System for determining filter status

Abstract

An example system for determining a filter state is provided. The system includes a database configured to electronically store data including past performance data for one or more water filter elements. The system includes a processing device in communication with a database. The processing device is configured to: receive past performance data as input; and identifying one or more data points within the past performance data indicative of a cleaning event of the water filter element. The processing device is configured to: divide past performance data into individual data segments, each of the individual data segments representing data between respective identified cleaning events in the past performance data; fitting a mathematical function to each of the individual data segments; and identifying a fouling type occurring during each of the individual data segments based on the mathematical functions fitted to the respective individual data segments.

Description

Cross-references to related applications

[0001] This application claims priority to Spanish Utility Model Application No. 202330840, filed on May 21, 2023, which is incorporated herein by reference in its entirety. Technical Field

[0002] This invention relates to a method and system for automatically monitoring filter membranes in water treatment facilities and for detecting and identifying the types of membrane fouling in water treatment facilities. The method and system can be used to efficiently determine when filter membranes need cleaning and provide accurate guidance for filter membrane cleaning based on the identified fouling types. Background Technology

[0003] Water treatment systems can be configured in various ways, including systems that perform pressure-driven membrane separation processes for water filtration. This pressure-driven membrane separation process allows the removal of a wide range of neutral and ionic species from the fluid. Membranes are generally classified into several categories according to their pore size, from largest to smallest: microfiltration (MF), ultrafiltration (UF), nanofiltration (NF), and reverse osmosis (RO). Microfiltration is used to remove suspended particles larger than 0.1 micrometers. Ultrafiltration typically excludes dissolved molecules with a molecular weight greater than 5,000 Daltons. Nanofiltration membranes allow at least some salts to pass through, but generally have a high rejection rate for organic compounds with a molecular weight greater than about 200 Daltons. Reverse osmosis membranes have a high rejection rate for almost all species.

[0004] NF and RO membranes are most commonly used in applications such as seawater or brackish water desalination, ultrapure water production, color removal, wastewater treatment, and liquid concentration in food processing. A key factor in almost all NF and RO applications is that the membrane can maintain high flux while achieving a high rejection rate for small solute molecules.

[0005] Spiral wound elements are the most common configuration for RO and NF membranes. Figure 1A conventional spiral-wound element design is shown. This element typically includes a membrane coating layer 2 and a feed separator 4 wound around a central permeate collection tube 6. The coating layer 2 comprises two membrane sheets 8 surrounding a permeate carrier sheet 10, wherein this structure is secured together along edges 14, 16, and 18 by an adhesive 12. A fourth edge 20 of the coating layer 2 abuts against the permeate collection tube 6, such that the permeate carrier sheet 10 is in fluid contact with an opening 22 in the permeate collection tube 6. Each coating layer 2 is separated by a feed separator 4, which is also wound around the collection tube 6. The feed separator 4 is in fluid contact with both ends of elements 24 and 26 and acts as a conduit for allowing the feed solution to pass through the front surface 28 of the membrane 8. The direction of the feed flow rate 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. Thus, the "feed" liquid flows axially through the feed separator 4 and exits as a "concentrate" at the opposite end. The "product water" passes through the membrane coating layer 2 under pressure and is guided by the product water carrier sheet 10 to the product water collection pipe 6.

[0006] Over time, the performance level of filter elements can decline due to the accumulation of foreign matter (e.g., fouling) and / or salt deposition (e.g., scaling) on ​​the feed screen or membrane. This decline in performance level can affect the quality of filtered water and / or place greater stress on the water filtration system during operation, leading to increased maintenance workload over time.

[0007] Manufacturers of filter elements and / or water treatment systems typically set certain guidelines for cleaning filter elements. This usually involves monitoring the overall operation of the water treatment system and shutting down the system to clean the filters when certain operating characteristics are detected (e.g., pressure drop across the element exceeds a recommended threshold). For proper cleaning, it is generally recommended to shut down the system, clean the affected filter elements, and send some of the affected elements to a laboratory for detailed analysis of the type of fouling and / or scaling. However, to avoid prolonged system shutdowns, water treatment plant operators often operate the filtration system beyond the recommended guidelines. This can lead to further problems, such as pump overheating and decreased product quality, ultimately forcing a system shutdown.

[0008] Instead of sending the filter elements to the lab, the operator might try to guess the type of fouling / scaling that has occurred based on experience and use chemicals they deem suitable to clean the system. In this case, the type of chemicals used may be inappropriate and may fail to address the actual fouling / scaling problem. This can result in the filter elements' performance baseline after cleaning being lower than what they would achieve with proper cleaning. After repeated cleaning attempts, additional operational failures may occur in the filter elements and / or the water treatment system, leading to increased operating costs and inadequate water filtration. Summary of the Invention

[0009] An exemplary system for determining filter status can be used by plant operators to improve their system performance. The system can analyze past performance to identify past Clean in Place (CIP) events and identify the type of filter module failure mode based on system performance between and within CIP periods. The system can be used in nanofiltration and / or reverse osmosis systems to identify fouling, scaling, and / or membrane failure modes. In some embodiments, the system can be used to predict when the next cleaning should / will be performed and recommend the most suitable cleaning procedure.

[0010] Membrane fouling is a complex problem in nanofiltration and reverse osmosis systems. Therefore, identifying the primary fouling mechanisms during the filtration process can be crucial for predicting the next cleaning cycle and controlling fouling. Real-time (or near-real-time) monitoring of water treatment facilities to detect and identify fouling types enables facility operators to identify and react early, preventing excessive fouling and potential negative impacts on the rest of the system. This system provides an accurate means of determining the type of fouling occurring and, consequently, accurate recommendations for cleaning cycles to ensure steps are taken to properly address the fouling event(s). In some embodiments, the system can be used to predict periodic and / or seasonal fouling, allowing for the minimization and / or avoidance of the fouling event(s).

[0011] According to embodiments of this disclosure, an exemplary method for analyzing the performance of an influent filtration system is provided. The method includes: collecting performance data from the filtration system; normalizing the dataset to startup conditions; removing physically inconsistent data points from the dataset; removing statistical outliers from the dataset; identifying membrane cleaning events in the dataset; dividing the dataset into multiple data segments between the membrane cleaning events; fitting a mathematical function to the data segments; analyzing the coefficient of determination of the mathematical function; calculating the derivative of the mathematical function with respect to time; and determining the fouling type 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. Performance data collection can be performed using sensors installed in the filtration system. The dataset can be standardized to account for variations in the influent temperature, influent composition, or feed pressure. Outlier removal from the dataset can be performed statistically, including the following steps: calculating data points (y... t ) relative to the previous data point (y t-1 The percentage change of y; calculate the next data point (y t+1 ) relative to the data point (y tThe percentage change of y; comparing the previous percentage change with the fall limit; and if the percentage change exceeds the fall limit, resetting the data point (y) t It was identified as an outlier.

[0013] The removal of physically inconsistent data points in the dataset can be performed by applying a set of criteria including one or more of the following: the feed flow rate must be greater than the concentrate flow rate; the feed flow rate must be greater than the product water flow rate; the feed pressure must be greater than the concentrate pressure; the feed pressure must be greater than the product water pressure; the feed pressure must be greater than the pressure drop across the filter module; the product water conductivity must be less than the feed conductivity; the pressure drop across the filter module must be less than or equal to the difference between the feed pressure and the concentrate pressure; and / or the osmotic pressure of the feed flow must be less than the feed pressure.

[0014] The dataset may include the normalized pressure drop (dP) across the filtration module, the normalized permeate flow rate (Pf) of the filtration module, and the normalized salt permeate rate (Sp) through the filtration module. A differential sequence method using dP and Pf can be used to identify membrane cleaning events, wherein the differential sequence method may include the following steps: calculating data points (y... t ) and the previous data point (y t-1 The difference between dP and Pf is used to generate the difference sequences of dP and Pf; the mean and standard deviation of the difference sequences of dP and Pf are calculated; each value in the difference sequence of dP or Pf is compared with the sum of the products of the corresponding difference sequence and the difference constant and the corresponding standard deviation of the difference sequence; gaps are checked in the dataset; and gaps are checked to see if they are greater than the CIP reference time. The difference constant is a positive integer, preferably a number between 1 and 10 (inclusive); more preferably a number between 3 and 7 (inclusive); and still more preferably 5. The CIP reference time is a time interval defined by the user to indicate the typical duration of CIP of the system of interest, ranging from several minutes to several days. Exemplary values ​​for the CIP reference time may be, for example, 120 minutes, 1 day, etc. Preferred CIP reference times are from 5 minutes to two weeks, and more preferably 1 day.

[0015] When determining the type of fouling occurring in (multiple) filter elements, the system analyzes data from (multiple) filter elements to determine whether various parameters are met. As discussed herein, depending on the type of fouling involved, some parameters are considered "primary" parameters, while others 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 cases, the data may meet criteria such as: only one primary parameter, more than one primary parameter, only one or more secondary parameters, etc. Therefore, the system may initially examine the data to determine whether one or more primary parameters are met. If so, the system may estimate the fouling type based on the met primary parameters. In some embodiments, the system may estimate the fouling type based on only one met primary parameter. In some embodiments, the system may rely on met additional met primary and / or secondary parameters to reinforce, strengthen, or support the initial estimate of the fouling type occurring based on the met primary parameters. Therefore, the system may initially determine whether the primary parameters are met to estimate the fouling type. If no primary parameter is met, the system can examine secondary parameters to estimate the fouling type based on the satisfied secondary parameter(s). In some embodiments, if there is overlap between possible fouling types based on the satisfied primary and / or secondary parameters(s), the system can perform a sorting operation to determine the likelihood of a fouling type occurring, for example, based on historical data. Although some parameters are discussed as being based on first- or second-order polynomial functions, in some embodiments, these parameters may be identified based on, for example, exponential functions, higher-order polynomial functions, linear functions, nonlinear functions, etc.

[0016] Statistical methods can be used to fit a set of curves to the data segment. In some embodiments, a filter module failure mode in a data segment can be identified as scaling if at least one of the following conditions is met: (a) the coefficient of determination of dP relative to a first-order polynomial is greater than 0.7; (b) the coefficient of determination of dP relative to a second-order polynomial is greater than 0.7; (c) the difference between the coefficients of determination of the second-order polynomial fitted to dP and the first-order polynomial is less than 0.3; (d) the coefficient of determination of Sp relative to a first-order polynomial is greater than 0.7; (e) the coefficient of determination of Sp relative to a second-order polynomial is greater than 0.7; (f) the difference between the coefficients of determination of the second-order polynomial fitted to Sp and the first-order polynomial is less than 0.3; (g) the coefficient of determination of Pf relative to a first-order polynomial is greater than 0.7; (h) the coefficient of determination of Pf relative to a second-order polynomial is greater than 0.7; (i) the difference between the coefficients of determination of the second-order polynomial fitted to Pf and the first-order polynomial is less than 0.3; (j) dP increases over time in the data segment; (k) Pf decreases over time in the data segment; and / or (l) Sp increases over time in the data segment.

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

[0018] In some embodiments, a filter module failure mode in a data segment can be identified as biofouling if at least one of the following conditions is met: (a) the coefficient of determination of dP relative to a first-order polynomial is greater than 0.4; (b) the coefficient of determination of dP relative to a second-order polynomial is greater than 0.7; (c) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial is greater than 0.3; (d) the coefficient of determination of Pf relative to a first-order polynomial is greater than 0.4; (e) the coefficient of determination of Pf relative to a second-order polynomial is greater than 0.7; (f) the difference between the coefficients of determination of the second-order polynomial fitted to Pf and the first-order polynomial is greater than 0.3; (g) the coefficient of determination of Sp relative to a first-order polynomial is greater than 0.4; (h) the coefficient of determination of Sp relative to a second-order polynomial is greater than 0.7; (i) the difference between the coefficients of determination of the second-order polynomial fitted to Sp and the first-order polynomial is greater than 0.3; (j) dP increases over time in the data segment; (k) Pf decreases over time in the data segment; and / or (l) Sp increases over time in the data segment.

[0019] In some embodiments, a filter module failure mode in a data segment 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 Pf relative to a first-order polynomial is greater than 0.7; (b) the coefficient of determination of Pf relative to a second-order polynomial is greater than 0.7; (c) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial fitted to Pf is less than 0.3; (d) the coefficient of determination of Sp relative to a first-order polynomial is greater than 0.7; (e) the coefficient of determination of Sp relative to a second-order polynomial is greater than 0.7; (f) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial fitted to Sp is less than 0.3; (g) the coefficient of determination of dP relative to a first-order polynomial is greater than 0.7; (h) the coefficient of determination of dP relative to a second-order polynomial is greater than 0.7; (i) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial fitted to dP is less than 0.3; (j) dP remains constant over time in the data segment; (k) Pf increases over time in the data segment; and / or (l) Sp increases over time in the data segment.

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

[0021] In some embodiments, the descent 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 greater than 0 and less than 10 days. This exemplary method may include the step of comparing performance parameters before and after cleaning to ensure correct CIP and / or dirt identification. Therefore, the exemplary system and method can be used to identify filter module failure modes and provide optimal cleaning guidance to ensure efficient operation of the water filtration system.

[0022] According to embodiments of this disclosure, an exemplary system for determining the state of a filter is provided. The system includes a database configured to electronically store data including past performance data of one or more water filter elements. The system includes a processing device in communication with the database. The processing device is configured to: receive the past performance data as input; and identify one or more data points within the past performance data that indicate cleaning events of the water filter elements. The processing device is configured to divide the past performance data into separate data segments, each of which represents data between corresponding identified cleaning events in the past performance data. The processing device is configured to fit a mathematical function to each of these separate data segments. The processing device is configured to identify the type of fouling that occurred during each of these separate data segments based on the mathematical function fitted to the corresponding separate data segment.

[0023] In some embodiments, the processing apparatus may be configured to normalize past performance data to the conditions at which the one or more water filtration elements were started before a cleaning event is identified. In some embodiments, the processing apparatus may take into account variations in at least one of inlet water temperature, inlet water composition, or feed pressure when normalizing past performance data.

[0024] In some embodiments, the processing apparatus may be configured to identify and remove physically inconsistent data points from past performance data before identifying a cleaning event. In some embodiments, physically inconsistent data points are removed from past performance data if at least one of the following conditions is not met: feed flow rate is greater than concentrate flow rate; feed flow rate is greater than permeate flow rate; feed pressure is greater than concentrate pressure; and / or feed pressure is greater than permeate pressure. In some embodiments, physically inconsistent data points are removed from past performance data if at least one of the following conditions is not met: feed flow rate is greater than concentrate flow rate; feed flow rate is greater than permeate flow rate; feed pressure is greater than concentrate pressure; feed pressure is greater than permeate pressure; feed pressure is greater than the pressure drop across one or more water filter elements; permeate conductivity is less than feed conductivity; pressure drop across one or more water filter elements is less than or equal to the difference between feed pressure and concentrate pressure; and / or the osmotic pressure of the feed flow is less than the feed pressure.

[0025] In some embodiments, the processing device can be configured to identify and remove statistical outlier data points from past performance data before identifying a cleaning event. In such an embodiment, identifying and removing statistical outlier data points from past performance data includes: calculating data points (y... t ) relative to the previous data point (y t-1 The percentage change of y; calculate the next data point (y t+1 ) relative to data point (y tThe percentage change of y; comparing the previous percentage change with the fall limit; and if the percentage change exceeds the fall limit, resetting the data point (y t It was identified as an outlier.

[0026] In some embodiments, identifying cleaning events may include applying differential series analysis to standardized pressure drop (dP) and standardized permeate flow rate (Pf) in past performance data. Applying differential series analysis may include the following steps: (i) calculating data points (y t ) and the previous data point (y t-1 (ii) Calculate the mean and standard deviation of the difference series of the normalized pressure drop (dP) and normalized product flow (Pf); (iii) Compare each value in the difference series of the normalized pressure drop (dP) and normalized product flow (Pf) with the sum of the products of the corresponding difference series and the difference constant and the corresponding standard deviation of the difference series; (iv) Determine if there are gaps in the dataset; and (v) Determine if the gaps are greater than the CIP reference time.

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

[0028] In some embodiments, past performance data may include pressure drop, salt permeability, and permeate flow rate for each of one or more water filtration elements. If no changes in pressure drop, salt permeability, and permeate flow rate are detected, the treatment device may identify the fouling type as a foul-free condition. If the increase in pressure drop follows a second-order polynomial function, the treatment device may identify the fouling type as biological fouling. In the case of some biological fouling, salt permeability may increase, while permeate flow rate may decrease. If the decrease in salt permeability follows a second-order polynomial function, the treatment device may identify the fouling type as organic fouling. In the case of some organic fouling, pressure drop may not change, while salt permeability may decrease. Elements at the head position (e.g., such as...) Figure 19If the pressure drop of the front-end filter element (in the process of adding a filter) increases sharply according to a first-order polynomial function, the treatment equipment can identify the fouling type as particulate fouling. In some cases of particulate fouling, the salt permeability may increase, while the permeate flow rate may decrease. In some cases, this effect is mainly present in the front-end elements. Elements at the tail end (e.g., such as...) Figure 19 When the gradual increase in pressure drop across the tail-end filter element conforms to a first-order polynomial function, the treatment equipment can identify the fouling type as scaling. In some scaling cases, salt permeate may increase, while permeate flow rate may decrease. In some cases, this effect is primarily present in the tail-end element. When both the increase in permeate flow rate and the increase in salt permeate conform to a first-order polynomial function, the treatment equipment can identify the fouling type as an integrity membrane damage event. In some oxidation or membrane damage events, the pressure drop may not change.

[0029] In some embodiments, the processing apparatus may be configured to: receive current performance data of one or more water filtration elements received from one or more sensors as input (e.g., multiple sensors may be installed in the same(s) filter element(s) and / or these sensors may be installed in multiple filter elements within the apparatus to provide a more comprehensive fouling diagnosis); analyze the current performance data based on prior analysis of past performance data and identification of the type of fouling occurring in each period of individual data segments; estimate the current type of fouling occurring at the water filtration elements; and / or output recommendations for cleaning procedures specific to the current type of fouling occurring at the water filtration elements. Data collected from sensors may be filter element-specific to identify whether certain conditions are occurring at the front or rear of the pressure vessel, thereby aiding in the estimation of the type of fouling occurring. In some embodiments, current performance data and / or past performance data may be used to predict potential future fouling (e.g., based on the fouling recurrence cycle during a specific time period of the year and / or based on environmental conditions).

[0030] According to embodiments of this disclosure, an exemplary method for determining the state of a filter is provided. The method includes receiving past performance data of one or more water filter 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 past performance data and a processing device communicating with the database. The method includes identifying one or more data points within the past performance data that indicate cleaning events of one or more water filter elements. The method includes dividing the past performance data into separate data segments, each of which represents data between corresponding identified cleaning events in the past performance data. The method includes fitting a mathematical function to each of the separate data segments. The method includes identifying the type of fouling that occurred during each of the separate data segments based on the mathematical function fitted to the respective separate data segment.

[0031] According to embodiments of this disclosure, an exemplary non-transitory computer-readable medium is provided that stores instructions executable by a processing device for determining filter status. The processing device executes these instructions to receive past performance data of one or more water filter elements as input to a system for determining filter status. The system for determining filter status includes a database configured to electronically store the past performance data and a processing device in communication with the database. The processing device executes these instructions to identify one or more data points within the past performance data that indicate cleaning events of one or more water filter elements. This can be used to divide the past performance data into separate data segments, each of which represents data between corresponding identified cleaning events in the past performance data. The processing device executes these instructions to fit a mathematical function to each of these separate data segments. The processing device executes these instructions to identify the type of fouling that occurred during each of these separate data segments based on the mathematical function fitted to the corresponding separate data segment.

[0032] Any combination and / or arrangement of the embodiments is conceivable. Other objects and features will become apparent from the following detailed description, taken in conjunction with the accompanying drawings. However, it should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of this disclosure. Attached Figure Description

[0033] To assist those skilled in the art in creating and using a system for determining filter status, please refer to the accompanying drawings, in which:

[0034] Figure 1 This is a schematic diagram of a traditional spiral wound filter element;

[0035] Figure 2This is a schematic diagram of a portion of the feed screen of a filter element, showing the thinning of the filaments and several geometric relationships;

[0036] Figure 3 This is a schematic diagram of the separation that occurs in a spiral wound reverse osmosis or nanofiltration element;

[0037] Figure 4 This is a block diagram of an exemplary system for determining filter status according to the present disclosure;

[0038] Figure 5 This is a block diagram of an exemplary computing device for implementing an exemplary system for determining filter status according to the present disclosure;

[0039] Figure 6 This is a block diagram of an exemplary system for determining the state environment of a filter according to the present disclosure;

[0040] Figure 7A and Figure 7B It is a graph of outlier identification performed by an exemplary system for determining filter status, wherein Figure 7A Including outliers, and Figure 7B Excluding outliers;

[0041] Figures 8A to 8C This demonstrates the ideal pressure drop (dP) of a reverse osmosis or nanofiltration element during operation. Figure 8A ), expected pressure reduction ( Figure 8B ) and observed pressure drop ( Figure 8C A graph showing how the curve changes over time;

[0042] Figure 9 It is a chart that displays the CIP events of the dataset;

[0043] Figure 10 It is a graph showing the unrecovered dP and the initiated dP of the dataset;

[0044] Figure 11 It is a graph that shows the cleanability of the dataset compared to its initial cleanability;

[0045] Figure 12 This is a table of fouling types and key factors based on standardized pressure drop, standardized permeate flow rate, and standardized salt permeability;

[0046] Figures 13A to 13F are charts showing the analysis of the datasets for pressure drop, permeate flow rate, and salt permeability. The specific results indicate the specific fouling types, which include no fouling (Figure 13A), biological fouling (Figure 13B), organic fouling (Figure 13C), particulate fouling (Figure 13D), scaling (Figure 13E), and oxidation or integrity damage (Figure 13F).

[0047] Figure 14 It is a chart showing biofouling identified based on a dataset;

[0048] Figure 15 It is a chart showing organic dirt identified based on a dataset;

[0049] Figure 16 It is a chart showing the identified organic dirt and the biofouling on the organic dirt;

[0050] Figure 17 It is a chart showing the identified organic dirt and the biofouling on the organic dirt;

[0051] Figure 18 It displays charts showing identified organic fouling, particulate fouling, biofouling, and CIP events; and

[0052] Figure 19 This is a schematic diagram of filter elements arranged in series, where water flows through the filter elements from the front end to the back end. Detailed Implementation

[0053] The exemplary system discussed in this article for determining filter condition is capable of accurately monitoring, analyzing, and identifying the types of fouling / scaling that occur in the filter elements of a water treatment facility. This system can be used to determine the types of fouling / scaling that occur and can provide operators with recommendations on when system cleaning should be performed to ensure optimal operation. By determining the types of fouling / scaling that occur, the system can provide recommendations on the type of cleaning to be performed and the chemicals to be used, thus providing accurate guidance for effective cleaning to ensure improved operation of the water treatment facility after cleaning.

[0054] Figure 2 This is a schematic diagram of a portion of the feed mesh 4 of the filter element, showing the thinning of the filaments and several geometric relationships. The feed mesh 4 is a nonwoven polymer web formed by a first set of substantially parallel filaments 34 and a second set of substantially parallel filaments 36 intersecting at angles 38° and 40°. These two sets of filaments 34 and 36 are fixed to each other at the intersection point 42. These two sets of intersecting substantially parallel filaments 34 and 36 form a parallelogram 44 (composed of...) Figure 2 The parallelogram is a two-dimensional array (shown by the dashed lines in the diagram), with side lengths defining the grid dimensions 46 and 48. Except when the two sets of filaments 34 and 36 are perpendicular to each other, the parallelogram has both acute angle 38 and obtuse angle 40. The acute angle 38 is bisected by a line 50 drawn substantially parallel to the flow direction 30. The angles at which filaments 34 and 36 intersect the flow direction 30 are called their transverse angles 52 and 54. These filaments have a certain spacing 46 and 48, and each filament has a width of 62 and 64.

[0055] Figure 3This is a schematic diagram of the separation occurring in a spiral wound reverse osmosis or nanofiltration element 70. A concentrated feed solution 72 can pass between two or more membranes 74, causing the concentrate (including waste or byproducts 78) to be directed in one direction, and a dilute solution 76 (e.g., permeate flow rate or product) to pass through the membranes 74 and exit the filtration system. Therefore, the semi-permeable membranes 74 allow water and small amounts of dissolved salt to pass through. The operational objectives of the water filtration system include maximizing the permeate flow rate (Pf), minimizing the salt permeability (Sp), and minimizing the pressure drop (dP). Feed pressure, feed temperature, and feed water quality (dissolved solids content) affect system operation.

[0056] This exemplary system can be used to identify the types of failure modes (e.g., fouling, scaling, membrane failure, or combinations thereof) of filtration modules in nanofiltration and / or reverse osmosis systems. The system can assist operators in improving the performance of water treatment systems by performing more detailed analysis of past performance. In some embodiments, the system can be used to predict when the next cleaning should be performed and recommend the most suitable cleaning procedure.

[0057] Advantageously, this system does not require additional external equipment specifically designed to identify fouling types. Instead, it relies on past system performance and Clean-in-Place (CIP) events to determine the types of fouling that have occurred / are occurring and the optimal cleaning method for addressing the fouling issue. The system can be used with any water type and does not require a special water treatment application. It can be used to identify time periods between cleanings (e.g., between CIP events) and analyze these periods to assess fouling types and cleaning recommendations. Based on this data, the system can help predict when the next cleaning should be performed and the most appropriate type of cleaning. Therefore, the system can operate in a highly automated and independent manner, enabling water treatment facilities to perform similar operations. As discussed herein, the system can utilize the first and second slopes of the evolution of pressure drop, permeate flow rate (net drive pressure), and water quality (conductivity), where this data evolution is normalized by temperature.

[0058] Therefore, this exemplary system can be used to identify the type of fouling occurring in filtration systems and / or components without adding any additional sensors or devices to the filtration system, thus simplifying overall use and reducing system operating costs. The system initially collects performance data associated with the filtration system, including, for example, differential pressure, permeate flow rate, and salt permeability. The system normalizes the data to startup conditions to obtain normalized pressure drop, normalized permeate flow rate, and normalized salt permeability, and stores these in the system electronically. Data normalization can be performed through industry procedures. (See, for example, FilmTec) ™Reverse Osmosis Membrane Technology Handbook, Water Solutions, DuPont, Table 27. Designequations for projecting RO system performance: Individual element performance, Table No. 45-D01504-en, Revision 13, page 110 (October 2022). Temperature can be sensed and recorded to standardize the data. The system automatically removes inconsistent data (e.g., feed flow rates less than the concentrate flow rate) and statistical outliers.

[0059] Once the data is standardized and inconsistencies are removed, the system can identify membrane cleaning events (CIPs). CIP identification can be performed by: generating difference sequences of dP and flow rate (differences between data points at time t and t-1); identifying the mean and standard deviation of the difference sequences; and identifying dP or flow rate differences that are below or above K. Data points with a standard deviation threshold; and to confirm whether there are gaps in the data greater than a given threshold (e.g., 1 day). As used herein, the term "difference series" refers to the creation of a series and can generally be described as taking the difference between consecutive occurrences of a time series. x t = x t – x t-1 , making x t It has a constant mean and variance and can therefore be considered a stationary series. (See, for example, Pal, A. et al., Practical Time Series Analysis: Master Time Series Data Processing, Visualization, UK: Packt Publishing (2017).) This approach can also identify plant shutdowns and restarts. In some cases, the system can be used to distinguish between CIP and plant shutdown-restart. In some embodiments, the system can use the lack of change in dP, flow rate, and / or salt permeability to indicate plant shutdown without considering the effects of CIP. In some embodiments, the system's detection of changes in temperature, pH, and / or flow rate can be correlated with CIP patterns compared to plant shutdown / restart.

[0060] This system can segment data between cleaning cycles (CIPs) and analyze each dataset independently between cleaning sessions. Once within a cleaning cycle and once the type of fouling is identified, a fitted equation programmed into the system can be used to predict the timing of the next cleaning. After identifying the next cleaning, the most suitable cleaning type is suggested. For biofouling, organic fouling, and particulate fouling, a conventional alkaline cleaning can be suggested. For scaling, an acidic cleaning can be suggested. Specifically, for biofouling, the acceleration of biofouling can be estimated using the second derivative of the slopes obtained from the previous and current periods (e.g., by analyzing the rate required for the next CIP). This acceleration can be calculated to more accurately predict the timing of the next cleaning due to biofouling, as the time between cleaning sessions shortens once biofouling is present. If the system detects and identifies a combination of fouling types, a comprehensive cleaning can be suggested, including an alkaline cleaning followed by an acidic cleaning. The system is capable of operating autonomously and provides recommendations for any identified dirt issues, enabling it to guide users on corrective actions to be taken, and allowing users to decide whether the system should implement these corrective actions autonomously.

[0061] Therefore, the system performs data collection and analysis on the past performance of the water treatment system, standardizes the data, removes outliers and checks data consistency, identifies CIPs (Constant Incidence Points), performs first- and second-order polynomial regression analysis and their coefficients of determination, applies programming logic to identify fouling / failure types, uses previous information to predict the next fouling type, and constructs an adaptive system that incorporates fouling considerations. The system may include artificial intelligence and / or machine learning capabilities to improve the identification of fouling types and / or the predictability of fouling events. The input to the artificial intelligence and machine learning capabilities can and preferably is based on feedback from the operator.

[0062] Figure 4 This is a block diagram of an exemplary system 100 (hereinafter referred to as "System 100") for determining the status of a filter. System 100 generally includes one or more water treatment facilities 102, which include one or more filter elements 104. The filter elements 104 may be arranged in series back-to-back within a pressure vessel (e.g., Figure 19The pressure vessel comprises filter elements 400 to 410, allowing water to flow into the inlet at the front filter element 400, sequentially through each of the filter elements 400 to 410, and then out from the rear filter element 410. Generally, particulate matter, biological fouling, and / or integrity failure typically occur in filter elements at or near the front end, scaling and / or integrity failure occur in filter elements at or near the rear end, while organic fouling can occur at any filter element. In some embodiments, the pressure vessel may accommodate 6 to 8 filter elements in series. Influent may be injected into the pressure vessel at the front end, where the filter element at the front end (e.g., the filter element at the head position) is the first to come into contact with the influent. The filter element furthest from the pressure vessel inlet defines the filter element at the tail position. Data captured for the filter elements within the pressure vessel can be filter element-specific and can identify and differentiate between data at the front and tail ends of the pressure vessel to achieve an accurate estimation of the fouling type.

[0063] System 100 includes sensors 106 installed within a water treatment facility 102 for detecting conditions associated with the filtration process, which system 100 can use to identify the type of fouling. In some embodiments, sensors 106 may be used to detect, for example, pressure drop across each respective filter element 104, permeate flow rate (net drive pressure) through each respective filter element 104, water quality (conductivity) relative to each filter element 104, and temperature of the water passing through the filter element 104. In some embodiments, the collected data may be specific to each of the filter elements 104 (e.g., where each filter element 104 is associated with at least one sensor 106) to provide a more detailed diagnosis of system 100. As an example, smart sensors 106 may be incorporated into system 100 to determine whether an increase in dP is more significant for upstream elements (indicating particulate fouling) or for downstream elements (indicating scaling). In some embodiments, the collected data may be for the entire filtration system (e.g., where one or more sensors 106 are installed at specific locations(s) of system 100). Sensor 106 communicates electronically with the central computing system 122 and / or processing device 124 of system 100 in order to use the collected data to determine the type of dirt and recommend cleaning.

[0064] System 100 includes one or more databases 108 for electronically storing data associated with the operation of facility 102 and system 100. Data can be electronically transmitted to and / or from database 108 via communication interface 110 of system 100. Database 108 may include past performance data 112 (e.g., historical data), which includes information related to, for example, measurement or detection conditions received from sensor 106, cleaning schedules and activities, facility shutdown events, (multiple) filter element replacements, changes in influent water source, etc. Database 108 may include current performance data 114, which includes, for example, measurement or detection conditions received from sensor 106 in real-time or near real-time.

[0065] System 100 may include one or more users and / or user devices 116 communicating with system 100 via communication interface 110. Users and / or user devices 116 may be, for example, operators of facility 102, individuals responsible for scheduling cleaning events, etc. Users 116 may electronically send data to or receive data from the system via user interface 118, which in some embodiments may have a graphical user interface (GUI) 120. GUI 120 may be a display incorporated in user device 116 to allow users 116 to communicate with each other and / or with system 100 via communication interface 110.

[0066] System 100 may include a central computing system 122 that communicates with each of the users 116 (e.g., via their user equipment) 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, thereby allowing components of system 100 to electronically send and / or receive data. System 100 may include at least one processing device 124 having a processor 126 for receiving and processing data stored in system 100.

[0067] During operation, system 100 can initially receive past performance data 112 as input at the standardization module 128, and system 100 can execute the standardization module 128 to output standardized data 130 based on temperature. Next, the system executes the processing module 132 to detect and remove outliers in the standardized data 130, and outputs cleaned data 134 for further processing. System 100 can execute the Clean In-Place (CIP) module 136 to analyze the cleaned data 134, thereby identifying and marking clean in-place events 138. This can be achieved by: generating a difference series of dP and permeate flow rate (the difference between data points at time t and t-1); identifying the mean and standard deviation of the difference series; and identifying differences in dP or flow rate that are below or above K. The system 100 identifies data points with a standard deviation threshold and checks for gaps in the data that exceed a given threshold (e.g., 1 day). If a gap exists in the data that exceeds the given threshold, the system 100 can identify that point as a CIP event 138.

[0068] System 100 segments the data between each identified CIP event 138 to independently analyze each dataset between cleaning sessions. Specifically, it should be understood that as the usage period of filter element 104 extends, the baseline associated with the operation of facility 102 and / or filter element 104 may change. For example, the performance baseline of a new filter element 104 will differ from that of a filter element that has been running for 6 months and cleaned multiple times. Therefore, System 100 segments the data and independently analyzes the database between each cleaning session to ensure accurate identification and prediction of dirt types.

[0069] System 100 executes the fouling identification module 140 for each of the operation-related datasets between corresponding CIP events 138 to determine the type of fouling that occurred during the operation of each dataset. System 100 fits each data segment to a mathematical function, preferably to first- and second-order polynomials. System 100 analyzes the first- and second-order slopes of the normalized pressure drop, normalized permeate flow rate, and normalized salt permeability. If all slopes are close to zero, system 100 determines that facility 102 should continue to operate normally (e.g., either no action is taken, or system 100 issues a notification via graphical user interface 120 indicating that no fouling type has been detected and cleaning is not required). For example, when reviewing past performance data 112, system 100 may determine that facility 102 should continue to operate normally without any detected fouling and without the need for cleaning. When reviewing current performance data 114, system 100 may determine that facility 102 should operate normally because no fouling has occurred and cleaning is not required.

[0070] If the increase in pressure drop over time conforms well to a second-order polynomial equation, then system 100 can conclude that biofouling may have occurred. A typical characteristic of isolated biofouling (without interference from other types of fouling) is that the normalized pressure drop (dP) is initially flat, then increases in a second-order polynomial manner as biofouling begins to form on the membrane. Biofouling is typically more pronounced on upstream elements. Generally, as dP increases, the net drive pressure decreases, and therefore the normalized permeate flow rate decreases over time (also in a second-order polynomial manner). Due to concentration polarization caused by the biofilm, the desalination rate can remain stable or worsen (leading to increased salt permeability). For example, when reviewing past performance data 112, system 100 can determine that biofouling occurred during that dataset and that corresponding cleaning should be performed. When reviewing current performance data 114, system 100 can determine that biofouling is occurring and appropriate cleaning is required.

[0071] In some embodiments, the system 100 may identify a filter module failure mode in a data segment as biofouling if at least one of the following conditions is met: (a) the coefficient of determination of dP relative to a first-order polynomial is greater than 0.4; (b) the coefficient of determination of dP relative to a second-order polynomial is greater than 0.7; (c) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial is greater than 0.3; (d) the coefficient of determination of Pf relative to a first-order polynomial is greater than 0.4; (e) the coefficient of determination of Pf relative to a second-order polynomial is greater than 0.7; (f) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial is greater than 0.3; (g) the coefficient of determination of Sp relative to a first-order polynomial is greater than 0.4; (h) the coefficient of determination of Sp relative to a second-order polynomial is greater than 0.7; (i) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial is greater than 0.3; (j) dP increases over time in the data segment; (k) Pf decreases over time in the data segment; and / or (l) Sp increases over time in the data segment. In some embodiments, if at least one of the dP conditions is met, it can be identified as biofouling, where Pf and Sp provide auxiliary (optional) support for identification.

[0072] If the decrease in standardized permeate flow rate over time conforms well to a second-order polynomial equation, then system 100 can conclude that organic fouling may have occurred. Typical characteristics of isolated organic fouling (without interference from other types of fouling) are: the standardized permeate flow rate decreases because organic matter rapidly deposits on the original membrane, but after a period of operation, the flow rate tends to plateau because the amount of organic matter deposited on the membrane equals the amount of organic matter removed due to the cross-flow filtration mechanism. Typically, under a pure organic fouling mechanism, the standardized pressure drop remains flat, and there is no bacterial growth that clogs the feed concentrate membrane channels. Salt permeability typically decreases because the organic matter deposited on the membrane creates “additional” thickness and resistance, which usually increases the membrane’s salt permeability over time. For example, when reviewing past performance data 112, system 100 can determine that organic fouling occurred during that dataset and that corresponding cleaning should be performed. When reviewing current performance data 114, system 100 can determine that organic fouling is occurring and appropriate cleaning is required.

[0073] In some embodiments, the system 100 may identify a filter module failure mode in a data segment as organic fouling if at least one of the following conditions is met: (a) the coefficient of determination of Pf relative to a first-order polynomial is greater than 0.4; (b) the coefficient of determination of Pf relative to a second-order polynomial is greater than 0.7; (c) the difference between the coefficients of determination of the second-order polynomial fitted to Pf and the first-order polynomial is greater than 0.3; (d) the coefficient of determination of Sp relative to a first-order polynomial is greater than 0.4; (e) the coefficient of determination of Sp relative to a second-order polynomial is greater than 0.7; (f) the difference between the coefficients of determination of the second-order polynomial fitted to Sp and the first-order polynomial is greater than 0.3; (g) the coefficient of determination of dP relative to a first-order polynomial is greater than 0.7; (h) the coefficient of determination of dP relative to a second-order polynomial is greater than 0.7; (i) the difference between the coefficients of determination of the second-order polynomial fitted to dP and the first-order polynomial is less than 0.3; (j) dP remains constant over time in the data segment; (k) Pf decreases over time in the data segment; and / or (l) Sp decreases over time. In some embodiments, if at least one of the Pf conditions is met, it can be identified as organic fouling, wherein dP and Sp provide auxiliary (optional) support for identification.

[0074] If the increase in normalized pressure drop conforms more to a first-order polynomial, then system 100 can conclude that either scaling or particulate fouling is occurring. Scaling is generally associated with a lower rate of pressure drop increase compared to particulate fouling because scaling deposits typically require a longer time to crystallize and form. Particulate fouling, on the other hand, is generally a faster process, for example, when ultrafiltration becomes fouled and an increase in transmembrane pressure is observed between backwash cycles. Scaling often occurs with or in conjunction with an increase in salt permeability over time because the scale deposited on the membrane increases concentration polarization at the membrane boundary layer. This may be associated with a decrease in normalized permeate flow rate over time, as the osmotic pressure increases accordingly. Particulate fouling occurs when particulate matter clogs the membrane, and this leads to a decrease in normalized permeate flow rate as the net drive pressure decreases over time. For example, when reviewing past performance data 112, system 100 can determine that scaling or particulate fouling occurred during that dataset and that corresponding cleaning should be performed. When reviewing the current performance data 114, system 100 can determine that scaling or particulate fouling is occurring and that appropriate cleaning is required.

[0075] In some embodiments, the system 100 may identify a filter module failure mode in a data segment as fouling if at least one of the following conditions is met: (a) the coefficient of determination of dP relative to a first-order polynomial is greater than 0.7; (b) the coefficient of determination of dP relative to a second-order polynomial is greater than 0.7; (c) the difference between the coefficients of determination of the second-order polynomial fitted to dP and the first-order polynomial is less than 0.3; (d) the coefficient of determination of Sp relative to a first-order polynomial is greater than 0.7; (e) the coefficient of determination of Sp relative to a second-order polynomial is greater than 0.7; (f) the difference between the coefficients of determination of the second-order polynomial fitted to Sp and the first-order polynomial is less than 0.3; (g) the coefficient of determination of Pf relative to a first-order polynomial is greater than 0.7; (h) the coefficient of determination of Pf relative to a second-order polynomial is greater than 0.7; (i) the difference between the coefficients of determination of the second-order polynomial fitted to Pf and the first-order polynomial is less than 0.3; (j) dP increases over time in the data segment, preferably in the tail element; (k) Pf decreases over time in the data segment; and / or (l) Sp increases over time in the data segment. In some embodiments, scaling can be identified if at least one of the dP conditions is met and the dP condition distribution in the system (preferably dP increases in the tail element), wherein Pf and Sp provide auxiliary (optional) support for identification.

[0076] In some embodiments, the system 100 may identify a filter module failure mode in a data segment as particulate fouling if at least one of the following conditions is met: (a) the coefficient of determination of dP relative to a first-order polynomial is greater than 0.7; (b) the coefficient of determination of dP relative to a second-order polynomial is greater than 0.7; (c) the difference between the coefficients of determination of the second-order polynomial fitted to dP and the first-order polynomial is less than 0.3; (d) the coefficient of determination of Pf relative to a first-order polynomial is greater than 0.7; (e) the coefficient of determination of Pf relative to a second-order polynomial is greater than 0.7; (f) the difference between the coefficients of determination of the second-order polynomial fitted to Pf and the first-order polynomial is less than 0.3; (g) the coefficient of determination of Sp relative to a first-order polynomial is greater than 0.7; (h) the coefficient of determination of Sp relative to a second-order polynomial is greater than 0.7; (i) the difference between the coefficients of determination of the second-order polynomial fitted to Sp and the first-order polynomial is less than 0.3; (j) dP increases over time in the data segment, preferably in the front element; (k) Pf decreases over time in the data segment; and / or (l) Sp increases over time in the data segment, preferably in the tail element. In some embodiments, if at least one of the dP conditions is met and the dP condition distribution in the system (preferably dP increases in the front element) is met, it can be identified as particulate fouling, wherein Pf and Sp provide auxiliary (optional) support for identification.

[0077] If the increase in standardized permeate flow rate conforms to a first-order polynomial, system 100 can conclude that a potential problem related to membrane integrity may have occurred (such as chemical degradation or halogenation of the membrane, or a problem with the physical integrity of the membrane element). Membrane integrity failure typically leads to an increase in salt permeability over time. For example, when reviewing past performance data 112, system 100 can determine that a potential problem related to membrane integrity has occurred and appropriate measures should be taken. When reviewing current performance data 114, system 100 can determine that a membrane integrity problem may have occurred and appropriate measures should be taken.

[0078] In some embodiments, the system 100 may identify a filter module failure mode in a data segment as a membrane integrity failure if at least one of the following conditions is met: (a) the coefficient of determination of Pf relative to a first-order polynomial is greater than 0.7; (b) the coefficient of determination of Pf relative to a second-order polynomial is greater than 0.7; (c) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial fitted to Pf is less than 0.3; (d) the coefficient of determination of Sp relative to a first-order polynomial is greater than 0.7; (e) the coefficient of determination of Sp relative to a second-order polynomial is greater than 0.7; (f) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial fitted to Sp is less than 0.3; (g) the coefficient of determination of dP relative to a first-order polynomial is greater than 0.7; (h) the coefficient of determination of dP relative to a second-order polynomial is greater than 0.7; (i) the difference between the coefficients of determination of the second-order polynomial and the first-order polynomial fitted to dP is less than 0.3; (j) dP remains constant over time in the data segment; (k) Pf increases over time in the data segment; and / or (l) Sp increases over time in the data segment. In some embodiments, membrane integrity failure can be identified based on the simultaneous increase in permeate flow rate and salt permeability, wherein dP provides auxiliary (optional) support for identification.

[0079] If system 100 concludes that the data indicates a specific type of fouling event, system 100 can output a notification via graphical user interface 120, including the detected fouling event, supporting data, and recommendations for cleaning strategies to resolve the fouling problem. If multiple fouling types are detected simultaneously based on previous analysis, such as organic fouling occurring first and then biological fouling occurring within the same period or dataset, a combined cleaning strategy is required, and system 100 can provide recommendations on how to implement the combined cleaning strategy. Therefore, past performance data can be used to identify different types of fouling and / or combinations of fouling that may occur based on the performance of facility 102, and the correlation of this fouling determination is stored electronically as fouling type data 142.

[0080] In some embodiments, dirt type data 142 and past performance data 112 can be used to evaluate current performance data 114 to detect one or more dirt types occurring at facility 102 and provide recommendations for cleaning operations. In some embodiments, dirt type data 142 and past performance data 112 can be used to evaluate current performance data 114 and predict potential dirt that may occur. For example, system 100 can execute prediction module 144 to receive current performance data 114 as input and use estimates of dirt types that may occur in the near future to predict the operating trajectory of facility 102. In some embodiments, system 100 can execute prediction module 144 to receive past performance data 112 as input and estimate when a specific type of dirt may occur at facility 102, such as a recurring pattern of a specific dirt type at the beginning of each summer or a specific month. In this case, system 100 can provide user 116 with notification of potential dirt types that may occur within a specific time window, allowing user 116 to plan cleaning operations in advance. Therefore, system 100 can provide accurate identification of (multiple) types of dirt and recommend dirt-type-specific cleaning procedures that focus on addressing the actual problems that occur in facility 102, thereby ensuring that filter element 104 is properly cleaned and extending the overall lifespan of the element 104.

[0081] Figure 5This is a block diagram of a computing device 200 according to exemplary embodiments of the present disclosure. The computing device 200 includes one or more non-transitory computer-readable media for storing one or more computer-executable instructions or software for implementing exemplary embodiments of the present disclosure. The non-transitory computer-readable media may include, but is not limited to, one or more types of hardware memory, non-transitory tangible media (e.g., one or more magnetic storage disks, one or more optical disks, one or more flash drives), etc. For example, the memory 206 included in the computing device 200 may store computer-readable and computer-executable instructions or software for implementing exemplary embodiments of the present disclosure (e.g., instructions for operating a standardization module, instructions for operating a cleaning module, instructions for operating a CIP module, instructions for operating a dirt identification module, instructions for operating a prediction module, instructions for operating a processing device, instructions for operating a communication interface, instructions for operating a user interface, instructions for operating a central computing system, combinations thereof, etc.). The computing device 200 also includes a configurable and / or programmable processor 202 and an associated core 204, and optionally one or more additional configurable and / or programmable processors 202' and (multiple) associated cores 204' (e.g., in the case of a computer system having multiple processors / cores), for executing computer-readable and computer-executable instructions or software stored in memory 206 and other programs for controlling system hardware. Processor 202 and (multiple) processors 202' may each be a single-core processor or a multi-core (204 and 204') processor.

[0082] Virtualization can be employed in computing device 200, enabling dynamic sharing of infrastructure and resources within computing device 200. Virtual machines 214 can be provided to handle processes running on multiple processors, making the process appear to use only one computing resource instead of multiple computing resources. Multiple virtual machines can also be used with a single processor. Memory 206 can include computer system memory or random access memory, such as DRAM, SRAM, EDO RAM, etc. Memory 206 can also include other types of memory or combinations thereof.

[0083] Users can interact with computing device 200 through 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) provided according to exemplary embodiments. Computing device 200 may include other I / O devices for receiving input from the user, such as a camera, keyboard, microphone, or any suitable multi-touch interface 208, pointing device 210 (e.g., a mouse). Keyboard 208 and pointing device 210 may be coupled to visual display device 218. Computing device 200 may include other suitable conventional I / O peripherals.

[0084] The computing device 200 may also include at least one storage device 224, such as a hard disk 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 for implementing exemplary embodiments of the system described herein. The exemplary storage device 224 may also store at least one database 226 for storing any suitable information required for implementing exemplary embodiments. For example, the exemplary storage device 224 may store at least one database 226 for storing information such as data relating to past performance data, current performance data, normalized data, cleaned data, CIP events, dirt type data, combinations thereof, etc., as well as computer-readable instructions and / or software for implementing exemplary embodiments described herein. The database 226 may be updated manually or automatically at any suitable time to add, delete, and / or update one or more items in the database.

[0085] Computing device 200 may include a network interface 212 configured to interface with one or more networks (e.g., local area network (LAN), wide area network (WAN), or the Internet) via at least one network device 222 through various connections, including but not limited to standard telephone lines, LAN or WAN links (e.g., 802.11, T1, T3, 56kb, X.25), broadband connections (e.g., ISDN, Frame Relay, ATM), wireless connections, controller area networks (CAN), or some combination of any or all of the foregoing. Network interface 212 may include a built-in network adapter, network interface card, PCMCIA network card, PaCI / PCIe network adapter, SD adapter, Bluetooth adapter, card bus network adapter, wireless network adapter, USB network adapter, modem, or any other device suitable for connecting the interface of computing device 200 to any type of network capable of communicating and performing the operations described herein. Furthermore, computing device 200 can be any computer system, such as a workstation, desktop computer, server, laptop computer, handheld computer, tablet computer (e.g., tablet computer), mobile computing or communication device (e.g., smartphone communication device), embedded computing platform, or other form of computing or telecommunications device capable of communicating and having sufficient processor power and memory capacity to perform the operations described herein.

[0086] Computing device 200 can run any operating system 216, such as any version of the Microsoft® Windows® operating system, different versions of 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 proprietary operating system, or any other operating system capable of running on a computing device and performing the operations described herein. In an exemplary embodiment, operating system 216 can run in native mode or emulation mode. In an exemplary embodiment, operating system 216 can run on one or more cloud machine instances.

[0087] Figure 6This is a block diagram of an exemplary system environment 300 for determining filter status according to exemplary embodiments of the present disclosure. Environment 300 may include servers 302, 304 configured to communicate via a communication platform 324 with 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. The communication platform may be any network through which information can be transmitted between devices communicatively 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.

[0088] Environment 300 may include storage facilities or databases 320, 322, which can communicate with servers 302, 304, water treatment facility 306, sensors 308, system 310, at least one processing device 312, at least one user interface 314, and central computing system 318 via communication platform 324. In an exemplary embodiment, servers 302, 304, water treatment facility 306, sensors 308, system 310, at least one processing device 312, at least one user interface 314, and 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 may be incorporated into at least one of servers 302, 304. In some embodiments, databases 320, 322 may store data related to past performance data, current performance data, standardized data, cleaned data, CIP events, dirt type data, combinations thereof, etc., and such data may be distributed across multiple databases 320, 322.

[0089] As discussed above, the exemplary system collects past performance data, standardizes the data, cleans the data to remove outliers and achieve data consistency, identifies CIPs (Contamination Indicators), performs first- and second-order polynomial regressions and determination coefficients, applies logic to identify fouling / failure types, and uses previous information to predict the next fouling type, forming an (optional) adaptive system that incorporates fouling considerations. In some embodiments, data smoothing may be performed after the data cleansing step. In some embodiments, three different methods may be used to remove outliers, such as removing data points that undergo abrupt changes, manual methods, and kernel smoothing, or combinations thereof. In some embodiments, the system may perform a cleanability calculation to determine when a cleaning procedure should be performed based on current performance data and the curve / direction of the data.

[0090] For the cleaning or outlier removal steps, the system can implement the method proposed by Wenyu, segmented kernel smoothing, or a combination thereof. Consistency checks may include the following attributes: feed pressure greater than concentrate pressure; feed pressure greater than permeate pressure; feed flow rate greater than concentrate flow rate; feed flow rate greater than permeate flow rate; and feed pressure greater than the pressure change (dP). Figure 7A and Figure 7B This is a graph showing the outlier identification performed by the system using the methods discussed, where Figure 7A Including outliers, and Figure 7B Excluding outliers. In this approach, outliers typically arise from process disturbances, measurement errors, etc. Outliers can lead to excessive false positive CIPs and process stoppage identification / indication. Wenyu's proposed method is based on Equation 1 below.

[0091] (1)

[0092] The system initially calculates the data points (y). t ) relative to the previous data point (y t-1 The percentage change of ) is expressed in Equation 1 as % t Then, the system calculates the next data point (y). t+1 ) relative to the previous data point (y t The percentage change is expressed as % t+1 .if % t Greater than or equal to the descent limit (DL) and % t+1 Less than or equal to –DL, or % t Less than or equal to -DL and % t+1 If it is greater than or equal to DL, then point y t These are identified as outliers. This process is repeated until all outliers have been identified and removed from the dataset. Figure 7A In the diagram, the circled points indicate examples of outliers that should be removed from the dataset (these outliers are in...). Figure 7B (Removed from the original text). The system uses this method to look for combinations of sudden drops-rises or sudden rises-drops. y refers to any Key Performance Indicator (KPI). It has been found that 1% DL is sufficient, but users may change the DL. Identifying outliers helps detect process anomalies and ensures that all further process data are free of false positive CIPs or process stop indications.

[0093] In some embodiments, the system can perform outlier identification based on piecewise kernel smoothing. In such embodiments, the entire data is divided into different segments, e.g., fragments. If the time interval between two fragments is greater than one (1) day, a kernel smoother (e.g., a locally weighted scatter plot smoother or LOWESS) is developed for each fragment. The kernel smoother generates curves by iteratively taking locally weighted fits of a simple curve to the sample points in the domain. The default settings in the system are linear (Lambda), cubic (weighting function), 0.5 (alpha), and 0 (sample increment). The system can automatically identify the optimal alpha value based on the data. In some embodiments, JMP can be used. ™ Nuclear smoothing.

[0094] After cleaning the dataset, System 100 can review and analyze the data to identify CIP events. System 100 can identify when a CIP event begins and ends, segmenting the data around the CIP event for further processing to identify the type of fouling that occurred between CIP events. Generally, CIP events are work done to “reset” or improve the water treatment process. CIP events also represent lost production time and chemical costs. System 100 can rely on a variety of factors as indicators of CIP events, such as the absence of data for more than one day, changes in KPIs (permeable flow rate (Pf), salinity (Sp), and element pressure drop (dP)) before and after, combinations thereof, etc. Some potential challenges in identifying CIPs may include, for example, the presence of outliers in the data (if not properly removed), inconsistent time intervals between CIPs, KPIs not always changing significantly due to CIPs, process stoppages being used as “low-cost” CIPs, combinations thereof, etc. Overall, regarding Figure 7A and Figure 7B The discussion process identified and removed outliers from the data. If the KPIs haven't changed significantly, this data might indicate a process stop (rather than a CIP), which is useful for the system to identify. If a process stop serves as a "low-cost" CIP, the system can treat this "low-cost" CIP as a CIP event.

[0095] The CIP identification process can be achieved by creating data points (y t ) and the previous data point (y t-1 The difference sequence of ) (represented as y t ; y t = y t – y t-1 The system executes the calculation of the mean and standard deviation of the difference sequence for each KPI. For each KPI difference sequence, the system determines whether the difference value of dP is lower than K near the mean. Is the standard deviation, or the difference in flow rate, higher than K, which is near the mean? Standard deviation. If the answer to either question is yes, the system determines whether there are gaps in the data greater than 1 day. If so, the data points (y... t The restart value identified after a CIP is determined. This method is based on the extreme values ​​(EVDS) in the differential sequence of dP and traffic. This method checks whether the change in the data point significantly exceeds the expected change. dP and Pf are likely the best KPIs for identifying CIP points. The default value for k is 5, but it can be changed by the user. The CIP identification process can be represented by the following Equation 2:

[0096] (2)

[0097] Therefore, the current observation corresponds to the restart time after CIP. The corresponding time of the previous observation indicates the CIP time.

[0098] Figures 8A to 8C It demonstrates the ideal voltage drop (dP) ( Figure 8A ), expected pressure reduction ( Figure 8B ) and observed pressure drop ( Figure 8C The goal of CIP is to restore the system's performance to (ideally) its initial state. Figure 8A In an ideal scenario, dP returns to its initial value after cleaning. Figure 8B In the expected scenario, dP decreases after each cleaning but then rises steadily. Figure 8C In the observed scenarios, the changes in dP are inconsistent. dP is typically used to check cleaning effectiveness (other KPIs may be used in other embodiments). Various indices have been developed over the years to measure cleaning effectiveness, such as static indices (uncovered dP, cleanability, etc.) compared to dP after commissioning, and dynamic indices (dynamic cleanability) compared to dP after the previous CIP.

[0099] In some embodiments, the system can identify the start and end points of the CIP, calculate the average of three (3) dP values ​​at the start and end of each CIP, and calculate the relevant cleaning effectiveness index for each CIP. Other KPIs can also be used to perform a similar process as a supplement to or alternative to dP. Other cleaning indices can be calculated. The system user or operator can change the number of data points used to calculate the average. For example, in some embodiments, the average can be taken over a period of at least two hours to ensure stable readings. However, in some embodiments, the average obtained over more or less than two hours can be used. Figure 9 It is a chart displaying the CIP events of the dataset. Figure 10 It is a graph showing the unrecovered dP of the dataset compared to the initial dP, and Figure 11It is a graph that shows the cleanability of the dataset compared to its initial cleanability. Figure 10 This demonstrates the difference between dP measured after CIP and the initial dP (e.g., dP measured at startup even before the first CIP is executed). In a perfect system, such as... Figure 8A The above, Figure 10 It will be a straight horizontal line at 0 (i.e., no unrecovered dP). Figure 10 The "to Initial" mentioned at the top indicates that the graph represents the initial dP measured at startup before the first CIP execution, compared to other dP values ​​after the first, second, third, etc., CIP events. Similarly, for Figure 11 Cleanability captures the ideal case of the amount of dP increase removed by CIP versus the total amount of dP increase removed by CIP since startup. In a perfect system, such as Figure 8A The above, Figure 11 This will be a straight horizontal line at 100% (i.e., each time the component is cleaned to the startup condition). Figure 9 In the middle, a i Let represent the dP value after the i-th CIP, and b i This represents the dP value before the i-th CIP. Use equations 3 and 4 below to compare these values ​​with the initial value (dP). 初始 Compare:

[0100] (3)

[0101] (4)

[0102] These values ​​can be further compared with the previous CIP values ​​using Equations 5 and 6 below (a i-1 Compare:

[0103] (5)

[0104] (6)

[0105] In some cases, CIP cleaning can be identified by detecting a low pressure drop, an increase in normalized flux, or a return of salt permeability to its starting point. When the system starts up / stops, permeate flow rate and salt permeability 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 that occurred based on the system's operating values. Figure 12 This is a table of fouling types and indicators / parameters based on standardized pressure drop, standardized permeate flow rate, and standardized salt permeability. The system can... Figure 12The information in Figure 13 is used in conjunction with the information in Figure 14 to identify specific types of fouling that have occurred. For certain fouling types, metrics / parameters are examined based on the location of the filter element (e.g., front-end, back-end, both front-end and back-end, etc.). Some fouling types can occur at any filter element, so these metrics / parameters are examined at any location on the filter element. Normalized pressure drop can serve as a primary indicator of no fouling, biological fouling, particulate fouling, and scaling. Normalized permeate flow rate can serve as a primary indicator of no fouling, organic fouling, particulate fouling, and element damage (e.g., integrity failure). Normalized salt permeability can serve as a primary indicator of scaling and element damage. Therefore, the system can examine these key factors for each dataset corresponding to the time period between CIP events to determine the type of fouling that has occurred.

[0106] As discussed in this paper, the system can initially determine the existence of a match based on at least one primary metric / parameter to identify the fouling type. This identification can be reinforced by additional primary and / or secondary metrics / parameters that match the dataset. However, the system only requires a single primary metric / parameter match to estimate the fouling type. In some cases, more than one fouling type may occur, and the system can identify this situation based on, for example, satisfying two or more different primary parameters. In some cases, if no primary metric / parameter match is identified, the system can determine the fouling type based on the matching of (multiple) secondary parameters.

[0107] In some embodiments, the “decision tree” executed by the system may involve the following steps: (i) identifying the slope of (multiple) primary parameters; (ii) identifying the fitting trend of (multiple) primary parameters; and (iii) determining the location of the filter element for the identified performance changes. Fouling types can be identified based on the matching of the slope of at least one primary parameter over time (or the slope over time and data fitting; or the slope over time, data fitting, and filter element location). If no matching of at least one primary parameter is found, the system’s “decision tree” can identify the slope and fitting trend of (multiple) secondary parameters to identify fouling types based on the matching of (multiple) secondary parameters. If the matching of (multiple) primary parameters and / or (multiple) secondary parameters identifies more than one potential fouling type, the system can provide potential matches to the user, who can then review the data to determine which potential match is the actual fouling type. In some cases, more than one type of fouling may occur in the filter element, and the system can identify multiple fouling types based on the matching of primary and / or secondary parameters. The identified fouling can be used to analyze current performance data (e.g., real-time or near real-time) to estimate the types of fouling that may occur and / or are likely to occur, and to recommend more specific and accurate cleaning procedures to address the fouling problem. The identified fouling can also be used to predict when fouling may occur based on the detection of recurring fouling trends over specific weeks or months and / or taking into account specific water conditions (e.g., temperature, etc.).

[0108] Pay special attention Figure 12 For cases without fouling, data from any filter element location can be used, and each of dP, Pf, and Sp is considered a primary metric / parameter. For cases identified as fouling-free, any one of the dP, Pf, and / or Sp curves conforms to a linear function whose slope changes approximately to zero over time (e.g., the dataset changes less than 5% over the entire operating period).

[0109] Still referencing Figure 12For biofouling, data regarding the pre-filter elements (multiple of them) are examined. These pre-filter elements may include only a first filter element (or, in some embodiments, may include both a first filter element and a second filter element at the front end of the pressure vessel). dP is a primary parameter of biofouling, whose data conforms to a non-linear function and whose slope changes positively over time (both must occur simultaneously to satisfy the primary parameter). Pf is a secondary parameter of biofouling, whose data conforms to a non-linear function and whose slope changes negatively over time (both must occur simultaneously to satisfy the secondary parameter). Sp is another secondary parameter of biofouling, whose data conforms to a non-linear function and whose slope changes positively over time (both must occur simultaneously to satisfy the secondary parameter). Therefore, in all cases discussed herein, both function fit and slope change over time must be satisfied to satisfy either the primary or secondary parameter. If the primary parameter condition is met, the system can identify the fouling type as biofouling even if the secondary parameters are not met. However, if one or more of the secondary parameters are met, the system can use this data to reinforce the initial identification based on the primary parameter.

[0110] For organic fouling, data is examined for any of the filter elements (e.g., not limited to front-end or back-end filter elements). Pf is a primary parameter for organic fouling, with data conforming to a non-linear function and a negative slope over time. dP is a secondary parameter for organic fouling, with data conforming to a linear function and a slope approximately zero over time. Sp is another secondary parameter for organic fouling, with data conforming to a non-linear function and a negative slope over time. If the primary parameter condition is met, the system can identify the fouling type as organic fouling even if the secondary parameters are not met. However, if one or more of the secondary parameters are met, the system can use this data to reinforce the initial identification based on the primary parameter.

[0111] For particulate fouling, data related to (multiple) pre-filter elements are reviewed. dP is the primary parameter for particulate fouling, with data conforming to a linear function and a positive slope over time. Pf is a secondary parameter for particulate fouling, with data conforming to a linear function and a negative slope over time. Sp is another secondary parameter for particulate fouling, with data conforming to a linear function and a positive slope over time. If the primary parameter condition is met, the system can identify the fouling type as particulate fouling even if the secondary parameters are not met. However, if one or more of the secondary parameters are met, the system can use this data to reinforce the initial identification based on the primary parameter.

[0112] For fouling, data regarding the tail filter(s) are reviewed. These tail filter(s) may include the last filter(s) at the tail end of the pressure vessel (or, in some embodiments, the last and penultimate filter(s)). dP is a primary parameter of fouling, with data conforming to a linear function and a positive slope over time. Pf is a secondary parameter of fouling, with data conforming to a linear function and a negative slope over time. Sp is another secondary parameter of fouling, with data conforming to a linear function and a positive slope over time. If the primary parameter condition is met, the system can identify the fouling type as fouling even if the secondary parameters are not met. However, if one or more of the secondary parameters are met, the system can use this data to reinforce the initial identification based on the primary parameter.

[0113] For integrity failure, data regarding the (multiple) front and rear filter elements are reviewed. These elements may consist only of the first and last filter elements located at the front and rear ends of the pressure vessel, respectively (or, in some embodiments, may include two filter elements at the front end and two at the rear end). Pf is a primary parameter of integrity failure, with data conforming to a linear function and a positive slope over time. Sp is another primary parameter of integrity failure, with data conforming to a linear function and a positive slope over time. dP is a secondary parameter of integrity failure, with data conforming to a linear function and a slope approximately zero over time. If only one primary parameter satisfies the primary parameter condition, the system can identify the fouling type as integrity failure even if both primary and / or the secondary parameter is not satisfied. However, if both primary parameters are satisfied and / or the secondary parameter is satisfied, the system can use this data to reinforce the initial identification based on the primary parameter.

[0114] Furthermore, "integrity failure" can be divided into two subcategories: "chemical degradation" and "physical integrity problems." The table below shows... Figure 12 The appendix details the parameters for each of these subcategories. Those marked " The annotations for "" and "a" are the same as those for "". Figure 12 The annotations appearing in the text are identical. The primary and secondary parameters for these two subcategories are the same, and the data for each primary and secondary parameter conform to a function of the same order (linear) and the same slope (~0 or positive), as described above for the parameters of the more general category of integrity failure. However, chemical degradation of any filter element can be evaluated while simultaneously analyzing the physical integrity issues of the same element, as described above regarding integrity failure.

[0115] surface

[0116] Figure 12Appendix

[0117]

[0118] Figures 13A through 13F are charts illustrating the analysis of datasets for pressure drop, permeate flow rate, and salt permeability. Specific results indicate specific fouling types, including no fouling (Figure 13A), biological fouling (Figure 13B), organic fouling (Figure 13C), particulate fouling (Figure 13D), scaling (Figure 13E), and integrity fouling (Figure 13F). As used herein with respect to Figures 13A through 13F and throughout the disclosure, the terms “rapid,” “step,” or “gradual” change refer to a change of at least 5% in a given parameter over an operating period of less than 24 hours; the terms “drastic” or “gradual” change refer to a change of at least 5% in a given parameter over an operating period of 24 hours or longer; and the terms “zero” or “no change” refer to a change of less than 5% in the dataset over the entire operating period.

[0119] As shown in Figure 13A, no fouling typically means that all factors remain unchanged. With these results, no cleaning is required. As shown in Figure 13B, biological fouling typically means an increase in pressure drop conforming to a second-order polynomial (optionally, a decrease in permeate flow rate and an increase in salt permeability). For biological fouling, a specific chemical combination will be recommended for cleaning. As shown in Figure 13C, organic fouling typically means a decrease in permeate flow rate conforming to a second-order polynomial (optionally, a decrease in salt permeability and a stable pressure drop). For organic fouling, a specific chemical combination will be recommended for cleaning.

[0120] As shown in Figure 13D, particulate fouling is typically represented by a sharp increase in pressure drop (e.g., a step change) conforming to a first-order polynomial (optionally, a sharp decrease in permeate flow rate (e.g., a step change) conforming to a first-order polynomial, and a sharp increase in salt permeability (e.g., a step change)). For particulate fouling, a specific chemical combination will be recommended for cleaning. Troubleshooting of the pretreatment is recommended. Although the increase may be linear, it will typically be represented as a ramp. As shown in Figure 13E, scaling is typically represented by an increase in pressure drop conforming to a first-order polynomial (optionally, a decrease in permeate flow rate, and an increase in salt permeability conforming to a first-order polynomial). For scaling, a specific chemical combination will be recommended for cleaning. Reducing the overall system recovery rate is recommended. Biofouling and scaling can have similar effects, but for biofouling, the increase in dP is more significant in the front-end components, while for scaling, this effect is more pronounced in the back-end components. As shown in Figure 13F, oxidation or integrity damage is typically represented by an increase in permeate flow rate conforming to a first-order polynomial and an increase in salt permeability conforming to a first-order polynomial (optionally, pressure drop is stable). It is recommended to replace the current filter element.

[0121] Figure 14 It displays charts showing biofouling identified based on a dataset, and Figure 15 This is a chart showcasing the identification of organic fouling based on different datasets. This fouling identification was performed by the system by reviewing and analyzing the data to determine key factor conditions and matching these conditions against the criteria discussed above. Based on these criteria, the system developed specific functions for the datasets and identified the specific types of fouling that occurred. Experiments on different datasets reproduced the differentiation of organic fouling with excellent results.

[0122] Figure 16 and Figure 17 It is a chart displaying the identified organic fouling and biofouling on the organic fouling. The identification and results achieved using this system during experiments showed excellent reproducibility. Figure 18 It is a chart that displays organic fouling, particulate fouling, biofouling, and CIP events identified based on different datasets.

[0123] In some cases, the system can analyze data and detect fouling types according to specific rules. The system can initially detect the cycles between CIP events and perform first- and second-order polynomial regressions on dP, salt permeability, and permeate flow rate for each cycle. This system can be used to detect CIP events and fouling types in both RO (single-pass) and CCRO (closed-loop multi-pass) systems.

[0124] Although exemplary embodiments have been described herein, it should be clearly stated that these embodiments should not be construed as limiting, but rather that supplements and modifications to the content explicitly described herein are also included within the scope of the invention. Furthermore, it should be understood that the features of the various embodiments described herein are not mutually exclusive, but can exist in various combinations and arrangements, even if such combinations or arrangements are not explicitly expressed herein, as long as they do not depart from the spirit and scope of the invention.

Claims

1. A system for determining the state of a filter, the system comprising: A database configured to store data electronically, the data including past performance data of one or more water filtration elements; as well as A processing device that communicates with the database, the processing device being configured to: Receive the past performance data as input; Identify one or more data points within the past performance data that indicate cleaning events of the one or more water filtration elements; The past performance data is divided into separate data segments, each of which represents data between corresponding identified cleaning events in the past performance data; Fit a mathematical function to each of the individual data segments; as well as The type of fouling that occurs in each period of the respective individual data segment is identified based on a mathematical function fitted to that segment.

2. The system as claimed in claim 1, wherein, The processing device is further configured to normalize the past performance data to the conditions at which the one or more water filtration elements are activated before the cleaning event is identified.

3. The system as claimed in claim 1 or claim 2, wherein, The processing equipment is further configured to take into account changes in at least one of the inlet water temperature, inlet water composition, or feed pressure when standardizing the past performance data.

4. The system as described in any of the preceding claims, wherein, The processing device is further configured to identify and remove physically inconsistent data points from the past performance data prior to identifying the cleaning event.

5. The system as described in claim 4, wherein, Remove physically inconsistent data points from the past performance data if the following conditions are not met: The feed flow rate is greater than the concentrate flow rate; The feed flow rate is greater than the product water flow rate; The feed pressure is greater than the concentration pressure; as well as The feed pressure is greater than the water production pressure.

6. The system as described in any of the preceding claims, wherein, The processing device is further configured to identify and remove statistical outlier data points from the past performance data before identifying the cleaning event.

7. The system of claim 6, wherein, Identifying and removing statistical outlier data points from the historical performance data includes: Calculate data points (y t ) relative to the previous data point (y t-1 The percentage change; Calculate the next data point (y t+1 ) relative to the data point (y) t The percentage change; Compare the previous percentage change with the decrease limit; and If the percentage change exceeds the decrease limit, the data point (y) will be... t It was identified as an outlier.

8. The system as described in any of the preceding claims, wherein, Identifying the cleaning event includes: The differential sequence method is applied to the standardized pressure drop (dP) and standardized permeate flow rate (Pf) in the historical performance data, wherein the application of the differential sequence method includes: Calculate the data points (y) t ) and the previous data point (y) t-1 The difference between the pressure drop (dP) and the normalized permeate flow rate (Pf) is used to generate a difference sequence of the normalized pressure drop (dP) and the normalized permeate flow rate (Pf); Calculate the mean and standard deviation of the difference series of the standardized pressure drop (dP) and the standardized permeate flow rate (Pf); Each value in the difference sequence of the standardized pressure drop (dP) and the standardized permeable flow rate (Pf) is compared with the sum of the products of the corresponding value in the difference sequence and the difference constant and the corresponding standard deviation of the difference sequence; Determine whether gaps exist in the dataset; and Determine whether the gap is greater than the CIP reference time.

9. The system as claimed in any of the preceding claims, wherein, The processing device is further configured to analyze the determination coefficients of the mathematical function and calculate the derivative of the mathematical function with respect to time, and wherein the processing device is further configured to identify the type of dirt based on the derivative of the determination coefficients.

10. The system as claimed in any of the preceding claims, wherein, The one or more water filtration elements include at least one element selected from the group consisting of reverse osmosis elements, nanofiltration elements, and ultrafiltration elements.

11. The system of any of the preceding claims, further comprising one or more sensors configured to detect and transmit data on pressure drop, salinity, and permeate flow rate associated with each of the one or more water filtration elements, as stored in the database as the past performance data.

12. The system as claimed in any of the preceding claims, wherein: The past performance data includes the pressure drop, salt permeability, and permeate flow rate of each of the one or more water filtration elements; and If no changes in the pressure drop, salt permeability, and permeate flow rate are detected, the treatment equipment identifies the fouling type as a fouling-free condition.

13. The system as claimed in any of the preceding claims, wherein: The past performance data includes the pressure drop, salt permeability, and permeate flow rate of each of the one or more water filtration elements; and When the increase in pressure drop conforms to a second-order polynomial function, the processing device identifies the type of fouling as biological fouling.

14. The system as claimed in any of the preceding claims, wherein: The past performance data includes the pressure drop, salt permeability, and permeate flow rate of each of the one or more water filtration elements; and If the decrease in salt permeability conforms to a second-order polynomial function, the treatment device identifies the type of fouling as organic fouling.

15. The system as claimed in any of the preceding claims, wherein: The past performance data includes the pressure drop, salt permeability, and permeate flow rate of each of the one or more water filtration elements; and When the sharp increase in voltage drop at the head position of the component conforms to a first-order polynomial function, the processing device defines the fouling type as particulate fouling.

16. The system as claimed in any of the preceding claims, wherein: The past performance data includes the pressure drop, salt permeability, and permeate flow rate of each of the one or more water filtration elements; and When the gradual increase in voltage drop across the component at the tail end conforms to a first-order polynomial function, the processing device identifies the type of fouling as scaling.

17. The system as claimed in any of the preceding claims, wherein: The past performance data includes the pressure drop, salt permeability, and permeate flow rate of each of the one or more water filtration elements; and If the increase in the permeate flow rate conforms to a first-order polynomial function and the increase in the salt permeability conforms to a first-order polynomial function, the treatment device identifies the fouling type as an integrity failure event.

18. The system as claimed in any of the preceding claims, wherein, The processing device is further configured to: Receive current performance data of the one or more water filtration elements received from one or more sensors as input; The current performance data is analyzed based on previous analysis of the past performance data and the identification of the type of fouling that occurred in each period of the individual data segments. Estimate the type of fouling currently occurring at the one or more water filtration elements; as well as Output recommendations for cleaning procedures specific to the current type of fouling occurring at one or more water filtration elements.

19. The system as described in any of the preceding claims, further comprising artificial intelligence, machine learning capabilities, or both artificial intelligence and machine learning capabilities, wherein, The artificial intelligence or machine learning capabilities are operated to improve the identification of dirt types, the predictability of dirt events, or both the identification of dirt types and the predictability of dirt events.

20. A method for determining the state of a filter, the method comprising: The system receives past performance data of one or more water filtration elements as input to a system for determining the state of the filter, the system for determining the state of the filter comprising (i) a database configured to electronically store the past performance data, and (ii) a processing device communicating with the database; Identify one or more data points within the past performance data that indicate cleaning events of the one or more water filtration elements; The past performance data is divided into separate data segments, each of which represents data between corresponding identified cleaning events in the past performance data; Fit a mathematical function to each of the individual data segments; as well as The type of fouling that occurs in each period of the respective individual data segment is identified based on a mathematical function fitted to that segment.

21. A non-transitory computer-readable medium storing instructions executable by a processing device for determining a filter state, wherein... The processing device executes the instructions to cause the processing device to perform the following operations: The system receives past performance data of one or more water filtration elements as input to a system for determining the state of the filter, the system for determining the state of the filter comprising (i) a database configured to electronically store the past performance data, and (ii) the processing device communicating with the database; Identify one or more data points within the past performance data that indicate cleaning events of the one or more water filtration elements; The past performance data is divided into separate data segments, each of which represents data between corresponding identified cleaning events in the past performance data; Fit a mathematical function to each of the individual data segments; as well as The type of fouling that occurs in each period of the respective individual data segment is identified based on a mathematical function fitted to that segment.

Images