A system for determining the filter status

Abstract

An exemplary system for determining the state of a filter is provided. The system includes a database configured to electronically store data containing historical performance data of one or more water filtration elements. The system includes a processing unit in communication with the database. The processing unit is configured to receive historical performance data as input and to identify one or more data points in the historical performance data that indicate cleaning events of the water filtration elements. The processing unit is configured to divide the historical performance data into individual data intervals, each representing data in the historical performance data between each identified cleaning event, to fit a mathematical function to each individual data interval, and to identify the type of fouling occurring between each individual data interval based on the mathematical function fitted to each individual data interval.

Description

[Technical Field]

[0001] Cross-references in related fields This application claims priority to Spanish Utility Model Application No. 62 / 202330840, filed on 21 May 2023, which is incorporated herein by reference in its entirety.

[0002] The present invention relates to a method and system for the automatic monitoring of filter membranes in water treatment facilities, and for detecting and identifying the type of fouling in the membranes in water treatment facilities. The method and system can be used to efficiently determine when cleaning of the filter membrane is necessary and to provide precise guidance for the filter membrane based on the identified type of fouling. [Background technology]

[0003] Water treatment systems are available in various configurations, including systems that perform pressure-driven membrane separation processes for water filtration. Such pressure-driven membrane separation processes allow for the removal of a wide range of neutral and ionic species from the fluid. To reduce pore size, membranes are generally classified into several categories: microfiltration (MF), ultrafiltration (UF), nanofiltration (NF), and reverse osmosis (RO). Microfiltration is used to remove suspended particles with a particle size greater than 0.1 microns. Ultrafiltration generally removes dissolved molecules with a molecular weight greater than 5,000 daltons. Nanofiltration membranes allow at least some salts to pass through, but typically retain organic compounds with a molecular weight greater than about 200 daltons with high retention rates. Reverse osmosis membranes retain almost all species with high retention rates.

[0004] NF and RO membranes are most commonly used for applications such as desalination of seawater or brackish water, production of ultrapure water, color removal, wastewater treatment, and concentration of food liquids. A key factor in almost all NF and RO applications is the membrane's ability to achieve high rejection rates for small solute molecules while maintaining high flow rates.

[0005] A helical-wound element is the most common configuration for RO and NF membranes. A conventional helical-wound element design is shown in Figure 1. The element generally includes a membrane envelope 2 and a supply spacer sheet 4 wound around a central permeate collection tube 6. The envelope 2 includes two membrane sheets 8 surrounding a permeate carrier sheet 10, and its structure is integrally held together along its edges 14, 16, and 18 by adhesive 12. The fourth edge 20 of the envelope 2 abuts against the permeate collection tube 6 so that the permeate carrier sheet 10 is in fluid contact with the opening 22 of the permeate collection tube 6. Each envelope 2 is separated by a supply spacer sheet 4 also wound around the collection tube 6. The supply spacer 4 is in fluid contact with both ends of the elements 24, 26 and functions as a conduit for supplying the solution across the front surface 28 of the membrane 8. The direction of the supply flow 30 is from the inlet end 24 to the concentric end 26, and this direction is parallel to the axis 32 of the central permeate collection tube 6. In this way, the "supply" liquid flows axially through the supply spacer sheet 4 and flows out as "concentrated liquid" from the opposite end. The "permeate" passes through the membrane envelope 2 under pressure and is guided to the permeate collection tube 6 by the permeate carrier sheet 10. [Overview of the Initiative] [Problems that the invention aims to solve]

[0006] Over time, the performance level of the filtration element may deteriorate due to the accumulation of foreign matter (e.g., fouling) and / or salt deposits (e.g., scaling) on ​​the supply spacer or membrane. Such deterioration in performance level may affect the quality of the filtered water and / or increase the pressure on the water filtration system during operation, potentially leading to increased maintenance effort over time.

[0007] Manufacturers of filtration elements and / or water treatment systems generally set specific guidelines for cleaning filtration elements. Typically, this involves monitoring the overall operation of the water treatment system and shutting down the system to clean the filter when specific operating characteristics are detected (e.g., pressure drops at both ends of the element exceed recommended thresholds). For proper cleaning, it is recommended to shut down the system, clean the affected filtration elements, and send some of the affected elements to the laboratory for detailed analysis of the type of fouling and / or scaling. However, typically, water treatment plant operators continue to run the filtration system beyond the recommended guidelines to avoid a prolonged shutdown of the entire system. This can result in further problems, such as pump overheating and reduced product quality, leading to a forced system shutdown.

[0008] At this point, instead of sending the filter element to the laboratory, the operator may attempt to clean the system using a chemical that they deem appropriate, based on their experience, inferring the type of fouling / scaling occurring. In such cases, the type of chemical used may be inappropriate and ineffective in addressing the actual fouling / scaling. As a result, the cleaned filter element may have a performance baseline lower than what it should have had if properly cleaned. After repeated cleaning attempts, the filter element and / or water treatment equipment may face further malfunctions, resulting in increased operating costs and insufficient water filtration. [Means for solving the problem]

[0009] To improve system performance, a plant operator can use an exemplary system to determine the filter status. This system can analyze past performance and identify past cleaning-in-place (CIP) events and the types of filter module failure modes based on the performance of the system between and within CIPs. This system can be used in nanofiltration and / or reverse osmosis systems that identify fouling, scaling, and / or membrane breakage modes. In some embodiments, this system can be used to predict the time when the next cleaning should be performed / scheduled and recommend an optimal cleaning procedure.

[0010] Membrane fouling is a complex problem in nanofiltration and reverse osmosis systems. Therefore, the identification of the dominant fouling mechanism during the filtration process can be extremely important for predicting the next cleaning cycle and controlling fouling. Real-time (or substantially real-time) monitoring of water treatment facilities to detect and identify the type of fouling allows facility operators to detect and respond early, preventing excessive fouling and potential adverse effects on other parts of the system. This system provides an accurate means to determine the type of fouling occurring, thereby providing an accurate recommendation for the cleaning cycle to ensure that appropriate measures are taken to address the fouling event. In some embodiments, this system can be used to predict periodic and / or seasonal fouling so that fouling events can be minimized and / or avoided.

[0011] According to multiple embodiments of the present disclosure, an exemplary method for analyzing the performance of a water supply filtration system is provided. The method includes collecting performance data from the filtration system, normalizing the data set to the state at the startup time, excluding physically inconsistent data points from the data set, excluding statistical outliers from the data set, identifying membrane cleaning events in the data set, dividing the data set into a plurality of data intervals between the membrane cleaning events, fitting a mathematical function to the data intervals, analyzing the coefficient of determination of the mathematical function, calculating the derivative with respect to time of the mathematical function, and determining the type of fouling based on the derivative and the coefficient of determination.

[0012] The filtration system includes at least one filtration module. The filtration module includes one or more of a reverse osmosis element, a nanofiltration element, or an ultrafiltration element. The collection of performance data can be performed by sensors installed in the filtration system. The normalization of the data set can be performed to account for variations in the feed water temperature, the feed water composition, or the feed water pressure. The exclusion of outliers in the data set can be performed by statistical means including calculating the rate of increase or decrease of a data point (y t-1 ) from a previous data point (y t ), calculating the rate of increase or decrease of the next data point (y t ) from the data point (y t+1 ), comparing the previous rate of increase or decrease with a lower limit value, and identifying the data point (y t ) as an outlier if the rate of increase or decrease exceeds the lower limit value.

[0013] The exclusion of physically inconsistent data points within the aforementioned dataset may be carried out by applying a set of criteria including one or more of the following: the supply flow must be greater than the concentrate flow, the supply flow must be greater than the permeate flow, the supply pressure must be greater than the concentrate pressure, the supply pressure must be greater than the permeate pressure, the supply pressure must be greater than the pressure drop at both ends of the filtration module, the permeate conductivity must be less than the supply conductivity, the pressure drop at both ends of the filtration module must be less than or equal to the difference between the supply pressure and the concentrate pressure, and / or the osmotic pressure of the supply flow must be less than the supply pressure.

[0014] The dataset may include normalized pressure drop (dP) at both ends of the filtration module, normalized permeate flow (Pf) from the filtration module, and normalized salt permeate ratio (Sp) through the filtration module. Membrane washing events can be identified using a difference sequence method of dP and Pf, where the difference sequence method is used for the data points (y t ) and the previous data point (y t-1 The steps include: calculating the difference between dP and Pf to calculate the mean and standard deviation of the difference sequence for dP and Pf; comparing each value of the difference sequence for dP or Pf with the sum of the product of the corresponding value in the difference sequence and the difference constant and the corresponding standard deviation of the difference sequence; and checking whether there are gaps in the dataset and confirming whether the gaps are wider than the CIP reference time. The difference constant is a positive integer, preferably a number that includes both ends from 1 to 10, more preferably a number that includes both ends from 3 to 7, and even more preferably 5. The CIP reference time is a period defined by the user as representing the typical duration of the CIP of the system of interest, and can range from a few minutes to a few days. Exemplary values ​​for the CIP reference time may be, for example, 120 minutes, 1 day, etc. A preferred CIP reference time is 5 minutes to 2 weeks, with 1 day being a more preferred CIP reference time.

[0015] When determining the type of fouling occurring within a filter element, the system analyzes data from the filter element to determine whether various parameters are met. As described herein, depending on the type of fouling involved, some parameters are considered "primary" parameters and some are considered "secondary" (e.g., optional) parameters. For each type of fouling, there may be one or more primary parameters and one or more secondary parameters. In some examples, the data may satisfy criteria such as, for example, one primary parameter, two or more primary parameters, or one or more secondary parameters. The system can therefore first evaluate the data to determine whether one or more primary parameters are met. If so, the system can estimate the type of fouling based on the primary parameters that are met. In some embodiments, the system can estimate the type of fouling based on only one primary parameter that is met. In some embodiments, the system can depend on additional primary and / or secondary parameters that are met to confirm, reinforce, or support the original estimate of the type of fouling occurring based on the original primary parameter that is met. The system can therefore first determine whether the linear parameters for estimating the type of fouling are met. If none of the linear parameters are met, the system can evaluate the quadratic parameters and estimate the type of fouling based on the met quadratic parameters. In some embodiments, if there is overlap among the possible types of fouling based on the met linear and / or quadratic parameters, the system can perform a ranking operation to determine the likelihood of the occurring type of fouling, for example, based on historical data. While some parameters are described as being based on linear or quadratic polynomial functions, in some embodiments, the parameters may be identified based on, for example, exponential functions, higher-order polynomial functions, linear functions, nonlinear functions, etc.

[0016] The fitting of the set of curves to the aforementioned data intervals can be performed using statistical means. In some embodiments, a mode of filtration module failure in a data interval can be identified as scaling if at least one of the following conditions is met: (a) the coefficient of determination of the linear polynomial dP is greater than 0.7, (b) the coefficient of determination of the quadratic polynomial dP is greater than 0.7, (c) the difference between the coefficients of determination of the quadratic and linear polynomials fitted to dP is less than 0.3, (d) the coefficient of determination of the linear polynomial Sp is greater than 0.7, (e) the coefficient of determination of the quadratic polynomial Sp is greater than 0.7, and (f) the difference between the coefficients of determination of the quadratic and linear polynomials fitted to Sp is less than 0.3. (g) the coefficient of determination of the linear polynomial Pf is greater than 0.7, (h) the coefficient of determination of the quadratic polynomial Pf is greater than 0.7, (i) the difference between the coefficients of determination of the quadratic and linear polynomials fitted to Pf is less than 0.3, (j) dP increases with time in the data interval, (k) Pf decreases with time in the data interval, and / or (l) Sp increases with time in the data interval.

[0017] In some embodiments, a mode of filtration module failure in a data interval can be identified as particulate fouling if at least one of the following conditions is met: (a) the coefficient of determination of the linear polynomial dP is greater than 0.7, (b) the coefficient of determination of the quadratic polynomial dP is greater than 0.7, (c) the difference between the coefficients of determination of the quadratic and linear polynomials fitted to dP is less than 0.3, (d) the coefficient of determination of the linear polynomial Pf is greater than 0.7, (e) the coefficient of determination of the quadratic polynomial Pf is greater than 0.7, and (f) the difference between the coefficients of determination of the quadratic and linear polynomials fitted to Pf is less than 0.3. (g) the coefficient of determination of Sp for a linear polynomial is greater than 0.7, (h) the coefficient of determination of Sp for a quadratic polynomial is greater than 0.7, (i) the difference between the coefficients of determination of the quadratic polynomial and the linear polynomial fitted to Sp is less than 0.3, (j) dP increases with time in the data interval, (k) Pf decreases with time in the data interval, and / or (l) Sp increases with time in the data interval.

[0018] In some embodiments, a mode of filtration module failure in a data interval may be identified as biofouling if at least one of the following conditions is met: (a) the coefficient of determination of the linear polynomial dP is greater than 0.4, (b) the coefficient of determination of the quadratic polynomial dP is greater than 0.7, (c) the difference between the coefficients of determination of the quadratic and linear polynomials is greater than 0.3, (d) the coefficient of determination of the linear polynomial Pf is greater than 0.4, (e) the coefficient of determination of the quadratic polynomial Pf is greater than 0.7, and (f) the difference between the coefficients of determination of the quadratic and linear polynomials fitted to Pf is greater than 0.3. (g) the coefficient of determination of Sp for a linear polynomial is greater than 0.4, (h) the coefficient of determination of Sp for a quadratic polynomial is greater than 0.7, (i) the difference between the coefficients of determination of the quadratic polynomial fitted to Sp and the linear polynomial is greater than 0.3, (j) dP increases with time in the data interval, (k) Pf decreases with time in the data interval, and / or (l) Sp increases with time in the data interval.

[0019] In some embodiments, a mode of filtration module failure in a data interval can be identified as a membrane integrity failure (e.g., due to oxidation or membrane damage) if at least one of the following conditions is met: (a) the coefficient of determination of the linear polynomial Pf is greater than 0.7; (b) the coefficient of determination of the quadratic polynomial Pf is greater than 0.7; (c) the difference between the coefficients of determination of the quadratic polynomial fitted to Pf and the linear polynomial is less than 0.3; (d) the coefficient of determination of the linear polynomial Sp is greater than 0.7; (e) the coefficient of determination of the quadratic polynomial Sp is greater than 0.7; (f) the difference between the coefficients of determination of the quadratic polynomial fitted to Sp and the linear polynomial is less than 0.3. (g) The coefficient of determination of dP for a linear polynomial is greater than 0.7, (h) The coefficient of determination of dP for a quadratic polynomial is greater than 0.7, (i) The difference between the coefficients of determination of the quadratic polynomial and the linear polynomial fitted to dP is less than 0.3, (j) dP remains constant over time in the data interval, (k) Pf increases over time in the data interval, and / or (l) Sp increases over time in the data interval.

[0020] In some embodiments, a mode of filtration module failure in a data interval can be identified as organic fouling if at least one of the following conditions is met: (a) the coefficient of determination of the linear polynomial Pf is greater than 0.7, (b) the coefficient of determination of the quadratic polynomial Pf is greater than 0.7, (c) the difference between the coefficients of determination of the quadratic polynomial fitted to Pf and the linear polynomial is greater than 0.3, (d) the coefficient of determination of the linear polynomial Sp is greater than 0.4, (e) the coefficient of determination of the quadratic polynomial Sp is greater than 0.7, and (f) the difference between the coefficients of determination of the quadratic polynomial fitted to Sp and the linear polynomial is 0. (g) the coefficient of determination of the linear polynomial dP is greater than 3, (h) the coefficient of determination of the quadratic polynomial dP is greater than 0.7, (i) the difference between the coefficients of determination of the quadratic polynomial and the linear polynomial fitted to dP is less than 0.3, (j) dP remains constant over time in the data interval, (k) Pf decreases over time in the data interval, and / or (l) Sp decreases over time.

[0021] In some embodiments, the reduction limit may be greater than 0 and less than 10%. In some embodiments, the difference constant may be greater than 0 and less than 10. In some embodiments, the CIP reference time may be longer than 0 days and less than 10 days. An exemplary method may include a step of comparing performance parameters before and after cleaning to ensure appropriate CIP and / or fouling identification. Thus, exemplary systems and methods can be used to identify filtration module failure modes and provide guidance for optimal cleaning to ensure efficient operation of the water filtration system.

[0022] Multiple embodiments of this disclosure provide an exemplary system for determining the state of a filter. The system includes a database configured to electronically store data containing historical performance data of one or more water filtration elements. The system includes a processing unit in communication with the database. The processing unit receives historical performance data as input and is configured to identify one or more data points in the historical performance data that indicate a cleaning event of a water filtration element. The processing unit is configured to divide the historical performance data into individual data intervals, each of which represents data in the historical performance data between each identified cleaning event. The processing unit is configured to fit a mathematical function to each of the individual data intervals. Based on the mathematical function fitted to each individual data interval, the processing unit is configured to identify the type of fouling occurring in each of the individual data intervals.

[0023] In some embodiments, the processing device may be configured to normalize historical performance data to the state of one or more water filtration elements at the time of activation before identifying a cleaning event. In some embodiments, the processing device may capture fluctuations in at least one of the following: feedwater temperature, feedwater composition, or feedwater pressure, when normalizing historical performance data.

[0024] In some embodiments, the processing device may be configured to identify and exclude physically inconsistent data points from past performance data before identifying a cleaning event. In some embodiments, if at least one of the following conditions, namely the feed flow is greater than the concentrate flow, the feed flow is greater than the permeate flow, the feed pressure is greater than the concentrate pressure, and / or the feed pressure is greater than the permeate pressure, is false, physically inconsistent data points are excluded from the past performance data. In some embodiments, if at least one of the following conditions, namely the feed flow is greater than the concentrate flow, the feed flow is greater than the permeate flow, the feed pressure is greater than the concentrate pressure, the feed pressure is greater than the permeate pressure, the feed pressure is greater than the pressure drop across one or more water filtration elements, the permeate conductivity is less than the feed conductivity, the pressure drop across one or more water filtration elements is less than or equal to the difference between the feed pressure and the concentrate pressure, and / or the osmotic pressure of the feed flow is lower than the feed pressure, is false, physically inconsistent data points are excluded from the past performance data.

[0025] In some embodiments, the processing device may be configured to identify and exclude statistically outlier data points from past performance data before identifying a cleaning event. In such embodiments, the step of identifying and excluding statistically outlier data points from past performance data includes calculating the rate of increase or decrease t of the data point (y t-1 ) from the previous data point (y t ), calculating the rate of increase or decrease of the data point (y t ) from the next data point (y t+1 ), comparing the previous rate of increase or decrease with a lower limit value, and identifying the data point (y t ) as an outlier if the rate of increase or decrease exceeds the lower limit.

[0026] In some embodiments, the step of identifying a cleaning event may include applying a difference sequence method to the normalized pressure drop (dP) and the normalized permeate flow (Pf) from past performance data. The step of applying the difference sequence method includes (i) the data point (y t ) and the previous data point (y t-1The method includes (ii) calculating the difference between (1) and (2) to generate a difference sequence of normalized pressure drop (dP) and normalized permeate flow (Pf); (ii) calculating the mean and standard deviation of the difference sequence of normalized pressure drop (dP) and normalized permeate flow (Pf); (iii) comparing each value in the difference sequence of normalized pressure drop (dP) and normalized permeate flow (Pf) with the corresponding value in the difference sequence and the sum of the product of the difference constant and the corresponding standard deviation of the difference sequence; (iv) determining whether a gap exists in the dataset; and (v) determining whether the gap is wider than the CIP reference time.

[0027] In some embodiments, the processing device may be configured to analyze the coefficient of determination of a mathematical function and to calculate the time derivative of the mathematical function. In such embodiments, the processing device may be configured to identify the type of fouling based on the derivative of the coefficient of determination. In some embodiments, one or more water filtration elements may be at least one of reverse osmosis elements, nanofiltration elements, or superfiltration elements. The system may include one or more sensors configured to detect and transmit data on the pressure drop, salt permeation ratio, and permeation flow associated with each of the one or more water filtration elements to be stored in a database as historical performance data.

[0028] In some embodiments, historical performance data may include pressure drop, salt permeability ratio, and permeate flow for each of one or more water filtration elements. If no changes are detected in pressure drop, salt permeability ratio, and permeate flow, the treatment system can identify a state of no fouling. If the increase in pressure drop fits a quadratic polynomial function, the treatment system can identify the type of fouling as biofouling. In some examples of biofouling, the salt permeability ratio may increase and the permeate flow may decrease. If the decrease in salt permeability ratio fits a quadratic polynomial function, the treatment system can identify the type of fouling as organic fouling. In some examples of organic fouling, the pressure drop may remain unchanged and the salt permeability ratio may decrease. If a rapid increase in pressure drop at the first position element (e.g., the tip filtration element in Figure 19) fits a linear polynomial function, the treatment system can identify the type of fouling as particulate fouling. In some examples of particulate fouling, the salt permeability ratio may increase and the permeate flow may decrease. In some examples, such phenomena are mainly observed at the tip element. If the gradual increase in the pressure drop at the rear end position element (e.g., the rear end filter element shown in Figure 19) fits a linear polynomial function, the processing unit can identify the type of fouling as scaling. In some examples of scaling, the salt permeation ratio may increase and the permeation flow may decrease. In some examples, such phenomena are mainly observed in the tail element. If the increase in permeation flow fits a linear polynomial function and the increase in the salt permeation ratio also fits a linear polynomial function, the processing unit can identify the type of fouling as a complete membrane damage event. In some examples of oxidation or membrane damage events, the pressure drop may not change.

[0029] In some embodiments, the processing device may be configured to receive current performance data of one or more water filter elements as input from one or more sensors (for example, multiple sensors may be installed on the same filter element to provide a more comprehensive fouling diagnosis, and / or sensors may be installed on multiple filter elements in the facility), analyze the current performance data based on a prior analysis of historical performance data and identification of the type of fouling occurring in each individual data interval, estimate the current type of fouling occurring in the water filter element, and / or output a recommendation for a cleaning procedure specific to the current type of fouling occurring in the water filter element. The data collected from the sensors may be a dedicated filter element to help estimate the type of fouling occurring by identifying whether a particular condition is occurring at the front or rear end of the pressure vessel. In some embodiments, the current performance data and / or historical performance data can be used to predict potential future fouling (for example, based on recurring fouling cycles at a particular time and / or based on environmental conditions).

[0030] Multiple embodiments of this disclosure provide exemplary methods for determining filter status. The method includes receiving historical performance data of one or more water filtration elements as input to a system for determining filter status. The system for determining filter status includes a database configured to electronically store historical performance data and a processing unit in communication with the database. The method includes identifying one or more data points in the historical performance data that indicate a cleaning event for one or more water filtration elements. The method includes dividing the historical performance data into individual data intervals, each of which represents data from the historical performance data between each identified cleaning event. The method includes fitting a mathematical function to each of the individual data intervals. The method includes identifying the type of fouling occurring in each of the individual data intervals based on the mathematical function fitted to each individual data interval.

[0031] According to several embodiments of this disclosure, an exemplary non-temporary computer-readable medium is provided for storing instructions that can be executed by a processing unit to determine the filter state. By executing the instructions, the processing unit receives historical performance data of one or more water filtration elements as input to a system for determining the filter state. The system for determining the filter state includes a database configured to electronically store the historical performance data and a processing unit in communication with the database. By executing the instructions, the processing unit identifies one or more data points in the historical performance data that represent cleaning events for one or more water filtration elements. This can be used to divide the historical performance data into individual data intervals, each representing data in the historical performance data between each identified cleaning event. By executing the instructions, the processing unit fits a mathematical function to each of the individual data intervals. By executing the instructions, the processing unit identifies the type of fouling occurring in each of the individual data intervals based on the mathematical function fitted to each individual data interval.

[0032] Any combination and / or rearrangement of multiple embodiments is envisioned. Other purposes and features will become apparent when the following detailed description is considered in conjunction with the accompanying drawings. However, it should be understood that the drawings are designed for illustrative purposes only and do not define the limitations of this disclosure.

[0033] Refer to the attached drawings to assist those skilled in the art in constructing and operating a system for determining the filter status. [Brief explanation of the drawing]

[0034] [Figure 1] This is a schematic diagram of a conventional spirally wound filtration element. [Figure 2] This is a schematic diagram of a portion of the supply spacer sheet for a filter element, showing strand thinning and some geometric relationships. [Figure 3] This is a schematic diagram illustrating the separation process occurring with spirally wound reverse osmosis or nanofiltration elements. [Figure 4] This is a block diagram of an exemplary system for determining the filter state according to this disclosure. [Figure 5] This is a block diagram of an exemplary computing device that implements an exemplary system for determining the filter state as described in this disclosure. [Figure 6] This is a block diagram of an exemplary system for determining the filter state environment according to this disclosure. [Figures 7A-7B] Figure 7A shows a graph of outlier identification performed by an exemplary system for determining the filter state, with outliers included and outliers excluded. [Figures 8A-8C] These graphs show the changes over time in the ideal (Figure 8A), expected (Figure 8B), and observed (Figure 8C) pressure drop (dP) profiles of a working reverse osmosis or nanofiltration element. [Figure 9] This graph shows the CIP events in the dataset. [Figure 10] This graph shows the unrecovered dP versus the startup dP for the dataset. [Figure 11] This graph shows the cleanability versus initial cleanability of the dataset. [Figure 12] This chart shows the types and main causes of fouling based on normalized pressure drop, normalized permeate flow, and normalized salt permeation ratio. [Figures 13A-13F] The graphs show the dataset analysis regarding pressure drop, permeate flow, and salt permeation ratio, with specific results indicating particular types of fouling, including no fouling (Figure 13A), biofouling (Figure 13B), organic fouling (Figure 13C), particulate fouling (Figure 13D), scaling (Figure 13E), and oxidation or complete damage (Figure 13F). [Figure 14] This graph shows biofoulings identified based on the dataset. [Figure 15] This graph shows organic fouling identified based on the dataset. [Figure 16]This graph shows identified organic fouling and biofouling superimposed on the organic fouling. [Figure 17] This graph shows identified organic fouling and biofouling superimposed on the organic fouling. [Figure 18] This graph shows identified organic fouling, particulate fouling, biofouling, and CIP events. [Figure 19] This is a schematic diagram of the filtration elements arranged in series with the water flow passing through the filtration elements from the front to the back. [Modes for carrying out the invention]

[0035] The exemplary filter condition determination system discussed herein provides accurate monitoring, analysis, and identification of the type of fouling / scaling occurring within the filtration elements of a water treatment facility. This system can be used to determine the type of fouling / scaling present and recommend to the operator when the system should be cleaned to ensure optimal operation. By determining the type of fouling / scaling, the system can recommend the type of cleaning to be performed and the chemicals to be used, thereby providing precise guidance for effective cleaning that ensures improved operation of the water treatment facility after cleaning.

[0036] Figure 2 is a schematic diagram of a portion of the supply spacer sheet 4 of the filtration element, showing strand thinning and some geometric relationships. The supply spacer sheet 4 is a nonwoven polymer net formed by intersecting a first set 34 of substantially parallel filaments with a second set 36 of substantially parallel filaments at angles 38, 40. The two sets of filaments 34, 36 are bonded to each other at the intersection 42. The two intersecting sets 34, 36 of substantially parallel filaments form a two-dimensional array of similar parallelograms 44 (shown by dotted lines in Figure 2), the lengths of which define the mesh dimensions 46, 48. The parallelograms have both acute angles 38 and obtuse angles 40, except when the two sets of filaments 34, 36 are perpendicular to each other. The acute angle 38 is bisected by a line 50 drawn substantially parallel to the flow direction 30. The angles at which the filaments 34, 36 intersect the flow direction 30 are referred to as their intersection angles 52, 54. The strands are spaced 46 and 48 apart, and each strand has a filament width of 62 and 64.

[0037] Figure 3 is a schematic diagram of the separation occurring in a spirally wound reverse osmosis or nanofiltration element 70. The concentrated feed solution 72 passes between two or more membranes 74, allowing the concentrate (containing wastewater or by-products 78) to be guided in one direction, and the diluted solution 76 (e.g., permeate or product) to pass through the membranes 74 and escape from the filtration system. The semipermeable membranes 74 thus allow water and small amounts of dissolved salts to pass through. The operational goals of the water filtration system include maximizing the permeate flow (Pf), minimizing the salt permeation ratio (Sp), and minimizing the pressure drop (dP). Feed pressure, feed temperature, and feed water quality (dissolved solids concentration) may affect the operation of the system.

[0038] Using an exemplary system, it is possible to identify the type of filtration module failure mode in nanofiltration and / or reverse osmosis systems (e.g., fouling, scaling, membrane failure, or a combination thereof). This system helps operators improve water treatment system performance through a more detailed analysis of past performance. In some embodiments, this system can be used to predict when the next cleaning should be performed and recommend the optimal cleaning procedure.

[0039] A key advantage of this system is that it does not require additional external equipment for identifying the type of fouling. Instead, the system relies on the system's past performance and clean-in-place (CIP) events to determine the type of fouling that has occurred / is occurring and the optimal cleaning method to address it. The system is usable with any type of water and does not require any special water treatment applications. Using this system, cleaning intervals (e.g., intervals between CIP events) can be identified, and these periods can be analyzed to evaluate the type of fouling and recommend cleaning. Based on this data, the system can help predict when the next cleaning should be performed and the most accurate type of cleaning. The system is therefore capable of operating in a substantially automated and independent manner, thus enabling the operation of similar types of water treatment equipment. As discussed herein, the system can utilize primary and secondary gradients of pressure drop, permeate flow (net driving pressure), and water quality (conductivity) changes, where these data changes are normalized by temperature.

[0040] Therefore, using the exemplary system, the type of fouling occurring within the filtration system and / or elements can be identified without the need to add further sensors or devices to the filtration system, simplifying overall use and reducing the operating cost of the system. The system first collects performance data associated with the filtration system, including, for example, differential pressure, permeate flow, and salt permeation ratio. The system normalizes the data to the activation conditions so that normalized pressure drop, normalized permeate flow, and normalized salt permeation ratio are available and electronically stored in the system. Data normalization can be performed according to industry procedures (see, for example, FilmTec® Reverse Osmosis membranes Technical Manual, Water Solutions, DuPont, Table 27. Design equations for projecting RO system performance: Individual element performance, Form No. 45-D01504-en, Rev. 13, p. 110 (October 2022)). Temperature can be detected and recorded to normalize the data. The system automatically excludes inconsistent data, such as feed flow less than concentrated flow, and excludes statistical outliers.

[0041] Once the data has been normalized and inconsistencies have been removed, this system can identify membrane cleaning events (CIPs). CIP identification generates a difference sequence of dP and flow (the difference between data points at time t and t-1), identifies the mean and standard deviation of the difference sequence, and determines the difference value of dP or flow rate. * This can be done by identifying data points that are below or above a standard deviation threshold and checking whether a gap larger than a given threshold (e.g., 1 day) exists in the data. The term "difference sequence" as used herein refers to the generation of a sequence, generally the difference Δx between consecutive occurrences in a time series. t =x t -x t-1 It can be described as taking Δx tThe time series has a constant mean and variance and can therefore be treated as a stationary time series. (See, for example, Pal, A. et al., Practical Time Series Analysis: Master Time Series Data Processing, Visualization, and Modeling Using Python, United Kingdom: Packt Publishing (2017)). This approach can also recognize plant shutdowns and restarts. In some examples, the system can be used to distinguish between CIP and plant shutdown-restart. In some embodiments, the system can utilize the absence of changes in dP, flow, and / or salt permeation ratio before and after to indicate a plant shutdown without a CIP effect. In some embodiments, the system's detection of changes in temperature, pH, and / or flow rate can be associated with the CIP mode compared to plant shutdown / restart.

[0042] This system can split data between CIPs and analyze each dataset independently between washes. Once a wash cycle has begun and the type of fouling has been identified, the system can predict when the next wash should be performed using equations programmed and fitted to the system. After the next wash is identified, the optimal type of wash is suggested. Conventional caustic washes are recommended for biofouling, organic fouling, and particulate fouling. Acid washes are recommended for scaling. In particular, for biofouling, the acceleration of biofouling can be estimated using the second derivative of the gradient obtained in the previous and current periods (for example, by analyzing how early the next CIP will be needed). By calculating this, the timing of the next wash due to biofouling can be predicted more accurately, as the wash interval will be shorter if biofouling is present. If the system detects and identifies a combination of fouling types, a comprehensive wash consisting of caustic wash followed by acid wash is recommended. This system is capable of operating autonomously and can provide guidance to the user regarding corrective actions that the system should take, and can advise on any identified fouling issues so that the user can determine whether or not the system should autonomously take those corrective actions.

[0043] This system therefore performs data collection and analysis of the historical performance of the water treatment system, performs data normalization, removes outliers from the data, checks the integrity of the data, identifies CIPs, performs regression analysis of first and second-order polynomials to obtain their coefficients of determination, applies programmed logic to identify types of fouling / faults, uses the previous information to predict the type of fouling in the next instance, and constructs an adaptive system that includes fouling considerations. This system may include artificial intelligence and / or machine learning functions to improve the identification of fouling types and / or the predictability of fouling events. The input to the artificial intelligence and machine learning functions may be, preferably, operator feedback.

[0044] Figure 4 is a block diagram of an exemplary system 100 (hereinafter, "system 100") for determining the filter state. System 100 generally includes one or more water treatment equipment 102, each containing one or more filtration elements 104. The filtration elements 104 may be arranged back-to-back in series within a pressure vessel, for example, the filtration elements 400-410 in Figure 19, so that water flows into the inlet of filtration element 400 at the front, sequentially through each of the filtration elements 400-410, and out through filtration element 410 at the rear. Generally, particulate matter, biofouling, and / or poor integrity typically occur within the filtration elements at or near the front, scaling and / or poor integrity occur within the filtration elements at or near the rear, and organic fouling may occur in any of the filtration elements. In some embodiments, the pressure vessel can accommodate 6-8 filtration elements in series. The feedwater can be injected into the pressure vessel from the tip, with the tip filter element initially exposed to the feedwater (e.g., the filter element at the first position). The filter element furthest from the pressure vessel inlet defines the rear-end filter element. The data obtained regarding the filter elements within the pressure vessel may be element-specific, allowing for identification and differentiation of data from the tip and rear of the pressure vessel to accurately estimate the type of fouling.

[0045] System 100 includes sensors 106 installed within the water treatment facility 102 to detect conditions associated with the filtration process that System 100 can use to identify the type of fouling. In some embodiments, the sensors 106 can be used to detect, for example, the pressure drop at both ends of each filter element 104, the permeate flow (net drive pressure) through each filter element 104, the water quality (conductivity) in each filter element 104, and the temperature of the water passing through the filter element 104. In some embodiments, the collected data may provide a more detailed diagnosis of System 100 for each filter element 104 (e.g., each filter element 104 has at least one sensor 106 associated with it). As an example, smart sensors 106 can be incorporated into System 100 to determine whether the increase in dP is more dominant in the leading element (indicating particulate fouling) or the trailing element (indicating scaling). In some embodiments, the collected data may be for the entire filtration system (e.g., one or more sensors 106 are installed at specific locations in System 100). Sensor 106 is in electronic communication with the central computing system 122 and / or processing unit 124 of system 100, making the collected data available for determining the type of fouling and the proposed cleaning.

[0046] System 100 includes one or more databases 108 that electronically store data associated with the operation of the equipment 102 and System 100. Data can be transmitted electronically to and / or from database 108 via the communication interface 110 of System 100. Database 108 may include historical performance data 112 (e.g., historical data) including, for example, information on measured or detected states received from sensor 106, cleaning schedules and activities, equipment shutdown events, filter element replacements, changes in water supply sources, etc. Database 108 may also include current performance data 114 including, for example, measured or detected states received from sensor 106 in real time or substantially real time.

[0047] System 100 may include one or more users and / or user devices 116 that are in communication with System 100 via a communication interface 110. Users and / or user devices 116 may be, for example, operators of equipment 102, individuals responsible for scheduling cleaning events, etc. Users 116 can electronically send and receive data to and from the system via a user interface 118, which may have a graphical user interface (GUI) 120 in some embodiments. The GUI 120 may be a display incorporated into the user device 116 to enable users 116 to communicate with each other and / or with System 100 via the communication interface 110.

[0048] System 100 may include a central computing system 122 that is in communication with each of the users 116 (for example, via user devices) and one or more databases 108 associated with System 100 via a communication interface 110. The communication interface 110 is configured to provide a communication network between components of System 100 so that components of System 100 can electronically transmit and / or receive data. System 100 may include at least one processing unit 124 having a processor 126 that receives and processes data stored in System 100.

[0049] During operation, system 100 first receives historical performance data 112 as input to the normalization module 128, which is then run by system 100 and outputs normalized data 130 based on temperature. Next, the system runs the processing module 132 to detect and remove outliers from the normalized data 130 and outputs purified data 134 for further processing. The cleanup (CIP) module 136 is run by system 100 and analyzes the purified data 134 to identify and mark cleanup events 138. This generates a difference sequence of dP and permeate flow (difference between data points at time t and t-1), identifies the mean and standard deviation of the difference sequence, and determines the difference value of dP or flow rate K* This can be achieved by finding data points that are below or above a standard deviation threshold and checking whether there is a gap larger than a given threshold (e.g., 1 day). If a gap larger than the given threshold exists in the data, system 100 can identify this point in time as a CIP event 138.

[0050] System 100 splits the data between each identified CIP event 138 and analyzes each dataset independently between washes. In particular, it should be understood that the baseline associated with the operation of the equipment 102 and / or filter element 104 may change as the filter element 104 is used for a longer period of time. For example, a new filter element 104 will have a different performance baseline compared to a filter element that has been in operation for 6 months and has been washed multiple times. Thus, System 100 splits the data and analyzes the database independently between each wash to ensure accurate identification and prediction of the type of fouling.

[0051] System 100 runs the fouling identification module 140 for each data set associated with the operation between each CIP event 138 to determine the type of fouling that occurred during the operation of each data set. System 100 fits each data interval to a mathematical function, preferably a first- and second-order polynomial. System 100 analyzes the first and second-order gradients of the normalized pressure drop, normalized permeate flow, and normalized salt permeate ratio. If all gradients are close to zero, System 100 determines whether the equipment 102 should continue normal operation (for example, no action has been taken, or System 100 issues a notification via the graphical user interface 120 indicating that no type of fouling has been detected and cleaning is unnecessary). For example, by evaluating past performance data 112, System 100 can determine that no fouling was detected in the equipment 102, and that it could continue normal operation without cleaning. Evaluating the current performance data 114, it can be determined that system 100 is not experiencing any fouling and does not require cleaning, therefore equipment 102 should be functioning normally.

[0052] If the increase in pressure drop over time fits well to a quadratic polynomial, system 100 can conclude that biofouling is likely occurring. Biofouling alone (without other types of adhesion interference) is typically characterized by an initial flat normalized pressure drop (dP), followed by a quadratic polynomial-order increase in the pressure drop as biofouling begins to deposit on the membrane. Biofouling is typically more pronounced in the leading elements. Typically, the normalized permeate flow decreases over time as the net driving pressure decreases during the increase in dP (likely a quadratic polynomial). Desalination may remain stable or deteriorate (and thus increase the salt permeation ratio) as a result of concentration polarization induced by the biofilm. For example, if evaluating historical performance data 112, system 100 can determine that biofouling occurred in this dataset and that corresponding washing should have been performed. If evaluating current performance data 114, system 100 can determine that biofouling has occurred and appropriate washing is required.

[0053] In some embodiments, a mode of filtration module failure in a given data interval can be identified as a biofouling by system 100 if at least one of the following conditions is met: (a) The coefficient of determination of dP for a linear polynomial is greater than 0.4, (b) The coefficient of determination of dP for a quadratic polynomial is greater than 0.7, (c) The difference between the coefficients of determination of the quadratic and linear polynomials is greater than 0.3, (d) The coefficient of determination of Pf for a linear polynomial is greater than 0.4, (e) The coefficient of determination of Pf for a quadratic polynomial is greater than 0.7, (f) The difference between the coefficients of determination of the quadratic and linear polynomials is greater than 0.3, (g) The coefficient of determination of Sp for a linear polynomial is greater than 0.4, (h) The coefficient of determination of Sp for a quadratic polynomial is greater than 0.7, (i) The difference between the coefficients of determination of the quadratic and linear polynomials is greater than 0.3, (j) dP increases with the passage of time in the data interval, (k) Pf decreases with the passage of time in the data interval, and / or (l) Sp increases with the passage of time in the data interval. In some embodiments, biofouling can be identified if at least one of the dP conditions is met, and Pf and Sp provide a secondary (optional) basis for identification.

[0054] If the normalized permeation flow decrease over time fits well to a quadratic polynomial, it can be concluded that system 100 is likely experiencing organic fouling. Organic fouling alone (without interference from other types of fouling) is typically characterized by a decrease in normalized permeation flow due to the rapid accumulation of organic matter on unused membranes, but levels off after a period of operation because the amount of organic matter accumulated on the membrane is equal to the amount of organic matter wiped away as a result of cross-flow filtration mechanisms. Typically, the normalized pressure drop remains flat, similar to pure organic fouling mechanisms, and no bacterial growth or blockage of supply and concentration membrane channels occurs. The salt permeation ratio typically increases over time because it typically decreases as the organic matter accumulated on the membrane generates "additional" thickness and resistance in the membrane. For example, if evaluating historical performance data 112, system 100 can determine that organic fouling occurred in this dataset and that corresponding washing should have been performed. If we evaluate the current performance data 114, we can determine that system 100 is experiencing organic fouling and requires proper cleaning.

[0055] In some embodiments, a mode of filtration module failure in a data interval can be identified by system 100 as organic fouling if at least one of the following conditions is met: (a) the coefficient of determination of the linear polynomial Pf is greater than 0.4, (b) the coefficient of determination of the quadratic polynomial Pf is greater than 0.7, (c) the difference between the coefficients of determination of the quadratic polynomial fitted to Pf and the linear polynomial is greater than 0.3, (d) the coefficient of determination of the linear polynomial Sp is greater than 0.4, (e) the coefficient of determination of the quadratic polynomial Sp is greater than 0.7, and (f) the difference between the coefficients of determination of the quadratic polynomial fitted to Sp and the linear polynomial is 0. (g) the coefficient of determination of dP for a linear polynomial is greater than 3, (h) the coefficient of determination of dP for a quadratic polynomial is greater than 0.7, (i) the difference between the coefficients of determination of the quadratic and linear polynomials fitted to dP is less than 0.3, (j) dP remains constant over time in the data interval, (k) Pf decreases over time in the data interval, and / or (l) Sp decreases over time. In some embodiments, organic fouling can be identified if at least one of the Pf conditions is met, and dP and Sp provide secondary (optional) grounds for identification.

[0056] If the increase in the normalized pressure drop fits well to a linear polynomial, it can be concluded that system 100 is experiencing either scaling or particulate fouling. Scaling typically involves a slower rate of increase in pressure drop compared to particulate fouling because it usually takes a somewhat longer time for scaling precipitates to crystallize and form. Particulate fouling, on the other hand, is typically a faster process, for example, when fouling occurs in ultrafiltration and an increase in the intermembrane pressure difference is observed between backwash cycles. Scaling typically occurs with, or in combination with, an increase in the salt permeation ratio over time, because the scaling precipitated on the membrane increases the concentration polarization on the membrane boundary layer. This is accompanied by a corresponding increase in osmotic pressure and a decrease in the normalized permeation flow over time. Particulate fouling occurs when particulate matter clogs the membrane and can lead to a decrease in the normalized permeation flow as the net driving pressure decreases over time. For example, when evaluating past performance data 112, system 100 can determine that scaling or particulate fouling occurred in this dataset and that corresponding cleaning should have been performed. When evaluating current performance data 114, system 100 can determine that scaling or particulate fouling has occurred and that appropriate cleaning is required.

[0057] In some embodiments, a filtration module failure mode in a data interval can be identified as scaling by the system 100 if at least one of the following conditions is met: (a) the coefficient of determination of the linear polynomial dP is greater than 0.7, (b) the coefficient of determination of the quadratic polynomial dP is greater than 0.7, (c) the difference between the coefficients of determination of the quadratic polynomial fitted to dP and the linear polynomial is less than 0.3, (d) the coefficient of determination of the linear polynomial Sp is greater than 0.7, (e) the coefficient of determination of the quadratic polynomial Sp is greater than 0.7, (f) the difference between the coefficients of determination of the quadratic polynomial fitted to Sp and the linear polynomial is less than 0.3, (g (h) The coefficient of determination of the linear polynomial Pf is greater than 0.7, (i) The difference in the coefficients of determination of the quadratic polynomial Pf and the linear polynomial fitted to Pf is less than 0.3, (j) In the data interval, preferably dP increases over time in the trailing element, (k) Pf decreases over time in the data interval, and / or (l) Sp increases over time in the data interval. In some embodiments, scaling can be identified if at least one of the dP conditions is met, and the distribution of dP conditions in the system (preferably dP increases in the trailing element), along with Pf and Sp, provides a secondary (optional) basis for identification.

[0058] In some embodiments, a filtration module failure mode in a given data interval can be identified by system 100 as particulate fouling if at least one of the following conditions is met: (a) the coefficient of determination of the linear polynomial dP is greater than 0.7, (b) the coefficient of determination of the quadratic polynomial dP is greater than 0.7, (c) the difference between the coefficients of determination of the quadratic polynomial and the linear polynomial fitted to dP is less than 0.3D, (d) the coefficient of determination of the linear polynomial Pf is greater than 0.7, (e) the coefficient of determination of the quadratic polynomial Pf is greater than 0.7, (f) the difference between the coefficients of determination of the quadratic polynomial and the linear polynomial fitted to Pf is less than 0.3, (g) the linear polynomial (h) The coefficient of determination of Sp is greater than 0.7, (i) The difference in the coefficients of determination of the quadratic polynomial and the linear polynomial fitted to Sp is less than 0.3, (j) dP increases over time, preferably at the leading element, in the data interval, (k) Pf decreases over time, in the data interval, and / or (l) Sp increases over time, preferably at the trailing element, in the data interval. In some embodiments, particulate fouling can be identified if at least one of the dP conditions is met, and the distribution of dP conditions in the system (preferably dP increasing at the leading element), along with Pf and Sp, provides a secondary (optional) basis for identification.

[0059] If the normalized increase in permeation flow fits a linear polynomial, it can be concluded that system 100 may have a potential problem with film integrity (such as chemical degradation or halogenation of the film, or problems with the physical integrity of film elements). Poor film integrity typically leads to an increase in salt permeation rate over time. For example, if evaluating past performance data 112, it can be determined that system 100 has a potential problem with film integrity and appropriate measures should have been taken. If evaluating current performance data 114, it can be determined that system 100 may have a problem with film integrity and appropriate measures should be taken.

[0060] In some embodiments, a filtration module failure mode in a data interval can be identified by system 100 as a membrane integrity failure if at least one of the following conditions is met: (a) the coefficient of determination of the linear polynomial Pf is greater than 0.7, (b) the coefficient of determination of the quadratic polynomial Pf is greater than 0.7, (c) the difference between the coefficients of determination of the quadratic polynomial fitted to Pf and the linear polynomial is less than 0.3, (d) the coefficient of determination of the linear polynomial Sp is greater than 0.7, (e) the coefficient of determination of the quadratic polynomial Sp is greater than 0.7, (f) the difference between the coefficients of determination of the quadratic polynomial fitted to Sp and the linear polynomial is less than 0.3. (i) (g) the coefficient of determination of dP for the linear polynomial is greater than 0.7, (h) the coefficient of determination of dP for the quadratic polynomial is greater than 0.7, (i) the difference between the coefficients of determination of the quadratic polynomial and the linear polynomial fitted to dP is less than 0.3, (j) dP remains constant over time in the data interval, (k) Pf increases over time in the data interval, and / or (l) Sp increases over time in the data interval. In some embodiments, poor film integrity can be identified based on an increase in permeate flow accompanied by a simultaneous increase in the salt permeation ratio, and dP provides a secondary (optional) basis for identification.

[0061] If system 100 concludes that the data indicates a specific type of fouling event, system 100 can output a notification via the graphical user interface 120, along with the detected fouling event, supporting data, and recommendations for a cleaning strategy to address the fouling. If multiple types of fouling occur simultaneously, as in the previous analysis, for example, if organic fouling and subsequent biofouling are detected within the same period or dataset, a combined cleaning strategy is necessary, and system 100 can recommend how to implement the combined cleaning strategy. Therefore, using historical performance data, different types of fouling and / or combinations of fouling that may occur based on the performance of the equipment 102 can be identified, and the correlation of such fouling determinations is electronically stored as fouling type data 142.

[0062] In some embodiments, the current performance data 114 can be evaluated using fouling type data 142 and historical performance data 112 to detect one or more types of fouling occurring in the equipment 102 and recommend a cleaning operation. In some embodiments, the current performance data 114 can be evaluated using fouling type data 142 and historical performance data 112 to predict potential foulings that may occur. For example, the system 100 can run a prediction module 144 to receive the current performance data 114 as input and estimate the types of foulings that may occur in the near future, as well as predict the operational trajectory of the equipment 102. In some embodiments, the system 100 can run a prediction module 144 to receive historical performance data 112 as input and estimate the recurring patterns of a particular type of fouling at times when a particular type of fouling may occur in the equipment 102, for example, every summer or at the beginning of a particular month. In such an example, the system 100 can provide the user 116 with a notification about potential fouling types that may occur within a particular time window so that the user 116 can plan a cleaning operation in advance. System 100 thus accurately identifies the type of fouling and recommends a cleaning procedure specific to that type of fouling, focusing on addressing the actual problem occurring in the equipment 102, thereby ensuring that the filter element 104 is properly cleaned and that the lifespan of the element 104 is extended.

[0063] Figure 5 is a block diagram of a computing device 200 according to several exemplary embodiments of the present disclosure. The computing device 200 includes one or more non-temporary computer-readable media for storing one or more computer-executable instructions or software that implement the exemplary embodiments. The non-temporary computer-readable media may include, but are not limited to, one or more types of hardware memory, non-temporary tangible media (e.g., one or more magnetic storage disks, one or more optical disks, one or more flash drives), etc. For example, memory 206 included in the computing device 200 contains computer-readable and computer-executable instructions or software that implement the exemplary embodiments of the present disclosure (e.g., instructions to operate a normalization module, instructions to operate a cleaning module, instructions to operate a CIP module, instructions to operate a fouling identification module, instructions to operate a prediction module, instructions to operate a processing unit, instructions to operate a communication interface, instructions to operate a user interface, instructions to operate a central computing system, and combinations thereof). The computing device 200 also includes a configurable and / or programmable processor 202 and associated core 204 that execute computer-readable and computer-executable instructions or software stored in memory 206, as well as other programs that control the system hardware, and optionally one or more additional configurable and / or programmable processors 202' and associated core 204' (for example, in a computer system with multiple processors / cores). Processors 202 and 202' may each be single-core processors or multi-core (204 and 204') processors.

[0064] Virtualization may be employed in the computing device 200 to allow for the dynamic sharing of infrastructure and resources within the computing device 200. A virtual machine 214 may be provided to handle processes running on multiple processors so that the process appears to be using only one computing resource rather than multiple computing resources. Multiple virtual machines may be used on a single processor. Memory 206 may include computer system memory or random access memory such as DRAM, SRAM, or EDO RAM. Memory 206 may also include other types of memory or combinations thereof.

[0065] The user can interact with the computing device 200 via a visual display device 218 (e.g., a personal computer, mobile smart device, etc.) such as a computer monitor, which can display at least one user interface 220 (e.g., a graphical user interface) that can be provided according to an exemplary embodiment. The computing device 200 may include other I / O devices, such as a camera, keyboard, microphone, or any suitable multipoint touch interface 208, pointing device 210 (e.g., mouse) to receive input from the user. The keyboard 208 and pointing device 210 may be coupled to the visual display device 218. The computing device 200 may include other suitable conventional I / O peripherals.

[0066] The computing device 200 may also include at least one storage device 224, such as a hard drive, CD-ROM, eMMC (Multimedia Card), SD (Secure Digital) card, flash drive, non-volatile storage medium, or other computer-readable medium, for storing data and computer-readable instructions and / or software implementing exemplary embodiments of the system described herein. The exemplary storage device 224 may also store at least one database 226 for storing any appropriate information necessary for implementing the exemplary embodiment. For example, the exemplary storage device 224 may store information such as historical performance data, current performance data, normalized data, purified data, CIP events, fouling type data, combinations thereof, etc., and at least one database 226 for storing computer-readable instructions and / or software implementing exemplary embodiments described herein. The database 226 may be updated manually or automatically at any appropriate time to add, delete, and / or update one or more items in the database.

[0067] The computing device 200 may include a network interface 212 configured to function as an interface to one or more networks, such as a local area network (LAN), a wide area network (WAN), or the internet, via at least one network device 222, by various connections including, but not limited to, a standard telephone line, a LAN or WAN link (e.g., 802.11, T1, T3, 56kb, X.25), a broadband connection (e.g., ISDN, Frame Relay, ATM), a wireless connection, a controller area network (CAN), or any combination of some or all of the above. The network interface 212 may include a built-in network adapter, a network interface card, a PCMCIA network card, a PaCI / PCIe network adapter, an SD adapter, a Bluetooth adapter, a CardBus network adapter, a wireless network adapter, a USB network adapter, a modem, or any other device that provides an interface between the computing device 200 and any type of network to which it can communicate and is suitable for performing the operations described herein. Furthermore, the computing device 200 may be a workstation, desktop computer, server, laptop, handheld computer, tablet computer (e.g., tablet computer), mobile computing or communication device (e.g., smartphone communication device), embedded computing platform, or other forms of computing or telecommunications device that are capable of communication and have sufficient processor power and memory capacity to perform the operations described herein.

[0068] The computing device 200 can run any operating system 216, such as any version of the Microsoft® Windows® operating system, different releases of the Unix and Linux operating systems, any version of macOS® for Macintosh computers, any embedded operating system, any real-time operating system, any open-source operating system, any intellectual property-protected operating system, or any other operating system that can run on the computing device and perform the operations described herein. In exemplary embodiments, the operating system 216 can run in native mode or emulated mode. In exemplary embodiments, the operating system 216 can run on one or more cloud machine instances.

[0069] Figure 6 is a block diagram of an exemplary system environment 300 for determining the filter state according to several exemplary embodiments of the present disclosure. The environment 300 may include at least one water treatment facility 306, at least one sensor 308, at least one system 310, at least one processing device 312, at least one user interface 314, and a central computing system 318, and servers 302, 304 configured to be in communication state via a communication platform 324, which may be any network capable of transmitting information between devices responsively coupled to the network. For example, the communication platform 324 may be the Internet, an intranet, a virtual private network (VPN), a wide area network (WAN), a local area network (LAN), etc. In some embodiments, the communication platform 324 may be part of a cloud environment.

[0070] Environment 300 may include repositories or databases 320, 322, which may be in communication via a communication platform 324 with servers 302, 304 as well as with water treatment equipment 306, sensors 308, system 310, at least one processing unit 312, at least one user interface 314, and a central computing system 318. In several exemplary embodiments, servers 302, 304, water treatment equipment 306, sensors 308, system 310, at least one processing unit 312, at least one user interface 314, and the central computing system 318 may be implemented as computing devices (e.g., computing device 200). Those skilled in the art will recognize that databases 320, 322 can be incorporated into at least one of servers 302, 304. In some embodiments, databases 320, 322 can store data related to historical performance data, current performance data, normalized data, purified data, CIP events, fouling type data, combinations thereof, etc., and such data may be distributed across multiple databases 320, 322.

[0071] As described above, the exemplary system collects historical performance data, normalizes the data, purifies the data to standardize it by removing outliers, identifies CIPs, performs linear and quadratic polynomial regression to obtain the coefficient of determination, applies logic to identify fouling / fault types, and uses the above information to predict the type of fouling in the next instance. In some embodiments, data smoothing may be performed after the data purification step. In some embodiments, three different methods can be used to remove outliers, e.g., removal of abruptly changing data points, manual and kernel smoothing, or a combination thereof. In some embodiments, the system can perform a cleanability calculation to determine when a cleanup procedure should be performed based on the current performance data and the curvature / direction of the data.

[0072] Regarding the cleaning or outlier exclusion step, this system can implement Wenyu's method, piecewise kernel smoothing, or a combination thereof. Consistency checks may include steps with the following characteristics: supply pressure exceeds concentration pressure, supply pressure exceeds permeate pressure, supply flow exceeds concentration flow, supply flow exceeds permeate flow, and supply pressure exceeds pressure change (dP). Figures 7A and 7B are graphs of outlier identification performed by the system using the methods described above, with Figure 7A including outliers and Figure 7B excluding outliers. In this method, data outliers generally arise due to process malfunctions, measurement errors, etc. Outliers may lead to excessive "false positive" CIP and process stoppage identification / indicators. Wenyu's method is performed based on Equation 1 below.

number

[0073] The system first uses the previous data point (y t-1 ) data point (y t The rate of change of ) (Δ% in Equation 1) t This system then calculates the data point (y t ) Next data point (y t+1 ) rate of change (Δ% t+1 Calculate Δ% (as indicated). t If the value is above the lower limit (DL), then Δ t+1 % is less than or equal to -DL, or Δ% t Δ% below -DL t+1 If DL is greater than or equal to, point y tThese are identified as outliers. This process is repeated until all outliers are identified and removed from the dataset. In Figure 7A, the circled points show examples of some outliers that should be removed from the dataset (and are removed in Figure 7B). This method is used by the system to find combinations of sudden decline-increase or sudden increase-decrease. y refers to some key performance indicator (KPI). A DL of 1% is sufficient, but it has been found that DL may be changed by the user. The step of identifying outliers is useful for detecting process anomalies and ensuring that all other process data does not have "false positive" CIPs or process stop instructions.

[0074] In some embodiments, outlier identification can be performed by the system based on piecewise kernel smoothing. In such embodiments, the entire data is divided into different intervals, e.g., segments. If the time interval between two segments exceeds one day, a kernel smoother (e.g., a locally weighted scatter smoother or LOWESS) is placed for each segment. The kernel smoother generates a curve formed by iteratively obtaining locally weighted fits of a simple curve at sampled points within the domain. The default settings in this system are linear (lambda), cubic (weight function), 0.5 (alpha), and 0 (sampling delta). Depending on the data, the system can automatically identify the optimal alpha value. In some embodiments, JMP® kernel smoothing can be used.

[0075] After the dataset has been purified, system 100 can evaluate and analyze the data to identify CIP events. System 100 can identify when a CIP event begins and ends, and can segment the data around the CIP event for further processing to identify the type of fouling occurring between CIP events. Generally, a CIP event is an effort to "reset" or improve a water treatment process. A CIP event also represents lost production time and chemical cost expenditures. System 100 may rely on data gaps of more than one day before and after changes in several factors indicating a CIP event, such as KPIs (permeation flow (Pf), salt permeation ratio (Sp), and element pressure drop (dP)), or combinations thereof. Some potential obstacles in identifying CIPs may include, for example, outliers in the data (if not properly excluded), inconsistent time intervals between CIPs, KPIs not necessarily changing significantly due to CIPs, process outages being used as "low-cost" CIPs, and combinations thereof. Generally, the processes described in Figures 7A and 7B identify and exclude outliers in the data. If KPIs do not change significantly, such data may indicate a process outage (rather than a CIP), which is useful for the system to identify. If a process outage functions as a "low-cost" CIP, the system can consider such a "low-cost" CIP as a CIP event.

[0076] The CIP identification process is performed on the previous data point (y t-1 ) and the difference sequence (∇y t ;∇y t =y t -y t-1 This can be executed by generating (notation). The mean and standard deviation are calculated for the difference sequence of each KPI. For the KPIs in the difference sequence, this system calculates the difference value of dP when it is near the mean. * Whether or not the difference in flow rate is below the standard deviation, or whether the difference in flow rate is near the mean, K * Determine whether the value exceeds the standard deviation. If the answer to either question is "yes," the system determines whether there was a gap of more than one day in the data. If "yes," the data point (yt ) is identified as the restart value after CIP. This method is based on the extrema (EVDS) of the difference sequence of dP. This method checks whether the change in the data point deviates significantly from the expected fluctuation. dP and Pf are the best KPIs for identifying CIP points. The default value of k is 5, but it can be changed by the user. The CIP identification process can be expressed by the following equation 2. (∇dP t ≤Column Mean(∇dP)-K·Column Standard Deviation(∇dP)) or (∇Flow t ≥ Column Mean (∇Flow) + K·Column Standard Deviation (∇Flow)) and (∇Date t >1) If (2) The current observation corresponds to the restart point after CIP. The previous observation corresponds to the CIP time.

[0077] Figures 8A-8C are graphs showing the ideal (Figure 8A), expected (Figure 8B), and observed (Figure 8C) pressure drop (dP). The purpose of CIP is to return the system performance to its initial state (ideally). In the ideal scenario (Figure 8A), dP returns to its initial value after cleaning. In the expected scenario (Figure 8B), dP decreases with each cleaning but steadily increases. In the observed scenario (Figure 8C), dP changes inconsistently. dP is generally used to confirm the cleaning effect (other KPIs may be used in other embodiments). Over several years, indices have been developed to measure the cleaning effect, such as static indices (uncoated dP, cleaning performance, etc.) compared to dP after commissioning, and dynamic indices (dynamic cleaning performance) compared to dP after the previous CIP.

[0078] In some embodiments, the system can identify the start and end points of a CIP, calculate the average of three dP values ​​at each start and end point of each CIP, and calculate an associated cleansing effectiveness index for each CIP. Similar processing may be used in addition to or as an alternative to dP using other KPIs. Other cleansing indices can be calculated. The number of data points used to calculate the average can be changed by the system user or operator. For example, in some embodiments, the average can be calculated over at least two hours to ensure stable readings. However, in some embodiments, an average calculated over more or less than two hours may be used. Figure 9 is a graph showing CIP events for a dataset, Figure 10 is a graph showing unrecovered dP versus the initial state of the dataset, and Figure 11 is a graph showing cleansing effectiveness versus the initial state of the dataset. Figure 10 shows the difference between dP measured after a CIP and the initial dP (e.g., dP measured at startup before the first CIP is performed). In a complete system, as described in Figure 8A, Figure 10 is a horizontal line at 0 (i.e., no unrecovered dP exists). The "To Initial State" at the top of Figure 10 indicates that the plot represents the initial dP measured at startup before the first CIP was performed, compared to other dP values ​​after the first, second, third, etc. CIP events. Similarly, the cleanliness in Figure 11 shows the extent to which the dP increase was excluded by CIP compared to the ideal case where all dP increases after startup are excluded by CIP. In the complete system described in Figure 8A, Figure 11 is a horizontal straight line at 100% (i.e., each element is cleaned to the startup state each time). In Figure 9, a i represents the dP value after the i-th CIP, and b i represents the dP value before the i-th CIP. These values ​​are obtained using equations 3 and 4 below to determine the initial value (dP initial It is compared to ).

number

number

[0079] In some cases, CIP (Clean-in-Place) cleaning can be identified by detecting a lower pressure drop, an increase in normalized flow rate, or a return of the salt permeation ratio to the initial point. If the system is started / stopped, the permeation flow and salt permeation ratio will oscillate until they stabilize. Once a CIP event is identified, the system can analyze the data between CIP events to determine the type of fouling occurring based on the system's operating values. Figure 12 is a chart of fouling types and indicators / parameters based on normalized pressure drop, normalized permeation flow rate, and normalized salt permeation ratio. The system uses the information in Figure 12 in combination with the information in Figure 13 to identify the specific type of fouling occurring. For some types of fouling, the indicators / parameters are evaluated based on the location of the filter element, e.g., front, rear, or both. Some types of fouling can occur on any filter element; therefore, the indicators / parameters are evaluated at any location on the filter element. Normalized pressure drop can serve as a primary indicator of no fouling, biofouling, particulate fouling, and scaling. Normalized permeation flow can serve as a primary indicator of no fouling, organic fouling, particulate fouling, and element damage (e.g., poor integrity). Normalized salt permeation ratio can serve as a primary indicator of scaling and element damage. These primary factors can therefore be evaluated by the system for each dataset corresponding to the interval of CIP events to determine the type of fouling occurring.

[0080] As discussed herein, the system can first identify the type of fouling by determining whether a match exists based on at least one primary indicator / parameter. Such identification can be enhanced by additional primary and / or secondary indicators / parameters that match the dataset. However, the system only requires a match on one primary indicator / parameter to estimate the type of fouling. In some cases, more than one type of fouling may occur, and the system can identify such scenarios, for example, based on two or more different primary parameters that are met. In some cases, if no match is identified for a primary indicator / parameter, the system can determine the type of fouling based on a match for a secondary parameter.

[0081] In some embodiments, the "decision tree" executed by the system is configured to perform the following steps: (i) identify the gradient of a primary parameter; (ii) identify the fit tendency of a group of primary parameters; and (iii) determine the location of the filter element for the identified performance change. The type of fouling can be identified based on the match between at least one primary parameter and gradient versus time (or gradient versus time and data fitting, or gradient versus time, data fitting and filter element location). If no match is found for at least one primary parameter, the system's "decision tree" can identify the gradient and fitting tendency of a secondary parameter and identify the type of fouling based on the match of the secondary parameter. If two or more potential types of fouling are identified by the match of primary and / or secondary parameters, the system uses the potential match to identify the type of fouling. The data can be provided to the user, who can evaluate the data and determine which potential matches represent the type of fouling actually occurring. In some cases, more than one type of fouling may occur within the filter element, and the system can identify multiple types of fouling based on matches of primary and / or secondary parameters. The identified fouling can be used to identify current performance data (e.g., in real time or substantially real time) and estimate the types of fouling that may be occurring and / or will occur soon, thereby recommending more specific and accurate cleaning procedures to address the fouling. The identified fouling can also be used to predict when fouling may occur, based on the detection of recurring fouling fluorescence occurring within a particular week or month, and / or in terms of specific water conditions (e.g., temperature).

[0082] Pay particular attention to Figure 12. If no fouling occurs, data can be used from any filter element position, and dP, Pf, and Sp are considered the primary indicators / parameters. To identify that no fouling has occurred, any of the dP, Pf, and / or Sp curves are fitted to a linear function with gradient versus time approximately zero (e.g., change over the entire operating time of the dataset is less than 5%).

[0083] Continuing with reference to Figure 12, for biofouling, data is evaluated with respect to a tip filter element that may include only a first filter element (or, in some embodiments, a first and second filter element may be included at the tip of the pressure vessel). dP is the first-order parameter of biofouling, where the data fits a nonlinear function and the gradient-to-time is positive (both of which must occur to satisfy the first-order parameter). Pf is the second-order parameter of biofouling, where the data fits a nonlinear function and the gradient-to-time is negative (both of which must occur to satisfy the second-order parameter). Sp is another second-order parameter of biofouling, where the data fits a nonlinear function and the gradient-to-time is positive (both of which must occur to satisfy the second-order parameter). Thus, in all examples discussed herein, both functions must be fitted to satisfy either the first-order or second-order parameter and the gradient-to-time must be satisfied. If the first-order parameter condition is satisfied, the system can identify the type of fouling as biofouling, even if the second-order parameter is not satisfied. However, if one or more of the secondary parameters are met, the system can use this data to enhance its original identification based on the primary parameters.

[0084] For organic fouling, data is evaluated for any filtration element (e.g., not limited to tip or terminal filtration elements). Pf is a first-order parameter of organic fouling, where the data fits a nonlinear function and the gradient-to-time is negative. dP is one second-order parameter of organic fouling, where the data fits a linear function and the gradient-to-time is approximately zero. Sp is another second-order parameter of organic fouling, where the data fits a nonlinear function and the gradient-to-time is negative. If the first-order parameter condition is met, the system can identify the type of fouling as organic fouling even if the second-order parameters are not met. However, if one or more of the second-order parameters are met, the system can use this data to enhance its original identification based on the first-order parameters.

[0085] For particulate fouling, data related to the tip filter element is evaluated. dP is a first-order parameter for particulate fouling, where the data fits a linear function and the gradient-time is positive. Pf is a second-order parameter for particulate fouling, where the data fits a linear function and the gradient-time is negative. Sp is another second-order parameter for particulate fouling, where the data fits a linear function and the gradient-time is positive. If the first-order parameter condition is met, the system can identify the type of fouling as particulate fouling even if the second-order parameters are not met. However, if one or more of the second-order parameters are met, the system can use this data to enhance its original identification based on the first-order parameter.

[0086] For scaling, data is evaluated with respect to end filtration elements that may include a final filtration element at the end of the pressure vessel (or, in some embodiments, the final and last adjacent filtration elements). dP is a first-order parameter of scaling, where the data fits a linear function and the gradient-time is positive. Pf is a second-order parameter of scaling, where the data fits a linear function and the gradient-time is negative. Sp is another second-order parameter of scaling, where the data fits a linear function and the gradient-time is positive. If the first-order parameter conditions are met, the system can identify the type of fouling as scaling even if the second-order parameters are not met. However, if one or more of the second-order parameters are met, the system can use this data to enhance its original identification based on the first-order parameters.

[0087] For integrity defects, data is evaluated with respect to both the front and rear filtration elements, which may include only the first and last filtration elements at the front and rear ends of the pressure vessel (or, in some embodiments, two filtration elements at the front and two at the rear). Pf is one linear parameter of integrity defects, where the data fits a linear function and the gradient versus time is positive. Sp is another linear parameter of integrity defects, where the data fits a linear function and the gradient versus time is positive. dP is a quadratic parameter of integrity defects, where the data fits a linear function and the gradient versus time is approximately zero. If the linear parameter condition is met for only one linear parameter, the system can identify the type of fouling as integrity defects even if both the linear and / or quadratic parameters are not met. However, if both linear parameters are met and / or the quadratic parameters are met, the system can use this data to enhance its original identification based on the linear parameters.

[0088] Furthermore, "impaired integrity" can be classified into two subcategories: "chemical degradation" and "physical integrity problems." The following table is a supplement to Figure 12, disclosing the parameters for each of these subcategories. * " and " a The notes marked with " are the same as those shown in Figure 12. The primary and secondary parameters for the two subcategories are the same, and the data for each of the primary and secondary parameters fit the same order function (linear) and the same gradient (approximately 0 or positive), as described immediately above for the parameters of the more general category, poor integrity. However, while any filtration element can be evaluated for chemical degradation, the same element is analyzed for the physical integrity problem described immediately above for poor integrity.

[0089] [Table 1]

[0090] Figures 13A–13F are graphs showing dataset analysis for pressure drop, permeate flow, and salt permeate ratio, with specific results indicating particular types of fouling, including no fouling (Figure 13A), biofouling (Figure 13B), organic matter (Figure 13C), particulate matter (Figure 13D), scaling (Figure 13E), and integrity (Figure 13F). As used herein with respect to Figures 13A–13F, as with respect to the entire disclosure, the terms “rapid,” “stepwise,” or “gradual” change refer to a change of at least 5% in an operating time of less than 24 hours, the terms “steep” or “gradual” change refer to a step in which the change of a given parameter is at least 5% in an operating time of 24 hours or more, and the terms “zero” or “no change” refer to a change of less than 5% over the entire operating time of the dataset.

[0091] As shown in Figure 13A, no fouling is generally represented by no change in any factor. Washing is unnecessary in these results. As shown in Figure 13B, biofouling is generally represented by an increasing pressure drop that fits a quadratic polynomial (accompanied by an arbitrarily selective decrease in permeate flow and an increase in salt permeation ratio). Washing with a specific combination of chemicals for biofouling would be recommended. As shown in Figure 13C, organic fouling is generally represented by a decrease in permeate flow that fits a quadratic polynomial (accompanied by an arbitrarily selective decrease in salt permeation ratio and a steady pressure drop). Washing with a specific combination of chemicals for organic fouling would be recommended.

[0092] As shown in Figure 13D, particulate fouling is generally represented by a steep increase in pressure drop that fits a linear polynomial (e.g., a stepwise change) (accompanied by an arbitrarily selected steep decrease in permeate flow (e.g., a stepwise change) and a steep increase in salt permeation ratio (e.g., a stepwise change) that fits a linear polynomial). Washing with a specific combination of chemicals for particulate fouling would be recommended. Pretreatment troubleshooting would be recommended. The increase can be linear, but generally such an increase is represented as a ramp. As shown in Figure 13E, scaling is generally represented by an increase in pressure drop that fits a linear polynomial (accompanied by an arbitrarily selected decrease in permeate flow and an increase in salt permeation ratio that fits a linear polynomial). Washing with a specific combination of chemicals for scaling would be recommended. Reducing overall system recovery would be recommended. While biofouling and scaling may have similar effects, the increase in dP is more dominant in the tip element for biofouling, whereas this effect is observed in the trailing element for scaling. Oxidation or integrity damage is generally represented by an increase in permeate flow fitting a linear polynomial and an increase in salt permeation ratio fitting a linear polynomial (with optionally steady-state pressure drop), as shown in Figure 13F. Replacement of the current filter element would be recommended.

[0093] Figure 14 is a graph showing biofouling identified based on one dataset, and Figure 15 is a graph showing organic fouling identified based on a different dataset. This fouling identification is performed by the system evaluating and analyzing the data to determine the primary causative state, and then matching the primary causative state against the aforementioned guidelines. Based on these guidelines, the system developed specific functions for the dataset to identify the type of specific fouling occurring. The organic fouling differences were reproduced with excellent results based on experiments with different datasets.

[0094] Figures 16 and 17 are graphs showing identified organic foulings and biofoulings overlaid on organic foulings. Excellent identification and reproducibility of results are achieved using this system during experiments. Figure 18 is a graph showing identified organic foulings, particulate foulings, biofoulings, and CIP events based on different datasets.

[0095] In some cases, the system can follow specific rules for analyzing data and detecting the type of fouling. The system can first detect the period of CIP events and then perform first- and second-order polynomial regressions on dP, salt permeation ratio, and permeation flow for each period. The system can be used to detect CIP events and the type of fouling in both RO (single-pass) and CCRO (closed-circuit multi-pass) systems.

[0096] While exemplary embodiments have been described herein, these embodiments should not be construed as limiting, and it should be explicitly noted that additions and modifications to those explicitly described herein are also within the scope of the invention. Furthermore, it should be understood that the features of the various embodiments described herein are not mutually exclusive and can be combined and rearranged in various ways, even if such combinations or rearrangements are not explicitly described herein, without departing from the spirit and scope of the invention.

Claims

1. A system for determining the filter state, A database configured to electronically store data including historical performance data of one or more water filtration elements, The processing unit that is in communication with the aforementioned database and The processing apparatus includes, The aforementioned past performance data is received as input, Identify one or more data points in the past performance data that indicate a cleaning event for one or more of the water filtration elements, The aforementioned past performance data is divided into individual data intervals, each of which represents the data of the past performance data between each identified cleaning event. A mathematical function is fitted to each of the aforementioned individual data intervals. Based on the mathematical function fitted to each of the individual data intervals, it is configured to identify the type of fouling occurring between each of the individual data intervals. system.

2. The system according to claim 1, wherein the processing apparatus is further configured to normalize the past performance data to the state of the one or more water filtration elements at the time of activation before identifying the cleaning event.

3. The system according to claim 1 or 2, wherein the processing apparatus is further configured to grasp fluctuations in at least one of the supply water temperature, supply water composition, or supply water pressure when normalizing the past performance data.

4. The system according to any one of claims 1 to 3, wherein the processing apparatus is further configured to identify and exclude from the historical performance data any physically inconsistent data points before identifying the cleaning event.

5. The aforementioned physically inconsistent data points meet the following conditions, namely: The supply flow is greater than the enrichment flow. The supply flow is greater than the permeate flow. The supply pressure is greater than the concentration pressure, and The supply pressure is greater than the permeation pressure. The system according to claim 4, wherein if the condition is not met, it is excluded from the aforementioned past performance data.

6. The system according to any one of claims 1 to 5, wherein the processing apparatus is further configured to identify statistical outlier data points and exclude them from the historical performance data before identifying the cleaning event.

7. The step of identifying and excluding statistical outlier data points from the aforementioned past performance data is: Previous data point (y t-1 ) Data point (y t The steps include calculating the rate of increase or decrease of ) and The aforementioned data point (y t ) Next data point (y t+1 The steps include calculating the rate of increase or decrease of ) and The steps include comparing the previous rate of increase or decrease with the lower limit value, If the rate of increase or decrease exceeds the decrease limit, the data point (y t The step of identifying ) as an outlier and The system according to claim 6, including the system described in claim 6.

8. The step of identifying the aforementioned cleaning event is, The step of applying the difference sequence method to the normalized pressure drop (dP) and normalized permeate flow (Pf) from the aforementioned past performance data, wherein the step of applying the difference sequence method is: The aforementioned data point (y t ) and the aforementioned data point (y t-1 The steps include: calculating the difference between the above and the normalized pressure drop (dP) and the normalized permeate flow (Pf), and generating a difference sequence for the normalized pressure drop (dP) and the normalized permeate flow (Pf). A step of calculating the mean and standard deviation of the difference sequence for the normalized pressure drop (dP) and the normalized permeate flow (Pf), The steps include comparing each value in the difference sequence for the normalized pressure drop (dP) and the normalized permeate flow (Pf) with the corresponding value in the difference sequence and the sum of the product of the difference constant and the corresponding standard deviation of the difference sequence, A step of determining whether or not gaps exist in the aforementioned dataset. The step of determining whether the gap is wider than the CIP reference time. The system according to any one of claims 1 to 7, including the system described in any one of claims 1 to 7.

9. The system according to any one of claims 1 to 8, wherein the processing device is further configured to analyze the coefficient of determination of the mathematical function and to calculate the time derivative of the mathematical function, and the processing device is further configured to identify the type of fouling based on the derivative of the coefficient of determination.

10. The system according to any one of claims 1 to 9, wherein the one or more water filtration elements include at least one element selected from the group including reverse osmosis elements, nanofiltration elements, and superfiltration elements.

11. The system according to any one of claims 1 to 10, further comprising one or more sensors configured to detect data on pressure drop, salt permeation ratio, and permeation flow associated with each of the one or more water filtration elements and to transmit this data to the database for storage as historical performance data.

12. The aforementioned past performance data includes pressure drop, salt permeation ratio, and permeation flow for each of the one or more water filtration elements. If no pressure drop, salt permeation ratio, or permeation flow change is detected, the processing device identifies a fouling-free state. The system according to any one of claims 1 to 11.

13. The aforementioned past performance data includes pressure drop, salt permeation ratio, and permeation flow for each of the one or more water filtration elements. If the increase in the pressure drop fits a quadratic polynomial function, the processing unit identifies the type of fouling as biofouling. The system according to any one of claims 1 to 12.

14. The aforementioned past performance data includes pressure drop, salt permeation ratio, and permeation flow for each of the one or more water filtration elements. If the decrease in the salt permeation ratio fits a quadratic polynomial function, the processing device identifies the type of fouling as organic fouling. The system according to any one of claims 1 to 13.

15. The aforementioned past performance data includes pressure drop, salt permeation ratio, and permeation flow for each of the one or more water filtration elements. If the rapid increase in the pressure drop of the first position element fits a linear polynomial function, the processing unit defines the type of fouling as particle fouling. The system according to any one of claims 1 to 14.

16. The aforementioned past performance data includes pressure drop, salt permeation ratio, and permeation flow for each of the one or more water filtration elements. If the gradual increase in the pressure drop of the rear end position element fits a linear polynomial function, the processing unit identifies the type of fouling as scaling. The system according to any one of claims 1 to 15.

17. The aforementioned past performance data includes pressure drop, salt permeation ratio, and permeation flow for each of the one or more water filtration elements. If the increase in the permeate flow fits a linear polynomial function and the increase in the salt permeate ratio fits a linear polynomial function, the processing unit identifies the type of fouling as a integrity failure event. The system according to any one of claims 1 to 16.

18. The aforementioned processing apparatus The system receives current performance data of one or more water filtration elements from one or more sensors as input, Based on the aforementioned analysis of past performance data and the identification of the type of fouling occurring between each of the individual data intervals, the current performance data is analyzed. The current type of fouling occurring in one or more of the aforementioned water filtration elements is estimated. Output a recommendation for a cleaning procedure specific to the current type of fouling occurring in one or more of the aforementioned water filtration elements. The system according to any one of claims 1 to 17, further configured as follows.

19. The system according to any one of claims 1 to 18, further comprising artificial intelligence, machine learning capabilities, or both artificial intelligence and machine learning capabilities, wherein the artificial intelligence or machine learning capabilities operate to improve the identification of types of fouling, the predictability of fouling events, or both the identification of types of fouling and the predictability of fouling events.

20. A method for determining the filter state, A system for determining the filter state, comprising the steps of: (i) receiving past performance data of one or more water filtration elements as input to a system for determining the filter state, which includes a database configured to electronically store the past performance data and a processing device in communication with the database; The steps include identifying one or more data points in the historical performance data that indicate a cleaning event for one or more water filtration elements, The steps include dividing the aforementioned past performance data into individual data intervals, each representing the data of the aforementioned past performance data between each identified cleaning event, The steps include fitting a mathematical function to each of the aforementioned individual data intervals, The steps include identifying the type of fouling occurring between each of the individual data intervals based on the mathematical function fitted to each of the individual data intervals, and A method that includes this.

21. A non-temporary computer-readable medium for storing instructions for determining a filter state that can be executed by a processing device, wherein the execution of the instructions by the processing device is performed by the processing device. A system for determining the filter state, which includes (i) a database configured to electronically store the past performance data of one or more water filtration elements, and (ii) a processing device in communication with the database, receiving this data as input to the system for determining the filter state. To identify one or more data points in the past performance data that indicate a cleaning event for one or more of the water filtration elements, The aforementioned past performance data is divided into individual data intervals, each representing the data of the past performance data between each identified cleaning event. A mathematical function is fitted to each of the aforementioned individual data intervals. Based on the mathematical function fitted to each of the individual data intervals, the type of fouling occurring between each of the individual data intervals is identified. Non-temporary computer-readable media.

Images