A method and system for judging the life of a water purifier filter element

Abstract

The present invention relates to the technical field of filter element life judgment, and discloses a method and system for judging the life of a water purifier filter element, including: obtaining the water quality and flow rate of the water inlet and outlet of the water purifier during the continuous operation of the water purifier; stratifying the filter element, cleaning the filter element according to the water quality and flow rate, and recording the cleaning time; after the cleaning is completed, continuously observing the water quality and flow rate of the water inlet and outlet of the water purifier, and when it is judged that the filter element needs to be cleaned, calculating the time interval with the last cleaning; analyzing each layer of the filter element according to the cleaning time and the time interval between two cleanings, and comprehensively evaluating the life of the water purifier filter element according to the analysis results. The filter element life judgment can be dynamically adjusted to avoid the problem of premature or delayed replacement, and improve the use efficiency of the water purifier and the water purification effect. It can better warn the need for cleaning or replacement of the filter element, reduce maintenance costs, and extend the service life of the equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of filter element life determination, and in particular to a method and system for determining the life of a water purifier filter element. Background Art

[0002] As water pollution becomes increasingly serious, water purifiers have become a commonly used water treatment device in homes and industries. As one of the core components of a water purifier, the filter element plays a key role in removing impurities and harmful substances from water. However, the service life of the filter element is affected by many factors, including water quality, flow rate, filter element material, and working environment. Traditional methods for determining the life of the filter element usually rely on regular replacement or simple time interval calculations, which cannot accurately reflect the actual use status of the filter element, resulting in premature or delayed replacement of the filter element, affecting the water purification effect and use cost. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is that the existing filter element life prediction method has optimization problems such as low accuracy and cost waste.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for determining the life of a water purifier filter element, comprising:

[0006] Through the sensor, the water quality and flow rate of the water inlet and outlet of the water purifier are obtained during the continuous operation of the water purifier;

[0007] The filter element is layered, and the filter element is cleaned according to the water quality and flow conditions, and the cleaning time is recorded;

[0008] After cleaning, continue to observe the water quality and flow rate at the water inlet and outlet of the water purifier. When it is determined that the filter element needs to be cleaned, calculate the time interval from the last cleaning;

[0009] According to the cleaning time and the time interval between two cleanings, each layer of the filter element is analyzed, and the life of the water purifier filter element is comprehensively evaluated based on the analysis results.

[0010] As a preferred solution of the method for determining the life of a water purifier filter element of the present invention, the water quality and flow rate conditions include arranging the same sensors at the water inlet and outlet of the water purifier, respectively, and obtaining the real-time flow rate through a flow meter;

[0011] Arrange sensors for detecting substances according to water purification needs to detect water quality and obtain real-time water quality data.

[0012] As a preferred solution of the method for determining the life of a water purifier filter element of the present invention, wherein: stratifying the filter element includes constructing a layered structure of the filter element according to the physical layers of the filter element material;

[0013] The filter element cleaning includes, if the flow rate of the water purifier is lower than the threshold value L, or the water quality purification ratio of the water inlet and outlet is lower than the threshold value B, or the water quality at the water outlet does not meet the detection index, it is judged that cleaning is required; otherwise, it is judged that cleaning is not required;

[0014] Wherein, L represents the minimum flow threshold of the water purifier, B represents the minimum value of the water purification ratio of the inlet and outlet; the water purification ratio of the inlet and outlet = the substance content detected by the outlet sensor / the substance content detected by the inlet sensor.

[0015] As a preferred solution of the method for judging the life of the filter element of the water purifier of the present invention, the cleaning time includes: pre-training a Bayesian algorithm, taking the flow rate of the water purifier, the water purification ratio of the inlet and outlet, and the water quality at the outlet as input, and analyzing the probability of abnormality of the filter element at each layer through the Bayesian algorithm;

[0016] The layers whose output abnormal probability exceeds the abnormal threshold are taken as cleaning factors;

[0017] The cleaning elements are matched by the preset optimal cleaning time of each layer; the matched optimal cleaning time is used as the recommended time consumption of each layer, and the maximum value of the recommended time consumption is output as the final cleaning time consumption;

[0018] After cleaning, it is put into use. When the time between two cleanings is less than the shortest time threshold, it is determined whether there is foreign matter blockage. If there is no foreign matter blockage, it is determined that the life has expired. If there is foreign matter blockage, a foreign matter cleaning warning is issued. When the time between two cleanings is not less than the shortest time threshold, the filter element life is evaluated.

[0019] As a preferred solution of the method for determining the life of a water purifier filter element of the present invention, the calculation of the time interval between the calculation and the last cleaning includes the time interval for the cleaning action of the entire filter element and the time interval for the cleaning action of each layer;

[0020] When it is determined that the filter element needs to be cleaned, the cleaning factors of the filter element are analyzed by using a Bayesian algorithm;

[0021] set up The filter element is judged as the i-th layer of the cleaning element during the current cleaning; When it is historical cleaning, the filter element is judged as the jth layer of the cleaning element, and t represents the time when the historical cleaning occurred;

[0022] The time interval for the cleaning action of the entire filter element includes, when i and j are not constrained, and The shortest time interval between occurrences is set to ;

[0023] The time interval for the cleaning action to occur on each layer includes constraints on i and j: Corresponding to the i-th layer, find The corresponding j-th layer in , so that i=j; get and The shortest time interval that occurs is obtained, and the time interval corresponding to each cleaning element during the current cleaning is obtained. Let the time interval between the i-th layer of this cleaning and the i-th layer of the most recent cleaning in history be .

[0024] As a preferred solution of the method for determining the life of a water purifier filter element of the present invention, wherein: analyzing each layer of the filter element includes, assuming that the layered structure of the filter element is M layers, and randomly selecting one layer m;

[0025] If the m-th layer does not have a determination of the cleaning element in the historical records and the current cleaning, the hierarchical structure is reselected until the m-th layer has a determination of the cleaning element in the historical records and the current cleaning; if the m-th layer has a determination of the cleaning element in the historical records and the current cleaning, the m-th layer is analyzed:

[0026] Use the retrained Bayesian algorithm, set as the second Bayesian algorithm, to judge the life span of the m layer; input: ;

[0027] in, represents the abnormal probability evaluated by the Bayesian algorithm. If the current cleaning determines that layer m is a cleaning element, then The Bayesian algorithm determines the abnormal probability of layer m based on the current cleaning; if the current cleaning does not determine layer m as a cleaning element, then in the historical records, is the abnormal probability determined by the Bayesian algorithm when the m layer was most recently determined to be a cleaning element; Indicates the m layer, for The anomaly probability of the previous Bayesian algorithm evaluation; express and The first cleaning of the filter element occurs between the two corresponding cleanings; express and Between the two corresponding cleanings, the filter element is cleaned for the second time; express and Between the two corresponding cleanings, the filter element is cleaned for the nth time; n represents and The number of cleanings between the two corresponding cleanings; express The corresponding filter element cleaning time;

[0028] According to the second Bayesian algorithm, the life span value corresponding to the maximum probability is output as the analysis result of the m layer.

[0029] As a preferred embodiment of the method for determining the life of a water purifier filter cartridge of the present invention, the comprehensive evaluation of the life of the water purifier filter cartridge based on the analysis results includes selecting the adjusted minimum life value in all layers as the overall life of the filter cartridge;

[0030]

[0031] Among them, H represents the life of the entire filter element; It represents the remaining life of layer m after adjustment;

[0032]

[0033] in, It represents the lifespan value output by the second Bayesian algorithm of layer m; U represents the number of layers wrapped by the filter element outside layer m, and the liquid reaches layer m after passing through layer U; u represents the index of the layer; suppose layer m is used to filter material V, Represents the attenuation ratio of the u-th layer to material V.

[0034] A water purifier filter element life determination system using any method as described in the present invention, characterized in that:

[0035] The acquisition module uses sensors to obtain the water quality and flow rate of the water inlet and outlet of the water purifier during the continuous operation of the water purifier;

[0036] A recording module is used to stratify the filter element, clean the filter element according to the water quality and flow rate, and record the cleaning time;

[0037] The cleaning module, after completing the cleaning, continuously monitors the water quality and flow rate at the water inlet and outlet of the water purifier. When it is determined that the filter element needs to be cleaned, the time interval from the last cleaning is calculated;

[0038] The analysis module analyzes each layer of the filter element according to the cleaning time and the time interval between two cleanings, and comprehensively evaluates the life of the water purifier filter element according to the analysis results.

[0039] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein: the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0040] A computer-readable storage medium stores a computer program, wherein: when the computer program is executed by a processor, the steps of any one of the methods of the present invention are implemented.

[0041] Beneficial effects of the present invention: The method for judging the life of a water purifier filter element provided by the present invention monitors the water quality and flow rate of the water inlet and outlet of the water purifier in real time, and analyzes the use status of each layer of the filter element in combination with the Bayesian algorithm, so as to accurately evaluate the remaining life of the filter element. The filter element life judgment can be adjusted dynamically to avoid the problem of premature or delayed replacement, and improve the use efficiency of the water purifier and the water purification effect. In addition, through hierarchical analysis and data-driven decision-making, the need for cleaning or replacement of the filter element can be better warned, which reduces maintenance costs and extends the service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0043] Figure 1 This is an overall flow chart of a method for determining the life of a water purifier filter element provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0045] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a method for determining the life of a water purifier filter element, comprising:

[0046] S1: The water quality and flow rate at the water inlet and outlet of the water purifier are obtained through sensors during the continuous operation of the water purifier.

[0047] Furthermore, the water quality and flow conditions include arranging the same sensors at the water inlet and outlet of the water purifier respectively, and obtaining the real-time flow through a flow meter; arranging sensors for detecting substances according to water purification needs, for detecting water quality, and obtaining real-time water quality data.

[0048] What needs to be said is that by real-time monitoring of the water quality and flow rate at the water inlet and outlet of the water purifier, the use status of the filter element can be dynamically evaluated and whether it needs to be cleaned or replaced can be determined. By arranging sensors to collect accurate water quality and flow rate data, intelligent prediction of the filter element life can be achieved, ensuring that the water purifier is always in the best working condition, thereby improving the water purification effect and extending the service life of the equipment.

[0049] Among them, sensors for detecting substances can be conductivity sensors, pH sensors, TDS sensors, turbidity sensors, heavy metal ion sensors (such as lead, mercury), chlorine content sensors, etc. They are used to detect indicators such as impurity concentration, pH, conductivity, etc. in water. Changes in water quality can reflect the filtering effect of the filter element and whether it needs to be cleaned or replaced. Through the cooperation of multiple sensors, changes in water quality can be comprehensively evaluated.

[0050] S2: The filter element is layered, and the filter element is cleaned according to the water quality and flow conditions, and the cleaning time is recorded.

[0051] The layering of the filter element includes constructing a layered structure of the filter element according to the physical layering of the filter element material. The filter element cleaning includes determining that cleaning is required if the flow rate of the water purifier is lower than a threshold value L, or the water quality purification ratio of the water inlet and outlet is lower than a threshold value B, or the water quality at the water outlet does not meet the detection index; otherwise, it is determined that cleaning is not required.

[0052] Wherein, L represents the minimum flow threshold of the water purifier, B represents the minimum value of the water purification ratio of the inlet and outlet; the water purification ratio of the inlet and outlet = the substance content detected by the outlet sensor / the substance content detected by the inlet sensor.

[0053] Filter layering can effectively optimize the management of filter layers of different materials and functions, and improve the performance and service life of the water purifier. By setting the cleaning threshold (flow threshold L and water purification ratio B), the system can determine whether the filter needs to be cleaned based on real-time data to ensure that the water purifier always maintains efficient water purification capabilities and avoids water quality degradation or equipment damage due to excessive contamination or blockage of the filter.

[0054] The cleaning time includes pre-training a Bayesian algorithm, taking the flow rate of the water purifier, the water quality purification ratio of the inlet and outlet, and the water quality at the outlet as input, and analyzing the probability of abnormality of each layer of the filter element through the Bayesian algorithm. The layer with an abnormal probability exceeding the abnormal threshold is output as a cleaning factor.

[0055] The cleaning elements are matched by the preset optimal cleaning time of each layer; the matched optimal cleaning time is used as the recommended time for each layer, and the maximum value of the recommended time is output as the final cleaning time.

[0056] After cleaning, it is put into use. When the time between two cleanings is less than the shortest time threshold, it is determined whether there is foreign matter blockage. If there is no foreign matter blockage, it is determined that the life has expired. If there is foreign matter blockage, a foreign matter cleaning warning is issued. When the time between two cleanings is not less than the shortest time threshold, the filter element life is evaluated.

[0057] It should be noted that the pre-training goal of the Bayesian algorithm is to predict the probability of abnormality in each layer of the filter element through the Bayesian algorithm, based on data such as flow rate, inlet and outlet water purification ratio, and outlet water quality as input, to analyze whether there is an abnormality in each layer of the filter element. The probability of abnormality can help us determine whether cleaning is needed. The training set contains historical data samples, including input features (flow rate, water quality, etc.) and labels (whether each layer of the filter element is abnormal). Use this data to train the Bayesian model. The validation set is used to evaluate the performance of the Bayesian classifier. We can use cross-validation to split the data set into a training set and a validation set, and evaluate the effectiveness of the model by calculating indicators such as accuracy, recall, and F1 score.

[0058] S3: After cleaning is completed, continue to observe the water quality and flow rate of the water inlet and outlet of the water purifier. When it is determined that the filter element needs to be cleaned, calculate the time interval from the last cleaning.

[0059] The calculation of the time interval between the last cleaning includes the time interval for the cleaning action of the entire filter element and the time interval for the cleaning action of each layer. When it is determined that the filter element needs to be cleaned, the cleaning elements of the filter element are analyzed by Bayesian algorithm.

[0060] set up The filter element is judged as the i-th layer of the cleaning element during the current cleaning; In the case of historical cleaning, the filter element is judged to be the jth layer of the cleaning element, and t represents the time when the historical cleaning occurred.

[0061] The time interval for the cleaning action of the entire filter element includes, when i and j are not constrained, and The shortest time interval between occurrences is set to ; Indicates the time interval between this cleaning and the most recent cleaning in history.

[0062] The time interval for the cleaning action to occur on each layer includes constraints on i and j: Corresponding to the i-th layer, find The corresponding j-th layer in , so that i=j; get and The shortest time interval that occurs is obtained, and the time interval corresponding to each cleaning element during the current cleaning is obtained. Let the time interval between the i-th layer of this cleaning and the i-th layer of the most recent cleaning in history be .

[0063] It should be said that the calculation of the cleaning time interval is to achieve more accurate prediction of filter element life and optimization of the cleaning cycle. By recording and analyzing the cleaning time interval, especially the time difference between historical cleaning and current cleaning, the system can determine the state change trend of the filter element, and then infer its life and whether it needs to be cleaned. This not only helps to avoid excessive cleaning of the filter element (causing waste of resources) or delayed cleaning (causing substandard water quality), but also provides key data support for subsequent life predictions. By calculating the overall cleaning interval, we can determine whether the filter element is already in the decline stage and whether it needs to be cleaned in advance. Therefore, analyzing the cleaning time interval of each layer of filter element helps to achieve hierarchical optimization and accurately predict the service life of each layer of filter element. The cleaning time interval of each layer is an important basis for the system to determine whether an abnormality has occurred in that layer. It helps the system to evaluate the independence of each layer of filter element to prevent a certain layer from failing prematurely and affecting the overall water purification effect.

[0064] S4: Analyze each layer of the filter element according to the cleaning time and the time interval between two cleanings, and comprehensively evaluate the life of the water purifier filter element according to the analysis results.

[0065] Analyzing each layer of the filter element includes assuming that the layered structure of the filter element is M layers and randomly selecting one layer m.

[0066] If the m-th layer does not have a determination of the cleaning element in the historical records and the current cleaning, the hierarchical structure is reselected until the m-th layer has a determination of the cleaning element in the historical records and the current cleaning; if the m-th layer has a determination of the cleaning element in the historical records and the current cleaning, the m-th layer is analyzed:

[0067] Use the retrained Bayesian algorithm, set as the second Bayesian algorithm, to judge the life span of the m layer; input: .

[0068] in, represents the abnormal probability evaluated by the Bayesian algorithm. If the current cleaning determines that layer m is a cleaning element, then The Bayesian algorithm determines the abnormal probability of layer m based on the current cleaning; if the current cleaning does not determine layer m as a cleaning element, then in the historical records, is the abnormal probability determined by the Bayesian algorithm when the m layer was most recently determined to be a cleaning element; Indicates the m layer, for The anomaly probability of the previous Bayesian algorithm evaluation; express and The first cleaning of the filter element occurs between the two corresponding cleanings; express and Between the two corresponding cleanings, the filter element is cleaned for the second time; express and Between the two corresponding cleanings, the filter element is cleaned for the nth time; n represents and The number of cleanings between the two corresponding cleanings; express The corresponding filter element cleaning time.

[0069] According to the second Bayesian algorithm, the life value corresponding to the maximum probability is output as the analysis result of the m layer. The above analysis process specifically includes: constructing the relationship between the usage degree and life of the m-layer single layer (through function fitting). Using the above second Bayesian algorithm, the output result is the usage degree of the m layer, and the usage degree data is substituted into the fitted function to obtain the life value of the m layer.

[0070] The training process of the second Bayesian algorithm is to train the sampled samples of the m layers (single layer) of the filter element under different usage conditions. In the training set and the validation set, the design of any set of training data or validation data includes taking any number of filter elements from the historical data, obtaining the relevant data of their entire life process, and taking any data set of a time node Tt. ; The above randomly selected data set is used as the input data of the training set, and the life cycle of the m-layer single-layer filter material is simulated, and the use of the filter element from the time of being put into use to the time Tt is simulated, and then the use is evaluated as the output data of the training set. Through training, the second Bayesian algorithm can predict the use degree of the single-layer filter material.

[0071] By analyzing each layer of the filter element independently, it is possible to make an accurate assessment of the usage level and life of each layer, avoiding making an overly rough estimate of the life of the entire filter element. Filter elements are usually composed of multiple layers of different materials, and the service life and performance of each layer may be different. By analyzing each layer independently, the usage evaluation criteria of each layer of the filter element can be adjusted according to the actual situation, so as to set different maintenance and replacement cycles for each layer. This avoids the simple unified treatment of the usage of different layers, thereby achieving accurate maintenance management. By correlating the usage level obtained by the Bayesian algorithm with the life through function fitting, the usage level data predicted by the Bayesian algorithm can be converted into an assessment of the actual life. This process ensures that the life prediction of each layer of the filter element is more reasonable and accurate by accurately fitting the performance degradation curve of each layer of the filter element (that is, the relationship between the usage level and the life).

[0072] The adjusted minimum life value among all layers is selected as the overall life of the filter element.

[0073]

[0074] Among them, H represents the life of the entire filter element; Indicates the remaining life of layer m after adjustment.

[0075]

[0076] in, It represents the lifespan value output by the second Bayesian algorithm of layer m; U represents the number of layers wrapped by the filter element outside layer m, and the liquid reaches layer m after passing through layer U; u represents the index of the layer; suppose layer m is used to filter material V, Represents the attenuation ratio of the u-th layer to material V.

[0077] Since filter elements usually have multiple layers, the filtering effect and attenuation of each layer have a significant impact on the overall water purification effect and filter element life, so a comprehensive evaluation is required based on the actual use of each layer. In the design of multi-layer filter elements, different layers have different functions and usage conditions. For example, a layer may have a shortened service life due to heavy pollution, while other layers may still continue to work. Therefore, adjusting the life of all layers and performing a comprehensive calculation will help to more accurately predict the overall life of the filter element.

[0078] The "adjusted minimum life value" of all layers is selected as the overall filter life for the following reasons: Even if some layers have a longer life, if other layers have been severely attenuated or clogged, the overall filter performance will be seriously affected. Therefore, the life of the weakest layer should be used as the standard to avoid ignoring the key layer that affects the overall effect. According to the use of each layer, the final overall life should take the shortest life value, so as to ensure that the overall performance of the filter element will not be reduced due to the premature failure of a certain layer.

[0079] The attenuation ratio of each layer (especially the filtration capacity for substance V) refers to the change ratio of the concentration of the substance contained in the liquid after passing through the layer. If the attenuation ratio of a layer is low, it means that the filtration effect of the layer is poor, so its life will be reduced, which will affect the overall life assessment. The purpose of designing the overall filter element life is to ensure that the life calculation of the filter element is more practical and accurate by comprehensively considering the use status and attenuation effects of each layer. By adjusting the remaining life of each layer and finally selecting the shortest life as the overall life of the filter element, it can effectively prevent the influence of individual layer failure on the overall filtration effect, while improving the accuracy of the filter element service life prediction and the reliability of the water purifier.

[0080] On the other hand, this embodiment also provides a water purifier filter life determination system, which includes:

[0081] The acquisition module uses sensors to obtain the water quality and flow rate of the water inlet and outlet of the water purifier during the continuous operation of the water purifier.

[0082] The recording module layers the filter element, cleans the filter element according to the water quality and flow rate, and records the cleaning time.

[0083] The cleaning module continuously observes the water quality and flow rate at the water inlet and outlet of the water purifier after cleaning is completed. When it is determined that the filter element needs to be cleaned, the time interval from the last cleaning is calculated.

[0084] The analysis module analyzes each layer of the filter element according to the cleaning time and the time interval between two cleanings, and comprehensively evaluates the life of the water purifier filter element according to the analysis results.

[0085] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0086] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0087] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0088] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0089] Example 2 is an embodiment of the present invention, which provides a method for determining the life of a water purifier filter element. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0090] Traditional methods usually predict filter life by real-time monitoring of water flow and water quality. It mainly determines whether the filter needs to be cleaned based on the decrease in flow and changes in water quality, but this method does not consider the dynamic changes in water quality, the status of each layer of the filter, and the impact of cleaning history. Therefore, the flow threshold is too simple, which often leads to large errors in predicting life.

[0091] The present invention designs the filter element in layers, combines multiple real-time data such as water quality and flow rate, and uses the Bayesian algorithm to analyze the abnormal probability of each layer of the filter element, thereby more accurately predicting the remaining life of the filter element. The life of each layer is dynamically evaluated, and the life of the entire filter element is derived from the life of each layer. This not only improves the accuracy of life prediction, but also reduces errors.

[0092] Comparative experiment settings:

[0093] Experimental object: The same type of water purifier was selected for the experiment. During the experiment, the traditional method and the method of the present invention were used to predict the life of the filter element, and compared with the actual service life.

[0094] Experimental conditions:

[0095] Water quality: Choose from 5 different water quality conditions (low hardness water, high hardness water, chlorinated water, heavy metal contaminated water, mixed contaminated water).

[0096] Flow conditions: Set low flow (2L / min), normal flow (5L / min), high flow (8L / min) and very high flow (10L / min).

[0097] Evaluation criteria:

[0098] Predicted life: The remaining life of the filter element is predicted using the traditional method and the method of the present invention.

[0099] Actual lifespan: The actual lifespan of the filter element (i.e. the moment when the filter element completely fails) is recorded through usage during the experiment.

[0100] The data records are shown in Table 1. The forecast results are in days, and the interference of decimals is removed to make a macro record of the forecast results.

[0101] Table 1 Data record table

[0102]

[0103] Through the analysis of experimental data and comparison with the data in the table, the traditional method generally has large errors, especially in the experiments of low flow (sample 1) and high flow (sample 5), the errors between the predicted life and the actual life are 8.33% and 11.11% respectively. This shows that the traditional method has a large prediction deviation and fails to accurately capture the actual use status of the filter element.

[0104] The method of the present invention can accurately predict the life of the filter element in all experiments with an error of 0%, and the predicted life is completely consistent with the actual life (such as sample 2, sample 4, sample 6, and sample 8). This shows that the method based on the Bayesian algorithm can fully consider the dynamic changes of water quality, flow rate, and filter element stratification, and more accurately reflect the actual use of the filter element.

[0105] The present invention predicts the life of the filter element by introducing the Bayesian algorithm and combining multiple parameters (such as water quality, flow rate, etc.), which can achieve more accurate life prediction. Experimental results show that the present invention can accurately predict the life of the filter element under different flow rates and water quality conditions. Whether it is low flow rate, high flow rate or extremely high flow rate conditions, the error is 0%, and the life prediction fully matches the actual life.

[0106] Traditional methods rely too much on flow rate and simple water quality monitoring and cannot accurately consider the complex changes in the filter element status, resulting in large errors in life prediction and low prediction accuracy.

[0107] From the perspective of overall error, the prediction error of the method of the present invention is 0%, while the error of the traditional method is generally between 6% and 14%. This shows that the present invention can not only accurately predict the life of the filter element, but also reduce the prediction error by about 6% to 14% compared with the traditional method.

[0108] By comparing the results of the experiments, we can draw the following conclusions:

[0109] The method of the present invention is based on the Bayesian algorithm and combines multiple data such as water quality and flow rate to predict the life span, which can achieve very high prediction accuracy. The experimental results show that the error between the predicted life span and the actual life span is 0%, which has obvious advantages.

[0110] The traditional method has large errors under different experimental conditions and fails to accurately capture the dynamic changes of filter element life, resulting in large deviations in the prediction results.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for determining the life of a water purifier filter element, characterized in that: include: Through the sensor, the water quality and flow rate of the water inlet and outlet of the water purifier are obtained during the continuous operation of the water purifier; The filter element is layered, and the filter element is cleaned according to the water quality and flow conditions, and the cleaning time is recorded; After cleaning, continue to observe the water quality and flow rate at the water inlet and outlet of the water purifier. When it is determined that the filter element needs to be cleaned, calculate the time interval from the last cleaning; Analyze each layer of the filter element according to the cleaning time and the time interval between two cleanings, and comprehensively evaluate the life of the water purifier filter element according to the analysis results; The layering of the filter element includes constructing a layered structure of the filter element according to the physical layers of the filter element material; The filter element cleaning includes, if the flow rate of the water purifier is lower than the threshold value L, or the water quality purification ratio of the water inlet and outlet is lower than the threshold value B, or the water quality at the water outlet does not meet the detection index, it is judged that cleaning is required; otherwise, it is judged that cleaning is not required; Wherein, L represents the minimum flow threshold of the water purifier, and B represents the minimum value of the water quality purification ratio of the water inlet and outlet; the water quality purification ratio of the water inlet and outlet = the substance content detected by the water outlet sensor / the substance content detected by the water inlet sensor; The cleaning time includes pre-training a Bayesian algorithm, taking the flow rate of the water purifier, the water purification ratio of the inlet and outlet, and the water quality at the outlet as input, and analyzing the probability of abnormality of the filter element at each layer through the Bayesian algorithm; The layers whose output abnormal probability exceeds the abnormal threshold are taken as cleaning factors; The cleaning elements are matched by the preset optimal cleaning time of each layer; the matched optimal cleaning time is used as the recommended time consumption of each layer, and the maximum value of the recommended time consumption is output as the final cleaning time consumption; After cleaning, it is put into use. When the time between two cleanings is less than the shortest time threshold, it is determined whether there is foreign matter blockage. If there is no foreign matter blockage, it is determined that the life has expired. If there is foreign matter blockage, a foreign matter cleaning warning is issued. When the time between two cleanings is not less than the shortest time threshold, the filter element life is evaluated.

2. The method for determining the life of a water purifier filter cartridge according to claim 1, wherein: The water quality and flow conditions include arranging the same sensors at the water inlet and outlet of the water purifier respectively, and obtaining the real-time flow through a flow meter; Arrange sensors for detecting substances according to water purification needs to detect water quality and obtain real-time water quality data.

3. The method for determining the life of a water purifier filter cartridge according to claim 2, wherein: The calculation of the time interval between the last cleaning and the last cleaning includes the time interval for the cleaning action of the entire filter element and the time interval for the cleaning action of each layer; When it is determined that the filter element needs to be cleaned, the cleaning factors of the filter element are analyzed by using a Bayesian algorithm; set up The filter element is judged as the i-th layer of the cleaning element during the current cleaning; When it is historical cleaning, the filter element is judged as the jth layer of the cleaning element, and t represents the time when the historical cleaning occurred; The time interval for the cleaning action of the entire filter element includes, when i and j are not constrained, and The shortest time interval between occurrences is set to ; The time interval for the cleaning action to occur on each layer includes constraints on i and j: Corresponding to the i-th layer, find The corresponding j-th layer in , so that i=j; get and The shortest time interval that occurs is obtained, and the time interval corresponding to each cleaning element during the current cleaning is obtained. Let the time interval between the i-th layer of this cleaning and the i-th layer of the most recent cleaning in history be .

4. The method for determining the life of a water purifier filter cartridge according to claim 3, wherein: Analyzing each layer of the filter element includes: assuming that the filter element layered structure is M layers, and randomly selecting a layer m; If the m-th layer does not have a determination of a cleaning element in the historical records and the current cleaning, the hierarchical structure is reselected until the m-th layer has a determination of a cleaning element in the historical records and the current cleaning; If the m layer exists in the historical records and the current cleaning, and the cleaning elements are determined, the m layer is analyzed: Use the retrained Bayesian algorithm, set as the second Bayesian algorithm, to judge the life span of the m layer; input: ; in, represents the abnormal probability evaluated by the Bayesian algorithm. If the current cleaning determines that layer m is a cleaning element, then The Bayesian algorithm determines the abnormal probability of layer m based on the current cleaning; if the current cleaning does not determine layer m as a cleaning element, then in the historical records, is the abnormal probability determined by the Bayesian algorithm when the m layer was most recently determined to be a cleaning element; Indicates the m layer, for The anomaly probability of the previous Bayesian algorithm evaluation; express and The first cleaning of the filter element occurs between the two corresponding cleanings; express and Between the two corresponding cleanings, the filter element is cleaned for the second time; express and Between the two corresponding cleanings, the filter element is cleaned for the nth time; n represents and The number of cleanings between the corresponding two cleanings; express The corresponding filter element cleaning time; According to the second Bayesian algorithm, the life span value corresponding to the maximum probability is output as the analysis result of the m layer.

5. The method for determining the life of a water purifier filter cartridge according to claim 4, characterized in that: The comprehensive evaluation of the life of the water purifier filter element according to the analysis results includes selecting the adjusted minimum life value in all layers as the overall life of the filter element; Among them, H represents the life of the entire filter element; It represents the remaining life of layer m after adjustment; in, It represents the lifespan value output by the second Bayesian algorithm of layer m; U represents the number of layers wrapped by the filter element outside layer m, and the liquid reaches layer m after passing through layer U; u represents the index of the layer; suppose layer m is used to filter material V, Represents the attenuation ratio of the u-th layer to material V.

6. A water purifier filter life determination system using the method according to any one of claims 1 to 5, characterized in that: The acquisition module uses sensors to obtain the water quality and flow rate of the water inlet and outlet of the water purifier during the continuous operation of the water purifier; A recording module is used to stratify the filter element, clean the filter element according to the water quality and flow rate, and record the cleaning time; The cleaning module, after completing the cleaning, continuously monitors the water quality and flow rate at the water inlet and outlet of the water purifier. When it is determined that the filter element needs to be cleaned, the time interval from the last cleaning is calculated; The analysis module analyzes each layer of the filter element according to the cleaning time and the time interval between two cleanings, and comprehensively evaluates the life of the water purifier filter element according to the analysis results.

7. A computer device comprising: Memory and processor; The memory stores a computer program, wherein the processor implements the steps of any one of the methods of claims 1-5 when executing the computer program.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images