced to 6.7%;

[0344] Additionally, it should be noted that:

[0345] 1. Connection with preceding and following steps

[0346] Input: Output of step 102 Normalization preprocessing is required;

[0347] Output: The hierarchical response of step 104 is directly driven (e.g.) >80 trigger resonance detection).

[0348] 2. Declaration of Terminology Consistency

[0349] "Weighted combination" specifically refers to Three system-level weight vectors;

[0350] "Genetic Algorithm Update" covers the entire process of initialization, fitness evaluation, selection, crossover, and mutation.

[0351] 3. Clarification of technical boundaries

[0352] Different intelligent algorithms can be used for weight optimization, but the core innovation lies in: "achieving the scientific integration of the three types of loss items through a dynamic weight allocation mechanism that adapts to water quality characteristics."

[0353] Step 104: Trigger the graded response mechanism based on the composite loss index.

[0354] Step 104 is the final execution stage of the filter element wear status evaluation method. Its technical essence lies in: based on the composite wear index ( The numerical range of ) triggers differentiated response strategies, enabling precise control from predictive maintenance to emergency shutdown.

[0355] 1. Technical necessity

[0356] Dynamic response adaptation: composite loss index Integrating three types of heterogeneous parameters—sudden risks, gradual losses, and physical anomalies (see step 103)—a hierarchical mechanism is needed to map the values ​​into specific actions to avoid the risks of "over-maintenance" or "under-response."

[0357] Resource optimization: minor damage is mainly predicted by software algorithms, moderate damage triggers hardware detection, and severe failure triggers physical intervention, thus achieving a match between resource investment and risk level.

[0358] System safety assurance: In the event of a severe failure, the equipment is forcibly shut down to prevent cascading failures (such as pipeline contamination caused by filter element rupture), in compliance with ISO 13849 Safety Integrity Level (SIL) requirements.

[0359] Optionally, step 104, triggering a graded response mechanism based on the composite loss index, includes:

[0360] Response Level 1: When the composite loss index indicates mild loss, generate a remaining life prediction and preventative maintenance plan;

[0361] Response Level 1: Mild Loss ( )

[0362] Technical role: Early warning of potential risks, prediction of remaining lifespan through algorithms and planning of preventive maintenance, reducing downtime losses caused by sudden failures.

[0363] Remaining life prediction methods:

[0364] A Weibull distribution model is constructed based on historical data, and the reliability function is calculated:

[0365] ( Characteristic lifetime, (shape parameters);

[0366] Combined with real-time loss rate Dynamically corrected predicted values:

[0367] ;

[0368] Preventive maintenance plan generation:

[0369] Time-driven: When When the time is right, maintenance work orders can be automatically scheduled (such as weekend downtime windows).

[0370] Event-driven: If a sudden change in water quality is detected (such as a daily increase in TDS > 10%), an additional chemical cleaning process will be added.

[0371] Example: Filter cartridges from a water purification plant ,predict The system automatically generates a work order for "replacing the filter element and disinfecting the pipeline after 45 days" and purchases spare parts.

[0372] Response Level 2: When the composite loss index indicates moderate damage, non-destructive testing methods are activated to identify micro-defects;

[0373] Response Level 2: Moderate injury (31≤ ≤70)

[0374] Technical function: to identify micro-defects (such as micro-cracks in filter media, local degumming) and prevent damage from evolving into structural failure.

[0375] Non-destructive testing method activation logic:

[0376] For flow fluctuation coefficients > 0.15, the preferred detection technology is ultrasonic phased array (PAUT), and the defect identification targets are filter material delamination and microcracks (> 0.1 mm).

[0377] When the TDS change acceleration is >10 ppm / min², the preferred detection technology is infrared thermal imaging (IRT), and the defect identification target is the temperature field anomaly caused by local leakage.

[0378] Microscopic defect quantification process:

[0379] Defect localization: PAUT scan generates C-scan images, marking areas with echo amplitude > 50% (suspected cracks).

[0380] Severity rating: Crack length L (measured) c The ratio of L to the filter element wall thickness W, if L c If / W>0.3, it is considered a high-risk defect.

[0381] Example: Petrochemical pump station filter element

[0382] =68, PAUT detection revealed 3 areas of stratification (maximum L). c (W=0.25), the system marked it as "moderate damage" and triggered a weekly ultrasound re-examination.

[0383] Response Level 3: When the composite loss index indicates severe failure, perform equipment shutdown and physical damage quantification analysis.

[0384] Response Level 3: Severe Failure ≥71)

[0385] Technical role: To prevent catastrophic consequences (such as system contamination caused by filter cartridge explosion) and to support insurance claims and root cause analysis through damage quantification.

[0386] Device shutdown safety logic:

[0387] Level 1 shutdown ( ≥71): Close the inlet valve and start the backup filter cartridge (if available).

[0388] Level 2 shutdown ( ≥85): Cut off the power supply to the upstream pump and trigger an audible and visual alarm.

[0389] Quantitative analysis of physical damage:

[0390] Damaged area calculation: The damaged area is reconstructed by high-speed photography or laser scanning, and the effective filtration area loss rate A is calculated as follows: A = (A0 – A d ) / A0.

[0391] Pollutant diffusion simulation: Based on computational fluid dynamics (CFD), the leakage path is simulated and a pollution range report is output (e.g., when the leakage amount is >10L, it affects 50m of downstream pipeline).

[0392] Example: Hydraulic oil filter element for power plants =92, after shutdown the scan showed A=40%, CFD simulation confirmed oil contamination of 3 valves, the report suggested "replace filter element + clean pipeline".

[0393] Regarding the technical advantages and robust design of this step:

[0394] 1. Response delay control

[0395] The time delay from the determination level to the execution action is ≤2 seconds (mild), ≤10 seconds (moderate), and ≤0.5 seconds (severe), and the timeliness is guaranteed by the real-time operating system (RTOS).

[0396] The severe failure response is linked to the Safety Instrumented System (SIS) to meet SIL-2 certification requirements.

[0397] 2. Misjudgment Prevention Mechanism

[0398] Data verification: Before a moderate / severe response is triggered, automatically verify 3 sets of historical data (such as...). (Three consecutive exceedances).

[0399] Manual intervention channel: Supports operators to reject erroneous instructions within 10 seconds (such as test peaks in maintenance mode).

[0400] 3. Scalable Design

[0401] New detection method: If the system integrates an X-ray detection module, it can be embedded into the moderate damage response process.

[0402] Alternative algorithms: In addition to the Weibull model, time series prediction algorithms based on LSTM neural networks can also be used to predict remaining lifetime.

[0403] Here are some examples illustrating (handling interlocking failures of filter cartridges in chemical plants):

[0404] 1. Background: The filter element of the hydrochloric acid filtration system is corroded. It jumped from 40 to 78.

[0405] 2. Graded response process:

[0406] Severe failure response: Shut down the acid inlet valve within 0.3 seconds and start the emergency neutralization tank to inject alkali solution.

[0407] Damage Quantitative Analysis: Laser scanning showed perforation at the bottom of the filter cartridge (A=35%), and CFD simulation confirmed a hydrochloric acid leakage of 2.3L.

[0408] Root cause tracing: PAUT re-examined historical data and found that L had existed for a week. c Crack with a / W=0.28 (originally a moderate response and not marked as high risk).

[0409] System optimization:

[0410] Update protocol: When crack L c When / W>0.25, the alert level will be automatically upgraded to a severe warning.

[0411] Additionally, it should be noted that:

[0412] 1. Integration with the overall approach

[0413] This step depends on the output of step 103. It is necessary to ensure that its normalization range [0, 100] is consistent with the classification threshold.

[0414] The non-destructive testing results (such as crack size) will be fed back to the physical anomaly calculation model in step 102 to achieve closed-loop optimization.

[0415] 2. Declaration of Terminology Consistency

[0416] "Microscopic defects" specifically refer to damage with a size of 0.1mm–1mm (such as microcracks or delamination), while damage larger than 1mm is defined as "physical breakage".

[0417] The "preventive maintenance plan" includes three types of actions: replacement, cleaning, and calibration, but does not include equipment modification.

[0418] 3. Clarification of technical boundaries

[0419] The core innovation of the tiered response lies in:

[0420] "Through the three-level mapping of composite loss indicators, a closed-loop control chain is formed by algorithm early warning, hardware detection and physical intervention."

[0421] The threshold setting (30 / 70) can be adjusted according to industry standards (e.g., it can be set to 20 / 50 in the nuclear power field), but it needs to be configured during initialization.

[0422] The specific detection tools (such as electromagnetic flowmeters and piezoelectric scanners), parameter settings (such as a flow sampling window of 30 seconds and a KL divergence threshold of 0.3) and formula expressions (such as sudden risk items) disclosed in the embodiments of this disclosure are merely exemplary implementation schemes. Their essence is to convey the feasibility of the technical principles. Those skilled in the art can make equivalent substitutions or adaptive adjustments to the tool types, parameter thresholds, and algebraic forms of formulas according to the actual application scenario requirements, without departing from the core innovative ideas of this disclosure. The embodiments only list representative parameter combinations and do not exhaust all configuration schemes.

[0423] Example 2

[0424] Corresponding to the aforementioned embodiments of the filter element wear status evaluation method, this disclosure also provides embodiments of the filter element wear status evaluation system.

[0425] Figure 3 A schematic diagram of a filter element wear status evaluation system provided for an exemplary embodiment of this disclosure, the system comprising:

[0426] This disclosure provides a filter element wear status evaluation system, the wear status evaluation system comprising:

[0427] The acquisition module 21 is used to acquire status data during the operation of the filter element. The status data includes fluid dynamics parameters, water quality chemical parameters and physical state parameters.

[0428] Evaluation module 22 is used to calculate sudden risk items, gradual loss items and physical anomaly items based on state data;

[0429] Evaluation module 22 is also used to superimpose sudden risk items, gradual loss items and physical anomaly items to generate a composite loss index;

[0430] The response module 23 is used to trigger a graded response mechanism based on the composite loss index.

[0431] Optionally, the fluid dynamics parameters include flow fluctuation characteristic parameters; the water quality chemical parameters include TDS change acceleration parameters; the evaluation module 22 is specifically used for:

[0432] Calculate the flow fluctuation coefficient based on flow fluctuation characteristic parameters;

[0433] Calculation of water quality deterioration acceleration based on TDS change acceleration parameters;

[0434] The flow fluctuation coefficient and the water quality deterioration acceleration are multiplied to generate a sudden risk term.

[0435] Optionally, water quality chemical parameters include TDS concentration and pH value; evaluation module 22 is specifically used for:

[0436] The first fusion term is formed based on the TDS concentration parameter and the corresponding first dynamic weighting coefficient;

[0437] A second fusion term is formed based on the pH value parameter and the corresponding second dynamic weighting coefficient;

[0438] The first fusion term and the second fusion term are linearly fused to generate an asymptotic loss term.

[0439] Optionally, the fluid dynamics parameters include real-time flow parameters; the physical state parameters include turbidity parameters; the evaluation module 22 is specifically used for:

[0440] Synchronize real-time flow and turbidity parameters;

[0441] Calculate the correlation characteristics between real-time flow rate and turbidity parameter. The correlation characteristics are used to characterize the consistency of the changing trends of real-time flow rate and turbidity parameter.

[0442] Physical outliers are generated based on associated features.

[0443] Optionally, the evaluation module 22 is specifically used for:

[0444] Obtain the weight combinations corresponding to sudden risk items, gradual loss items, and physical anomaly items; the weight combinations are updated based on a genetic algorithm.

[0445] The composite loss index is calculated based on sudden risk items, gradual loss items, physical anomaly items, and weight combinations.

[0446] Optionally, the response module 23 is specifically used for:

[0447] When the composite loss index indicates mild wear, a remaining life prediction and preventative maintenance plan are generated.

[0448] When the composite loss index indicates moderate damage, non-destructive testing methods are activated to identify micro-defects.

[0449] When the composite loss index indicates severe failure, the equipment is shut down and a physical damage quantification analysis is performed.

[0450] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs.

[0451] Example 3

[0452] Figure 4 This is a schematic diagram of the structure of a smart appliance according to an example embodiment of the present disclosure. The smart appliance includes a memory, a processor, and a computer program stored in the memory and used to run on the processor. When the processor executes the computer program, it implements the filter element wear status evaluation method described in any of the above embodiments. Figure 4 The smart appliance 90 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0453] like Figure 4 As shown, the intelligent appliance 90 can be represented in the form of a general-purpose computing device, such as a server device. The components of the intelligent appliance 90 may include, but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 connecting different system components (including memory 92 and processor 91).

[0454] Bus 93 includes a data bus, an address bus, and a control bus.

[0455] The memory 92 may include volatile memory, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923.

[0456] The memory 92 may also include a program tool 925 (or utility) having a set (at least one) program module 924, such program module 924 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0457] The processor 91 executes various functional applications and data processing by running computer programs stored in the memory 92, such as the filter element wear status evaluation method provided in any of the above embodiments.

[0458] The smart appliance 90 can also communicate with one or more external devices 94 (e.g., keyboards, pointing devices, etc.). This communication can be achieved through input / output (I / O) interface 95. Furthermore, the smart appliance 90 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 96. As shown in the figure, network adapter 96 communicates with other modules of the smart appliance 90 via bus 93. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the smart appliance 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0459] It should be noted that although several units / modules or sub-units / modules of smart appliances have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0460] The smart appliance can be controlled by a voice module, which is equipped with a controller, a voice receiving module, and a voice parsing module. The voice receiving module receives user commands, and the voice parsing module parses the commands. Based on the parsed commands, the controller controls the smart appliance to perform corresponding operations, thereby realizing intelligent control of the smart appliance and improving the user experience.

[0461] Example 4

[0462] This disclosure also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the filter element wear status evaluation method provided in any of the above embodiments.

[0463] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0464] Example 5

[0465] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the filter element wear status evaluation method described in any of the above embodiments.

[0466] The program code for executing the computer program product of this disclosure can be written in any combination of one or more programming languages, and the program code can be executed entirely on a user device, partially on a user device, as a stand-alone software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0467] While specific embodiments of this disclosure have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of this disclosure is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of this disclosure, but all such changes and modifications fall within the scope of protection of this disclosure.

Claims

1. A method for evaluating the wear status of a filter element, characterized in that, The loss status evaluation method includes: Collect status data during the operation of the filter element, including fluid dynamics parameters, water quality chemical parameters, and physical state parameters; Based on the aforementioned state data, the sudden risk item, the gradual loss item, and the physical anomaly item are calculated respectively. The sudden risk item, the gradual loss item, and the physical anomaly item are superimposed to generate a composite loss index; The graded response mechanism is triggered based on the composite loss index.

2. The loss condition evaluation method according to claim 1, characterized in that, The fluid dynamics parameters include flow rate fluctuation characteristic parameters; The water quality chemical parameters include the TDS change acceleration parameter; The calculation of the sudden risk item, the gradual loss item, and the physical anomaly item based on the state data includes: Calculate the flow fluctuation coefficient based on the aforementioned flow fluctuation characteristic parameters; Calculate the water quality deterioration acceleration based on the TDS change acceleration parameters; The sudden risk item is generated by multiplying the flow fluctuation coefficient with the water quality deterioration acceleration.

3. The loss condition evaluation method according to claim 1, characterized in that, The water quality chemical parameters include TDS concentration and pH value; the calculation of sudden risk items, gradual loss items, and physical anomaly items based on the state data includes: Based on the TDS concentration parameter and the corresponding first dynamic weighting coefficient, a first fusion term is formed; A second fusion term is formed based on the pH value parameter and the corresponding second dynamic weighting coefficient; The first fusion term and the second fusion term are linearly fused to generate an asymptotic loss term.

4. The loss condition evaluation method according to claim 1, characterized in that, The fluid dynamics parameters include real-time flow parameters; the physical state parameters include turbidity parameters; the calculation of sudden risk terms, asymptotic loss terms, and physical anomaly terms based on the state data includes: Synchronize the real-time flow rate with the turbidity parameter; Calculate the correlation characteristic between the real-time flow rate and the turbidity parameter, wherein the correlation characteristic is used to characterize the consistency of the changing trends of the real-time flow rate and the turbidity parameter; Physical anomaly values ​​are generated based on the associated feature values.

5. The loss condition evaluation method according to claim 1, characterized in that, The step of superimposing the sudden risk item, the gradual loss item, and the physical anomaly item to generate a composite loss index includes: Obtain the weight combination corresponding to the sudden risk item, the gradual loss item, and the physical anomaly item; the weight combination is updated based on a genetic algorithm; The composite loss index is calculated based on the sudden risk item, the gradual loss item, the physical anomaly item, and the weight combination.

6. The loss condition evaluation method according to claim 1, characterized in that, The step of triggering a graded response mechanism based on the composite loss index includes: In response to the composite loss index indicating mild loss, a remaining life prediction and preventative maintenance plan are generated. When the composite loss index indicates moderate damage, non-destructive testing is activated to identify micro-defects. In response to the composite loss index indicating severe failure, equipment shutdown and physical damage quantification analysis are performed.

7. A filter element wear status evaluation system, characterized in that, The loss status evaluation system includes: The data acquisition module is used to collect status data during the operation of the filter element. The status data includes fluid dynamics parameters, water quality chemical parameters, and physical state parameters. The evaluation module is used to calculate the sudden risk item, the gradual loss item, and the physical anomaly item based on the state data. The evaluation module is also used to superimpose the sudden risk item, the gradual loss item, and the physical anomaly item to generate a composite loss index. The response module is used to trigger a graded response mechanism based on the composite loss index.

8. A smart electrical appliance, comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, characterized in that, When the processor executes the computer program, it implements the method for evaluating the wear status of the filter element as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for evaluating the wear status of the filter element as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for evaluating the wear status of the filter element as described in any one of claims 1 to 6.

Images