CN112131740B - Method for predicting service life of filter element of water purifier - Google Patents

Method for predicting service life of filter element of water purifier Download PDF

Info

Publication number
CN112131740B
CN112131740B CN202011000975.6A CN202011000975A CN112131740B CN 112131740 B CN112131740 B CN 112131740B CN 202011000975 A CN202011000975 A CN 202011000975A CN 112131740 B CN112131740 B CN 112131740B
Authority
CN
China
Prior art keywords
filter element
service life
water
water purifier
days
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011000975.6A
Other languages
Chinese (zh)
Other versions
CN112131740A (en
Inventor
陈耿
杨智程
黄鹏
王熙
付贵
曹幼霖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan Qing Ting Technology Co ltd
Chengdu Qingting Technology Co ltd
Original Assignee
Hunan Qing Ting Technology Co ltd
Chengdu Qingting Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hunan Qing Ting Technology Co ltd, Chengdu Qingting Technology Co ltd filed Critical Hunan Qing Ting Technology Co ltd
Priority to CN202011000975.6A priority Critical patent/CN112131740B/en
Publication of CN112131740A publication Critical patent/CN112131740A/en
Application granted granted Critical
Publication of CN112131740B publication Critical patent/CN112131740B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F9/00—Multistage treatment of water, waste water or sewage
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2101/00—Nature of the contaminant
    • C02F2101/10—Inorganic compounds
    • C02F2101/12—Halogens or halogen-containing compounds
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/10—Solids, e.g. total solids [TS], total suspended solids [TSS] or volatile solids [VS]
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/40—Liquid flow rate
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/44—Time
    • C02F2209/445—Filter life
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computer Hardware Design (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Hydrology & Water Resources (AREA)
  • Environmental & Geological Engineering (AREA)
  • Water Supply & Treatment (AREA)
  • Chemical & Material Sciences (AREA)
  • Organic Chemistry (AREA)
  • Water Treatment By Sorption (AREA)

Abstract

The invention provides a method for predicting the service life of a filter element of a water purifier, which belongs to the technical field of water purifiers and comprises the following steps: judging whether the early-warning water purifier filter element is available; calculating to obtain the actual service life of the filter element of the water purifier; extracting the actual service life of the filter element of the water purifier and the characteristic value of the information about whether the filter element of the water purifier is available or not, and unifying the data dimension of the characteristic value; training a multiple linear regression model; optimizing the trained multiple linear regression model by using a gradient descent method; and predicting the service life of all current water purifier filter elements which do not reach the early warning threshold value. According to the invention, a big data and artificial intelligence mode is adopted, regression analysis is reversely carried out on the filter element use data in a result data driving mode, and the difference between the actual filter element use data and the analysis data is found out and calibrated, so that the purposes of individuation in use and accurate data are achieved, and the problem of potential safety hazard of drinking water caused by inaccurate monitoring of the service life of the filter element in the actual use process of the water purifying equipment is solved.

Description

Method for predicting service life of filter element of water purifier
Technical Field
The invention belongs to the technical field of water purifiers, and particularly relates to a method for predicting the service life of a filter element of a water purifier.
Background
In recent years, along with the development of industry, there are many reports on water pollution all over the country, and people pay more attention to the health and safety of drinking water, and the sales of water purifiers and other related water purifying equipment are increasing year by year. The fundamental reason is that the tap water pipe network is built in a long time, rust deposits in the water pipe and secondary water supply of a high-rise building are caused, and the water outlet at the tail end of drinking water is worried by uncontrollable factors of a plurality of links.
In the existing water purification equipment, the water purification equipment is distinguished according to functions, and the most common water purification equipment is an ultrafiltration water purifier and a reverse osmosis water purifier. Regardless of the type of water purifier, the filter element types generally include a PP cotton filter element, an activated carbon filter element, a reverse osmosis membrane filter element, a nanofiltration reverse osmosis membrane filter element, an ion exchange resin filter element, and the like. From the perspective of the filtration and adsorption mechanism of the filter element, the physical and chemical characteristics, namely, the technologies of pore size filtration, physical adsorption, charge repulsion, ion exchange and the like, are utilized to achieve the purposes of filtration, adsorption and separation, but the functions and the flow rate are not unchanged, and the functions or the flow rate can be reduced along with the prolonging of the service time and the increasing of the purified water amount, namely, the service life is consumed.
At present, in the industry, for defining the service life of a filter element, the common method is that manual judgment is carried out, only the initial state is evaluated, the difference of the consumption degree of the filter element caused by regional water quality difference is not considered, and meanwhile, the real use condition is not automatically analyzed and calibrated by utilizing big data and an artificial intelligence technology. The prior art has the defects that: in the current water purification industry and the actual use process of water purification equipment, the service life of a filter element is monitored or evaluated mainly through two modes, namely a countdown mode, namely, countdown is started from the installation of the filter element, and the expired service life is ended; and the second mode is a flow mode, namely, the water passing amount is calculated from the installation of the filter element, and the service life is ended when the water passing amount reaches a certain limit value. It can be seen from the two modes that no matter which mode is adopted, the water quality difference of all places is not taken into calculation, and the water quality of one area is not invariable, but adopts a simple and rough mode, so that the problem of accurate filter element service life evaluation in the actual use process cannot be fundamentally solved, and the filter element service life evaluation is determined by a manual mode, the efficiency is very low, and the scale cannot be realized.
Disclosure of Invention
Aiming at the defects in the prior art, the method for predicting the service life of the filter element of the water purifier provided by the invention solves the problems that the service life of the filter element is inaccurate in monitoring and the potential safety hazard of drinking water is caused in the actual use process of water purifying equipment, and the service life detection at present usually depends on a manual judgment mode and cannot realize large-scale data analysis.
In order to achieve the above purpose, the invention adopts the technical scheme that:
the scheme provides a method for predicting the service life of a filter element of a water purifier, which comprises the following steps:
s1, judging whether the pre-warning water purifier filter element is available;
s2, performing labeling treatment on the available filter element of the water purifier to obtain the actual service life of the filter element of the water purifier;
s3, extracting characteristic values of the actual service life of the filter element of the water purifier and the information about whether the filter element of the water purifier is available or not, and unifying the data dimensions of the characteristic values;
s4, training a multivariate linear regression model by using the characteristic values with unified dimensionality;
s5, optimizing the trained multiple linear regression model by using a gradient descent method;
and S6, predicting the service life of all current water purifier filter elements which do not reach the early warning threshold value by using the optimized multiple linear regression model, and completing the prediction of the service life of the water purifier filter elements.
Further, the feature values in step S3 include: the characteristic value extracted aiming at the PP cotton filter element, the characteristic value extracted aiming at the front active carbon filter element, the characteristic value extracted aiming at the rear active carbon filter element and the characteristic value extracted aiming at the RO membrane filter element.
Still further, the characteristic values extracted for the PP cotton filter element include: the number of days the PP cotton filter element is used and the actual measured service life, the current available state, the current residual service life of the filter element, the water quality turbidity and the total flow of water;
the characteristic values extracted aiming at the front activated carbon filter element comprise: the number of days of use of the preposed active carbon filter element, the actual measured service life, the current available state, the current residual service life of the filter element, the residual chlorine content and the total flow of water;
the characteristic values extracted aiming at the rear activated carbon filter element comprise: the number of days of used post-positioned active carbon filter elements and the actual measured service life, the current available state, the current residual service life of the filter elements and the total flow of water;
the characteristic values extracted for the RO membrane cartridge include: the number of days the RO membrane filter has been in service and the actual measured life, the current state of availability, the current remaining life of the filter, the TDS mean value of the source water and the total flow of water.
Still further, the expression of the number of days the PP cotton cartridge has been used and the actual measured life is as follows:
Lp＝Tb*Dq
wherein Lp represents the number of days that the PP cotton filter element has been used and the actual measurement life, Tb represents the water turbidity, and Dq represents the flow difference between the current flow accumulated value and the previous value;
the expression of the used days and the actual measured service life of the preposed active carbon filter element is as follows:
Lc＝C1*Dq
wherein Lc represents the number of days the front activated carbon filter element has been used and the actual measured service life, C1Representing the residual chlorine information of the water quality acquired by a residual chlorine sensor;
the expression of the number of days the RO membrane cartridge has been used and the actual measured life is as follows:
Lk＝C1*R*Dq*TDS
wherein Lk represents the number of days the RO membrane filter has been used and the actual measured life, R represents the ratio of the permeate water yield to the water inflow, and TDS represents the total solid dissolved amount of water quality acquired by the TDS sensor.
Still further, the expression of the optimized multiple linear regression model in step S5 is as follows:
ak+1＝ak+ρks-(k)
wherein, ak+1Represents a multiple linear regression model optimized in the gradient direction, akRepresenting the current value, p, of a multiple linear regression model calculationkDenotes the search step in the gradient direction, s-(k)Indicating the negative direction of the gradient.
Still further, the expression of the prediction function of the multiple linear regression model in step S6 is as follows:
y＝β0+β1x1+β2x2+...+βpxp+ε
where y represents the prediction function of the multiple linear regression model, ε represents the random error, βpDenotes partial and regression constants, xpRepresenting the input feature value.
The invention has the beneficial effects that:
(1) according to the invention, a big data and artificial intelligence mode is adopted, regression analysis is reversely carried out on the filter element use data in a result data driving mode, and the difference between the actual filter element use data and the analysis data is found out and calibrated, so that the purposes of individuation in use and accurate data are achieved, and the problem of potential safety hazard of drinking water caused by inaccurate monitoring of the service life of the filter element in the actual use process of the water purifying equipment is solved.
(2) The calibration of the filter element service life is based on the actual water consumption data of the user and the water source water quality data of the actual position, so that the filter element service life of the user is reduced by ' thousands of people ' and thousands of faces ', the purpose of personalized use is achieved, and a foundation is laid for subsequent service expansion and business models.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
Examples
The invention takes the data generated in the actual use process of the filter element life of the water purifier as the basis, leads the consumption data of the filter element life to become more accurate through big data and artificial intelligence, and fundamentally ensures the continuous drinking water safety of customers, as shown in figure 1, the invention discloses a method for predicting the filter element life of the water purifier, which comprises the following steps:
s1, judging whether the pre-warning water purifier filter element is available;
in this embodiment, make preliminary judgement to the recovery filter core life-span that uses the early warning threshold value, judge promptly whether the filter core is available and the life-span value of consumption.
S2, performing labeling treatment on the available filter element of the water purifier to obtain the actual service life of the filter element of the water purifier;
in this embodiment, the filter core that does not use the early warning threshold value will be tentatively judged and the survey is added the mark, survey filter core surplus practical life result.
S3, extracting characteristic values of the actual service life of the filter element of the water purifier and the information about whether the filter element of the water purifier is available or not, and unifying the data dimensions of the characteristic values;
in this embodiment, the characteristic values extracted for the PP cotton filter element include: the number of days the PP cotton filter element is used and the actual service life is measured, the current available state, the current residual service life of the filter element, the water turbidity and the total flow of water are measured; the characteristic values extracted for the preposed activated carbon filter element comprise: the number of days of use of the preposed active carbon filter element, the actual measured service life, the current available state, the current residual service life of the filter element, the residual chlorine content and the total flow of water; the characteristic values extracted by aiming at the rear active carbon filter element comprise: the number of days of used post-positioned active carbon filter elements and the actual measured service life, the current available state, the current residual service life of the filter elements and the total flow of water; the characteristic values extracted for the RO membrane cartridge include: the number of days the RO membrane filter has been in service and the actual measured life, the current state of availability, the current remaining life of the filter, the TDS mean value of the source water and the total flow of water.
In this embodiment, the expression of the number of days the PP cotton filter element has been used and the actual measured life is as follows:
Lp＝Tb*Dq
wherein Lp represents the number of days the PP cotton filter element has been used and the actual measured service life, Tb represents the turbidity of the water, and Dq represents the flow difference between the current flow accumulated value and the previous value;
the expression of the used days and the actual measured service life of the preposed active carbon filter element is as follows:
Lc＝C1*Dq
wherein Lc represents the number of days the front activated carbon filter element has been used and the actual measured service life, C1Representing the residual chlorine information of the water quality acquired by a residual chlorine sensor;
the expression of the number of days the RO membrane cartridge has been used and the actual measured life is as follows:
Lk＝C1*R*Dq*TDS
wherein Lk represents the number of days the RO membrane filter has been used and the actual measured life, R represents the ratio of the permeate water yield to the water inflow, and TDS represents the total solid dissolved amount of water quality acquired by the TDS sensor.
In this embodiment, since the labeling experiment is not necessarily performed on all the recovered filter elements, the actual measured life parameters cannot be obtained for the filter elements that have not undergone the labeling experiment. In this case, the "actual measured life" is equal to the "current remaining life of the filter element", and the "current availability status" is equal to 1(1 represents available, and 2 represents unavailable). No matter whether through the experiment of adding mark, other parameters including filter core days of having used, residual chlorine content, water turbidity, source water TDS mean value, water purification TDS mean value, with water total flow all need do the completion operation as training data after acquireing from the data warehouse.
In this embodiment, the feature scaling is performed by dividing all feature values by the maximum value of the feature to obtain a normalized mean value, so that the numerical value becomes a number between 0 and 1:
Rx＝(xp-μi)/Si
wherein Rx represents the mean value after normalization, μiRepresenting a characteristic value xpAverage value of (1), SiRepresenting a range of characteristic values.
S4, training a multiple linear regression model by using the characteristic values after the unified dimensionality:
in this embodiment, parameters are set based on the linear regression method of the linear model in skleran, the cut-off value is set to True, and the normalized value is set to false. Starting regression calculation by using a fit (training) method and adding training set data as input, performing predictive analysis by using a predict method and adding verification set data as input, performing model evaluation by using a score (evaluation) method, stopping training when the evaluation score of the model is greater than a preset score (0.8), and storing the training model. The process is repeated every day according to newly-recycled filter elements and filter element service life data triggering early warning, and model evaluation scores are continuously improved.
S5, optimizing the trained multiple linear regression model by using a gradient descent method:
ak+1＝ak+ρks-(k)
wherein, ak+1Represents a multiple linear regression model optimized in the gradient direction, akRepresenting the current value, p, of a multiple linear regression model calculationkDenotes the search step in the gradient direction, s-(k)Indicating the negative direction of the gradient.
And S6, predicting the service life of all current water purifier filter elements which do not reach the early warning threshold value by using the optimized multiple linear regression model, and completing the prediction of the service life of the water purifier filter elements.
The expression of the prediction function of the multiple linear regression model is as follows:
y＝β0+β1x1+β2x2+...+βpxp+ε
where y represents the prediction function of the multiple linear regression model, ε represents the random error, βpDenotes partial and regression constants, xpRepresenting the input feature value.
In the embodiment, the trained and optimized multivariate linear regression model is used for calibrating life data of other water purifier filter elements which do not reach the early warning threshold value, and the prediction result is more accurate.
Through the design, the purposes of individuation in use and accurate data are achieved, and the problem of potential safety hazards of drinking water caused by inaccurate monitoring of the service life of the filter element in the actual use process of the water purifying equipment is solved.

Claims (3)

1. A method for predicting the service life of a filter element of a water purifier is characterized by comprising the following steps:
s1, judging whether the pre-warning water purifier filter element is available;
s2, performing labeling treatment on the available filter element of the water purifier to obtain the actual service life of the filter element of the water purifier;
s3, extracting characteristic values of the actual service life of the filter element of the water purifier and the information about whether the filter element of the water purifier is available or not, and unifying the data dimensions of the characteristic values;
s4, training a multivariate linear regression model by using the characteristic values with unified dimensionality;
s5, optimizing the trained multiple linear regression model by using a gradient descent method;
s6, predicting the service life of all current water purifier filter elements which do not reach the early warning threshold value by using the optimized multiple linear regression model, and completing prediction of the service life of the water purifier filter elements;
the characteristic values in the step S3 include: the characteristic value extracted aiming at the PP cotton filter element, the characteristic value extracted aiming at the front activated carbon filter element, the characteristic value extracted aiming at the rear activated carbon filter element and the characteristic value extracted aiming at the RO membrane filter element;
the characteristic value extracted aiming at the PP cotton filter element comprises: the number of days the PP cotton filter element is used and the actual measured service life, the current available state, the current residual service life of the filter element, the water quality turbidity and the total flow of water;
the characteristic values extracted aiming at the front activated carbon filter element comprise: the number of days of use of the preposed active carbon filter element, the actual measured service life, the current available state, the current residual service life of the filter element, the residual chlorine content and the total flow of water;
the characteristic values extracted aiming at the rear activated carbon filter element comprise: the number of days of used post-positioned active carbon filter elements and the actual measured service life, the current available state, the current residual service life of the filter elements and the total flow of water;
the characteristic values extracted for the RO membrane cartridge include: the number of days the RO membrane filter element is used and the actual measured service life, the current available state, the current residual service life of the filter element, the TDS mean value of source water and the total flow of water;
the expression of the number of days the PP cotton filter element has been used and the actual measured life is as follows:
Lp＝Tb*Dq
wherein Lp represents the number of days the PP cotton filter element has been used and the actual measured service life, Tb represents the turbidity of the water, and Dq represents the flow difference between the current flow accumulated value and the previous value;
the expression of the used days and the actual measured service life of the preposed active carbon filter element is as follows:
Lc＝C1*Dq
wherein Lc represents the number of days the front activated carbon filter element has been used and the actual measured service life, C1Representing the residual chlorine information of the water quality acquired by a residual chlorine sensor;
the expression of the number of days the RO membrane cartridge has been used and the actual measured life is as follows:
Lk＝C1*R*Dq*TDS
wherein Lk represents the number of days the RO membrane cartridge has been used and the actual measured life, R represents the ratio of permeate water output to water input, and TDS represents the total solid dissolved amount of water acquired by the TDS sensor.
2. The method for predicting the lifetime of a filter element of a water purifier as recited in claim 1, wherein the expression of the optimized multiple linear regression model in the step S5 is as follows:
ak+1＝ak+ρks-(k)
wherein, ak+1Represents a multiple linear regression model optimized in the gradient direction, akRepresenting the current value, p, of a multiple linear regression model calculationkDenotes the search step in the gradient direction, s-(k)Indicating the negative direction of the gradient.
3. The method for predicting the lifetime of a filter element of a water purifier as recited in claim 1, wherein the expression of the prediction function of the multiple linear regression model in step S6 is as follows:
y＝β0+β1x1+β2x2+...+βpxp+ε
where y represents the prediction function of the multiple linear regression model, ε represents the random error, βpDenotes partial and regression constants, xpRepresenting the input feature value.
CN202011000975.6A 2020-09-22 2020-09-22 Method for predicting service life of filter element of water purifier Active CN112131740B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011000975.6A CN112131740B (en) 2020-09-22 2020-09-22 Method for predicting service life of filter element of water purifier

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011000975.6A CN112131740B (en) 2020-09-22 2020-09-22 Method for predicting service life of filter element of water purifier

Publications (2)

Publication Number Publication Date
CN112131740A CN112131740A (en) 2020-12-25
CN112131740B true CN112131740B (en) 2022-06-14

Family

ID=73841544

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011000975.6A Active CN112131740B (en) 2020-09-22 2020-09-22 Method for predicting service life of filter element of water purifier

Country Status (1)

Country Link
CN (1) CN112131740B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112890729B (en) * 2021-01-19 2022-05-13 北京红岸水滴科技发展有限公司 Scale detection method, water tank suitable for scale detection method and equipment comprising water tank
CN116813028A (en) * 2023-06-30 2023-09-29 深圳安吉尔饮水产业集团有限公司 Method for intelligently detecting service life of filter element of water purifier
CN116870573A (en) * 2023-06-30 2023-10-13 深圳安吉尔饮水产业集团有限公司 Water purifier with life-span detects function

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109117565A (en) * 2018-08-23 2019-01-01 海尔优家智能科技（北京）有限公司 The method, apparatus and cloud server managed to water purifier filter core
CN109342034A (en) * 2018-09-14 2019-02-15 天津大学 A kind of determination method in filtering element for air purifier service life
CN109850961A (en) * 2019-01-28 2019-06-07 杭州深渡科技有限公司 For judging the methods, devices and systems of filter element of water purifier remaining life

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10006393B2 (en) * 2016-01-22 2018-06-26 GM Global Technology Operations LLC Methods and systems for determining and reporting a remaining useful life of an air filter
CN108264106B (en) * 2016-12-30 2021-01-05 福州品行科技发展有限公司 Filter element early warning method and system of water purifier

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109117565A (en) * 2018-08-23 2019-01-01 海尔优家智能科技（北京）有限公司 The method, apparatus and cloud server managed to water purifier filter core
CN109342034A (en) * 2018-09-14 2019-02-15 天津大学 A kind of determination method in filtering element for air purifier service life
CN109850961A (en) * 2019-01-28 2019-06-07 杭州深渡科技有限公司 For judging the methods, devices and systems of filter element of water purifier remaining life

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
"Prediction of the potential fates of future pharmaceutical compounds in indirect potable reuse systems";Seung JooLim等;《Science of The Total Environment》;20121229;第444卷;第417-422页 *
"家用直饮水活性炭滤芯吸附性能及其对余氯去除效果研究";朱建华;《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》;20180615(第06期);C038-988 *
反渗透膜经济寿命分析;李颖等;《工业安全与环保》;20071110;第33卷(第11期);第30-31+9页，第2-4节 *
线性回归在水质过滤卫生检验预测中的应用;乔明山等;《中国卫生工程学》;19981115;第07卷(第04期);第183-185+封3页 *

Also Published As

Publication number Publication date
CN112131740A (en) 2020-12-25

Similar Documents

Publication Publication Date Title
CN112131740B (en) Method for predicting service life of filter element of water purifier
CN104083936B (en) Monitor the method for the state of filter element of purifier, monitoring device and purifier
Roehl Jr et al. Modeling fouling in a large RO system with artificial neural networks
US20120217170A1 (en) Apparatus and method for removal of ions
US20170217788A1 (en) Water supply management system
CN106840732B (en) A kind of performance evaluation methodology and device
JP2007330843A (en) Management system of water treatment facility
KR102530502B1 (en) Water purifier and method for controlling water purifier
CN102548909A (en) Water purifier
JP4010514B2 (en) Water quality management method and water quality management system for tap water
CN108931619A (en) A kind of waste water of heat-engine plant processing equipment life-span prediction method and device
WO2020152100A1 (en) Fouling type detection
KR20210137925A (en) Water purifier and method for controlling water purifier
JP2009178713A (en) Control system for water treatment facility
CN112417765A (en) Sewage treatment process fault detection method based on improved teacher-student network model
CN104843919A (en) Proton heavy ion accelerator high-purity water circulating consumable automatic analysis system
JP2006302049A (en) Water quality management system
CN204582719U (en) A kind of Novel water purifier filter element detection system
Ba-Alawi et al. Explainable multisensor fusion-based automatic reconciliation and imputation of faulty and missing data in membrane bioreactor plants for fouling alleviation and energy saving
WO2012050216A1 (en) Billing method for use of water purification system
Liu et al. Application of microfiltration–nanofiltration combined technology for drinking water advanced treatment in a large-scale engineering project
CN219031837U (en) Hydrogen-conductive resin regeneration system
CN106587411A (en) Effluent monitoring treatment method and system of water purifier
KR20040056596A (en) A water purifier having water analysis function and management method thereof
CN116402233A (en) Ultrafiltration membrane pollution prediction method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant